TY - JOUR
T1 - The ordering of expression among a few genes can provide simple cancer biomarkers and signal BRCA1 mutations
AU - Lin, Xue
AU - Afsari, Bahman
AU - Marchionni, Luigi
AU - Cope, Leslie
AU - Parmigiani, Giovanni
AU - Naiman, Daniel
AU - Geman, Donald
N1 - Funding Information:
The work of DN and BA was partially supported by NIH-NCRR Grant UL1 RR 025005; the work of DG by NIH-NCRR Grant UL1 RR 025005 and NSF CCF-0625687; the work of LC by NSF Grant DMS034211; the work of LM by NIH-NCI Grants P30CA006973, 1R21CA135877 and 5P30 CA06973-39; and the work of GP by NSF Grant DMS034211 and NIH-NCI Grants 5P30 CA06973-39, 2P50CA88843-06A1, 5R01CA105090-03 and NIH 1UL1RR025005-01.
PY - 2009/8/20
Y1 - 2009/8/20
N2 - Background: A major challenge in computational biology is to extract knowledge about the genetic nature of disease from high-throughput data. However, an important obstacle to both biological understanding and clinical applications is the "black box" nature of the decision rules provided by most machine learning approaches, which usually involve many genes combined in a highly complex fashion. Achieving biologically relevant results argues for a different strategy. A promising alternative is to base prediction entirely upon the relative expression ordering of a small number of genes. Results: We present a three-gene version of "relative expression analysis" (RXA), a rigorous and systematic comparison with earlier approaches in a variety of cancer studies, a clinically relevant application to predicting germline BRCA1 mutations in breast cancer and a cross-study validation for predicting ER status. In the BRCA1 study, RXA yields high accuracy with a simple decision rule: in tumors carrying mutations, the expression of a "reference gene" falls between the expression of two differentially expressed genes, PPP1CB and RNF14. An analysis of the protein-protein interactions among the triplet of genes and BRCA1 suggests that the classifier has a biological foundation. Conclusion: RXA has the potential to identify genomic "marker interactions" with plausible biological interpretation and direct clinical applicability. It provides a general framework for understanding the roles of the genes involved in decision rules, as illustrated for the difficult and clinically relevant problem of identifying BRCA1 mutation carriers.
AB - Background: A major challenge in computational biology is to extract knowledge about the genetic nature of disease from high-throughput data. However, an important obstacle to both biological understanding and clinical applications is the "black box" nature of the decision rules provided by most machine learning approaches, which usually involve many genes combined in a highly complex fashion. Achieving biologically relevant results argues for a different strategy. A promising alternative is to base prediction entirely upon the relative expression ordering of a small number of genes. Results: We present a three-gene version of "relative expression analysis" (RXA), a rigorous and systematic comparison with earlier approaches in a variety of cancer studies, a clinically relevant application to predicting germline BRCA1 mutations in breast cancer and a cross-study validation for predicting ER status. In the BRCA1 study, RXA yields high accuracy with a simple decision rule: in tumors carrying mutations, the expression of a "reference gene" falls between the expression of two differentially expressed genes, PPP1CB and RNF14. An analysis of the protein-protein interactions among the triplet of genes and BRCA1 suggests that the classifier has a biological foundation. Conclusion: RXA has the potential to identify genomic "marker interactions" with plausible biological interpretation and direct clinical applicability. It provides a general framework for understanding the roles of the genes involved in decision rules, as illustrated for the difficult and clinically relevant problem of identifying BRCA1 mutation carriers.
UR - http://www.scopus.com/inward/record.url?scp=70349731768&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=70349731768&partnerID=8YFLogxK
U2 - 10.1186/1471-2105-10-256
DO - 10.1186/1471-2105-10-256
M3 - Article
C2 - 19695104
AN - SCOPUS:70349731768
SN - 1471-2105
VL - 10
SP - 256
JO - BMC Bioinformatics
JF - BMC Bioinformatics
M1 - 1471
ER -