Classification and Design of HIV-1 Integrase Inhibitors Based on Machine Learning

Abstract

A key enzyme in human immunodeficiency virus type 1 (HIV-1) life cycle, integrase (IN) aids the integration of viral DNA into the host DNA, which has become an ideal target for the development of anti-HIV drugs. A total of 1785 potential HIV-1 IN inhibitors were collected from the databases of ChEMBL, Binding Database, DrugBank, and PubMed, as well as from 40 references. The database was divided into the training set and test set by random sampling. By exploring the correlation between molecular descriptors and inhibitory activity, it is found that the classification and specific activity data of inhibitors can be more accurately predicted by the combination of molecular descriptors and molecular fingerprints. The calculation of molecular fingerprint descriptor provides the additional substructure information to improve the prediction ability. Based on the training set, two machine learning methods, the recursive partition (RP) and naive Bayes (NB) models, were used to build the classifiers of HIV-1 IN inhibitors. Through the test set verification, the RP technique accurately predicted 82.5% inhibitors and 86.3% noninhibitors. The NB model predicted 88.3% inhibitors and 87.2% noninhibitors with correlation coefficient of 85.2%. The results show that the prediction performance of NB model is slightly better than that of RP, and the key molecular segments are also obtained. Additionally, CoMFA and CoMSIA models with good activity prediction ability both were constructed by exploring the structure-activity relationship, which is helpful for the design and optimization of HIV-1 IN inhibitors.

A computational overview of integrase strand transfer inhibitors (INSTIs) against emerging and evolving drug-resistant HIV-1 integrase mutants

“…These strict requirements are addressed by employing several computational techniques, like molecular docking (Tewtrakul et al 2015 ; Ercan et al 2019 ; Arslan 2019 ; Dogan and Durdagi 2021 ; Esmaeili et al 2021 ), pharmacophore modelling (Martin 2014 ; Bhatt et al 2014 ; Xue et al 2014 ; Islam and Pillay 2016 ), molecular dynamics (MD) simulation (Chen et al 2014 ; Islam and Pillay 2016 ; Chitongo et al 2019 ; Samorlu et al 2019 ), quantitative structure–activity relationships (QSAR) (Gupta et al 2013 ; Reddy et al 2013 ; Zhou et al 2021 ; Xuan et al 2021 ), and many more. The human cells lack structural or functional integrase homologues, making IN a desirable drug target for HAART (Siwe-Noundou et al 2019 ); further IN depicts greater tolerability, high efficacy, and fewer drug–drug interactions as compared to other HAART classes (Brooks et al 2019 ).…”

“…It is present at the 3’-end of the pol gene and is produced during the cleavage of gag - pol polyprotein during early virus maturation (Mbhele et al 2021 ). This enzyme catalyses the insertion of virally reverse-transcribed cDNA into the patient’s genome via dual stages (S N 2 nucleophilic reaction) (Siwe-Noundou et al 2019 ; Zhou et al 2021 ). The first step is ‘3’-processing’ (3’P), wherein a dinucleotide (GT) pair is cleaved from both the cDNA’s 3’-ends, forming the pre-integration complex (PIC).…”

“…This domain also encompasses a flexible 10 residues loop (140–149) that is adjacent to the catalytic site, involved in vcDNA substrate recognition. Residues 213–288: C-terminal domain (CTD) This region serves as a non-specific binding site for the vcDNA and further contributes to stabilizing the IN–vcDNA complex (Arora et al 2013 ; Ross 2015 ; Thierry et al 2017 ; Nusrath Unissa et al 2017 ; Zhou et al 2021 ). …”

“…This region serves as a non-specific binding site for the vcDNA and further contributes to stabilizing the IN–vcDNA complex (Arora et al 2013 ; Ross 2015 ; Thierry et al 2017 ; Nusrath Unissa et al 2017 ; Zhou et al 2021 ).…”

Can plant-derived anti-HIV compounds be used in COVID-19 cases?

“…Integrase (IN), a critical enzyme in the human immunodeficiency virus type 1 (HIV-1) life cycle, helps the integration of viral DNA to host DNA, making it a potential target for anti-HIV medication development. Zhou et al (2021) used machine learning to classify and design HIV-1 Integrase inhibitors [46] . HIV particles have a diameter of 100 nm and are surrounded by a lipoprotein-rich membrane.…”