US20050260671A1 - Process for discriminating between biological states based on hidden patterns from biological data - Google Patents

Process for discriminating between biological states based on hidden patterns from biological data Download PDF

Info

Publication number
US20050260671A1
US20050260671A1 US11/189,808 US18980805A US2005260671A1 US 20050260671 A1 US20050260671 A1 US 20050260671A1 US 18980805 A US18980805 A US 18980805A US 2005260671 A1 US2005260671 A1 US 2005260671A1
Authority
US
United States
Prior art keywords
data
cluster
sample
data stream
disease
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Abandoned
Application number
US11/189,808
Inventor
Ben Hitt
Peter Levine
Emanuel Petricoin
Lance Liotta
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
US Department of Health and Human Services
Aspira Womens Health Inc
Original Assignee
Individual
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Individual filed Critical Individual
Priority to US11/189,808 priority Critical patent/US20050260671A1/en
Publication of US20050260671A1 publication Critical patent/US20050260671A1/en
Assigned to CORRELOGIC SYSTEMS, INC. reassignment CORRELOGIC SYSTEMS, INC. ASSIGNMENT OF ASSIGNORS INTEREST (SEE DOCUMENT FOR DETAILS). Assignors: HITT, BEN, LEVINE, PETER J.
Assigned to THE UNITED STATES OF AMERICA AS REPRESENTED BY THE DEPARTMENT OF HEALTH AND HUMAN SERVICES reassignment THE UNITED STATES OF AMERICA AS REPRESENTED BY THE DEPARTMENT OF HEALTH AND HUMAN SERVICES ASSIGNMENT OF ASSIGNORS INTEREST (SEE DOCUMENT FOR DETAILS). Assignors: LIOTTA, LANCE A., PETRICOIN, EMMANUEL F., III
Assigned to VERMILLION, INC. reassignment VERMILLION, INC. ASSIGNMENT OF ASSIGNORS INTEREST (SEE DOCUMENT FOR DETAILS). Assignors: CORRELOGIC SYSTEMS, INC.
Abandoned legal-status Critical Current

Links

Classifications

    • GPHYSICS
    • G01MEASURING; TESTING
    • G01NINVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N33/00Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
    • G01N33/48Biological material, e.g. blood, urine; Haemocytometers
    • GPHYSICS
    • G16INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16BBIOINFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR GENETIC OR PROTEIN-RELATED DATA PROCESSING IN COMPUTATIONAL MOLECULAR BIOLOGY
    • G16B40/00ICT specially adapted for biostatistics; ICT specially adapted for bioinformatics-related machine learning or data mining, e.g. knowledge discovery or pattern finding
    • GPHYSICS
    • G16INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16BBIOINFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR GENETIC OR PROTEIN-RELATED DATA PROCESSING IN COMPUTATIONAL MOLECULAR BIOLOGY
    • G16B40/00ICT specially adapted for biostatistics; ICT specially adapted for bioinformatics-related machine learning or data mining, e.g. knowledge discovery or pattern finding
    • G16B40/10Signal processing, e.g. from mass spectrometry [MS] or from PCR
    • GPHYSICS
    • G16INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16HHEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H10/00ICT specially adapted for the handling or processing of patient-related medical or healthcare data
    • G16H10/40ICT specially adapted for the handling or processing of patient-related medical or healthcare data for data related to laboratory analysis, e.g. patient specimen analysis
    • GPHYSICS
    • G16INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16BBIOINFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR GENETIC OR PROTEIN-RELATED DATA PROCESSING IN COMPUTATIONAL MOLECULAR BIOLOGY
    • G16B25/00ICT specially adapted for hybridisation; ICT specially adapted for gene or protein expression
    • GPHYSICS
    • G16INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16HHEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/70ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
    • YGENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y10TECHNICAL SUBJECTS COVERED BY FORMER USPC
    • Y10STECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y10S707/00Data processing: database and file management or data structures
    • Y10S707/99931Database or file accessing
    • Y10S707/99933Query processing, i.e. searching
    • YGENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y10TECHNICAL SUBJECTS COVERED BY FORMER USPC
    • Y10STECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y10S707/00Data processing: database and file management or data structures
    • Y10S707/99941Database schema or data structure
    • Y10S707/99943Generating database or data structure, e.g. via user interface

Definitions

  • the field of the invention concerns a process for determining a biological state through the discovery and analysis of hidden or non-obvious, discriminatory biological data patterns.
  • the biological data can be from health data, clinical data, or from a biological sample, (e.g., a biological sample from a human, e.g., serum, blood, saliva, plasma, nipple aspirants, synovial fluids, cerebrospinal fluids, sweat, urine, fecal matter, tears, bronchial lavage, swabbings, needle aspirantas, semen, vaginal fluids, pre-ejaculate, etc.), etc. which is analyzed to determine the biological state of the donor.
  • the biological state can be a pathologic diagnosis, toxicity state, efficacy of a drug, prognosis of a disease, etc.
  • the invention concerns analytical methods that a) discover hidden discriminatory biological data patterns (e.g., patterns of protein expression in a serum sample that classify the biological state of an organ) that are subsets of the larger data stream, said discrimination implying the ability to distinguish between two or more biological states in a learning set of data and b) the application of the aforementioned patterns to classify unknown or test samples. More specifically, the invention concerns a method for analysis of a data stream, which is derived from a physical or chemical analysis of molecules (e.g., proteins, peptides, DNA, RNA, etc.) in the biological sample (e.g., a mass spectrum analysis of the sample).
  • hidden discriminatory biological data patterns e.g., patterns of protein expression in a serum sample that classify the biological state of an organ
  • the invention concerns a method for analysis of a data stream, which is derived from a physical or chemical analysis of molecules (e.g., proteins, peptides, DNA, RNA, etc.) in the biological sample (e.
  • These patterns are defined as “hidden” because they are often buried within a larger highly complex data set and are not obvious or apparent to the eye or other current classification systems.
  • the pattern itself can be defined as the combination of three or more values such that the position of the vectors in an n-dimensional space is discriminatory between biological states even when individual values may not be discriminatory.
  • the discriminatory patterns of the invention are novel because they can be defined without any knowledge of the identity or relationship between the individual data points in the biological data or any knowledge of the identity or relationship between the molecules in the biological samples.
  • One analytical method to discover such biological states comprises the application of two related heuristic algorithms, a learning algorithm and a diagnostic algorithm, wherein the parameters of the diagnostic algorithm are set by the application of the learning algorithm to a learning set of data such that two or more biological states may be distinguished.
  • biological states may be the presence or absence of a disease, efficacy or non-efficacy of a drug, toxicity or non-toxicity of a drug, etc.
  • the invention is generic, specific implementations for diagnosis of various cancers (including, but not limited to carcinomas, melanomas, lymphomas, sarcomas, blastomas, leukemias, myelomas, neural tumors, etc., and cancers of organs like the ovary, prostate, and breast), presence of a pathogen, and toxicity are disclosed.
  • the preferred embodiment of the invention is the discovery and use of molecular patterns that reflect the current or future biological state of an organ or tissue.
  • Another embodiment of the invention is the combination of data describing the molecular patterns of a biological state with other non-biological or clinical data (e.g., psychiatric questioning) to yield a classification describing the health of a patient.
  • the detection of changes in biological states, particularly the early detection of diseases has been a central focus of the medical research and clinical community.
  • the prior art includes examples of efforts to extract diagnostic information from the data streams formed by physical or chemical analysis of tissue samples. These techniques are generically termed “data-mining.”
  • the data streams that have been mined are typically of two forms: analysis of the levels of mRNA expression by hybridization to DNA oligonucleotide arrays (“DNA microarrays”) and analysis of the levels of proteins present in a cell or in a serum sample, wherein the proteins are characterized either by molecular weight using mass spectroscopy or by a combination of molecular weight and charge using a 2-D gel technique.
  • Liotta and Petricoin provide additional examples of protein based diagnostic methods using both 2-D gels and mass spectroscopy.
  • the analysis of Liotta and Petricoin is similar to Parekh in that it consists of a search for specific tumor markers.
  • Efforts to identify tumor markers have also been performed using DNA microarrays.
  • Loging, W. T., 2000, Genome Res. 10, 1393-02 describes efforts to identify tumor markers by DNA microarrays in glioblastoma multiforme.
  • Heldenfalk, I., et al., 2001, New England J. Med. 344, 539 report efforts to identify tumor markers that distinguish the hereditary forms of breast cancer resulting from BRCA1 and BRCA2 mutations from each other and from common idiopathic breast cancer by data-mining of DNA microarray data.
  • Each vector is composed of scalars that individually correspond to the relative levels of expression of the gene under a variety of different conditions.
  • Brown et al. analyzes vectors in a 79 dimension vector space where each dimension corresponds to a time point in a stage of the yeast life-cycle and each of 2,467 vectors correspond to a gene.
  • the pattern recognition algorithms are used to identify clusters of genes whose expression is correlated with each other. Because the primary concern is the correlation of gene expression, the metric that is employed in the pattern recognition algorithms of Eisen et al. and related works is a Pearson coefficient or inner product type metric, not a Euclidean distance metric.
  • the pattern recognition techniques of Eisen et al. were applied by Alizadeh and Staudt to the diagnosis of types of malignancy.
  • Alizadeh and Staudt began by constructing vectors, each corresponding to a gene, having scalars that correspond to the relative level of expression of the gene under some differentiation condition, e.g., resting peripheral blood lymphocyte or mitogen stimulated T cells.
  • the pattern recognition algorithm then clusters the genes according to the correlation of their expression and defines a pattern of expression characteristic of each differentiation state.
  • Samples of diffuse large B-cell lymphomas (DLBCL) were then analyzed by hybridization of mRNA to the same DNA microarrays as used to determine the gene clusters.
  • DLBCL diffuse large B-cell lymphomas
  • DLBCL were found to have at least two different gene expression patterns, each characteristic of a normal differentiation state.
  • the prognosis of the DLBCL was found to correlate with the characteristic differentiation state.
  • the diagnostic question posed and answered in Alizadeh and Staudt was not benign or malignant but rather of determining the type or subtype of malignancy by identifying the type of differentiated cell having a pattern of gene expression most similar to that of the malignancy.
  • data-mining methods based on the physical or chemical analyses having large numbers, i.e., greater than 1,000, of data points consist of two types: data-mining to identify individual markers such as genes or proteins having expression levels that are increased or suppressed in malignant cells of a defined type compared to normal cell; and data-mining wherein a pattern of known gene expression characteristic of a normal differentiated cell type is used to classify a known malignant cell according to the normal cell type it most closely resembles.
  • gene expression cluster analysis is limited in scope because such analysis incorporates an analysis of all expressed genes irrespective of whether the expression of such genes is causative or merely influenced by the causative action of those genes that are characteristic of the biological state.
  • the clustering analysis does not incorporate solely those genes that are characteristic of the biological state of interest, but uses the entire range of data emanating from the assay, thus making it complex and cumbersome.
  • gene expression analysis must involve nucleic acid extraction methods, making it complex, and time-consuming. Pattern recognition algorithms when applied are also rendered difficult because the correlation of gene expression that is employed is a complex Pearson coefficient or inner product type metric, and not a simple Euclidean distance metric.
  • the current invention discovers optimal hidden molecular patterns as subsets within a larger complex data field, whereby the pattern itself is discriminatory between biological states.
  • the current invention avoids all the aforementioned problems associated with the analytical methods disclosed in the prior art, and has the ability to discover heretofore unknown diagnostic patterns.
  • Such hidden molecular patterns are present in data streams derived from health data, clinical data, or biological data.
  • Biological data may be derived from simple biological fluids, such as serum, blood, saliva, plasma, nipple aspirants, synovial fluids, cerebrospinal fluids, sweat, urine, fecal matter, tears, bronchial lavage, swabbings, needle aspirantas, semen, vaginal fluids, pre-ejaculate, etc., making routine sampling easy, although the expression of such molecular patterns are characteristic of disease states of remote organs. No prior knowledge of specific tumor markers or the relationship of molecules present in the biological sample to each other is required or even desired.
  • the current invention also discloses methods of data generation and analysis. Such methods of data analysis incorporate optimization algorithms in which the molecular patterns are recognized, and subjected to a fitness test in which the fitness pattern that best discriminates between biological states is chosen for the analysis of the biological samples.
  • the invention comprises the use of pattern discovery methods and algorithms to detect subtle, if not totally hidden, patterns in the expression of certain molecules in biological samples that are potentially diagnostic in nature, or predictive of a biological state.
  • patterns of molecular expression are patterns of protein expression, particularly patterns of low molecular weight proteins (i.e. less than 20,000 Da).
  • Such hidden patterns of protein expression may be obtained from only a sub-set of the total data-stream provided to the algorithm, several subsets, or may be obtained from an analysis of the total data stream.
  • the pattern can be defined as a vector of three or more values such that the position of the vectors in an n-dimensional space is discriminatory between biological states even when individual values may not be discriminatory.
  • the molecules of interest may be any relevant biological material such as proteins (full, cleaved, or partially expressed), peptides, phospholipids, DNA, RNA, etc.
  • the discriminatory patterns that discriminate between biological states are often small subsets of data hidden in the larger data stream derived from physical or chemical analysis of the biological sample.
  • a means for finding an optimal set of features that make up the discriminatory pattern is required.
  • the invention incorporates the process for finding this optimal set of features.
  • a number of feature selection methods for discriminatory patterns may be used to practice the invention with varying degrees of classification success. These include, but are not limited to, statistical methods, stepwise regression methods, linear optimization methods, etc.
  • statistical methods have some limitations in that they are often linear, at least in their simple, well-known forms such as multivariate linear regressions.
  • statistical models tend not to be robust with respect to non-linear data.
  • the number of independent variables a statistical model can successfully employ is generally ten or less, with a practical preferred limit of five or six.
  • the preferred embodiment uses a method that couples the genetic algorithm, an evolutionary computation method, directly to an adaptive pattern recognition algorithm to efficiently find the optimal feature set. See U.S. Patent Application titled “Heuristic Method of Classification,” (filing date: Jun. 19, 2001, claiming priority of application Ser. No. 60/212,404, filed Jun. 19, 2000).
  • the diagnostic algorithm is generated by the application of the learning algorithm to a learning (or training) data set.
  • the learning data set is a data set formed from biological samples for which the biological state of interest is provided for the pattern discovery operation.
  • the learning data set may comprise data taken from the sera of individuals with an established biopsy diagnosis, e.g., a benign tumor and a malignant tumor. This would enable the learning algorithm to find a signature pattern of proteins that could discriminate normal from cancerous sera samples.
  • the method according to the invention begins by subjecting a biological sample to a high throughput physical or chemical analysis to obtain a data stream.
  • data streams include, but are not limited to, mass spectral data of proteins found in the sample or in the intensity of mRNA hybridization to an array of different test polynucleotides.
  • the data stream is characterized by a large number (10,000 or more) of intensities which are generated in a way that allow for the corresponding individual datum in data streams of different samples to be identified.
  • the first step of the diagnostic method is to calculate a vector, i.e., an ordered set of a small number (between 2 and 20100, more typically between 5 and 208) that is characteristic of the data stream.
  • a vector i.e., an ordered set of a small number (between 2 and 20100, more typically between 5 and 208) that is characteristic of the data stream.
  • Abstraction The transformation of the data steam into a vector is termed “abstraction.”
  • abstraction is performed by selection of a small number of specific intensities from the data stream.
  • the second step of the diagnostic method is to determine in which, if any, data cluster the vector rests.
  • Data clusters are mathematical constructs that are the multidimensional equivalents of non-overlapping “spheres” of fixed size in the vector space. Such data clusters are known as hyperspheres.
  • the location and associated diagnosis of each data cluster is determined by the learning algorithm from the training data set. If the vector of the biological sample lies within a known cluster, the sample is given the diagnosis associated with that cluster.
  • a diagnosis can be made that the sample does not meet that classification criteria or that it is of an unspecified atypia, i.e., an “atypical sample, NOS.”
  • an unspecified atypia i.e., an “atypical sample, NOS.”
  • NOS an unspecified atypia
  • a biological sample taken from a patient does not meet the classification of a malignant state for a specified cancer, it will be classified as non-malignant non-normal or of an unspecified atypia, “atypical sample, NOS.”
  • the learning algorithm utilizes a combination of known mathematical techniques and two pre-set parameters.
  • the user pre-sets the number of dimensions of the vector space and the size of the data clusters.
  • the vector space is a normalized vector space such that the variation of intensities in each dimension is constant.
  • the size of the cluster can be expressed as a minimum percent similarity among the vectors resting within the cluster.
  • the learning algorithm contains of two generic parts, which have been developed by others and are well known in the field—a genetic algorithm (J. H. Holland, Adaptation in Natural and Artificial Systems, MIT Press 1992) and a self-organizing adaptive pattern recognition system (T. Kohonen, Self Organizing and Associative Memory, 8 Series in Information Sciences, Springer Verlag, 1984; Kohonen, T, Self-organizing Maps, Springer Verlag, Heidelberg 1997 ). Genetic algorithms organize and analyze complex data sets as if they were information comprised of individual elements that can be manipulated through a computer driven natural selection process.
  • the search for hidden or subtle patterns of molecular expression that are, in and of themselves “diagnostic” is qualitatively different from those generated by prior art implementations of learning algorithms or data-mining techniques.
  • Previous implementations of data-mining have identified specific molecular products that are indicative of a classification, e.g., proteins or transcripts that are elevated or depressed in pathological conditions.
  • the level of the identified molecular products is termed per se diagnostic, because the level of the product is diagnostic without any further consideration of the level of any other molecular products in the sample, other than perhaps a normalizing molecular product that is used to normalize the level of the molecular products.
  • One example of such per se diagnostic molecular products are tumor markers.
  • the diagnostic significance of the level of any particular marker e.g., a protein or transcript is a function of the levels of the other elements that are used to calculate the sample vector.
  • Such products are termed hereinafter as contextual diagnostic products.
  • the likeness between the biological sample of interest and the learning data set was based on the specified groupings of the biological sample compared to the specified diagnostic molecular products.
  • the learning algorithm discovers wholly new classification patterns without knowing any prior information about the identity or relationships of the data pattern, i.e., without prior input that a specified diagnostic molecular product is indicative of a particular classification.
  • the present invention is based, in part, on the unexpectedness or non-obvious discovery of finding hidden contextual diagnostic patterns to yield a classification, e.g., the diagnosis of malignancy in cancers such as carcinomas, melanomas, lymphomas, sarcomas, blastomas, leukemias, myelomas, and neural tumors.
  • cancers such as carcinomas, melanomas, lymphomas, sarcomas, blastomas, leukemias, myelomas, and neural tumors.
  • the invention comprises a) creating a data stream representing the biological data (or combinations of data streams representing the biological data with clinical, health, or non-biological data) and abstraction of that data into characteristic vectors; b) the discovery of hidden diagnostic patterns of molecular expression (i.e. pattern discovery); and c) determining which biological state of interest such a pattern of molecular expression represents.
  • the molecules of interest may comprise, but are not limited to, proteins, peptides, RNA, DNA, etc.
  • the biological samples comprise, but are not limited to serum, blood, saliva, plasma, nipple aspirants, synovial fluids, cerebrospinal fluids, sweat, urine, fecal matter, tears, bronchial lavage, swabbings, needle aspirantas, semen, vaginal fluids, pre-ejaculate, etc.
  • the biological states of interest may be a pathologic diagnosis, toxicity state, efficacy of a drug, prognosis of a disease, stage of a disease, biological state of an organ, presence of a pathogen (e.g., a virus), toxicity of one or more drugs, etc.
  • the invention may be used for the diagnosis of any disease in which changes in the patterns of expression of certain molecules like proteins allow it to be distinguished from a non-diseased state.
  • any disease that has a genetic component in which the genetic abnormality is expressed, one in which the expression of drug toxicity is observed, or one in which the levels of molecules in the body are affected may be studied by the current invention.
  • Such diseases include, but are not limited to, cancers (carcinomas, melanomas, lymphomas (both Hodgkin's and non-Hodgkin's type), sarcomas, blastomas, leukemias, myelomas, and neural tumors, such as glioblastoma, etc.), Alzheimer's disease, arthritis, glomeruulonephritis, auto-immune diseases, etc.
  • carcinomas include, but are not limited to, carcinomas of the pancreas, kidney, liver and lung; gastrointestinal carcinomas.
  • the present invention is particularly valuable for the diagnosis of specific diseases for which early diagnosis is important, but is technically difficult because of the absence of symptoms, and for which the disease may be expected to produce differences that are detectable in the serum because of the metabolic activity of the pathological tissue.
  • the early diagnosis of malignancies are a primary focus of the use of the invention.
  • the data stream can be any reproducible physical or chemical analysis of the biological sample that results in a high throughput data stream.
  • the high throughput data stream is characterized by 1,000 or more measurements that can be quantified to at least 1 part per thousand (three significant figures) and more preferably one part in 10,000.
  • time of flight mass spectra of proteins may be used to generate a data stream. More specifically, matrix assisted laser desorption ionization time of flight (MALDI-TOF) and surface enhanced laser desorption ionization time of flight (SELDI-TOF) spectroscopy may be used when the molecules of interest are proteins or peptides.
  • MALDI-TOF matrix assisted laser desorption ionization time of flight
  • SELDI-TOF surface enhanced laser desorption ionization time of flight
  • SELDI-TOF may be used to generate data streams for biological states representing toxicity, and detection of pathogens.
  • data streams may be generated using serially amplified gene expression (SAGE) for gene expression classification.
  • SAGE serially amplified gene expression
  • data streams may be generated using 2-D Gels such as two-dimensional polyacrylamide gel electrophoreses (2D-PAGE).
  • the preferred patient sample for analysis is serum.
  • biopsy specimens that are relatively homogenous may also be used.
  • other fluids e.g., synovial fluid may be used in the differential diagnosis of arthritis or urine in the differential diagnosis of glomerulonephritis.
  • proteins that are included in either SELDI-TOF and MALDI-TOF analysis depend upon the surface or matrix that is employed. Lipophylic surfaces such as C-18 alkane surfaces are particularly convenient compared to anionic or cationic surfaces. However, those skilled in the art will appreciate that multiple spectra can be generated from the same sample using different surfaces. These spectra can be concatenated to yield “superspectra” which can be analyzed according to the invention. Likewise, data from two or more high throughput assay methods can also be joined which can be analyzed by the invention. Furthermore, biological data as described in this invention can be joined with clinical, health, or non-biological data.
  • the data stream can also include measurements that are not inherently organized by a single ordered parameter such as molecular weight, but have an arbitrary order.
  • DNA microarray data that simultaneously measures the expression levels of 2,000 or more genes can be used as a data stream when the tissue sample is a biopsy specimen, recognizing that the order of the individual genes in the data stream is arbitrary.
  • the first step in the diagnostic process of the invention is the transformation or abstraction of the data stream into a characteristic vector.
  • the data may be conveniently normalized prior to abstraction by assigning the overall peak an arbitrary value of 1.0 and, thus, all other points fractional values.
  • the most simple abstraction of TOF mass spectrum consists of the selection of a small number of data points.
  • more complex functions of multiple points could be constructed, such as averages over intervals or more complex sums or differences between data points that are at predetermined distance from a selected prototype data point.
  • Such functions of the intensity values of the data stream could also be used and are expected to function equivalently to the simple abstract illustrated in the working examples.
  • Pattern discovery is achieved by numerous methods as discussed in the Summary above.
  • the pattern discovery comprises a diagnostic algorithm and a learning algorithm.
  • the routine practitioner in order to practice this embodiment of the invention the routine practitioner must develop a diagnostic algorithm by employing a learning algorithm.
  • the routine practitioner uses a training data set and must select two parameters, the number of dimensions and the data cluster size. See U.S. Patent Application titled “Heuristic Method of Classification,” (filing date: Jun. 19, 2001, claiming priority of application Ser. No. 60/212,404, filed Jun. 19, 2000).
  • the learning algorithm can be implemented by combining two different types of publicly available generic software, which have been developed by others and are well known in the field—a genetic algorithm (J. H. Holland, Adaptation in Natural and Artificial Systems, MIT Press 1992) that processes a set of logical chromosomes 1 to identify an 1
  • a genetic algorithm J. H. Holland, Adaptation in Natural and Artificial Systems, MIT Press 1992
  • logical chromosome is used in connection with genetic learning algorithms because the logical operations of the algorithm are analogous to reproduction, selection, recombination and mutation.
  • T. adaptive self-organizing pattern recognition system
  • the genetic algorithm essentially determines the data points which are used to calculate the characteristic vector.
  • the list of the specific points to be selected is termed a logical chromosome.
  • the logical chromosome contains as many “genes” as there are dimensions of the characteristic vector. Any set of the appropriate number of data points can be a logical chromosome, provided only that no gene of a logical chromosome is duplicated. The order of the genes has no significance to the invention.
  • Genetic algorithms can be used when two conditions are met.
  • a particular solution to a problem must be able to be expressed by a set or string of fixed size of discrete elements, which elements can be numbers or characters, and the strings can be recombined to yield further solutions.
  • One must also be able to calculate a numerical value of the relative merit of each solution, namely its fitness. Under these circumstances, the details of the genetic algorithm are unrelated to the problem whose solution is sought. Accordingly, for the present invention any generic genetic algorithm software may be employed.
  • the genetic learning algorithms of the invention are purely computational devices, and should not be confused with schemes for biologically-based information processing. libraries, available from Argonne National Laboratory is suitable. The calculation of the fitness of any particular logical chromosome is discussed below.
  • a training data set of about 100 sample data streams was used, each sample data stream containing about 15,000 data points.
  • the genetic algorithms were initialized with about 1,500 randomly chosen logical chromosomes. As the algorithm progressed, the more fit logical chromosomes are duplicated and the less fit are terminated. There is recombination between logical chromosomes and mutation, which occurs by the random replacement of an element of a logical chromosome. It is not an essential feature of the invention that the initially selected collection of logical chromosome be random. Certain prescreening of the total set of data streams to identify those data points having the highest variability may be useful, although such techniques may also introduce an unwanted initialization bias. The best fitted pattern that survives this process is used to discriminate between biological states and determine the desired classification.
  • the fitness score of each of the logical chromosomes that are generated by the genetic algorithm is calculated.
  • the calculation of the fitness score requires an optimal set of data clusters be generated for the given logical chromosome.
  • Data clusters are simply the volumes in the vector space in which the characteristic vectors of the training data set rest.
  • the method of generating the optimal set of data clusters is not critical to the invention and will be considered below. However, whatever method is used to generate the data cluster map, the map is constrained by the following rules: (i) each data cluster should be located at the centroid of the data points that lie within the data cluster; (ii) no two data clusters may overlap; and (iii) the dimension of each cluster in the normalized vector space is fixed prior to the generation of the map.
  • the routine practitioner must use a learning data set and select two parameters, the number of dimensions and the data cluster size. Both parameters can be set using routine experimentation. Although there is no absolute or inherent upper limit on the number of dimensions in the vector, the learning algorithm itself inherently limits the number of dimensions in each implementation. If the number of dimensions is too low or the size of the cluster is too large, the learning algorithm fails to generate any logical chromosomes that correctly classify all samples into homogeneous clusters, and conversely if the number of dimensions can be too large. Under this circumstance, the learning algorithm generates many logical chromosomes that have the maximum possible fitness early in the learning process and, accordingly, there is only abortive selection. Similarly, when the size of the data clusters is too small, the number of clusters will be found to approach the number of samples in the training data set and, again, the routine practitioner will find that a large number of logical chromosomes will yield the maximum fitness.
  • a training data set can nearly always be assigned into homogeneous data clusters.
  • the value of the diagnostic algorithm generated by a learning algorithm must be tested by its ability to sort a set of data other than the training data set.
  • the training data is said to be overfitted by the learning algorithm. Overfitting results when the number of dimensions is too large and/or the size of the data clusters is too small.
  • the method used to define the size of the data cluster is a part of the invention.
  • the cluster size is defined by the maximum of the equivalent the Euclidean distance (root sum of the squares) between any two members of the data cluster.
  • a data cluster size that corresponds to a requirement of 90% similarity is suitable for the invention when the data stream is generated by SELDI-TOF mass spectroscopy data.
  • 90% similarity is defined by requiring that the distance between any two members of a cluster is less than 0.1 of the maximum distance between two points in a normalized vector space.
  • the vector space is normalized so that the range of each scalar of the vectors within the training data set is between 0.0 and 1.0.
  • the maximal possible distance between any two vectors in the vector space is then root N, where N is the number of dimensions.
  • the Euclidean diameter of each cluster is then 0.1 ⁇ root (N).
  • the data stream may be converted into logarithmic form if the distribution of values within the data stream is log normal and not normally distributed.
  • the fitness score for that chromosome can be calculated.
  • the fitness score of the chromosome roughly corresponds to the number of vectors of the training data set that rest in clusters that are homogeneous, i.e., clusters that contain the characteristic vectors from samples having a single diagnosis. More precisely, the fitness score is calculated by assigning to each cluster a homogeneity score, which varies, for example, from 0.0 for homogeneous clusters to 0.5 for clusters that contain equal numbers of malignant and benign sample vectors.
  • the fitness score of the chromosome is the average fitness score of the data clusters. Thus, a fitness score of 0.0 is the most fit.
  • a preferred technique for generating for generating data clusters is using the self-organizing map algorithm as developed by Kohonen. (Kohonen, T, Self-organizing maps, Springer Verlag, Heidelberg 1997). This type of technique is variously termed a “Lead Cluster Map” (“LCM”) or an “Adaptive Feature Map” can be implemented by generic software that is publicly available. Suitable vendors and products include Model 1 from Group One Software (Greenbelt, Md.) and Adaptive Fuzzy Feature Map (American Heuristics Corp.).
  • the LCM has significant advantages in that it is a) it is a non-linear modeling method; b) the number of independent variables is virtually unlimited; and c) compared to other non-linear modeling techniques, the LCM has the advantage of being adaptive. It can detect novel patterns in the data stream and track rare patterns. This is particularly important in classification of biological states, viz, mutations to viruses.
  • the current invention was employed to develop a diagnostic for prostatic cancer using SELDI-TOF mass spectra (MS) of 55 patient serum samples, 30 having biopsy diagnosed prostatic cancer and prostatic serum antigen (PSA) levels greater than 4.0 ng/ml and 25 normals having PSA levels below 1 ng/ml.
  • MS data was abstracted by selection of 7 molecular weight values (2092, 2367, 2582, 3080, 4819, 5439 and 18,220 Da).
  • the specific molecular weights are not a critical parameter of the invention and may varying depending on the absorptive surface.
  • a cluster map that assigned each vector in the training data set to a homogeneous data cluster was generated. The cluster map contained 34 clusters, 17 benign and 17 malignant.
  • the diagnostic algorithm was tested using 231 samples that were excluded from the training data set. Six sets of samples from patients with various clinical and pathological diagnoses were used. The clinical and pathological description and the algorithm results were as follows: 1) 24 patients with PSA>4 ng/ml and biopsy proven cancer, 22 map to diseased data clusters, 2 map to no cluster; 2) 6 normal, all map to healthy clusters; 3) 39 with benign hypertrophy (BPH) or prostatitis and PSA ⁇ 4 ng/ml, 7 map to diseased data clusters, none to healthy data clusters and 32 to no data cluster; 4) 139 with BPH or prostatitis and PSA>4 and ⁇ 10 ng/ml, 42 map to diseased data clusters, 2 to healthy data clusters and 95 to no data cluster; 5) 19 with BPH or prostatitis and PSA>10 ng/ml, 9 map to diseased data clusters none to healthy and 10 to no data cluster.
  • a sixth set of data was developed by taking pre- and post-prostatectomy samples from patients having biopsy proven carcinoma and PSA>10 ng/ml. As expected, each of the 7 pre-surgical samples was assigned to a diseased data set. However, none of the sample taken 6 weeks post surgery, at a time when the PSA levels had fallen to below 1 ng/ml, were not assignable to any data set.
  • the diagnostic algorithm is able to classify a significant fraction of the samples in 3), 4) and 5) to a non-cancerous, non-normal category despite the fact that such category was not presented during training. Indeed, the fact that any samples from this group would necessarily include a substantial number with occult carcinoma carriers argues that BPH or prostatitis samples should not be included in the training data set.
  • the above described methods were employed to generate a diagnostic algorithm for ovarian carcinoma again using SELDI-TOF MS analysis of patient serum.
  • a training set of 100 samples was used to construct a cluster set map.
  • the MS data was abstracted by selection of 5 molecular weights (531, 681, 903, 1108 and 2863 m/e).
  • a cluster map consisting of 15 disease clusters and 11 healthy clusters was constructed.
  • 40 were assigned to diseased data clusters, leaving 10 false negative; of the 50 samples from normals, 44 were assigned to healthy data clusters leaving 6 false positives.
  • the range of values of the healthy and diseased data clusters overlapped. Indeed, for 4 of the 5 molecular weights, the range for the diseased encompassed the range for the healthy data clusters. Additionally, the diagnostic patterns being detected were not caused by tumor markers, but rather by contextual diagnostic products.
  • the diagnostic algorithm was tested using a further 100 samples, which were divided into three clinical, pathological groups.
  • the groups and the algorithm results were as follows: 1) 50 samples from patients with no disease, 47 were assigned to healthy data clusters and 3 to disease data clusters; 2) 32 patients with ovarian carcinoma Stages II, III or IV, all of which were assigned to diseased data clusters; and 3) 18 patients with ovarian carcinoma stage I, all of which mapped to diseased data clusters.
  • a pattern of mass intensities at 5 independent molecular weight regions of 534, 989, 2111, 2251, and 2465 Da discovered from a starting set of 15,0005 pattern permutations correctly segregated 98% (49/50) of the ovarian cancer samples and 94% of the controls (47/50) in the training set.
  • the optimal proteomic pattern challenged with 100 SELDI-TOF data streams from diagnosis-blinded cases was able to accurately predict the presence of ovarian cancer in all 50 cancer specimens contained within the 100 unknown test samples (50/50, 95% confidence interval 93% to 100%). This included the correct classification of 18/18 stage I cancers (95% confidence interval 82% to 100%) while maintaining specificity for the blinded cancer-free samples (47/50, 95% confidence interval 84% to 99%, overall p ⁇ 10 ⁇ 10 by chi-squared test). These results support the hypothesis that low molecular weight proteomic patterns in sera reflect changes in the pathology of tissue within an organ at a distant site. Moreover, such patterns may be sensitive indicators of early pathological changes, since they correctly classified all 18 sera from organ-confined stage I ovarian cancer specimens.
  • the training set was comprised of 56 sera, 31 from asymptomatic men with biopsy-proven prostate cancer (PSA>4 ng/ml, avg. 14.5 ng/ml), and 25 age-matched men with no evidence of prostate cancer (PSA ⁇ 1 ng/ml, avg. 0.3 ng/ml).
  • PSA asymptomatic men with biopsy-proven prostate cancer
  • PSA ⁇ 1 ng/ml avg. 0.3 ng/ml
  • the 56 sera were analyzed by SELDI-TOF.
  • the pattern discovery analysis found a signature pattern of the combined normalized intensities of 7 protein peaks (out of 15,000 7 possible permutations) at the specific molecular weights of 2092, 2367, 2582, 3080, 4819, 5439, and 18220 Da that could distinguish all 56 samples analyzed in the prostate sera training set.
  • the optimal proteomic pattern was tested with 227 blinded sera samples.
  • the blinded study set contained a) 24 sera from asymptomatic men who had subsequent biopsy-proven cancer, and whose PSA values were between 4-10 ng/ml at the time of collection, b) control sera from 6 age-matched males (PSA ⁇ 1 ng/ml) and c) 197 sera from men with biopsy-proven benign prostatic hypertrophy or prostatitis (PSA values ranged from 0.4 ng/ml to 36 ng/ml).
  • the data-mining tool was able to accurately predict the presence of prostate cancer in the blinded test set (92%, 22/24, p ⁇ 0.000001 compared to patients with BPH), including 17/18 containing PSA values of 4-10 ng/ml.
  • 70% of the patients (137/197) with biopsy proven BPH were classified as belonging to a unique (non-normal, non-cancer) phenotype.
  • Only 1% of the sera from the BPH-positive cohort was categorized as a normal phenotype.
  • sera from 6 healthy controls were compared to those of the 24 patients with biopsy proven cancer, 6/6 healthy patients were classified correctly, compared to 22/24 patients with prostate cancer (p ⁇ 0.000001).
  • the anonymized ovarian screening serum study set was obtained from the Early Detection Research Network (“EDRN”) National Ovarian Cancer Early Detection Program according to full Institutional Review Board (“IRB”) oversight.
  • EDRN Early Detection Research Network
  • IRB Institutional Review Board
  • This set contained sera from 200 asymptomatic women, 100 with ovarian cancer at the time of sample collection and 100 control women at risk for ovarian cancer as defined by family history or previous breast cancer diagnosis (Table 3). This group of unaffected women had been followed and was disease-free for at least five years. All sera were obtained prior to diagnosis and intervention.
  • the disease cohort included histology confirmed papillary serous, endometrioid, clear cell, mucinous, adenocarcinoma, and mixed ovarian cancers of all stages.
  • the anonymized prostate screening serum study set was obtained from a prostate cancer-screening clinic where samples were obtained under approved informed consent (277 samples) (Table 3). An additional 20 anonymized specimens were collected at the National Cancer Institute under IRB approved informed consent. The Chilean trial was initiated in 1996 and lasted for five years. The subject eligibility criteria required asymptomatic men over the age of 50 with no previous history of prostate cancer. All men provided a serum sample and then received a medical evaluation and a digital rectal examination. Subsequently, men with a serum PSA>4.0 ng/ml, or suspicious digital rectal examinations were subjected to a single core needle biopsy for pathologic diagnosis. The prostate adenocarcinomas represented were of a full spectrum of grades (I-III) and Gleason scores (4-9).
  • the 20 sera acquired at the NCI were taken from a) 7 men at the time of diagnosis and six weeks after prostatectomies for biopsy-proven organ confined prostate cancer and b) 6 normal healthy male volunteers, PSA ⁇ 1.0 ng/ml. All sera were obtained prior to medical examination, diagnosis, and treatment. All sera were collected, spun down, aliquoted and stored in liquid nitrogen until use. Received sera were thawed once, separated into 10 microliter aliquots, and then refrozen in liquid nitrogen until SELDI-TOF analysis was performed.
  • Sample preparation One microliter of acetonitrile (Sigma-Aldrich Co., St. Louis, Mo.) was added to the sample spots of the 8-feature C18 hydrophobic interaction protein chip (Ciphergen Biosystems, Inc., Freemont, Calif.). This chip will bind proteins through hydrophobic interactions that are dependent upon the intrinsic primary amino acid sequences specific for every protein.
  • the acetonitrile application was followed by the addition of 1 ⁇ l of serum. The sample was allowed to air dry on the chip. The chips were vigorously washed by vortexing in deionized water for 4 minutes and allowed to air dry. Lastly, 0.5 ⁇ l of CHCA solution was added.
  • SELDI-TOF like other time-of-flight spectrometric techniques, has its best sensitivity at the low molecular weight range ( ⁇ 20,000 Da). Data were recorded and optimized for analysis with the SELDI Protein Biology System version 2.0 software (Ciphergen Biosystems, Inc., Palo Alto, Calif.). Raw SELDI data, not filtered or scaled in any way, were converted to ASCII data files for analysis by the data-mining tool.
  • the method of the invention was tested on data streams obtained from biological samples from rats treated with doxorubicin that developed proven cardiotoxicity. Controls were treated with saline. The biological samples obtained from rats showing cardiotoxicity were classified correctly with 100% selectivity and 100% sensitivity and no false positives. See Table 4. TABLE 4 Count - Actual Actual Score 0 1 Total Result 0 29 29 1 1 7 8 Total Result 30 7 37 Sensitivity 100.00% Selectivity 0.00%
  • Nipple aspirants taken from breast cancer patients were analyzed using the process of the invention.
  • the nipple aspirants were subjected to a mass spectral analysis and subjected to a pattern finding method. A sensitivity of nearly 92% was observed. See Table 8. TABLE 8 Count - Actual Actual Score 0 1 Total Result 0 7 2 9 0.5 3 3 0.67 5 5 1 6 6 Total Result 10 13 23 Sensitivity @ 0.67 91.67% Selectivity @ 0.67 0.00%

Abstract

The invention describes a process for determining a biological state through the discovery and analysis of hidden or non-obvious, discriminatory biological data patterns. The biological data can be from health data, clinical data, or from a biological sample, (e.g., a biological sample from a human, e.g., serum, blood, saliva, plasma, nipple aspirants, synovial fluids, cerebrospinal fluids, sweat, urine, fecal matter, tears, bronchial lavage, swabbings, needle aspirantas, semen, vaginal fluids, pre-ejaculate.), etc. which is analyzed to determine the biological state of the donor. The biological state can be a pathologic diagnosis, toxicity state, efficacy of a drug, prognosis of a disease, etc. Specifically, the invention concerns processes that discover hidden discriminatory biological data patterns (e.g., patterns of protein expression in a serum sample that classify the biological state of an organ) that describe biological states.

Description

  • This application claims benefit under 35 U.S.C. sec. 119(e)(1) of the priority of applications Ser. No. 60/232,909, filed Sep. 12, 2000, Ser. No. 60/278,550, filed Mar. 23, 2001, Ser. No. 60/219,067, filed Jul. 18, 2000, and U.S. Provisional Application titled “A Data Method Algorithm Reveals Disease with Protein Signal of Ovarian and Prostate Cancer in Serum,” (Serial. No. to be assigned), filed May 8, 2001 which is hereby incorporated by reference in its entirety.
  • FIELD OF THE INVENTION
  • The field of the invention concerns a process for determining a biological state through the discovery and analysis of hidden or non-obvious, discriminatory biological data patterns. The biological data can be from health data, clinical data, or from a biological sample, (e.g., a biological sample from a human, e.g., serum, blood, saliva, plasma, nipple aspirants, synovial fluids, cerebrospinal fluids, sweat, urine, fecal matter, tears, bronchial lavage, swabbings, needle aspirantas, semen, vaginal fluids, pre-ejaculate, etc.), etc. which is analyzed to determine the biological state of the donor. The biological state can be a pathologic diagnosis, toxicity state, efficacy of a drug, prognosis of a disease, etc.
  • Specifically, the invention concerns analytical methods that a) discover hidden discriminatory biological data patterns (e.g., patterns of protein expression in a serum sample that classify the biological state of an organ) that are subsets of the larger data stream, said discrimination implying the ability to distinguish between two or more biological states in a learning set of data and b) the application of the aforementioned patterns to classify unknown or test samples. More specifically, the invention concerns a method for analysis of a data stream, which is derived from a physical or chemical analysis of molecules (e.g., proteins, peptides, DNA, RNA, etc.) in the biological sample (e.g., a mass spectrum analysis of the sample).
  • These patterns are defined as “hidden” because they are often buried within a larger highly complex data set and are not obvious or apparent to the eye or other current classification systems. The pattern itself can be defined as the combination of three or more values such that the position of the vectors in an n-dimensional space is discriminatory between biological states even when individual values may not be discriminatory. The discriminatory patterns of the invention are novel because they can be defined without any knowledge of the identity or relationship between the individual data points in the biological data or any knowledge of the identity or relationship between the molecules in the biological samples.
  • One analytical method to discover such biological states comprises the application of two related heuristic algorithms, a learning algorithm and a diagnostic algorithm, wherein the parameters of the diagnostic algorithm are set by the application of the learning algorithm to a learning set of data such that two or more biological states may be distinguished. Such biological states may be the presence or absence of a disease, efficacy or non-efficacy of a drug, toxicity or non-toxicity of a drug, etc. Although the invention is generic, specific implementations for diagnosis of various cancers (including, but not limited to carcinomas, melanomas, lymphomas, sarcomas, blastomas, leukemias, myelomas, neural tumors, etc., and cancers of organs like the ovary, prostate, and breast), presence of a pathogen, and toxicity are disclosed. The preferred embodiment of the invention is the discovery and use of molecular patterns that reflect the current or future biological state of an organ or tissue. Another embodiment of the invention is the combination of data describing the molecular patterns of a biological state with other non-biological or clinical data (e.g., psychiatric questioning) to yield a classification describing the health of a patient.
  • BACKGROUND OF THE INVENTION
  • The detection of changes in biological states, particularly the early detection of diseases has been a central focus of the medical research and clinical community. The prior art includes examples of efforts to extract diagnostic information from the data streams formed by physical or chemical analysis of tissue samples. These techniques are generically termed “data-mining.” The data streams that have been mined are typically of two forms: analysis of the levels of mRNA expression by hybridization to DNA oligonucleotide arrays (“DNA microarrays”) and analysis of the levels of proteins present in a cell or in a serum sample, wherein the proteins are characterized either by molecular weight using mass spectroscopy or by a combination of molecular weight and charge using a 2-D gel technique.
  • Rajesh Parekh and colleagues have described protein based data-mining diagnosis of hepatocellular cancer using serum or plasma samples (WO 99/41612), breast cancer using tissue samples (WO 00/55628) and rheumatoid arthritis using serum or plasma samples (WO 99/47925). In each publication, a two dimensional gel analysis is performed. The analysis consists of measuring the levels of individual proteins as determined by the 2-D gels and identifying those proteins that are elevated or depressed in the malignant as compared to the normal tissue.
  • Liotta and Petricoin (WO 00/49410) provide additional examples of protein based diagnostic methods using both 2-D gels and mass spectroscopy. However, the analysis of Liotta and Petricoin is similar to Parekh in that it consists of a search for specific tumor markers. Efforts to identify tumor markers have also been performed using DNA microarrays. Loging, W. T., 2000, Genome Res. 10, 1393-02, describes efforts to identify tumor markers by DNA microarrays in glioblastoma multiforme. Heldenfalk, I., et al., 2001, New England J. Med. 344, 539, report efforts to identify tumor markers that distinguish the hereditary forms of breast cancer resulting from BRCA1 and BRCA2 mutations from each other and from common idiopathic breast cancer by data-mining of DNA microarray data.
  • Alon et al., 1999, PNAS 96, 6745-50, describe the use of DNA microarray techniques to identify clusters of genes that have coordinated levels of expression in comparisons of colonic tumor samples and normal colonic tissue. These studies did, in fact, identify genes that were relatively over or under expressed in the tumor compared to normal tissue. However, the clustering algorithm was not designed to be able to identify diagnostic patterns of gene expression other than a tumor marker type pattern.
  • Data-mining efforts directed towards indicators other than tumor markers have been used for diagnosis. These efforts routinely employ pattern recognition methods to identify individual diagnostic markers or classify relationships between data sets. The use of pattern recognition methods to classify genes into categories based on correlated expression under a variety of different conditions was pioneered by Eisen, M., et al., 1998, PNAS 95, 14863-68; Brown, M P S, et al., 2000, PNAS 97, 262-67 and Alter, O., et al., 2000, PNAS 97, 10101-06. In general, these techniques use a vector space in which each vector corresponds to a gene or location on the DNA micro array. Each vector is composed of scalars that individually correspond to the relative levels of expression of the gene under a variety of different conditions. Thus, for example, Brown et al. analyzes vectors in a 79 dimension vector space where each dimension corresponds to a time point in a stage of the yeast life-cycle and each of 2,467 vectors correspond to a gene. The pattern recognition algorithms are used to identify clusters of genes whose expression is correlated with each other. Because the primary concern is the correlation of gene expression, the metric that is employed in the pattern recognition algorithms of Eisen et al. and related works is a Pearson coefficient or inner product type metric, not a Euclidean distance metric. Once clustering is established, the significance of each cluster is determined by noting any common, known properties of the genes of a cluster. The inference is made that the heretofore uncharacterized genes found in the same cluster may share one or more of these common properties.
  • The pattern recognition techniques of Eisen et al. were applied by Alizadeh and Staudt to the diagnosis of types of malignancy. Alizadeh and Staudt began by constructing vectors, each corresponding to a gene, having scalars that correspond to the relative level of expression of the gene under some differentiation condition, e.g., resting peripheral blood lymphocyte or mitogen stimulated T cells. The pattern recognition algorithm then clusters the genes according to the correlation of their expression and defines a pattern of expression characteristic of each differentiation state. Samples of diffuse large B-cell lymphomas (DLBCL) were then analyzed by hybridization of mRNA to the same DNA microarrays as used to determine the gene clusters. DLBCL were found to have at least two different gene expression patterns, each characteristic of a normal differentiation state. The prognosis of the DLBCL was found to correlate with the characteristic differentiation state. Thus, the diagnostic question posed and answered in Alizadeh and Staudt was not benign or malignant but rather of determining the type or subtype of malignancy by identifying the type of differentiated cell having a pattern of gene expression most similar to that of the malignancy. Alizadeh et al., 2000, Nature 403, 503-511. Similar techniques have been used to distinguish between acute myeloid leukemia and acute lymphocytic leukemia. Golub, T. R., et al., 1999, Science 286, 531-537.
  • Accordingly, it can be seen that data-mining methods based on the physical or chemical analyses having large numbers, i.e., greater than 1,000, of data points consist of two types: data-mining to identify individual markers such as genes or proteins having expression levels that are increased or suppressed in malignant cells of a defined type compared to normal cell; and data-mining wherein a pattern of known gene expression characteristic of a normal differentiated cell type is used to classify a known malignant cell according to the normal cell type it most closely resembles.
  • Thus, there is a need for methods that can determine biological states using biological data other than single markers (such as tumor markers), or gene expression clusters. Usually, the role that single markers play in the pathology of a disease must be known and established, quite often at great cost, prior to the analysis of a biological sample. Additionally, these markers are often localized in internal organs or tumors, and complex, invasive, localized biopsies must be performed to obtain biological samples containing such markers. Given the complexity of biological states such as a disease there is an exceptional need for the ability to diagnose biological states using complex data inherent to such biological states without prior extensive knowledge of the relationship of molecules present in such samples to each other.
  • Additionally, gene expression cluster analysis is limited in scope because such analysis incorporates an analysis of all expressed genes irrespective of whether the expression of such genes is causative or merely influenced by the causative action of those genes that are characteristic of the biological state. The clustering analysis does not incorporate solely those genes that are characteristic of the biological state of interest, but uses the entire range of data emanating from the assay, thus making it complex and cumbersome. Furthermore, gene expression analysis must involve nucleic acid extraction methods, making it complex, and time-consuming. Pattern recognition algorithms when applied are also rendered difficult because the correlation of gene expression that is employed is a complex Pearson coefficient or inner product type metric, and not a simple Euclidean distance metric.
  • In contrast to the prior art, the current invention discovers optimal hidden molecular patterns as subsets within a larger complex data field, whereby the pattern itself is discriminatory between biological states. Thus, the current invention avoids all the aforementioned problems associated with the analytical methods disclosed in the prior art, and has the ability to discover heretofore unknown diagnostic patterns. Such hidden molecular patterns are present in data streams derived from health data, clinical data, or biological data. Biological data may be derived from simple biological fluids, such as serum, blood, saliva, plasma, nipple aspirants, synovial fluids, cerebrospinal fluids, sweat, urine, fecal matter, tears, bronchial lavage, swabbings, needle aspirantas, semen, vaginal fluids, pre-ejaculate, etc., making routine sampling easy, although the expression of such molecular patterns are characteristic of disease states of remote organs. No prior knowledge of specific tumor markers or the relationship of molecules present in the biological sample to each other is required or even desired. The current invention also discloses methods of data generation and analysis. Such methods of data analysis incorporate optimization algorithms in which the molecular patterns are recognized, and subjected to a fitness test in which the fitness pattern that best discriminates between biological states is chosen for the analysis of the biological samples.
  • SUMMARY OF THE INVENTION
  • The invention comprises the use of pattern discovery methods and algorithms to detect subtle, if not totally hidden, patterns in the expression of certain molecules in biological samples that are potentially diagnostic in nature, or predictive of a biological state. In one embodiment of the invention such patterns of molecular expression are patterns of protein expression, particularly patterns of low molecular weight proteins (i.e. less than 20,000 Da). Such hidden patterns of protein expression may be obtained from only a sub-set of the total data-stream provided to the algorithm, several subsets, or may be obtained from an analysis of the total data stream. The pattern can be defined as a vector of three or more values such that the position of the vectors in an n-dimensional space is discriminatory between biological states even when individual values may not be discriminatory. The molecules of interest may be any relevant biological material such as proteins (full, cleaved, or partially expressed), peptides, phospholipids, DNA, RNA, etc.
  • The discriminatory patterns that discriminate between biological states are often small subsets of data hidden in the larger data stream derived from physical or chemical analysis of the biological sample. Thus, in order to find such discriminatory patterns that distinguish between biological states, a means for finding an optimal set of features that make up the discriminatory pattern is required. The invention incorporates the process for finding this optimal set of features. A number of feature selection methods for discriminatory patterns may be used to practice the invention with varying degrees of classification success. These include, but are not limited to, statistical methods, stepwise regression methods, linear optimization methods, etc. However, statistical methods have some limitations in that they are often linear, at least in their simple, well-known forms such as multivariate linear regressions. Furthermore, statistical models tend not to be robust with respect to non-linear data. The number of independent variables a statistical model can successfully employ is generally ten or less, with a practical preferred limit of five or six. The preferred embodiment uses a method that couples the genetic algorithm, an evolutionary computation method, directly to an adaptive pattern recognition algorithm to efficiently find the optimal feature set. See U.S. Patent Application titled “Heuristic Method of Classification,” (filing date: Jun. 19, 2001, claiming priority of application Ser. No. 60/212,404, filed Jun. 19, 2000).
  • One method disclosed by this invention consists of two related heuristic algorithms, a diagnostic algorithm and a learning algorithm. The diagnostic algorithm is generated by the application of the learning algorithm to a learning (or training) data set. The learning data set is a data set formed from biological samples for which the biological state of interest is provided for the pattern discovery operation. For instance, the learning data set may comprise data taken from the sera of individuals with an established biopsy diagnosis, e.g., a benign tumor and a malignant tumor. This would enable the learning algorithm to find a signature pattern of proteins that could discriminate normal from cancerous sera samples.
  • In one embodiment, the method according to the invention begins by subjecting a biological sample to a high throughput physical or chemical analysis to obtain a data stream. Such data streams include, but are not limited to, mass spectral data of proteins found in the sample or in the intensity of mRNA hybridization to an array of different test polynucleotides. Generally, the data stream is characterized by a large number (10,000 or more) of intensities which are generated in a way that allow for the corresponding individual datum in data streams of different samples to be identified.
  • The first step of the diagnostic method is to calculate a vector, i.e., an ordered set of a small number (between 2 and 20100, more typically between 5 and 208) that is characteristic of the data stream. The transformation of the data steam into a vector is termed “abstraction.” In the present embodiments, abstraction is performed by selection of a small number of specific intensities from the data stream.
  • The second step of the diagnostic method is to determine in which, if any, data cluster the vector rests. Data clusters are mathematical constructs that are the multidimensional equivalents of non-overlapping “spheres” of fixed size in the vector space. Such data clusters are known as hyperspheres. The location and associated diagnosis of each data cluster is determined by the learning algorithm from the training data set. If the vector of the biological sample lies within a known cluster, the sample is given the diagnosis associated with that cluster. If the sample vector rests outside of any known cluster a diagnosis can be made that the sample does not meet that classification criteria or that it is of an unspecified atypia, i.e., an “atypical sample, NOS.” For example, if a biological sample taken from a patient does not meet the classification of a malignant state for a specified cancer, it will be classified as non-malignant non-normal or of an unspecified atypia, “atypical sample, NOS.”
  • The learning algorithm utilizes a combination of known mathematical techniques and two pre-set parameters. The user pre-sets the number of dimensions of the vector space and the size of the data clusters. Typically, the vector space is a normalized vector space such that the variation of intensities in each dimension is constant. Thus, the size of the cluster can be expressed as a minimum percent similarity among the vectors resting within the cluster.
  • In one embodiment, the learning algorithm contains of two generic parts, which have been developed by others and are well known in the field—a genetic algorithm (J. H. Holland, Adaptation in Natural and Artificial Systems, MIT Press 1992) and a self-organizing adaptive pattern recognition system (T. Kohonen, Self Organizing and Associative Memory, 8 Series in Information Sciences, Springer Verlag, 1984; Kohonen, T, Self-organizing Maps, Springer Verlag, Heidelberg 1997 ). Genetic algorithms organize and analyze complex data sets as if they were information comprised of individual elements that can be manipulated through a computer driven natural selection process.
  • In the present invention, the search for hidden or subtle patterns of molecular expression that are, in and of themselves “diagnostic” is qualitatively different from those generated by prior art implementations of learning algorithms or data-mining techniques. Previous implementations of data-mining have identified specific molecular products that are indicative of a classification, e.g., proteins or transcripts that are elevated or depressed in pathological conditions. Thus, the level of the identified molecular products is termed per se diagnostic, because the level of the product is diagnostic without any further consideration of the level of any other molecular products in the sample, other than perhaps a normalizing molecular product that is used to normalize the level of the molecular products. One example of such per se diagnostic molecular products are tumor markers.
  • By contrast, in the data cluster analysis according to the invention, the diagnostic significance of the level of any particular marker, e.g., a protein or transcript is a function of the levels of the other elements that are used to calculate the sample vector. Such products are termed hereinafter as contextual diagnostic products. Thus, in prior implementations of data-mining techniques, the likeness between the biological sample of interest and the learning data set was based on the specified groupings of the biological sample compared to the specified diagnostic molecular products. However, in the invention, the learning algorithm discovers wholly new classification patterns without knowing any prior information about the identity or relationships of the data pattern, i.e., without prior input that a specified diagnostic molecular product is indicative of a particular classification.
  • The present invention is based, in part, on the unexpectedness or non-obvious discovery of finding hidden contextual diagnostic patterns to yield a classification, e.g., the diagnosis of malignancy in cancers such as carcinomas, melanomas, lymphomas, sarcomas, blastomas, leukemias, myelomas, and neural tumors.
  • DETAILED DESCRIPTION OF THE INVENTION
  • The invention comprises a) creating a data stream representing the biological data (or combinations of data streams representing the biological data with clinical, health, or non-biological data) and abstraction of that data into characteristic vectors; b) the discovery of hidden diagnostic patterns of molecular expression (i.e. pattern discovery); and c) determining which biological state of interest such a pattern of molecular expression represents. The molecules of interest may comprise, but are not limited to, proteins, peptides, RNA, DNA, etc. The biological samples comprise, but are not limited to serum, blood, saliva, plasma, nipple aspirants, synovial fluids, cerebrospinal fluids, sweat, urine, fecal matter, tears, bronchial lavage, swabbings, needle aspirantas, semen, vaginal fluids, pre-ejaculate, etc.
  • The biological states of interest may be a pathologic diagnosis, toxicity state, efficacy of a drug, prognosis of a disease, stage of a disease, biological state of an organ, presence of a pathogen (e.g., a virus), toxicity of one or more drugs, etc. The invention may be used for the diagnosis of any disease in which changes in the patterns of expression of certain molecules like proteins allow it to be distinguished from a non-diseased state. Thus, any disease that has a genetic component in which the genetic abnormality is expressed, one in which the expression of drug toxicity is observed, or one in which the levels of molecules in the body are affected may be studied by the current invention. Such diseases include, but are not limited to, cancers (carcinomas, melanomas, lymphomas (both Hodgkin's and non-Hodgkin's type), sarcomas, blastomas, leukemias, myelomas, and neural tumors, such as glioblastoma, etc.), Alzheimer's disease, arthritis, glomeruulonephritis, auto-immune diseases, etc. Examples of carcinomas include, but are not limited to, carcinomas of the pancreas, kidney, liver and lung; gastrointestinal carcinomas.
  • The present invention is particularly valuable for the diagnosis of specific diseases for which early diagnosis is important, but is technically difficult because of the absence of symptoms, and for which the disease may be expected to produce differences that are detectable in the serum because of the metabolic activity of the pathological tissue. Thus, the early diagnosis of malignancies are a primary focus of the use of the invention.
  • The particular components of the invention are described below.
  • A. Creation of the Data Stream
  • The data stream can be any reproducible physical or chemical analysis of the biological sample that results in a high throughput data stream. Preferably, the high throughput data stream is characterized by 1,000 or more measurements that can be quantified to at least 1 part per thousand (three significant figures) and more preferably one part in 10,000. There exist numerous methods for the generation of data streams. In one embodiment of the invention when the molecules of interest are proteins or peptides, “time of flight” mass spectra of proteins may be used to generate a data stream. More specifically, matrix assisted laser desorption ionization time of flight (MALDI-TOF) and surface enhanced laser desorption ionization time of flight (SELDI-TOF) spectroscopy may be used when the molecules of interest are proteins or peptides. See generally WO 00/49410. In one embodiment, SELDI-TOF may be used to generate data streams for biological states representing toxicity, and detection of pathogens. In yet another embodiment, data streams may be generated using serially amplified gene expression (SAGE) for gene expression classification. In some circumstances, data streams may be generated using 2-D Gels such as two-dimensional polyacrylamide gel electrophoreses (2D-PAGE).
  • For clinical pathology, the preferred patient sample for analysis is serum. However, biopsy specimens that are relatively homogenous may also be used. For certain disease states, other fluids can be used, e.g., synovial fluid may be used in the differential diagnosis of arthritis or urine in the differential diagnosis of glomerulonephritis.
  • The particular proteins that are included in either SELDI-TOF and MALDI-TOF analysis depend upon the surface or matrix that is employed. Lipophylic surfaces such as C-18 alkane surfaces are particularly convenient compared to anionic or cationic surfaces. However, those skilled in the art will appreciate that multiple spectra can be generated from the same sample using different surfaces. These spectra can be concatenated to yield “superspectra” which can be analyzed according to the invention. Likewise, data from two or more high throughput assay methods can also be joined which can be analyzed by the invention. Furthermore, biological data as described in this invention can be joined with clinical, health, or non-biological data.
  • Whatever surface, matrix or combination of surfaces and matrixes are to be used, great care must be exercised to ensure that the surfaces are uniform from one biological sample to the next.
  • The data stream can also include measurements that are not inherently organized by a single ordered parameter such as molecular weight, but have an arbitrary order. Thus, DNA microarray data that simultaneously measures the expression levels of 2,000 or more genes can be used as a data stream when the tissue sample is a biopsy specimen, recognizing that the order of the individual genes in the data stream is arbitrary.
  • Those skilled in the art will appreciate that in keeping with the available commercial embodiments of the instruments, the description of the invention considers the generation of the data stream from a biological sample and the abstraction of the data stream based on the optimal logical chromosome to be two separate processes. However, it is apparent that only routine design choices would allow for the measuring instrument itself to perform the abstracting function. This in no way changes the contribution of the invention to such a diagnostic method and the claims are to be construed as allowing the abstraction and vector analysis portions of the claimed diagnostic method to be performed on different computing devices.
  • It should be noted that a single data stream from a patient sample can be analyzed for multiple diagnoses using the method of the invention. The additional cost of such multiple analysis would be trivial because the steps specific to each diagnosis are computational only.
  • B. The Abstraction Process
  • The first step in the diagnostic process of the invention is the transformation or abstraction of the data stream into a characteristic vector. The data may be conveniently normalized prior to abstraction by assigning the overall peak an arbitrary value of 1.0 and, thus, all other points fractional values. For example, in the embodiment in which the data stream is generated by TOF Mass spectra, the most simple abstraction of TOF mass spectrum consists of the selection of a small number of data points. Those skilled in the art will recognize that more complex functions of multiple points could be constructed, such as averages over intervals or more complex sums or differences between data points that are at predetermined distance from a selected prototype data point. Such functions of the intensity values of the data stream could also be used and are expected to function equivalently to the simple abstract illustrated in the working examples.
  • Those skilled in the art will also appreciate that routine experimentation can determine whether abstraction by taking the instantaneous slope at arbitrary points could also function in the present invention. Accordingly, such routinely available variations of the illustrated working examples are within the scope of the invention.
  • C. Pattern Discovery
  • Pattern discovery is achieved by numerous methods as discussed in the Summary above. However, in a preferred embodiment, the pattern discovery comprises a diagnostic algorithm and a learning algorithm. Thus, in order to practice this embodiment of the invention the routine practitioner must develop a diagnostic algorithm by employing a learning algorithm. To employ the learning algorithm, the routine practitioner uses a training data set and must select two parameters, the number of dimensions and the data cluster size. See U.S. Patent Application titled “Heuristic Method of Classification,” (filing date: Jun. 19, 2001, claiming priority of application Ser. No. 60/212,404, filed Jun. 19, 2000).
  • In one embodiment, the learning algorithm can be implemented by combining two different types of publicly available generic software, which have been developed by others and are well known in the field—a genetic algorithm (J. H. Holland, Adaptation in Natural and Artificial Systems, MIT Press 1992) that processes a set of logical chromosomes1 to identify an
    1The term logical chromosome is used in connection with genetic learning algorithms because the logical operations of the algorithm are analogous to reproduction, selection, recombination and mutation. There is, of course, no biological embodiment of a logical optimal logical chromosome that controls the abstraction of the data steam and a adaptive self-organizing pattern recognition system (see, T. Kohonen, Self Organizing and Associative Memory, 8 Series in Information Sciences, Springer Verlag, 1984; Kohonen, T, Self-organizing Maps, Springer Verlag, Heidelberg 1997), available from Group One Software, Greenbelt, Md., which identifies a set of data clusters based on any set of vectors generated by a logical chromosome. Specifically, the adaptive pattern recognition software maximizes the number of vectors that rest in homogeneous data clusters, i.e., clusters that contain vectors of the learning set having only one classification type.
  • The genetic algorithm essentially determines the data points which are used to calculate the characteristic vector. However, in keeping with the nomenclature of the art, the list of the specific points to be selected is termed a logical chromosome. The logical chromosome contains as many “genes” as there are dimensions of the characteristic vector. Any set of the appropriate number of data points can be a logical chromosome, provided only that no gene of a logical chromosome is duplicated. The order of the genes has no significance to the invention.
  • Genetic algorithms can be used when two conditions are met. A particular solution to a problem must be able to be expressed by a set or string of fixed size of discrete elements, which elements can be numbers or characters, and the strings can be recombined to yield further solutions. One must also be able to calculate a numerical value of the relative merit of each solution, namely its fitness. Under these circumstances, the details of the genetic algorithm are unrelated to the problem whose solution is sought. Accordingly, for the present invention any generic genetic algorithm software may be employed. The algorithms PGAPack
    chromosome in DNA or otherwise. The genetic learning algorithms of the invention are purely computational devices, and should not be confused with schemes for biologically-based information processing. libraries, available from Argonne National Laboratory is suitable. The calculation of the fitness of any particular logical chromosome is discussed below.
  • In the illustrative examples, a training data set of about 100 sample data streams was used, each sample data stream containing about 15,000 data points. The genetic algorithms were initialized with about 1,500 randomly chosen logical chromosomes. As the algorithm progressed, the more fit logical chromosomes are duplicated and the less fit are terminated. There is recombination between logical chromosomes and mutation, which occurs by the random replacement of an element of a logical chromosome. It is not an essential feature of the invention that the initially selected collection of logical chromosome be random. Certain prescreening of the total set of data streams to identify those data points having the highest variability may be useful, although such techniques may also introduce an unwanted initialization bias. The best fitted pattern that survives this process is used to discriminate between biological states and determine the desired classification.
  • D. The Pattern Recognition Process and Fitness Score Generation
  • The fitness score of each of the logical chromosomes that are generated by the genetic algorithm is calculated. The calculation of the fitness score requires an optimal set of data clusters be generated for the given logical chromosome. Data clusters are simply the volumes in the vector space in which the characteristic vectors of the training data set rest. The method of generating the optimal set of data clusters is not critical to the invention and will be considered below. However, whatever method is used to generate the data cluster map, the map is constrained by the following rules: (i) each data cluster should be located at the centroid of the data points that lie within the data cluster; (ii) no two data clusters may overlap; and (iii) the dimension of each cluster in the normalized vector space is fixed prior to the generation of the map.
  • As stated above, to employ the learning algorithm, the routine practitioner must use a learning data set and select two parameters, the number of dimensions and the data cluster size. Both parameters can be set using routine experimentation. Although there is no absolute or inherent upper limit on the number of dimensions in the vector, the learning algorithm itself inherently limits the number of dimensions in each implementation. If the number of dimensions is too low or the size of the cluster is too large, the learning algorithm fails to generate any logical chromosomes that correctly classify all samples into homogeneous clusters, and conversely if the number of dimensions can be too large. Under this circumstance, the learning algorithm generates many logical chromosomes that have the maximum possible fitness early in the learning process and, accordingly, there is only abortive selection. Similarly, when the size of the data clusters is too small, the number of clusters will be found to approach the number of samples in the training data set and, again, the routine practitioner will find that a large number of logical chromosomes will yield the maximum fitness.
  • Those skilled in the art understand that a training data set can nearly always be assigned into homogeneous data clusters. Thus, the value of the diagnostic algorithm generated by a learning algorithm must be tested by its ability to sort a set of data other than the training data set. When a learning algorithm generates a diagnostic algorithm that successfully assigns the training data set but only poorly assigns the test data set, the training data is said to be overfitted by the learning algorithm. Overfitting results when the number of dimensions is too large and/or the size of the data clusters is too small.
  • The method used to define the size of the data cluster is a part of the invention. The cluster size is defined by the maximum of the equivalent the Euclidean distance (root sum of the squares) between any two members of the data cluster. A data cluster size that corresponds to a requirement of 90% similarity is suitable for the invention when the data stream is generated by SELDI-TOF mass spectroscopy data. Mathematically, 90% similarity is defined by requiring that the distance between any two members of a cluster is less than 0.1 of the maximum distance between two points in a normalized vector space. For this calculation, the vector space is normalized so that the range of each scalar of the vectors within the training data set is between 0.0 and 1.0. Thus normalized, the maximal possible distance between any two vectors in the vector space is then root N, where N is the number of dimensions. The Euclidean diameter of each cluster is then 0.1 × root (N).
  • The specific normalization of the vector space is not a critical feature of the method. The foregoing method was selected for ease of calculation. Alternative normalization can be accomplished by scaling each dimension not to the range but so that each dimension has an equal variance.
  • Those skilled in the art will ftrther recognize that the data stream may be converted into logarithmic form if the distribution of values within the data stream is log normal and not normally distributed.
  • Once the optimal set of data clusters for a logical chromosome has been generated, the fitness score for that chromosome can be calculated. For the present invention, the fitness score of the chromosome roughly corresponds to the number of vectors of the training data set that rest in clusters that are homogeneous, i.e., clusters that contain the characteristic vectors from samples having a single diagnosis. More precisely, the fitness score is calculated by assigning to each cluster a homogeneity score, which varies, for example, from 0.0 for homogeneous clusters to 0.5 for clusters that contain equal numbers of malignant and benign sample vectors. The fitness score of the chromosome is the average fitness score of the data clusters. Thus, a fitness score of 0.0 is the most fit. There is a bias towards logical chromosomes that generate more data clusters, in that when two logical chromosomes that have equal numbers of errors in assigning the data, the chromosome that generates the more clusters will have a lower average homogeneity score and thus a better fitness score.
  • A preferred technique for generating for generating data clusters is using the self-organizing map algorithm as developed by Kohonen. (Kohonen, T, Self-organizing maps, Springer Verlag, Heidelberg 1997). This type of technique is variously termed a “Lead Cluster Map” (“LCM”) or an “Adaptive Feature Map” can be implemented by generic software that is publicly available. Suitable vendors and products include Model 1 from Group One Software (Greenbelt, Md.) and Adaptive Fuzzy Feature Map (American Heuristics Corp.). The LCM has significant advantages in that it is a) it is a non-linear modeling method; b) the number of independent variables is virtually unlimited; and c) compared to other non-linear modeling techniques, the LCM has the advantage of being adaptive. It can detect novel patterns in the data stream and track rare patterns. This is particularly important in classification of biological states, viz, mutations to viruses.
  • E. Description and Verification of Specific Embodiments
      • 1. Development of a Diagnostic for Prostatic Cancer
  • Using the above-described learning algorithm, the current invention was employed to develop a diagnostic for prostatic cancer using SELDI-TOF mass spectra (MS) of 55 patient serum samples, 30 having biopsy diagnosed prostatic cancer and prostatic serum antigen (PSA) levels greater than 4.0 ng/ml and 25 normals having PSA levels below 1 ng/ml. The MS data was abstracted by selection of 7 molecular weight values (2092, 2367, 2582, 3080, 4819, 5439 and 18,220 Da). The specific molecular weights are not a critical parameter of the invention and may varying depending on the absorptive surface. A cluster map that assigned each vector in the training data set to a homogeneous data cluster was generated. The cluster map contained 34 clusters, 17 benign and 17 malignant.
  • The diagnostic algorithm was tested using 231 samples that were excluded from the training data set. Six sets of samples from patients with various clinical and pathological diagnoses were used. The clinical and pathological description and the algorithm results were as follows: 1) 24 patients with PSA>4 ng/ml and biopsy proven cancer, 22 map to diseased data clusters, 2 map to no cluster; 2) 6 normal, all map to healthy clusters; 3) 39 with benign hypertrophy (BPH) or prostatitis and PSA <4 ng/ml, 7 map to diseased data clusters, none to healthy data clusters and 32 to no data cluster; 4) 139 with BPH or prostatitis and PSA>4 and <10 ng/ml, 42 map to diseased data clusters, 2 to healthy data clusters and 95 to no data cluster; 5) 19 with BPH or prostatitis and PSA>10 ng/ml, 9 map to diseased data clusters none to healthy and 10 to no data cluster. A sixth set of data was developed by taking pre- and post-prostatectomy samples from patients having biopsy proven carcinoma and PSA>10 ng/ml. As expected, each of the 7 pre-surgical samples was assigned to a diseased data set. However, none of the sample taken 6 weeks post surgery, at a time when the PSA levels had fallen to below 1 ng/ml, were not assignable to any data set. These results are summarized in Table 1.
  • When evaluating the results of the foregoing test, it should be recalled that the rate of occult carcinoma in patients having PSA of 4-10 ng/ml and benign biopsy diagnosis is about 30%. Thus, the finding that between 18% and 47% of the patients with elevated PSA, but no tissue diagnosis of cancer, is consistent with a highly accurate assay that correctly predicts the presence of carcinoma.
  • Of greater present interest is the fact that the diagnostic algorithm is able to classify a significant fraction of the samples in 3), 4) and 5) to a non-cancerous, non-normal category despite the fact that such category was not presented during training. Indeed, the fact that any samples from this group would necessarily include a substantial number with occult carcinoma carriers argues that BPH or prostatitis samples should not be included in the training data set.
    TABLE 1
    PREDICTED PHENOTYPE
    STUDY SET N CANCER(%) NORMAL(%) OTHER(%)
    Biopsy proven cancer 24 22 (92%) 0 (0%) 2 (8%)
    (PSA > 4 ng/ml)a
    Control Men 6 0 (0%)  6 (100%) 0 (0%)
    (PSA > 1 ng/ml)
    Biopsy provenBPH/Prostatitis 39  7 (18%) 0 (0%) 32 (82%)
    (PSA > 4 ng/ml)
    Biopsy provenBPH/Prostatitisb 139 42 (30%) 2 (1%) 95 (68%)
    (PSA4 −10 ng/ml)
    Biopsy provenBPH/Prostatitis 19  9 (47%) 0 (0%) 10 (52%)
    (PSA > 10 ng/ml)
    Biopsy proven cancer PRE-SURGERYc 7  7 (100%) 0 (0%) 0 (0%)
    (PSA > 10 ng/ml)
    Biopsy proven cancer POST-SURGERYc,d 7 0 (0%) 0 (0%)  7 (100%)
    (PSA > 1 ng/ml)

    aMale subjects entered in screening trial; entrance criteria: >50 years old, asymptomatic. Biopsy conducted it PSA > 4 ng/ml or a positive digital rectal exam. Includes 6 patients with PSA > 10 ng/ml and 18 patients with PSA 4-10 ng/ml.

    b30-35% occult cancer expected

    cPatient-matched

    dSerum taken at six-week post-surgery follow-up
      • 2. Development of a Diagnostic for Ovarian Cancer
  • The above described methods were employed to generate a diagnostic algorithm for ovarian carcinoma again using SELDI-TOF MS analysis of patient serum. A training set of 100 samples was used to construct a cluster set map. The MS data was abstracted by selection of 5 molecular weights (531, 681, 903, 1108 and 2863 m/e). A cluster map consisting of 15 disease clusters and 11 healthy clusters was constructed. Of the 50 samples in the training data set having proven ovarian cancer, 40 were assigned to diseased data clusters, leaving 10 false negative; of the 50 samples from normals, 44 were assigned to healthy data clusters leaving 6 false positives.
  • It was observed that for each of the selected molecular weights, the range of values of the healthy and diseased data clusters overlapped. Indeed, for 4 of the 5 molecular weights, the range for the diseased encompassed the range for the healthy data clusters. Additionally, the diagnostic patterns being detected were not caused by tumor markers, but rather by contextual diagnostic products.
  • The diagnostic algorithm was tested using a further 100 samples, which were divided into three clinical, pathological groups. The groups and the algorithm results were as follows: 1) 50 samples from patients with no disease, 47 were assigned to healthy data clusters and 3 to disease data clusters; 2) 32 patients with ovarian carcinoma Stages II, III or IV, all of which were assigned to diseased data clusters; and 3) 18 patients with ovarian carcinoma stage I, all of which mapped to diseased data clusters. These results are summarized in Table 2.
    TABLE 2
    Predicted Predicted
    Cohort N Cancer Negative Accuracy
    No Evidence of 50 3 47  94%
    Disease
    Biopsy Proven 32 32 0 100%
    Ovarian Cancer
    Stage II, III, IV
    Biopsy Proven 18 18 0 100%
    Ovarian Cancer
    Stage I
      • 3. Sensitivity for Early Stage Disease
  • A set of randomly chosen sera (50 from the control cohort and 50 sera from the disease cohort) within the ovarian cancer study set of 200 specimens was selected for SELDI-TOF mass spectrometry analysis and subsequent training of the bioinformatics method. A pattern of mass intensities at 5 independent molecular weight regions of 534, 989, 2111, 2251, and 2465 Da discovered from a starting set of 15,0005 pattern permutations correctly segregated 98% (49/50) of the ovarian cancer samples and 94% of the controls (47/50) in the training set. The optimal proteomic pattern, challenged with 100 SELDI-TOF data streams from diagnosis-blinded cases was able to accurately predict the presence of ovarian cancer in all 50 cancer specimens contained within the 100 unknown test samples (50/50, 95% confidence interval 93% to 100%). This included the correct classification of 18/18 stage I cancers (95% confidence interval 82% to 100%) while maintaining specificity for the blinded cancer-free samples (47/50, 95% confidence interval 84% to 99%, overall p<10−10 by chi-squared test). These results support the hypothesis that low molecular weight proteomic patterns in sera reflect changes in the pathology of tissue within an organ at a distant site. Moreover, such patterns may be sensitive indicators of early pathological changes, since they correctly classified all 18 sera from organ-confined stage I ovarian cancer specimens.
      • 4. Specificity, Prediction and Discrimination of the Presence of Prostate Cancer and Benign Prostate Hypertrophy
  • Initially, the current invention was challenged to find a pattern of proteins that could discriminate the sera from men with biopsy-proven prostate cancer from sera derived from asymptomatic aged-matched males. The training set was comprised of 56 sera, 31 from asymptomatic men with biopsy-proven prostate cancer (PSA>4 ng/ml, avg. 14.5 ng/ml), and 25 age-matched men with no evidence of prostate cancer (PSA<1 ng/ml, avg. 0.3 ng/ml). The 56 sera were analyzed by SELDI-TOF. The pattern discovery analysis found a signature pattern of the combined normalized intensities of 7 protein peaks (out of 15,0007 possible permutations) at the specific molecular weights of 2092, 2367, 2582, 3080, 4819, 5439, and 18220 Da that could distinguish all 56 samples analyzed in the prostate sera training set.
  • After training, the optimal proteomic pattern was tested with 227 blinded sera samples. The blinded study set contained a) 24 sera from asymptomatic men who had subsequent biopsy-proven cancer, and whose PSA values were between 4-10 ng/ml at the time of collection, b) control sera from 6 age-matched males (PSA<1 ng/ml) and c) 197 sera from men with biopsy-proven benign prostatic hypertrophy or prostatitis (PSA values ranged from 0.4 ng/ml to 36 ng/ml).
  • Using the prostate signature pattern, the data-mining tool was able to accurately predict the presence of prostate cancer in the blinded test set (92%, 22/24, p<0.000001 compared to patients with BPH), including 17/18 containing PSA values of 4-10 ng/ml. Importantly 70% of the patients (137/197) with biopsy proven BPH were classified as belonging to a unique (non-normal, non-cancer) phenotype. Only 1% of the sera from the BPH-positive cohort was categorized as a normal phenotype. When sera from 6 healthy controls were compared to those of the 24 patients with biopsy proven cancer, 6/6 healthy patients were classified correctly, compared to 22/24 patients with prostate cancer (p<0.000001). In addition, a statistically significant trend emerged in the relationship between increasing PSA levels (normal, BPH with increasing PSA) and increasing classification of severity of disease (p=1.4×10−4). The optimized prostate signatures reverted from a cancerous to a non-cancerous (but not normal) phenotype in a blinded set of matched sera from patients who underwent curative prostate resection in 7 of 7 subjects (p=0.016; 95% confidence interval 59% to 100%).
      • 5. Sample Source Preparation and Analysis
        • a. Ovarian Cancer
  • The anonymized ovarian screening serum study set was obtained from the Early Detection Research Network (“EDRN”) National Ovarian Cancer Early Detection Program according to full Institutional Review Board (“IRB”) oversight. This set contained sera from 200 asymptomatic women, 100 with ovarian cancer at the time of sample collection and 100 control women at risk for ovarian cancer as defined by family history or previous breast cancer diagnosis (Table 3). This group of unaffected women had been followed and was disease-free for at least five years. All sera were obtained prior to diagnosis and intervention. The disease cohort included histology confirmed papillary serous, endometrioid, clear cell, mucinous, adenocarcinoma, and mixed ovarian cancers of all stages. All women in the disease cohort underwent extensive surgical exploration and formal FIGO staging.
    TABLE 3
    Total Training Unknown
    PANEL SET Patients Subset Test Set DIAGNOSIS
    Ovarian Cancer 100 50 50 No Evidence of
    Screening Clinic disease: 5 year
    follow-up.
    100 50 50 Path Dx: Ovarian
    Cancer
    Prostate Cancer 31 25 6 No evidence of
    Screening Clinic disease: PSA < 1.0
    ng/mL
    55 31 24 Path Dx: Prostate
    Cancer: PSA > 4.0
    ng/mL
    197 0 197 Path Diagnosis:
    BPH/Prostatitis
    7 0 7 Biopsy proven
    cancer
    PRE-SURGERY
    7 0 7 Biopsy proven
    cancer
    Post-SURGERY
        • b. Prostate Cancer
  • The anonymized prostate screening serum study set was obtained from a prostate cancer-screening clinic where samples were obtained under approved informed consent (277 samples) (Table 3). An additional 20 anonymized specimens were collected at the National Cancer Institute under IRB approved informed consent. The Chilean trial was initiated in 1996 and lasted for five years. The subject eligibility criteria required asymptomatic men over the age of 50 with no previous history of prostate cancer. All men provided a serum sample and then received a medical evaluation and a digital rectal examination. Subsequently, men with a serum PSA>4.0 ng/ml, or suspicious digital rectal examinations were subjected to a single core needle biopsy for pathologic diagnosis. The prostate adenocarcinomas represented were of a full spectrum of grades (I-III) and Gleason scores (4-9). The 20 sera acquired at the NCI were taken from a) 7 men at the time of diagnosis and six weeks after prostatectomies for biopsy-proven organ confined prostate cancer and b) 6 normal healthy male volunteers, PSA<1.0 ng/ml. All sera were obtained prior to medical examination, diagnosis, and treatment. All sera were collected, spun down, aliquoted and stored in liquid nitrogen until use. Received sera were thawed once, separated into 10 microliter aliquots, and then refrozen in liquid nitrogen until SELDI-TOF analysis was performed.
      • 5. Proteomic Analysis
  • Sera were thawed and used once to generate protein mass signatures on the Protein Biology System 1 SELDI-TOF mass spectrometer (Ciphergen Biosystems, Freemont, Calif.). External mass calibration was accomplished using angiotensin I (amino acid sequence 1-10) and bovine cytochrome c (Ciphergen Biosystems, Freemont, Calif.) with respective masses of 1296.5 Da and 12230.9 Da. Protein profiles of all proteins that can bind to the C18 reverse-phase hydrophobic interaction surface within the 1000-20,000 Da mass range were generated. The organic acid matrix surface was α-cyano-4-hydroxy-cinnamic acid (CHCA). This matrix is required to co-crystallize with the protein mixture for full protein ionization off of the selected bait.
  • Sample preparation: One microliter of acetonitrile (Sigma-Aldrich Co., St. Louis, Mo.) was added to the sample spots of the 8-feature C18 hydrophobic interaction protein chip (Ciphergen Biosystems, Inc., Freemont, Calif.). This chip will bind proteins through hydrophobic interactions that are dependent upon the intrinsic primary amino acid sequences specific for every protein. The acetonitrile application was followed by the addition of 1 μl of serum. The sample was allowed to air dry on the chip. The chips were vigorously washed by vortexing in deionized water for 4 minutes and allowed to air dry. Lastly, 0.5 μl of CHCA solution was added. After the matrix solution dried, an additional 0.5 μl of matrix was applied to each sample and allowed to air dry. The C18 chip was chosen because it was found to consistently and reproducibly produce the greatest number of different protein and peptide signatures (data not shown). SELDI-TOF, like other time-of-flight spectrometric techniques, has its best sensitivity at the low molecular weight range (<20,000 Da). Data were recorded and optimized for analysis with the SELDI Protein Biology System version 2.0 software (Ciphergen Biosystems, Inc., Palo Alto, Calif.). Raw SELDI data, not filtered or scaled in any way, were converted to ASCII data files for analysis by the data-mining tool.
      • 6. Detection of Drug Toxicity
  • The method of the invention was tested on data streams obtained from biological samples from rats treated with doxorubicin that developed proven cardiotoxicity. Controls were treated with saline. The biological samples obtained from rats showing cardiotoxicity were classified correctly with 100% selectivity and 100% sensitivity and no false positives. See Table 4.
    TABLE 4
    Count - Actual Actual
    Score 0 1 Total Result
    0 29 29
    1  1 7  8
    Total Result 30 7 37
    Sensitivity 100.00%
    Selectivity  0.00%
      • 7. Detection of Drug Treatment
  • Rats were treated with doxorubicin and a cardioprotectant. Thus, some animals had toxicity while others did not. Table 8 shows that using the method of the invention all but one of the treated animals could be correctly identified, while only misclassifying 2 control animals. See Table 5.
    TABLE 5
    Count - Actual Actual
    Score 0 1 Total Result
    0 15 15
      0.1 10  1 11
      0.56  2  4  6
    1 13 13
    Total Result 27 18 45
    @ Score = 0.56 Sensitivity 94.44%
    Selectivity 10.53%
      • 8. Detection of Virus
  • Simian Foamy Virus was detected in cell lysates. Lysates from infected cells were correctly classified 80% of the time (8/10) with no false positives. See Table 6.
    TABLE 6
    Count - Actual Actual
    Score 0 1 Total Result
    0   9 9
    0.5 3 2 5
    0.8 6 6
    1   2 2
    Total Result 12  10  22 
    @ Score = 0.8 Sensitivity 80.00%
    Selectivity  0.00%
      • 9. Use of a Windowing Technique for Ovarian Cancer
  • Initial reduction to practice was based on a simple trial and error selection of groups of 100 contiguous features in the proteomic data stream. An adaptive pattern recognition algorithm, the Lead Cluster Map, (LCM) was employed. Sampling of the data stream started at a different point in the data stream for each run. A run consisted of collection of 14-15 collections of 100 features. After a series of 25 runs, the best models accurately predicted the correct biological state 80% with a false positive rate of approximately 30%. These results demonstrate the effectiveness of using proteomic patterns in the classification of biological states. Indeed, models with this level of accuracy would be well suited for batch screening of potentially therapeutic compounds. See Table 7.
    TABLE 7
    Count - Actual Actual
    Score 0 1 Total Result
    0   18  3 21
    0.25 10  1 11
    0.29 5 6 11
    0.33 5 5 10
    0.5  6 6 12
    0.67 2 11  13
    1   4 18  22
    Total Result 50  50  100 
    Sensitivity @ 0.33   80%
    Specificity @ 0.33 29.82%
      • 10. Detection of Breast Cancer
  • Nipple aspirants taken from breast cancer patients were analyzed using the process of the invention. The nipple aspirants were subjected to a mass spectral analysis and subjected to a pattern finding method. A sensitivity of nearly 92% was observed. See Table 8.
    TABLE 8
    Count - Actual Actual
    Score 0 1 Total Result
    0 7 2 9
      0.5 3 3
      0.67 5 5
    1 6 6
    Total Result 10  13  23 
    Sensitivity @ 0.67 91.67%
    Selectivity @ 0.67  0.00%

Claims (33)

1-65. (canceled)
66. A method of determining whether a biological sample taken from a subject indicates that the subject has a disease by analyzing a data stream that is obtained by performing an analysis of the biological sample, wherein the data stream has been abstracted to produce a sample vector that characterizes the data stream in a predetermined vector space containing a diagnostic cluster, the diagnostic cluster being a disease cluster, and the disease cluster corresponding to the presence of the disease, comprising the steps of:
determining whether the sample vector rests within the disease cluster; and
if the sample vector rests within the disease cluster, providing an indication that the subject has the disease.
67. The method of claim 66, wherein the data stream is data describing an expression of molecules in the biological sample.
68. The method of claim 67, wherein the molecules are proteins.
69. The method of claim 67, wherein the molecules are selected from the group consisting of proteins, peptides, phospholipids, DNA, and RNA.
70. The method of claim 66, wherein the data stream is formed by any high throughput data generation method.
71. The method of claim 66, wherein the data stream is based on data associated with a time of flight mass spectrum.
72. The method of claim 71, wherein the time of flight mass spectrum is generated by surface-enhanced laser desorption time-of-flight mass spectroscopy.
73. The method of claim 71, wherein the time of flight mass spectrum is generated by matrix assisted laser desorption ionization time of flight.
74. The method of claim 66, wherein the data stream is based on data associated with a spectrum.
75. The method of claim 66, wherein the data stream is based on data associated with a mass spectrum.
76. The method of claim 66, the vector space contains a healthy cluster, the healthy cluster corresponding to an absence of the disease, further comprising:
determining whether the sample vector rests within the healthy cluster; and
if the sample vector rests within the healthy cluster, providing an indication that the subject does not have the disease.
77. A method of determining whether a biological sample taken from a subject indicates that the subject does not have a disease by analyzing a data stream that is obtained by performing an analysis of the biological sample, wherein the data stream has been abstracted to produce a sample vector that characterizes the data stream in a predetermined vector space containing a diagnostic cluster, the diagnostic cluster being a healthy cluster, and the healthy cluster corresponding to the absence of the disease, comprising the steps of:
determining whether the sample vector rests within the healthy cluster; and
if the sample vector rests within the healthy cluster, providing an indication that the subject does not have the disease.
78. The method of claim 77, wherein the data stream is data describing an expression of molecules in the biological sample.
79. The method of claim 78, wherein the molecules are proteins.
80. The method of claim 78, wherein the molecules are selected from the group consisting of proteins, peptides, phospholipids, DNA, and RNA.
81. The method of claim 77, wherein the data stream is formed by any high throughput data generation method.
82. The method of claim 77, wherein the data stream is based on data associated with a time of flight mass spectrum.
83. The method of claim 82, wherein the time of flight mass spectrum is generated by surface-enhanced laser desorption time-of-flight mass spectroscopy.
84. The method of claim 82, wherein the time of flight mass spectrum is generated by matrix assisted laser desorption ionization time of flight.
85. The method of claim 77, wherein the data stream is based on data associated with a spectrum.
86. The method of claim 77, wherein the data stream is based on data associated with a mass spectrum.
87. The method of claim 77, wherein the vector space contains a disease cluster, the disease cluster corresponding to the presence of the disease, further comprising:
determining whether the sample vector rests within the disease cluster; and
if the sample vector rests within the disease cluster, providing an indication that the subject has the disease.
88. A method of determining whether a sample is of a first state or a second state by analyzing a data stream that is obtained by performing an analysis of the sample, comprising:
abstracting the data stream to produce a sample vector that characterizes the data stream in a predetermined vector space containing a cluster, the cluster being associated with the first state;
determining whether the sample vector rests within the cluster; and
if the sample vector rests within the cluster, identifying the sample as being of the first state and displaying the result.
89. The method of claim 88, wherein the sample is a biological sample.
90. The method of claim 88, wherein the sample is a biological sample taken from a human subject.
91. The method of claim 88, wherein the first state is a disease state.
92. The method of claim 88, wherein the data stream is data describing an expression of molecules in the sample.
93. The method of claim 92, wherein the molecules are selected from the group consisting of proteins, peptides, phospholipids, DNA, and RNA.
94. The method of claim 88, wherein the data stream is based on data associated with a time of flight mass spectrum.
95. The method of claim 88, wherein the data stream is based on data associated with a spectrum.
96. The method of claim 88, wherein the data stream is based on data associated with a mass spectrum.
97. The method of claim 88, wherein the cluster is a first cluster, the vector space contains a second cluster, the second cluster is associated with the second state, further comprising:
determining whether the sample vector rests within the second cluster; and
if the sample vector rests within the second cluster, identifying the sample as being of the second state and displaying the result.
US11/189,808 2000-07-18 2005-07-27 Process for discriminating between biological states based on hidden patterns from biological data Abandoned US20050260671A1 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
US11/189,808 US20050260671A1 (en) 2000-07-18 2005-07-27 Process for discriminating between biological states based on hidden patterns from biological data

Applications Claiming Priority (6)

Application Number Priority Date Filing Date Title
US21906700P 2000-07-18 2000-07-18
US23229900P 2000-09-12 2000-09-12
US27855001P 2001-03-23 2001-03-23
US28936201P 2001-05-08 2001-05-08
US09/906,661 US6925389B2 (en) 2000-07-18 2001-07-18 Process for discriminating between biological states based on hidden patterns from biological data
US11/189,808 US20050260671A1 (en) 2000-07-18 2005-07-27 Process for discriminating between biological states based on hidden patterns from biological data

Related Parent Applications (1)

Application Number Title Priority Date Filing Date
US09/906,661 Continuation US6925389B2 (en) 2000-07-18 2001-07-18 Process for discriminating between biological states based on hidden patterns from biological data

Publications (1)

Publication Number Publication Date
US20050260671A1 true US20050260671A1 (en) 2005-11-24

Family

ID=30119299

Family Applications (2)

Application Number Title Priority Date Filing Date
US09/906,661 Expired - Lifetime US6925389B2 (en) 2000-07-18 2001-07-18 Process for discriminating between biological states based on hidden patterns from biological data
US11/189,808 Abandoned US20050260671A1 (en) 2000-07-18 2005-07-27 Process for discriminating between biological states based on hidden patterns from biological data

Family Applications Before (1)

Application Number Title Priority Date Filing Date
US09/906,661 Expired - Lifetime US6925389B2 (en) 2000-07-18 2001-07-18 Process for discriminating between biological states based on hidden patterns from biological data

Country Status (15)

Country Link
US (2) US6925389B2 (en)
EP (1) EP1386275A2 (en)
JP (2) JP5246984B2 (en)
KR (1) KR101054732B1 (en)
CN (1) CN1484806A (en)
AU (2) AU2001280581A1 (en)
BR (1) BR0112667A (en)
CA (1) CA2415775A1 (en)
EA (1) EA200300161A1 (en)
IL (1) IL153856A0 (en)
MX (1) MXPA03000506A (en)
NO (1) NO20030251L (en)
NZ (1) NZ524171A (en)
SG (1) SG144731A1 (en)
WO (1) WO2002006829A2 (en)

Cited By (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20040058372A1 (en) * 2002-07-29 2004-03-25 Hitt Ben A. Quality assurance for high-throughput bioassay methods
US20050283347A1 (en) * 2002-12-09 2005-12-22 Ajinomoto Co., Inc. Apparatus and method for processing information concerning biological condition, system, program and recording medium for managing information concerning biological condition
US20060064253A1 (en) * 2003-08-01 2006-03-23 Hitt Ben A Multiple high-resolution serum proteomic features for ovarian cancer detection
US20060112041A1 (en) * 2000-06-19 2006-05-25 Ben Hitt Heuristic method of classification
US20070003996A1 (en) * 2005-02-09 2007-01-04 Hitt Ben A Identification of bacteria and spores
US20070231921A1 (en) * 2006-03-31 2007-10-04 Heinrich Roder Method and system for determining whether a drug will be effective on a patient with a disease
US20080147368A1 (en) * 2005-03-16 2008-06-19 Ajinomoto Co., Inc. Biological state-evaluating apparatus, biological state-evaluating method, biological state-evaluating system, biological state-evaluating program, evaluation function-generating apparatus, evaluation function-generating method, evaluation function-generating program and recording medium
US20080201095A1 (en) * 2007-02-12 2008-08-21 Yip Ping F Method for Calibrating an Analytical Instrument
US20080312514A1 (en) * 2005-05-12 2008-12-18 Mansfield Brian C Serum Patterns Predictive of Breast Cancer
US20090004687A1 (en) * 2007-06-29 2009-01-01 Mansfield Brian C Predictive markers for ovarian cancer
US20110208433A1 (en) * 2010-02-24 2011-08-25 Biodesix, Inc. Cancer patient selection for administration of therapeutic agents using mass spectral analysis of blood-based samples

Families Citing this family (169)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CA2410158A1 (en) * 2000-06-02 2001-12-13 Large Scale Proteomics, Corp. Protein markers for pharmaceuticals and related toxicity
US6925389B2 (en) * 2000-07-18 2005-08-02 Correlogic Systems, Inc., Process for discriminating between biological states based on hidden patterns from biological data
US6980674B2 (en) 2000-09-01 2005-12-27 Large Scale Proteomics Corp. Reference database
US6539102B1 (en) * 2000-09-01 2003-03-25 Large Scale Proteomics Reference database
CN1623091A (en) 2000-11-16 2005-06-01 赛弗根生物系统股份有限公司 Method for analyzing mass spectra
EP1355666B1 (en) 2000-12-22 2012-06-13 Max-Planck-Gesellschaft zur Förderung der Wissenschaften e.V. Use of repulsive guidance molecule (RGM) and its modulators
US8041541B2 (en) * 2001-05-24 2011-10-18 Test Advantage, Inc. Methods and apparatus for data analysis
US20030009293A1 (en) * 2001-01-09 2003-01-09 Anderson Norman G. Reference database
US20050170372A1 (en) * 2001-08-13 2005-08-04 Afeyan Noubar B. Methods and systems for profiling biological systems
US8068987B2 (en) * 2001-08-13 2011-11-29 Bg Medicine, Inc. Method and system for profiling biological systems
US20050222972A1 (en) * 2002-01-04 2005-10-06 Hewlett-Packard Development Company, L.P. Computer implemented, fast, approximate clustering based on sampling
US20020193950A1 (en) * 2002-02-25 2002-12-19 Gavin Edward J. Method for analyzing mass spectra
JP2005521138A (en) * 2002-03-15 2005-07-14 パシフィック エッジ バイオテクノロジー リミティド Medical application of adaptive learning system using gene expression data
JP2005526972A (en) * 2002-05-02 2005-09-08 シファーゲン バイオシステムズ, インコーポレイテッド Biochip with surface coated with polysaccharide hydrogel
EP1394715A1 (en) * 2002-08-02 2004-03-03 Europroteome AG An expert system for clinicial outcome prediction
EP1394549A1 (en) * 2002-08-23 2004-03-03 Bayer HealthCare AG Biomarkers for diagnosing Alzheimer's disease
BR0316197A (en) * 2002-11-12 2005-09-27 Becton Dickinson Co Kit, biomarker profile and method of isolating a host response biomarker
CA2505902A1 (en) * 2002-11-12 2004-05-27 Becton, Dickinson And Company Diagnosis of sepsis or sirs using biomarker profiles
WO2004044555A2 (en) * 2002-11-12 2004-05-27 Becton, Dickinson And Company Diagnosis of sepsis or sirs using biomarker profiles
US20040096896A1 (en) * 2002-11-14 2004-05-20 Cedars-Sinai Medical Center Pattern recognition of serum proteins for the diagnosis or treatment of physiologic conditions
US8014952B2 (en) 2002-12-18 2011-09-06 Queen Elizabeth Hospital Serum biomarkers in lung cancer
EP1604184A4 (en) * 2003-02-27 2010-10-27 Stephen A Lesko Standardized evaluation of therapeutic efficacy based on cellular biomarkers
US6977370B1 (en) 2003-04-07 2005-12-20 Ciphergen Biosystems, Inc. Off-resonance mid-IR laser desorption ionization
WO2004094460A2 (en) 2003-04-17 2004-11-04 Ciphergen Biosystems, Inc. Polypeptides related to natriuretic peptides and methods of their identification and use
US20060177870A1 (en) * 2003-04-28 2006-08-10 Ciphergen Biosystems, Inc Immunoassays
US20040236603A1 (en) * 2003-05-22 2004-11-25 Biospect, Inc. System of analyzing complex mixtures of biological and other fluids to identify biological state information
US7425700B2 (en) 2003-05-22 2008-09-16 Stults John T Systems and methods for discovery and analysis of markers
WO2004111201A2 (en) * 2003-06-11 2004-12-23 Research Foundation Of State University Of New York Data classification using point-wise tests
ATE427496T1 (en) * 2003-07-02 2009-04-15 Canon Kk METHOD FOR COLLECTING INFORMATION AND METHOD FOR DIAGNOSIS OF DISEASE USING SECONDARY MASS SPECTROMETERY
US20050100967A1 (en) * 2003-07-11 2005-05-12 Science & Technology Corporation @ Unm Detection of endometrial pathology
US7634360B2 (en) * 2003-09-23 2009-12-15 Prediction Sciences, LL Cellular fibronectin as a diagnostic marker in stroke and methods of use thereof
EP2369347A1 (en) 2003-11-07 2011-09-28 Ciphergen Biosystems, Inc. Biomarkers for Alzheimer's disease
WO2005055812A2 (en) 2003-12-05 2005-06-23 Ciphergen Biosystems, Inc. Serum biomarkers for chagas disease
EP1709442A4 (en) * 2003-12-11 2010-01-20 Correlogic Systems Inc Method of diagnosing biological states through the use of a centralized, adaptive model, and remote sample processing
US7259258B2 (en) * 2003-12-17 2007-08-21 Illumina, Inc. Methods of attaching biological compounds to solid supports using triazine
US20050181398A1 (en) * 2004-01-16 2005-08-18 Fung Eric T. Specific detection of host response protein clusters
JP2007523324A (en) * 2004-02-05 2007-08-16 メドトロニック・インコーポレーテッド Method and apparatus for identifying a patient at risk for a life-threatening arrhythmia
US7608458B2 (en) * 2004-02-05 2009-10-27 Medtronic, Inc. Identifying patients at risk for life threatening arrhythmias
US20050209785A1 (en) * 2004-02-27 2005-09-22 Wells Martin D Systems and methods for disease diagnosis
US7035740B2 (en) * 2004-03-24 2006-04-25 Illumina, Inc. Artificial intelligence and global normalization methods for genotyping
US7485430B2 (en) * 2004-04-15 2009-02-03 The Curators Of The University Of Missouri Methods and compositions for evaluation of fertility
CA2563847A1 (en) * 2004-04-20 2005-11-03 Board Of Regents, The University Of Texas System Using plasma proteomic pattern for diagnosis, classification, prediction of response to therapy and clinical behavior, stratification of therapy, and monitoring disease in hematologic malignancies
CA2564396A1 (en) 2004-04-26 2005-11-03 Children's Medical Center Corporation Platelet biomarkers for the detection of disease
US20050244973A1 (en) * 2004-04-29 2005-11-03 Predicant Biosciences, Inc. Biological patterns for diagnosis and treatment of cancer
US8027791B2 (en) * 2004-06-23 2011-09-27 Medtronic, Inc. Self-improving classification system
US8335652B2 (en) * 2004-06-23 2012-12-18 Yougene Corp. Self-improving identification method
US20050287574A1 (en) * 2004-06-23 2005-12-29 Medtronic, Inc. Genetic diagnostic method for SCD risk stratification
US20060024746A1 (en) * 2004-07-14 2006-02-02 Artann Laboratories, Inc. Methods and devices for optical monitoring and rapid analysis of drying droplets
EP1827507A4 (en) * 2004-11-30 2008-06-25 Bg Medicine Inc Biological systems analysis
US20060115429A1 (en) * 2004-11-30 2006-06-01 Noubar Afeyan Biological systems analysis
ATE501267T1 (en) * 2005-01-06 2011-03-15 Eastern Virginia Med School APOLIPOPROTEIN A-II ISOFORM AS A BIOMARKER FOR PROSTATE CANCER
US20060160156A1 (en) * 2005-01-13 2006-07-20 Suzanne Klimberg Tears as a screening medium
US20060157647A1 (en) * 2005-01-18 2006-07-20 Becton, Dickinson And Company Multidimensional liquid chromatography/spectrometry
JP2008529538A (en) * 2005-02-16 2008-08-07 ジェネティック テクノロジーズ リミテッド Gene analysis method including amplification of complementary duplicon
JP4843987B2 (en) * 2005-04-05 2011-12-21 ソニー株式会社 Information processing apparatus, information processing method, and program
EP1869463A4 (en) * 2005-04-15 2010-05-05 Becton Dickinson Co Diagnosis of sepsis
US7499751B2 (en) * 2005-04-28 2009-03-03 Cardiac Pacemakers, Inc. Cardiac signal template generation using waveform clustering
US20100197561A1 (en) 2005-06-24 2010-08-05 Ciphergen Biosystems, Inc. Biomarkers for Ovarian Cancer: B2 Microglobulin
WO2007012052A1 (en) * 2005-07-20 2007-01-25 Medical College Of Georgia Research Institute Use of protein profiles in disease diagnosis and treatment
WO2007010439A1 (en) * 2005-07-21 2007-01-25 Koninklijke Philips Electronics, N.V. Method and apparatus for subset selection with preference maximization
US8921102B2 (en) * 2005-07-29 2014-12-30 Gpb Scientific, Llc Devices and methods for enrichment and alteration of circulating tumor cells and other particles
JP4966305B2 (en) 2005-08-05 2012-07-04 コーニンクレッカ フィリップス エレクトロニクス エヌ ヴィ Search space protection by dynamic gene distribution
WO2007038414A2 (en) * 2005-09-27 2007-04-05 Indiana University Research & Technology Corporation Mining protein interaction networks
US9955438B2 (en) 2005-09-27 2018-04-24 Qualcomm Incorporated Method and apparatus for carrier allocation and management in multi-carrier communication systems
JP2009510002A (en) 2005-09-30 2009-03-12 アボット ゲゼルシャフト ミット ベシュレンクテル ハフツング ウント コンパニー コマンディトゲゼルシャフト Binding domains of proteins of the repulsion-inducing molecule (RGM) protein family, and functional fragments thereof, and uses thereof
US7599893B2 (en) * 2005-10-13 2009-10-06 Aureon Laboratories, Inc. Methods and systems for feature selection in machine learning based on feature contribution and model fitness
US20090215086A1 (en) * 2005-12-12 2009-08-27 Momar Ndao Biomarkers for Babesia
AU2007209980A1 (en) * 2006-01-27 2007-08-09 Eastern Virginia Medical School Proteomic fingerprinting of human IVF-derived embryos: identification of biomarkers of developmental potential
WO2007106466A2 (en) 2006-03-11 2007-09-20 The Board Of Trustees Of The Leland Stanford Junior University Beta-2 microglobulin as a biomarker for peripheral artery disease
US7533070B2 (en) * 2006-05-30 2009-05-12 Honeywell International Inc. Automatic fault classification for model-based process monitoring
EP2589668A1 (en) 2006-06-14 2013-05-08 Verinata Health, Inc Rare cell analysis using sample splitting and DNA tags
US8137912B2 (en) 2006-06-14 2012-03-20 The General Hospital Corporation Methods for the diagnosis of fetal abnormalities
WO2007147074A2 (en) 2006-06-14 2007-12-21 Living Microsystems, Inc. Use of highly parallel snp genotyping for fetal diagnosis
US20080050739A1 (en) 2006-06-14 2008-02-28 Roland Stoughton Diagnosis of fetal abnormalities using polymorphisms including short tandem repeats
US20080124721A1 (en) * 2006-06-14 2008-05-29 Martin Fuchs Analysis of rare cell-enriched samples
US20080163824A1 (en) * 2006-09-01 2008-07-10 Innovative Dairy Products Pty Ltd, An Australian Company, Acn 098 382 784 Whole genome based genetic evaluation and selection process
US8221984B2 (en) 2007-03-27 2012-07-17 Vermillion, Inc. Biomarkers for ovarian cancer
EP2639316A1 (en) 2007-05-11 2013-09-18 The Johns Hopkins University Biomarkers for melanoma
US20090049856A1 (en) * 2007-08-20 2009-02-26 Honeywell International Inc. Working fluid of a blend of 1,1,1,3,3-pentafluoropane, 1,1,1,2,3,3-hexafluoropropane, and 1,1,1,2-tetrafluoroethane and method and apparatus for using
WO2009058331A2 (en) 2007-10-29 2009-05-07 Vermilllion, Inc. Biomarkers for the detection of early stage ovarian cancer
US20110143956A1 (en) * 2007-11-14 2011-06-16 Medtronic, Inc. Diagnostic Kits and Methods for SCD or SCA Therapy Selection
EP2222877A4 (en) * 2007-11-14 2011-10-12 Medtronic Inc Genetic markers for scd or sca therapy selection
EP2245177B1 (en) 2008-02-19 2015-05-13 Becton Dickinson and Company Systems and methods for identifying a culture as positive for microorganisms with high confidence
US8962803B2 (en) 2008-02-29 2015-02-24 AbbVie Deutschland GmbH & Co. KG Antibodies against the RGM A protein and uses thereof
US8669113B2 (en) 2008-04-03 2014-03-11 Becton, Dickinson And Company Advanced detection of sepsis
US7776522B2 (en) * 2008-04-24 2010-08-17 Becton, Dickinson And Company Methods for diagnosing oncogenic human papillomavirus (HPV)
SI2334812T1 (en) 2008-09-20 2017-05-31 The Board of Trustees of the Leland Stanford Junior University Office of the General Counsel Building 170 Noninvasive diagnosis of fetal aneuploidy by sequencing
US9332973B2 (en) 2008-10-01 2016-05-10 Covidien Lp Needle biopsy device with exchangeable needle and integrated needle protection
US11298113B2 (en) 2008-10-01 2022-04-12 Covidien Lp Device for needle biopsy with integrated needle protection
US9186128B2 (en) 2008-10-01 2015-11-17 Covidien Lp Needle biopsy device
US9782565B2 (en) 2008-10-01 2017-10-10 Covidien Lp Endoscopic ultrasound-guided biliary access system
US8968210B2 (en) 2008-10-01 2015-03-03 Covidien LLP Device for needle biopsy with integrated needle protection
US8543625B2 (en) * 2008-10-16 2013-09-24 Intelliscience Corporation Methods and systems for analysis of multi-sample, two-dimensional data
GB2464677A (en) 2008-10-20 2010-04-28 Univ Nottingham Trent A method of analysing data by using an artificial neural network to identify relationships between the data and one or more conditions.
BRPI0923806A2 (en) 2008-12-30 2015-07-14 Centocor Ortho Biotech Inc Serum markers for predicting clinical response to anti-tnfa antibodies in patients with ankylosing spondylitis.
US20100191790A1 (en) * 2009-01-29 2010-07-29 Agilent Technologies, Inc. System and method for correlation scoring of signals
WO2010132546A2 (en) * 2009-05-12 2010-11-18 Medtronic, Inc. Sca risk stratification by predicting patient response to anti-arrhythmics
US20110071033A1 (en) 2009-09-23 2011-03-24 Celmatix, Inc. Methods and devices for assessing infertility and/or egg quality
US20110105856A1 (en) * 2009-10-29 2011-05-05 Robyn Aylor Haines Diagnostic testing
CA2780069C (en) 2009-12-08 2018-07-17 Abbott Gmbh & Co. Kg Monoclonal antibodies against the rgm a protein for use in the treatment of retinal nerve fiber layer degeneration
US8187979B2 (en) * 2009-12-23 2012-05-29 Varian Semiconductor Equipment Associates, Inc. Workpiece patterning with plasma sheath modulation
JP5786020B2 (en) 2010-04-16 2015-09-30 アボットジャパン株式会社 Methods and reagents for diagnosing rheumatoid arthritis
EP2628013B1 (en) 2010-10-14 2019-06-12 The Johns Hopkins University Biomarkers of brain injury
CN103229179B (en) * 2010-12-08 2016-08-24 霍夫曼-拉罗奇有限公司 The system and method for the pattern in display biological monitoring data automatically
MX341840B (en) 2011-06-27 2016-09-05 Eisai R&D Man Co Ltd Microrna biomarkers indicative of alzheimer's disease.
US20130073221A1 (en) * 2011-09-16 2013-03-21 Daniel Attinger Systems and methods for identification of fluid and substrate composition or physico-chemical properties
KR20140072160A (en) 2011-10-03 2014-06-12 셀매틱스, 인크. Methods and devices for assessing risk to a putative offspring of developing a condition
JP6336397B2 (en) 2011-12-14 2018-06-06 アッヴィ・ドイチュラント・ゲー・エム・ベー・ハー・ウント・コー・カー・ゲー Compositions and methods for diagnosing and treating iron-related disorders
EP3800200A1 (en) 2011-12-14 2021-04-07 AbbVie Deutschland GmbH & Co. KG Composition and method for the diagnosis and treatment of iron-related disorders
MX352772B (en) 2012-01-27 2017-12-07 Abbvie Deutschland Composition and method for diagnosis and treatment of diseases associated with neurite degeneration.
RU2014141059A (en) 2012-03-13 2016-04-27 Эббви Инк. METHOD FOR SELECTING OR IDENTIFYING A SUBJECT FOR THERAPY BY AN V1B ANTAGONIST
US20140024546A1 (en) 2012-05-01 2014-01-23 Synapdx Corporation Systems and methods for normalizing gene expression profiles of biological samples having a mixed cell population
EP2844773B1 (en) 2012-05-04 2017-08-16 Boreal Genomics Corp. Biomarker analysis using scodaphoresis
NZ728724A (en) 2012-05-11 2018-03-23 Reset Therapeutics Inc Carbazole-containing sulfonamides as cryptochrome modulators
US10288626B2 (en) 2012-09-14 2019-05-14 University Of Kentucky Research Foundation Secreted tumor-associated cytochrome as a blood-based biomarker for cancer
US9177098B2 (en) 2012-10-17 2015-11-03 Celmatix Inc. Systems and methods for determining the probability of a pregnancy at a selected point in time
US10162800B2 (en) 2012-10-17 2018-12-25 Celmatix Inc. Systems and methods for determining the probability of a pregnancy at a selected point in time
EP2914752B1 (en) 2012-11-02 2022-03-09 The Johns Hopkins University Dna methylation biomarkers of post-partum depression risk
US9087298B2 (en) 2012-12-05 2015-07-21 International Business Machines Corporation Inference of anomalous behavior of members of cohorts and associate actors related to the anomalous behavior based on divergent movement from the cohort context centroid
US9836577B2 (en) 2012-12-14 2017-12-05 Celmatix, Inc. Methods and devices for assessing risk of female infertility
WO2014182896A1 (en) 2013-05-10 2014-11-13 Johns Hopkins University Compositions for ovarian cancer assessment having improved specificity
WO2014210611A1 (en) * 2013-06-28 2014-12-31 Nantomics, Llc Pathway analysis for identification of diagnostic tests
US10280464B2 (en) 2013-07-11 2019-05-07 The Johns Hopkins University DNA methylation and genotype specific biomarker of suicide attempt and/or suicide ideation
JP6611710B2 (en) 2013-07-17 2019-11-27 ザ・ジョンズ・ホプキンス・ユニバーシティ Multiprotein biomarker assay for detection and outcome of brain injury
US9898575B2 (en) 2013-08-21 2018-02-20 Seven Bridges Genomics Inc. Methods and systems for aligning sequences
US9116866B2 (en) 2013-08-21 2015-08-25 Seven Bridges Genomics Inc. Methods and systems for detecting sequence variants
AU2014324438B2 (en) 2013-09-30 2019-12-05 Seven Bridges Genomics Inc. Methods and system for detecting sequence variants
US9753131B2 (en) * 2013-10-09 2017-09-05 Massachusetts Institute Of Technology Motion tracking via body radio reflections
KR101473705B1 (en) * 2013-10-11 2014-12-18 삼성에스디에스 주식회사 System and method for analyzing biological sample
AU2014337089B2 (en) 2013-10-18 2019-08-08 Seven Bridges Genomics Inc. Methods and systems for genotyping genetic samples
CA2927637A1 (en) 2013-10-18 2015-04-23 Seven Bridges Genomics, Inc. Methods and systems for identifying disease-induced mutations
US10832797B2 (en) 2013-10-18 2020-11-10 Seven Bridges Genomics Inc. Method and system for quantifying sequence alignment
WO2015058120A1 (en) 2013-10-18 2015-04-23 Seven Bridges Genomics Inc. Methods and systems for aligning sequences in the presence of repeating elements
US9092402B2 (en) 2013-10-21 2015-07-28 Seven Bridges Genomics Inc. Systems and methods for using paired-end data in directed acyclic structure
AU2015204819B2 (en) 2014-01-10 2021-05-06 Seven Bridges Genomics Inc. Systems and methods for use of known alleles in read mapping
US10619210B2 (en) 2014-02-07 2020-04-14 The Johns Hopkins University Predicting response to epigenetic drug therapy
US9817944B2 (en) 2014-02-11 2017-11-14 Seven Bridges Genomics Inc. Systems and methods for analyzing sequence data
TWI690521B (en) 2014-04-07 2020-04-11 美商同步製藥公司 Carbazole-containing amides, carbamates, and ureas as cryptochrome modulators
KR20150137283A (en) * 2014-05-29 2015-12-09 사회복지법인 삼성생명공익재단 System and method for analyzing biological sample
SG11201700303UA (en) 2014-07-17 2017-02-27 Celmatix Inc Methods and systems for assessing infertility and related pathologies
WO2016044697A1 (en) 2014-09-19 2016-03-24 The Johns Hopkins University Biomarkers of cognitive dysfunction
CN107408043A (en) 2014-10-14 2017-11-28 七桥基因公司 System and method for the intelligence tool in sequence streamline
GB2533098B (en) * 2014-12-09 2016-12-14 Ibm Automated management of confidential data in cloud environments
US11041865B2 (en) 2015-02-20 2021-06-22 The Johns Hopkins University Biomarkers of myocardial injury
US10192026B2 (en) 2015-03-05 2019-01-29 Seven Bridges Genomics Inc. Systems and methods for genomic pattern analysis
US10275567B2 (en) 2015-05-22 2019-04-30 Seven Bridges Genomics Inc. Systems and methods for haplotyping
US10793895B2 (en) 2015-08-24 2020-10-06 Seven Bridges Genomics Inc. Systems and methods for epigenetic analysis
US10724110B2 (en) 2015-09-01 2020-07-28 Seven Bridges Genomics Inc. Systems and methods for analyzing viral nucleic acids
US10584380B2 (en) 2015-09-01 2020-03-10 Seven Bridges Genomics Inc. Systems and methods for mitochondrial analysis
US11347704B2 (en) 2015-10-16 2022-05-31 Seven Bridges Genomics Inc. Biological graph or sequence serialization
US20170199960A1 (en) 2016-01-07 2017-07-13 Seven Bridges Genomics Inc. Systems and methods for adaptive local alignment for graph genomes
US10364468B2 (en) 2016-01-13 2019-07-30 Seven Bridges Genomics Inc. Systems and methods for analyzing circulating tumor DNA
US10460829B2 (en) 2016-01-26 2019-10-29 Seven Bridges Genomics Inc. Systems and methods for encoding genetic variation for a population
US10262102B2 (en) 2016-02-24 2019-04-16 Seven Bridges Genomics Inc. Systems and methods for genotyping with graph reference
US11250931B2 (en) 2016-09-01 2022-02-15 Seven Bridges Genomics Inc. Systems and methods for detecting recombination
US11266344B2 (en) 2016-09-21 2022-03-08 Samsung Electronics Co., Ltd. Method for measuring skin condition and electronic device therefor
US11633411B2 (en) 2016-10-04 2023-04-25 University Of Maryland, Baltimore Methods of treating sepsis using anti-sepsis lipid A (ASLA) based therapeutics
JP2020511674A (en) 2017-03-09 2020-04-16 クリラ バイオテック ベー.フェー. Cell aging biomarker
WO2018227202A1 (en) * 2017-06-09 2018-12-13 Bellwether Bio, Inc. Determination of cancer type in a subject by probabilistic modeling of circulating nucleic acid fragment endpoints
WO2019133717A1 (en) 2017-12-29 2019-07-04 Abbott Laboratories Novel biomarkers and methods for diagnosing and evaluating traumatic brain injury
JP6852004B2 (en) * 2018-03-07 2021-03-31 株式会社東芝 Data analysis system, data analysis method, and program
WO2019213619A1 (en) 2018-05-04 2019-11-07 Abbott Laboratories Hbv diagnostic, prognostic, and therapeutic methods and products
US20200097879A1 (en) * 2018-09-25 2020-03-26 Oracle International Corporation Techniques for automatic opportunity evaluation and action recommendation engine
KR102206905B1 (en) 2018-12-28 2021-01-25 (주)아이쿱 Method for inferring life pattern and changed factor based on blood test result
AU2020227319A1 (en) 2019-02-27 2021-09-09 Epiaxis Therapeutics Pty Ltd Methods and agents for assessing T-cell function and predicting response to therapy
EP4010456A4 (en) 2019-08-05 2023-09-13 Seer, Inc. Systems and methods for sample preparation, data generation, and protein corona analysis
US20220284269A1 (en) * 2021-03-03 2022-09-08 Lanzatech, Inc. System for control and analysis of gas fermentation processes
WO2023122723A1 (en) 2021-12-23 2023-06-29 The Broad Institute, Inc. Panels and methods for diagnosing and treating lung cancer
WO2024044578A1 (en) 2022-08-22 2024-02-29 University Of Virginia Dna methylation biomarkers of premenstrual dysphoric disorder and perimenopausal depression

Citations (42)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4122343A (en) * 1976-05-03 1978-10-24 Chemetron Corporation Method to generate correlative data from various products of thermal degradation of biological specimens
US4646355A (en) * 1985-03-15 1987-02-24 Tektronix, Inc. Method and apparatus for input picture enhancement by removal of undersired dots and voids
US4697242A (en) * 1984-06-11 1987-09-29 Holland John H Adaptive computing system capable of learning and discovery
US4881178A (en) * 1987-05-07 1989-11-14 The Regents Of The University Of Michigan Method of controlling a classifier system
US5136686A (en) * 1990-03-28 1992-08-04 Koza John R Non-linear genetic algorithms for solving problems by finding a fit composition of functions
US5352613A (en) * 1993-10-07 1994-10-04 Tafas Triantafillos P Cytological screening method
US5649030A (en) * 1992-09-01 1997-07-15 Apple Computer, Inc. Vector quantization
US5687716A (en) * 1995-11-15 1997-11-18 Kaufmann; Peter Selective differentiating diagnostic process based on broad data bases
US5697369A (en) * 1988-12-22 1997-12-16 Biofield Corp. Method and apparatus for disease, injury and bodily condition screening or sensing
US5716825A (en) * 1995-11-01 1998-02-10 Hewlett Packard Company Integrated nucleic acid analysis system for MALDI-TOF MS
US5719060A (en) * 1993-05-28 1998-02-17 Baylor College Of Medicine Method and apparatus for desorption and ionization of analytes
US5769074A (en) * 1994-10-13 1998-06-23 Horus Therapeutics, Inc. Computer assisted methods for diagnosing diseases
US5790761A (en) * 1992-12-11 1998-08-04 Heseltine; Gary L. Method and apparatus for the diagnosis of colorectal cancer
US5839438A (en) * 1996-09-10 1998-11-24 Neuralmed, Inc. Computer-based neural network system and method for medical diagnosis and interpretation
US5905258A (en) * 1997-06-02 1999-05-18 Advanced Research & Techology Institute Hybrid ion mobility and mass spectrometer
US5946640A (en) * 1995-06-08 1999-08-31 University Of Wales Aberystwyth Composition analysis
US5974412A (en) * 1997-09-24 1999-10-26 Sapient Health Network Intelligent query system for automatically indexing information in a database and automatically categorizing users
US6025128A (en) * 1994-09-29 2000-02-15 The University Of Tulsa Prediction of prostate cancer progression by analysis of selected predictive parameters
US6035230A (en) * 1995-09-13 2000-03-07 Medison Co., Ltd Real-time biological signal monitoring system using radio communication network
US6081797A (en) * 1997-07-09 2000-06-27 American Heuristics Corporation Adaptive temporal correlation network
US6128608A (en) * 1998-05-01 2000-10-03 Barnhill Technologies, Llc Enhancing knowledge discovery using multiple support vector machines
US6225047B1 (en) * 1997-06-20 2001-05-01 Ciphergen Biosystems, Inc. Use of retentate chromatography to generate difference maps
US6234006B1 (en) * 1998-03-20 2001-05-22 Cyrano Sciences Inc. Handheld sensing apparatus
US6295514B1 (en) * 1996-11-04 2001-09-25 3-Dimensional Pharmaceuticals, Inc. Method, system, and computer program product for representing similarity/dissimilarity between chemical compounds
US6329652B1 (en) * 1999-07-28 2001-12-11 Eastman Kodak Company Method for comparison of similar samples in liquid chromatography/mass spectrometry
US20020046198A1 (en) * 2000-06-19 2002-04-18 Ben Hitt Heuristic method of classification
US20020059030A1 (en) * 2000-07-17 2002-05-16 Otworth Michael J. Method and apparatus for the processing of remotely collected electronic information characterizing properties of biological entities
US20020193950A1 (en) * 2002-02-25 2002-12-19 Gavin Edward J. Method for analyzing mass spectra
US20030054367A1 (en) * 2001-02-16 2003-03-20 Ciphergen Biosystems, Inc. Method for correlating gene expression profiles with protein expression profiles
US20030077616A1 (en) * 2001-04-19 2003-04-24 Ciphergen Biosystems, Inc. Biomolecule characterization using mass spectrometry and affinity tags
US6558902B1 (en) * 1998-05-07 2003-05-06 Sequenom, Inc. Infrared matrix-assisted laser desorption/ionization mass spectrometric analysis of macromolecules
US6571227B1 (en) * 1996-11-04 2003-05-27 3-Dimensional Pharmaceuticals, Inc. Method, system and computer program product for non-linear mapping of multi-dimensional data
US20030129589A1 (en) * 1996-11-06 2003-07-10 Hubert Koster Dna diagnostics based on mass spectrometry
US20030134304A1 (en) * 2001-08-13 2003-07-17 Jan Van Der Greef Method and system for profiling biological systems
US6615199B1 (en) * 1999-08-31 2003-09-02 Accenture, Llp Abstraction factory in a base services pattern environment
US6675104B2 (en) * 2000-11-16 2004-01-06 Ciphergen Biosystems, Inc. Method for analyzing mass spectra
US6680203B2 (en) * 2000-07-10 2004-01-20 Esperion Therapeutics, Inc. Fourier transform mass spectrometry of complex biological samples
US20040116797A1 (en) * 2002-11-29 2004-06-17 Masashi Takahashi Data managing system, x-ray computed tomographic apparatus, and x-ray computed tomograhic system
US20040260478A1 (en) * 2001-08-03 2004-12-23 Schwamm Lee H. System, process and diagnostic arrangement establishing and monitoring medication doses for patients
US6882990B1 (en) * 1999-05-01 2005-04-19 Biowulf Technologies, Llc Methods of identifying biological patterns using multiple data sets
US6925389B2 (en) * 2000-07-18 2005-08-02 Correlogic Systems, Inc., Process for discriminating between biological states based on hidden patterns from biological data
US7057168B2 (en) * 1999-07-21 2006-06-06 Sionex Corporation Systems for differential ion mobility analysis

Family Cites Families (24)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US3935562A (en) * 1974-02-22 1976-01-27 Stephens Richard G Pattern recognition method and apparatus
GB2187035A (en) * 1986-01-27 1987-08-26 Eric James Sjoberg Pyrolysis mass spectrometer disease diagnosis aid
US5210412A (en) * 1991-01-31 1993-05-11 Wayne State University Method for analyzing an organic sample
US5784162A (en) * 1993-08-18 1998-07-21 Applied Spectral Imaging Ltd. Spectral bio-imaging methods for biological research, medical diagnostics and therapy
DE69218912T2 (en) 1991-08-28 1997-10-09 Becton Dickinson Co GRAVITY ATTRACTION MACHINE FOR ADAPTABLE AUTOCLUSTER FORMATION OF N-DIMENSIONAL DATA FLOWS
US5632957A (en) * 1993-11-01 1997-05-27 Nanogen Molecular biological diagnostic systems including electrodes
US5995645A (en) * 1993-08-18 1999-11-30 Applied Spectral Imaging Ltd. Method of cancer cell detection
US5848177A (en) * 1994-12-29 1998-12-08 Board Of Trustees Operating Michigan State University Method and system for detection of biological materials using fractal dimensions
DE19543020A1 (en) * 1995-11-18 1997-05-22 Boehringer Mannheim Gmbh Method and device for determining analytical data on the interior of a scattering matrix
SE9602545L (en) * 1996-06-25 1997-12-26 Michael Mecklenburg Method of discriminating complex biological samples
EP1055126A1 (en) 1998-02-13 2000-11-29 Oxford GlycoSciences (UK) Limited Methods and compositions for diagnosis of hepatoma
GB9805477D0 (en) 1998-03-13 1998-05-13 Oxford Glycosciences Limited Methods and compositions for diagnosis of rheumatoid arthritis
JP2002511949A (en) * 1998-03-30 2002-04-16 イーエスエー インコーポレーテッド Method for predicting and / or diagnosing disease
CA2331508A1 (en) 1998-05-09 1999-11-18 Ikonisys, Inc. Method and apparatus for computer controlled rare cell, including fetal cell, based diagnosis
US6077693A (en) * 1998-05-14 2000-06-20 Incyte Pharmaceuticals, Inc. Polynucleotide encoding a promonocyte associated protein
CA2356195A1 (en) * 1998-12-23 2000-06-29 Medispectra, Inc. Optical methods and systems for cervical screening
WO2000049410A2 (en) 1999-02-16 2000-08-24 The Government Of The United States Of America, As Represented By The Secretary Department Of Health & Human Services, The National Institutes Of Health Lcm (laser capture microdissection) for cellular protein analysis
GB9905817D0 (en) 1999-03-12 1999-05-05 Oxford Glycosciences Uk Ltd Methods
AU7586100A (en) 1999-09-17 2001-04-17 Affymetrix, Inc. Method of cluster analysis of gene expression profiles
EP1236173A2 (en) 1999-10-27 2002-09-04 Biowulf Technologies, LLC Methods and devices for identifying patterns in biological systems
AU1350501A (en) 1999-10-27 2001-05-08 Barnhill Technologies, Llc Methods and devices for identifying patterns in biological systems and methods for uses thereof
DE10021737C2 (en) 2000-05-04 2002-10-17 Hermann Haller Method and device for the qualitative and / or quantitative determination of a protein and / or peptide pattern of a liquid sample which is taken from the human or animal body
DE60239012D1 (en) 2001-01-24 2011-03-03 Isabelle Guyon METHOD FOR IDENTIFYING PATTERNS IN BIOLOGICAL SYSTEMS AND THEIR APPLICATIONS
US20020160420A1 (en) 2001-04-30 2002-10-31 George Jackowski Process for diagnosis of physiological conditions by characterization of proteomic materials

Patent Citations (48)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4122343A (en) * 1976-05-03 1978-10-24 Chemetron Corporation Method to generate correlative data from various products of thermal degradation of biological specimens
US4697242A (en) * 1984-06-11 1987-09-29 Holland John H Adaptive computing system capable of learning and discovery
US4646355A (en) * 1985-03-15 1987-02-24 Tektronix, Inc. Method and apparatus for input picture enhancement by removal of undersired dots and voids
US4881178A (en) * 1987-05-07 1989-11-14 The Regents Of The University Of Michigan Method of controlling a classifier system
US5697369A (en) * 1988-12-22 1997-12-16 Biofield Corp. Method and apparatus for disease, injury and bodily condition screening or sensing
US5136686A (en) * 1990-03-28 1992-08-04 Koza John R Non-linear genetic algorithms for solving problems by finding a fit composition of functions
US5649030A (en) * 1992-09-01 1997-07-15 Apple Computer, Inc. Vector quantization
US5790761A (en) * 1992-12-11 1998-08-04 Heseltine; Gary L. Method and apparatus for the diagnosis of colorectal cancer
US5719060A (en) * 1993-05-28 1998-02-17 Baylor College Of Medicine Method and apparatus for desorption and ionization of analytes
US5352613A (en) * 1993-10-07 1994-10-04 Tafas Triantafillos P Cytological screening method
US6025128A (en) * 1994-09-29 2000-02-15 The University Of Tulsa Prediction of prostate cancer progression by analysis of selected predictive parameters
US6248063B1 (en) * 1994-10-13 2001-06-19 Horus Therapeutics, Inc. Computer assisted methods for diagnosing diseases
US5769074A (en) * 1994-10-13 1998-06-23 Horus Therapeutics, Inc. Computer assisted methods for diagnosing diseases
US5946640A (en) * 1995-06-08 1999-08-31 University Of Wales Aberystwyth Composition analysis
US6035230A (en) * 1995-09-13 2000-03-07 Medison Co., Ltd Real-time biological signal monitoring system using radio communication network
US5716825A (en) * 1995-11-01 1998-02-10 Hewlett Packard Company Integrated nucleic acid analysis system for MALDI-TOF MS
US5687716A (en) * 1995-11-15 1997-11-18 Kaufmann; Peter Selective differentiating diagnostic process based on broad data bases
US5839438A (en) * 1996-09-10 1998-11-24 Neuralmed, Inc. Computer-based neural network system and method for medical diagnosis and interpretation
US6571227B1 (en) * 1996-11-04 2003-05-27 3-Dimensional Pharmaceuticals, Inc. Method, system and computer program product for non-linear mapping of multi-dimensional data
US6295514B1 (en) * 1996-11-04 2001-09-25 3-Dimensional Pharmaceuticals, Inc. Method, system, and computer program product for representing similarity/dissimilarity between chemical compounds
US20030129589A1 (en) * 1996-11-06 2003-07-10 Hubert Koster Dna diagnostics based on mass spectrometry
US5905258A (en) * 1997-06-02 1999-05-18 Advanced Research & Techology Institute Hybrid ion mobility and mass spectrometer
US6579719B1 (en) * 1997-06-20 2003-06-17 Ciphergen Biosystems, Inc. Retentate chromatography and protein chip arrays with applications in biology and medicine
US6225047B1 (en) * 1997-06-20 2001-05-01 Ciphergen Biosystems, Inc. Use of retentate chromatography to generate difference maps
US6844165B2 (en) * 1997-06-20 2005-01-18 Ciphergen Biosystems, Inc. Retentate chromatography and protein chip arrays with applications in biology and medicine
US6081797A (en) * 1997-07-09 2000-06-27 American Heuristics Corporation Adaptive temporal correlation network
US5974412A (en) * 1997-09-24 1999-10-26 Sapient Health Network Intelligent query system for automatically indexing information in a database and automatically categorizing users
US6234006B1 (en) * 1998-03-20 2001-05-22 Cyrano Sciences Inc. Handheld sensing apparatus
US6157921A (en) * 1998-05-01 2000-12-05 Barnhill Technologies, Llc Enhancing knowledge discovery using support vector machines in a distributed network environment
US6427141B1 (en) * 1998-05-01 2002-07-30 Biowulf Technologies, Llc Enhancing knowledge discovery using multiple support vector machines
US6128608A (en) * 1998-05-01 2000-10-03 Barnhill Technologies, Llc Enhancing knowledge discovery using multiple support vector machines
US6558902B1 (en) * 1998-05-07 2003-05-06 Sequenom, Inc. Infrared matrix-assisted laser desorption/ionization mass spectrometric analysis of macromolecules
US6882990B1 (en) * 1999-05-01 2005-04-19 Biowulf Technologies, Llc Methods of identifying biological patterns using multiple data sets
US7057168B2 (en) * 1999-07-21 2006-06-06 Sionex Corporation Systems for differential ion mobility analysis
US6329652B1 (en) * 1999-07-28 2001-12-11 Eastman Kodak Company Method for comparison of similar samples in liquid chromatography/mass spectrometry
US6615199B1 (en) * 1999-08-31 2003-09-02 Accenture, Llp Abstraction factory in a base services pattern environment
US20020046198A1 (en) * 2000-06-19 2002-04-18 Ben Hitt Heuristic method of classification
US6680203B2 (en) * 2000-07-10 2004-01-20 Esperion Therapeutics, Inc. Fourier transform mass spectrometry of complex biological samples
US20020059030A1 (en) * 2000-07-17 2002-05-16 Otworth Michael J. Method and apparatus for the processing of remotely collected electronic information characterizing properties of biological entities
US6925389B2 (en) * 2000-07-18 2005-08-02 Correlogic Systems, Inc., Process for discriminating between biological states based on hidden patterns from biological data
US6675104B2 (en) * 2000-11-16 2004-01-06 Ciphergen Biosystems, Inc. Method for analyzing mass spectra
US7027933B2 (en) * 2000-11-16 2006-04-11 Ciphergen Biosystems, Inc. Method for analyzing mass spectra
US20030054367A1 (en) * 2001-02-16 2003-03-20 Ciphergen Biosystems, Inc. Method for correlating gene expression profiles with protein expression profiles
US20030077616A1 (en) * 2001-04-19 2003-04-24 Ciphergen Biosystems, Inc. Biomolecule characterization using mass spectrometry and affinity tags
US20040260478A1 (en) * 2001-08-03 2004-12-23 Schwamm Lee H. System, process and diagnostic arrangement establishing and monitoring medication doses for patients
US20030134304A1 (en) * 2001-08-13 2003-07-17 Jan Van Der Greef Method and system for profiling biological systems
US20020193950A1 (en) * 2002-02-25 2002-12-19 Gavin Edward J. Method for analyzing mass spectra
US20040116797A1 (en) * 2002-11-29 2004-06-17 Masashi Takahashi Data managing system, x-ray computed tomographic apparatus, and x-ray computed tomograhic system

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
Wright et al. (Prostate Cancer and Prostatic Diseases, 1999, 2, 264-276). *

Cited By (27)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20060112041A1 (en) * 2000-06-19 2006-05-25 Ben Hitt Heuristic method of classification
US7240038B2 (en) 2000-06-19 2007-07-03 Correlogic Systems, Inc. Heuristic method of classification
US7499891B2 (en) 2000-06-19 2009-03-03 Correlogic Systems, Inc. Heuristic method of classification
US20040058372A1 (en) * 2002-07-29 2004-03-25 Hitt Ben A. Quality assurance for high-throughput bioassay methods
US7333895B2 (en) 2002-07-29 2008-02-19 Correlogic Systems, Inc. Quality assurance for high-throughput bioassay methods
US7395160B2 (en) 2002-07-29 2008-07-01 Correlogic Systems, Inc. Quality assurance/quality control for electrospray ionization processes
US20050283347A1 (en) * 2002-12-09 2005-12-22 Ajinomoto Co., Inc. Apparatus and method for processing information concerning biological condition, system, program and recording medium for managing information concerning biological condition
US8234075B2 (en) 2002-12-09 2012-07-31 Ajinomoto Co., Inc. Apparatus and method for processing information concerning biological condition, system, program and recording medium for managing information concerning biological condition
US20060064253A1 (en) * 2003-08-01 2006-03-23 Hitt Ben A Multiple high-resolution serum proteomic features for ovarian cancer detection
US20070003996A1 (en) * 2005-02-09 2007-01-04 Hitt Ben A Identification of bacteria and spores
US20080147368A1 (en) * 2005-03-16 2008-06-19 Ajinomoto Co., Inc. Biological state-evaluating apparatus, biological state-evaluating method, biological state-evaluating system, biological state-evaluating program, evaluation function-generating apparatus, evaluation function-generating method, evaluation function-generating program and recording medium
US20080312514A1 (en) * 2005-05-12 2008-12-18 Mansfield Brian C Serum Patterns Predictive of Breast Cancer
US20100174492A1 (en) * 2006-03-31 2010-07-08 Biodesix, Inc. Method and system for determining whether a drug will be effective on a patient with a disease
US7736905B2 (en) 2006-03-31 2010-06-15 Biodesix, Inc. Method and system for determining whether a drug will be effective on a patient with a disease
US9152758B2 (en) 2006-03-31 2015-10-06 Biodesix, Inc. Method and system for determining whether a drug will be effective on a patient with a disease
US20100305868A1 (en) * 2006-03-31 2010-12-02 Biodesix, Inc. Method and system for determining whether a drug will be effective on a patient with a disease
US7879620B2 (en) 2006-03-31 2011-02-01 Biodesix, Inc. Method and system for determining whether a drug will be effective on a patient with a disease
US9824182B2 (en) 2006-03-31 2017-11-21 Biodesix, Inc. Method and system for determining whether a drug will be effective on a patient with a disease
US8097469B2 (en) 2006-03-31 2012-01-17 Biodesix, Inc. Method and system for determining whether a drug will be effective on a patient with a disease
US20070231921A1 (en) * 2006-03-31 2007-10-04 Heinrich Roder Method and system for determining whether a drug will be effective on a patient with a disease
US20080201095A1 (en) * 2007-02-12 2008-08-21 Yip Ping F Method for Calibrating an Analytical Instrument
US20090004687A1 (en) * 2007-06-29 2009-01-01 Mansfield Brian C Predictive markers for ovarian cancer
US8664358B2 (en) 2007-06-29 2014-03-04 Vermillion, Inc. Predictive markers for ovarian cancer
US9274118B2 (en) 2007-06-29 2016-03-01 Vermillion, Inc. Predictive markers for ovarian cancer
US9846158B2 (en) 2007-06-29 2017-12-19 Vermillion, Inc. Predictive biomarkers for ovarian cancer
US10605811B2 (en) 2007-06-29 2020-03-31 Vermillion, Inc. Predictive biomarkers for ovarian cancer
US20110208433A1 (en) * 2010-02-24 2011-08-25 Biodesix, Inc. Cancer patient selection for administration of therapeutic agents using mass spectral analysis of blood-based samples

Also Published As

Publication number Publication date
SG144731A1 (en) 2008-08-28
EP1386275A2 (en) 2004-02-04
US20030004402A1 (en) 2003-01-02
WO2002006829A2 (en) 2002-01-24
JP5246984B2 (en) 2013-07-24
US6925389B2 (en) 2005-08-02
MXPA03000506A (en) 2004-09-10
BR0112667A (en) 2006-05-09
WO2002006829A3 (en) 2003-11-20
EA200300161A1 (en) 2003-12-25
AU2001280581A1 (en) 2002-01-30
KR101054732B1 (en) 2011-08-05
NO20030251L (en) 2003-03-17
NZ524171A (en) 2006-09-29
JP2013101130A (en) 2013-05-23
NO20030251D0 (en) 2003-01-17
IL153856A0 (en) 2003-07-31
AU2010246364A1 (en) 2010-12-16
CA2415775A1 (en) 2002-01-24
CN1484806A (en) 2004-03-24
US20050043593A9 (en) 2005-02-24
KR20030074585A (en) 2003-09-19
JP2004519659A (en) 2004-07-02

Similar Documents

Publication Publication Date Title
US6925389B2 (en) Process for discriminating between biological states based on hidden patterns from biological data
US8478534B2 (en) Method for detecting discriminatory data patterns in multiple sets of data and diagnosing disease
Conrads et al. High-resolution serum proteomic features for ovarian cancer detection.
Ornstein et al. Serum proteomic profiling can discriminate prostate cancer from benign prostates in men with total prostate specific antigen levels between 2.5 and 15.0 ng/ml
US10713590B2 (en) Bagged filtering method for selection and deselection of features for classification
Li et al. Data mining techniques for cancer detection using serum proteomic profiling
KR101047575B1 (en) Heuristic Method of Classification
US20060064253A1 (en) Multiple high-resolution serum proteomic features for ovarian cancer detection
US20020095260A1 (en) Methods for efficiently mining broad data sets for biological markers
JP2004522980A (en) How to analyze a mass spectrum
US20100017356A1 (en) Method for Identifying Protein Patterns in Mass Spectrometry
WO2005024648A1 (en) Methods of processing biological data
Zhang et al. Multiple biomarker panels for early detection of breast cancer in peripheral blood
AU2008201163A1 (en) A process for discriminating between biological states based on hidden patterns from biological data
Oh et al. An extended Markov blanket approach to proteomic biomarker detection from high-resolution mass spectrometry data
Leung et al. Gene selection for brain cancer classification
Assareh et al. A novel ensemble strategy for classification of prostate cancer protein mass spectra
Mohamad et al. A recursive genetic algorithm to automatically select genes for cancer classification
Hu et al. Gene Selection in Terms of Performance Based Consistency
Luo et al. Weighted top score pair method for gene selection and classification
Ahluwalia et al. Proteomic pattern analysis using neural networks
Sung et al. Fundamentals of Cancer Genomics and Proteomics
Lakshmidevi et al. SUPERVISED MULTI ATTRIBUTE GENE MANIPULATION FOR CANCER

Legal Events

Date Code Title Description
AS Assignment

Owner name: THE UNITED STATES OF AMERICA AS REPRESENTED BY THE

Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNORS:LIOTTA, LANCE A.;PETRICOIN, EMMANUEL F., III;REEL/FRAME:019635/0850

Effective date: 20030328

Owner name: CORRELOGIC SYSTEMS, INC., MARYLAND

Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNORS:HITT, BEN;LEVINE, PETER J.;REEL/FRAME:019635/0793

Effective date: 20030213

AS Assignment

Owner name: VERMILLION, INC., TEXAS

Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:CORRELOGIC SYSTEMS, INC.;REEL/FRAME:028209/0828

Effective date: 20120514

STCB Information on status: application discontinuation

Free format text: ABANDONED -- FAILURE TO RESPOND TO AN OFFICE ACTION