Recommender Systems in Antiviral Drug Discovery

Abstract

Recommender systems (RSs), which underwent rapid development and had an enormous impact on e-commerce, have the potential to become useful tools for drug discovery. In this paper, we applied RS methods for the prediction of the antiviral activity class (active/inactive) for compounds extracted from ChEMBL. Two main RS approaches were applied: collaborative filtering (Surprise implementation) and content-based filtering (sparse-group inductive matrix completion (SGIMC) method). The effectiveness of RS approaches was investigated for prediction of antiviral activity classes (“interactions”) for compounds and viruses, for which some of their interactions with other viruses or compounds are known, and for prediction of interaction profiles for new compounds. Both approaches achieved relatively good prediction quality for binary classification of individual interactions and compound profiles, as quantified by cross-validation and external validation receiver operating characteristic (ROC) score >0.9. Thus, even simple recommender systems may serve as an effective tool in antiviral drug discovery.

Recommendation System to Predict Missing Adsorption Properties of Nanoporous Materials

“…Loosely related, meta-learning has been used to predict an adsorption property of materials at different conditions by learning an intermediate representation of the material based only on available adsorption data . N.b., recommendation systems have been built for use in chemical sciences to impute missing gas permeabilities in polymers, antiviral activities of molecules, and stabilities of inorganic materials. , …”

Hybrid semantic recommender system for chemical compounds in large-scale datasets

“…The datasets used has the format of target-drug pairs, but it does not contain any information about the researcher choices. Most recently, Sosnina et al [ 33 ] used RS approaches to discover new antiviral drugs, extracting compounds from ChEMBL [ 34 ], a database of molecules with drug-like properties. The dataset used has the format of compound-viral species-interaction value.…”

Hybrid Semantic Recommender System for Chemical Compounds in Large-Scale Datasets

“…In the Chemistry domain, RS have been generally used in studies related to drugs, for example, for new drugs design [31], and for finding candidate drugs for diseases [32]. Most recently, [33] used RS approaches to discover new antiviral drugs, extracting compounds from ChEMBL [34], a database of molecules with drug-like properties. Other RS applications in Chemistry may be found in [2], which describes the use of CF methods for creating possibilities for new chemical compounds.…”