Neighborhood-based inference and restricted Boltzmann machine for microbe and drug associations prediction.

Background: Efficient identification of microbe-drug associations is critical for drug development and solving problem of antimicrobial resistance. Traditional wet-lab method requires a lot of money and labor in identifying potential microbe-drug associations. With development of machine learning and publication of large amounts of biological data, computational methods become feasible. Methods: In this article, we proposed a computational model of neighborhood-based inference (NI) and restricted Boltzmann machine (RBM) to predict potential microbe-drug association (NIRBMMDA) by using integrated microbe similarity, integrated drug similarity and known microbe-drug associations. First, NI was used to obtain a score matrix of potential microbe-drug associations by using different thresholds to find similar neighbors for drug or microbe. Second, RBM was employed to obtain another score matrix of potential microbe-drug associations based on contrastive divergence algorithm and sigmoid function. Because generalization ability of individual method is poor, we used an ensemble learning to integrate two score matrices for predicting potential microbe-drug associations more accurately. In particular, NI can fully utilize similar (neighbor) information of drug or microbe and RBM can learn potential probability distribution hid in known microbe-drug associations. Moreover, ensemble learning was used to integrate individual predictor for obtaining a stronger predictor. Results: In global leave-one-out cross validation (LOOCV), NIRBMMDA gained the area under the receiver operating characteristics curve (AUC) of 0.8666, 0.9413 and 0.9557 for datasets of DrugVirus, MDAD and aBiofilm, respectively. In local LOOCV, AUCs of 0.8512, 0.9204 and 0.9414 were obtained for NIRBMMDA based on datasets of DrugVirus, MDAD and aBiofilm, respectively. For five-fold cross validation, NIRBMMDA acquired AUC and standard deviation of 0.8569 ± -0.0027, 0.9248 ± -0.0014 and 0.9369 ± -0.0020 on the basis of datasets of DrugVirus, MDAD and aBiofilm, respectively. Moreover, case study for severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) showed that 13 out of the top 20 predicted drugs were verified by searching literature. The other two case studies indicated that 17 and 17 out of the top 20 predicted microbes for the drug of ciprofloxacin and minocycline were confirmed by identifying published literature, respectively.

A computational framework of host-based drug repositioning for broad-spectrum antivirals against RNA viruses.

RNA viruses are responsible for many zoonotic diseases that post great challenges for public health. Effective therapeutics against these viral infections remain limited. Here, we deployed a computational framework for host-based drug repositioning to predict potential antiviral drugs from 2,352 approved drugs and 1,062 natural compounds embedded in herbs of traditional Chinese medicine. By systematically interrogating public genetic screening data, we comprehensively cataloged host dependency genes (HDGs) that are indispensable for successful viral infection corresponding to 10 families and 29 species of RNA viruses. We then utilized these HDGs as potential drug targets and interrogated extensive drug-target interactions through database retrieval, literature mining, and de novo prediction using artificial intelligence-based algorithms. Repurposed drugs or natural compounds were proposed against many viral pathogens such as coronaviruses including severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), flaviviruses, and influenza viruses. This study helps to prioritize promising drug candidates for in-depth evaluation against these virus-related diseases.