Machine learning predicts treatment sensitivity in multiple myeloma based on molecular and clinical information coupled with drug response

Author(s)

Venezian Povoa, Lucas ^{[1, 2, 3, 4]} ; Ribeiro, Carlos Henrique Costa ^{[1, 2]} ; da Silva, Israel Tojal ^[3]

Affiliation

^[1] Aeronaut Inst Technol ITA, Bioengn Lab, Sao Jose Dos Campos - Brazil

^[2] Aeronaut Inst Technol ITA, Comp Sci Div, Sao Jose Dos Campos - Brazil

^[3] Int Res & Educ Ctr, AC Camargo Canc Ctr ACCCC, Sao Paulo - Brazil

^[4] Fed Inst Educ Sci & Technol Sao Paulo IFPS, Jacarei - Brazil

• Document type: Journal article
• Source: PLoS One; v. 16, n. 7 JUL 28 2021.
• Web of Science Citations: 0

Abstract

Providing treatment sensitivity stratification at the time of cancer diagnosis allows better allocation of patients to alternative treatment options. Despite many clinical and biological risk markers having been associated with variable survival in cancer, assessing the interplay of these markers through Machine Learning (ML) algorithms still remains to be fully explored. Here, we present a Multi Learning Training approach (MuLT) combining supervised, unsupervised and self-supervised learning algorithms, to examine the predictive value of heterogeneous treatment outcomes for Multiple Myeloma (MM). We show that gene expression values improve the treatment sensitivity prediction and recapitulates genetic abnormalities detected by Fluorescence in situ hybridization (FISH) testing. MuLT performance was assessed by cross-validation experiments, in which it predicted treatment sensitivity with 68.70% of AUC. Finally, simulations showed numerical evidences that in average 17.07% of patients could get better response to a different treatment at the first line. (AU)

• FAPESP's process: 15/19324-6 - Retrotransposons and nucleic acid-editing enzymes: activation, somatic events and association with cancer
• Grantee: Israel Tojal da Silva
• Support Opportunities: Regular Research Grants