Associating gene expression data with a disease name

Abstract

The present invention relates to a method and system for associating gene expression data with a disease name. A first data set associated with a plurality of genetic probes for a plurality of biological samples may be received. The first data set may be sorted based on a normalized gene expression values for the plurality of genetic probes. A largest value gap of the normalized gene expression values may be identified. A set of expressed genes within the first data set may be identified. An indexable document may be generated for a biological sample of the plurality of biological samples comprising data associated with the set of expressed genes. A second data set associated with an expressed gene of the set of expressed genes may be searched. A disease name may be associated with an expressed gene based on a threshold correlation between the disease name and the expressed gene.

What is claimed is: 
     
         1 . A method comprising:
 receiving a first data set associated with a plurality of genetic probes for a plurality of biological samples, wherein the first data set comprises gene expression values for the plurality of genetic probes;   identifying a largest value gap of the gene expression values, wherein a gap comprises a difference between two consecutive scores;   identifying a set of expressed genes within the first data set, wherein the identifying comprises converting the gene expression values to binary expressions; and   associating at least one disease name of the set of disease names with at least one expressed gene of the set of expressed genes based on a threshold correlation between the at least one expressed gene and at least one disease name associated with the at least one expressed gene.   
     
     
         2 . The method of  claim 1 , wherein the first data set comprises a vector comprising:
 rows representing a number of genetic probes measured by a genetic sequencing apparatus; and   columns representing genetic information of a number of biological samples.   
     
     
         3 . The method of  claim 1 , wherein further comprising:
 sorting the first data set based on normalized gene expression values for the plurality of gene probes, wherein the sorting includes assigning a score for the gene expression values by subtracting a lowest non-outlier value from a highest non-outlier value.   
     
     
         4 . The method of  claim 1 , wherein the largest value gap is a largest difference between consecutive scores assigned for the gene expression values. 
     
     
         5 . The method of  claim 1 , wherein a largest value gap is a region having a more sparse population of scored gene expression values than adjacent regions. 
     
     
         6 . The method of  claim 1 , wherein the binary expressions include expressed and unexpressed. 
     
     
         7 . The method of  claim 1 , wherein identifying a set of expressed genes within the first data set comprises:
 identifying gene probes of the plurality of gene probes having a gene expression value greater than the largest value gap as expressed; and   identifying gene probes of the plurality of gene probes having a gene expression value less than the largest value gap as unexpressed.   
     
     
         8 . The method of  claim 1 , further comprising:
 generating an indexable document for a biological sample in the plurality of biological samples comprising data associated with set of expressed genes, wherein a generated indexable document comprises at least data associated with an expressed gene, and either or both of:   one or more canonical disease names; and   a second data set comprising data associated with an expressed gene of the set of expressed genes, wherein the second data set comprises expressed gene data associated with one or more canonical disease names, and wherein the second data set is derived from one or more natural language documents.   
     
     
         9 . The method of  claim 8 , further comprising:
 receiving unstructured text associated with one or more medical studies; and   generating the second data set by structuring the unstructured text by producing a parse tree based on relationships identified in the content of the unstructured text.   
     
     
         10 . A computer program product for associating gene expression information with a disease name, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, wherein the computer readable storage medium is not a transitory signal per se, the program instructions executable by a computer to cause the computer to perform a method comprising:
 receiving, by a computer, a first data set associated with a plurality of genetic probes for a plurality of biological samples, wherein the first data set comprises gene expression values for the plurality of genetic probes;   identifying, by a computer, a largest value gap of the gene expression values, wherein a gap comprises a difference between two consecutive scores;   identifying, by a computer, a set of expressed genes within the first data set, wherein the identifying comprises converting the normalized gene expression values to binary expressions; and   associating, by a computer, at least one disease name of the set of disease names with at least one expressed gene of the set of expressed genes based on a threshold correlation between the at least one expressed gene and at least one disease name associated with the at least one expressed gene.   
     
     
         11 . The computer program product of  claim 10 , wherein the first data set comprises a vector comprising:
 rows representing a number of genetic probes measured by a genetic sequencing apparatus; and   columns representing genetic information of a number of biological samples.   
     
     
         12 . The computer program product of  claim 10 , wherein the method further comprises:
 sorting, by the computer, the first data set based on normalized gene expression values for the plurality of gene probes, wherein the sorting includes assigning a score for the gene expression values by subtracting a lowest non-outlier value from a highest non-outlier value.   
     
     
         13 . The computer program product of  claim 10 , wherein identifying the set of expressed genes within the first data set comprises:
 identifying gene probes of the plurality of gene probes having a gene expression value greater than the largest value gap as expressed; and   identifying gene probes of the plurality of gene probes having a gene expression value less than the largest value gap as unexpressed.   
     
     
         14 . The computer program product of  claim 10 , wherein the method further comprises:
 generating an indexable document for a biological sample in the plurality of biological samples comprising data associated with set of expressed genes, the generated indexable documents comprise at least one of text from one or more studies, data associated with a set of expressed genes, or canonical disease names.   
     
     
         15 . The computer program product of  claim 10 , further comprising:
 receiving unstructured text associated with one or more medical studies; and   generating a second data set comprising data associated with an expressed gene of the set of expressed genes, wherein the generating comprises structuring the unstructured text by producing a parse tree based on relationships identified in the content of the unstructured text.   
     
     
         16 . A computer system for associating gene expression information with a disease name, the computer system comprising:
 one or more computer processors;   one or more computer-readable storage media;   program instructions stored on the computer-readable storage media for execution by at least one of the one or more processors, the program instructions comprising:   instructions to receive a first data set associated with a plurality of genetic probes for a plurality of biological samples, wherein the first data set comprises gene expression values for the plurality of genetic probes;   instructions to identify a largest value gap of the gene expression values, wherein a gap comprises a difference between two consecutive scores;   instructions to identify a set of expressed genes within the first data set, wherein the instructions to identify comprise instructions to convert the gene expression values to binary expressions; and   instructions to associate at least one disease name of the set of disease names with at least one expressed gene of the set of expressed genes based on a threshold correlation between the at least one expressed gene and at least one disease name associated with the at least one expressed gene.   
     
     
         17 . The system of  claim 15 , wherein the first data set comprises a vector comprising:
 rows representing a number of genetic probes measured by a genetic sequencing apparatus; and   columns representing genetic information of a number of biological samples.   
     
     
         18 . The system of  claim 15 , wherein the instructions further comprise instructions to:
 sorting the first data set based on normalized gene expression values for the plurality of gene probes, wherein the instructions to sort include instructions to assign a score for the gene expression values by subtracting a lowest non-outlier value from a highest non-outlier value.   
     
     
         19 . The system of  claim 15 , wherein the instructions to identify the set of expressed genes within the first data set comprise:
 instructions to identify gene probes of the plurality of gene probes having a gene expression value greater than the largest value gap as expressed; and   instructions to identify gene probes of the plurality of gene probes having a gene expression value less than the largest value gap as unexpressed.   
     
     
         20 . The system of  claim 15 , further comprising:
 receiving unstructured text associated with one or more medical studies; and   generating a second data set comprising data associated with an expressed gene of the set of expressed genes, wherein the generating comprises structuring the unstructured text by producing a parse tree based on relationships identified in the content of the unstructured text.