Highly predictive support vector machine (SVM) models for anthrax toxin lethal factor (LF) inhibitors

Abstract

Anthrax is a highly lethal, acute infectious disease caused by the rod-shaped, Gram-positive bacterium Bacillus anthracis. The anthrax toxin lethal factor (LF), a zinc metalloprotease secreted by the bacilli, plays a key role in anthrax pathogenesis and is chiefly responsible for anthrax-related toxemia and host death, partly via inactivation of mitogen-activated protein kinase kinase (MAPKK) enzymes and consequent disruption of key cellular signaling pathways. Antibiotics such as fluoroquinolones are capable of clearing the bacilli but have no effect on LF-mediated toxemia; LF itself therefore remains the preferred target for toxin inactivation. However, currently no LF inhibitor is available on the market as a therapeutic, partly due to the insufficiency of existing LF inhibitor scaffolds in terms of efficacy, selectivity, and toxicity. In the current work, we present novel support vector machine (SVM) models with high prediction accuracy that are designed to rapidly identify potential novel, structurally diverse LF inhibitor chemical matter from compound libraries. These SVM models were trained and validated using 508 compounds with published LF biological activity data and 847 inactive compounds deposited in the Pub Chem BioAssay database. One model, M1, demonstrated particularly favorable selectivity toward highly active compounds by correctly predicting 39 (95.12%) out of 41 nanomolar-level LF inhibitors, 46 (93.88%) out of 49 inactives, and 844 (99.65%) out of 847 Pub Chem inactives in external, unbiased test sets. These models are expected to facilitate the prediction of LF inhibitory activity for existing molecules, as well as identification of novel potential LF inhibitors from large datasets.

Use of artificial intelligence in infectious diseases

“…Naïve Bayes, random forest, and C4.5 J48 algorithms were used with an approach to improve models by avoiding over fitting and generating faster and cost-effective models. Overall, this and previous studies (Zhanga and Amin, 2016) suggest that machine learning provides good accuracy confirming other studies validating in silico methods to be used for screening of large datasets to identify potential antiinfectious candidates. In line with this, Shen et al have clearly shown how treatments can be assisted using mathematical models (Shen et al, 2018).…”

Opportunities and challenges of 5G network technology toward precision medicine

“…58 Predictive models can be created using several AI techniques, such as ML, statistical modeling, and artificial neural networks (ANNs). 59 ANN represents an algorithm encompassing multiple hidden layers of nodes that process the given inputs to produce an output prediction. 60 The other neural network including graph neural network (GNN) is a type of neural network designed to process and analyze structured data that can be represented as graphs.…”

“…They can be used to model the spread of infection, identify hotspots of transmission, and predict the potential number of infected individuals in a certain geographic area 58 . Predictive models can be created using several AI techniques, such as ML, statistical modeling, and artificial neural networks (ANNs) 59 …”

Recognition of nucleophilic substitution reaction mechanisms of carboxylic esters based on support vector machine

“…[39,40] Because it is based on the principle of structural risk minimization (SRM), SVM has shown to be superior to the traditional algorithms based on the empirical risk minimization (ERM) principle and has been widely applied to various regression and classification problems. [41][42][43][44] The theory of SVM has been introduced detailedly in many studies, [41][42][43][44][45][46] so only the main ideas were briefly summarized here. The aim of SVM for classification is to construct an "optimal hyperplane" as the decision surface so as to make the separation margin between 2 different classes maximum.…”