Training host-pathogen protein–protein interaction predictors

Abstract

Detection of protein-protein interactions (PPIs) plays a vital role in molecular biology. Particularly, pathogenic infections are caused by interactions of host and pathogen proteins. It is important to identify host-pathogen interactions (HPIs) to discover new drugs to counter infectious diseases. Conventional wet lab PPI detection techniques have limitations in terms of cost and large-scale application. Hence, computational approaches are developed to predict PPIs. This study aims to develop machine learning models to predict inter-species PPIs with a special interest in HPIs. Specifically, we focus on seeking answers to three questions that arise while developing an HPI predictor: (1) How should negative training examples be selected? (2) Does assigning sample weights to individual negative examples based on their similarity to positive examples improve generalization performance? and, (3) What should be the size of negative samples as compared to the positive samples during training and evaluation? We compare two available methods for negative sampling: random versus DeNovo sampling and our experiments show that DeNovo sampling offers better accuracy. However, our experiments also show that generalization performance can be improved further by using a soft DeNovo approach that assigns sample weights to negative examples inversely proportional to their similarity to known positive examples during training. Based on our findings, we have also developed an HPI predictor called HOPITOR (Host-Pathogen Interaction Predictor) that can predict interactions between human and viral proteins. The HOPITOR web server can be accessed at the URL: http://faculty.pieas.edu.pk/fayyaz/software.html#HoPItor .

Translocatome: a novel resource for the analysis of protein translocation between cellular organelles

“…XGBoost was successfully applied in hundreds of recent studies to predict, e.g. host-pathogen protein–protein interactions (16), microRNA disease association (17) and DNA methylation (18). Several studies including our own previous paper showed that XGBoost gives the best performance if compared with a number of known machine learning methods (see e.g.…”

“…Following the methodology of several XGBoost studies (11,16–18) including our previously published work (12) we evaluated the XGBoost-selected feature sets by 5-fold cross-validation, and we evaluated their predictive power by the area under the curve of the receiver operating characteristic curve (ROC AUC or shortly AUC, 21). 5-fold cross-validation is a widely used method where the training data is split into five random parts and four parts are used to train the XGBoost machine learning tool and the prediction of the fifth part is evaluated.…”

A multitask transfer learning framework for novel virus-human protein interactions

“…Virus protein sequences of different species share only little in common (Eid et al, 2016). Therefore, models trained for other human PPI (Li & Ilie, 2020; Sun et al, 2017; Li, 2020; Chen et al, 2019; Sarkar & Saha, 2019) or for other pathogen-human PPI (Sudhakar et al, 2020; Mei & Zhang, 2020; Dick et al, 2020; Li et al, 2014; Guven-Maiorov et al, 2019; Basit et al, 2018)(for which more data might be available) cannot be directly used for predictions for novel viral-human protein interactions.…”

SARS-CoV-2-human protein-protein interaction network

“…Nourani used Naïve Bayes [ 23 ]. Decision tree related classifier was the approach taken by Basit [ 24 ]. Random forest was the approach followed by both Yang [ 25 ] and Barman [ 26 ].…”