FOLFOX treatment response prediction in metastatic or recurrent colorectal cancer patients via machine learning algorithms

• Published in: Cancer medicine (Malden, MA) Vol. 9; no. 4; pp. 1419 - 1429
• Main Authors: Lu, Wei, Fu, Dongliang, Kong, Xiangxing, Huang, Zhiheng, Hwang, Maxwell, Zhu, Yingshuang, Chen, Liubo, Jiang, Kai, Li, Xinlin, Wu, Yihua, Li, Jun, Yuan, Ying, Ding, Kefeng
• Format: Journal Article
• Language: English
• Published: United States John Wiley & Sons, Inc 01.02.2020; John Wiley and Sons Inc; Wiley
• Subjects: Accuracy; Algorithms; Antineoplastic Combined Chemotherapy Protocols - therapeutic use; Apoptosis; Autophagy; Biomarkers, Tumor - genetics; Cancer therapies; Cell Cycle Proteins - genetics; Chemotherapy; Clinical Cancer Research; Colorectal cancer; Colorectal carcinoma; Colorectal Neoplasms - drug therapy; Colorectal Neoplasms - genetics; Colorectal Neoplasms - pathology; Datasets; Datasets as Topic; DNA microarrays; Endocytosis; ErbB protein; Fluorouracil - therapeutic use; FOLFOX; Forkhead protein; Gene expression; Gene Expression Profiling - statistics & numerical data; Gene Expression Regulation, Neoplastic; Genomes; Humans; Interferon regulatory factor 7; Intracellular Signaling Peptides and Proteins - genetics; Learning algorithms; Leucovorin - therapeutic use; Machine Learning; machine learning algorithm; Meta-analysis; Metastases; Metastasis; microarray meta‐analysis; Neoplasm Recurrence, Local - drug therapy; Neoplasm Recurrence, Local - genetics; Oligonucleotide Array Sequence Analysis - statistics & numerical data; Ontology; Organoplatinum Compounds - therapeutic use; Original Research; Oxaliplatin; Phagocytosis; Prognosis; Protein Kinases - genetics; Quality control; Response Evaluation Criteria in Solid Tumors; Signal transduction; colorectal cancer; FOLFOX; microarray meta-analysis; machine learning algorithm
• ISSN: 2045-7634; 2045-7634
• DOI: 10.1002/cam4.2786

Early identification of metastatic or recurrent colorectal cancer (CRC) patients who will be sensitive to FOLFOX (5‐FU, leucovorin and oxaliplatin) therapy is very important. We performed microarray meta‐analysis to identify differentially expressed genes (DEGs) between FOLFOX responders and nonresponders in metastatic or recurrent CRC patients, and found that the expression levels of WASHC4, HELZ, ERN1, RPS6KB1, and APPBP2 were downregulated, while the expression levels of IRF7, EML3, LYPLA2, DRAP1, RNH1, PKP3, TSPAN17, LSS, MLKL, PPP1R7, GCDH, C19ORF24, and CCDC124 were upregulated in FOLFOX responders compared with nonresponders. Subsequent functional annotation showed that DEGs were significantly enriched in autophagy, ErbB signaling pathway, mitophagy, endocytosis, FoxO signaling pathway, apoptosis, and antifolate resistance pathways. Based on those candidate genes, several machine learning algorithms were applied to the training set, then performances of models were assessed via the cross validation method. Candidate models with the best tuning parameters were applied to the test set and the final model showed satisfactory performance. In addition, we also reported that MLKL and CCDC124 gene expression were independent prognostic factors for metastatic CRC patients undergoing FOLFOX therapy. We performed the microarray meta‐analysis to identify common differentially expressed genes between FOLFOX responders and non‐responders in metastatic or recurrent colorectal cancer patients, and built prediction models with machine learning algorithms.