Premium
MO‐DE‐207B‐03: Improved Cancer Classification Using Patient‐Specific Biological Pathway Information Via Gene Expression Data
Author(s) -
Young M,
Craft D
Publication year - 2016
Publication title -
medical physics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.473
H-Index - 180
eISSN - 2473-4209
pISSN - 0094-2405
DOI - 10.1118/1.4957252
Subject(s) - cancer , cluster analysis , survival analysis , oncology , medicine , bioinformatics , computational biology , biology , artificial intelligence , computer science
Purpose: To develop an efficient, pathway‐based classification system using network biology statistics to assist in patient‐specific response predictions to radiation and drug therapies across multiple cancer types. Methods: We developed PICS (Pathway Informed Classification System), a novel two‐step cancer classification algorithm. In PICS, a matrix m of mRNA expression values for a patient cohort is collapsed into a matrix p of biological pathways. The entries of p, which we term pathway scores, are obtained from either principal component analysis (PCA), normal tissue centroid (NTC), or gene expression deviation (GED). The pathway score matrix is clustered using both k‐means and hierarchical clustering, and a clustering is judged by how well it groups patients into distinct survival classes. The most effective pathway scoring/clustering combination, per clustering p‐value, thus generates various ‘signatures’ for conventional and functional cancer classification. Results: PICS successfully regularized large dimension gene data, separated normal and cancerous tissues, and clustered a large patient cohort spanning six cancer types. Furthermore, PICS clustered patient cohorts into distinct, statistically‐significant survival groups. For a suboptimally‐debulked ovarian cancer set, the pathway‐classified Kaplan‐Meier survival curve (p = .00127) showed significant improvement over that of a prior gene expression‐classified study (p = .0179). For a pancreatic cancer set, the pathway‐classified Kaplan‐Meier survival curve (p = .00141) showed significant improvement over that of a prior gene expression‐classified study (p = .04). Pathway‐based classification confirmed biomarkers for the pyrimidine, WNT‐signaling, glycerophosphoglycerol, beta‐alanine, and panthothenic acid pathways for ovarian cancer. Despite its robust nature, PICS requires significantly less run time than current pathway scoring methods. Conclusion: This work validates the PICS method to improve cancer classification using biological pathways. Patients are classified with greater specificity and physiological relevance as compared to current gene‐specific approaches. Focus now moves to utilizing PICS for pan‐cancer patient‐specific treatment response prediction.