1st International and 10th National Iranian Conference on Bioinformatics

A Novel Method for Predicting Drug Synergy Based on Matrix Factorization

Paper ID : 1383-ICB10

Authors:

Fatemeh Abbasi, Sajjad Gharaghani *

دانشگاه تهران مرکز تحقیقات بیوشیمی بیوفیزیک گروه بیوانفورماتیک آزمایشگاه LBD

Abstract:

Combination therapy has proven to be highly effective in the treatment of complex diseases such as cancer and infectious diseases. When compared to monotherapy, drug combination therapy can improve cancer treatment efficacy, reduce drug dose-dependent toxicity, and prevent drug resistance. In this study, we present a novel regression method based on matrix factorization. Using K-fold nested cross-validation, we compare the results of the presented method to the results of two novel regression methods, PRODeepSyn[1] and DeepSynergy[2], on the DrugComb[3] database. DrugComb collects data from four studies: I the O'Neil dataset, (ii) the Forcina dataset, (iii) the NCI Almanac dataset, and (iv) the CLOUD dataset. DeepSynergy is a feed forward neural network that converts sample input vectors into a single output value known as the synergy score. DeepSynergy used chemical information derived from drugs as well as genomic data pertaining to disease biology. PRODeepSyn is a deep neural network that predicts synergy scores based on cell line embeddings and drug features using Batch Normalization. PRODeepSyn constructs the feature vector for each drug using the molecular fingerprint and descriptors to represent the structural and physicochemical properties of drugs, and for cell line features they integrate three types of heterogeneous cell line features containing gene expression data, gene mutation data, and interactions between gene expression products to construct cell line embeddings. To compare these methods, the mean square error (MSE), root mean square error (RMSE), and Pearson correlation coefficient (PCC) between predictions and ground truth are used as primary evaluation metrics. The results show that the presented matrix factorization method outperformed the PRODeepSyn and DeepSynergy methods across the platform.

Keywords:

drug synergy; deep learning; graph convolutional network; feed forward neural network

Status : Paper Accepted (Oral Presentation)