Biosimulation Using the Cellworks Computational Omics Biology Model (CBM) Predicted Novel Biomarkers for Hyper-CVAD (CVAD) Treatment Response and Combination of Rituximab and Cladribine (RC) in CVAD Resistant Cases of Mantle Cell Lymphoma (MCL)

Background: Mantle Cell Lymphoma (MCL) accounts for 3-10% of all non-Hodgkin lymphomas with a median overall survival of 3-4 years. Hyper-CVAD (CVAD) with or without Rituximab constitutes first line therapy for treatment of MCL, yet the use of this combination is associated with high toxicity and only modest efficacy. On the other hand, impressive clinical efficacy has been reported in relapsed MCL patients treated with rituximab and cladribine (RC). Prediction of response based on cancer genomics heterogeneity creates an opportunity to personalize treatment and avoid toxic therapy which has little chance of response. We conducted a study using the Cellworks Biosimulation Platform to identify novel genomic biomarkers associated with response to CVAD and RC among MCL patients. Method: Newly-diagnosed MCL patients were selected for this study based largely on genomic data (i.e. aberrations and copy number variations) published in PubMed and TCGA. The Cellworks Computational Omics Biology Model (CBM) is a computational multi-omic biology software model created using artificial intelligence heuristics and literature sourced from PubMed, to generate a patient-specific protein network map. Genomic data from each patient served as input for the CBM. Biomarkers unique to each patient were identified within protein network-maps. Drug impact on the disease network was biosimulated using the Cellworks Biosimulation Platform to determine a treatment efficacy value by measuring the treatment effects on the cell growth score, a composite of cell proliferation, viability, apoptosis, metastasis, DNA damage and other cancer hallmarks. The mechanism of action of each drug was mapped to each patient's CBM and the predicted biological consequences were used to determine response. Biosimulation of CVAD was applied to the patients in this cohort. RC was biosimulated on all CVAD non-responders. Results: Among the 94 MCL patients treated with CVAD, the Cellworks Biosimulation Platform identified novel biomarkers (Table 1) to predict treatment response or failure. The biosimulation also identified unique drug combinations for patients that were non-responders (NR) to both treatments. Of the 94 patients, 57 were deemed responders (R) and 37 non-responders (NR). ATM LOF/del, RAD51 del, LIG4A del, RB1 del, ERCC5 del, CARD11 amp, IKZF1 amp, and FANCC del were major predictors of CVAD response. These genes contributed to drug efficacy by impacting various pathways, including DNA repair