Rational design of isonicotinic acid hydrazide derivatives with antitubercular activity: Machine learning, molecular docking, synthesis and biological testing

Abstract

The problem of designing new antitubercular drugs against multiple drug-resistant tuberculosis (MDR-TB) was addressed using advanced machine learning methods. As there are only few published measurements against MDR-TB, we collected a large literature data set and developed models against the non-resistant H37Rv strain. The predictive accuracy of these models had a coefficient of determination q = .7-.8 (regression models) and balanced accuracies of about 80% (classification models) with cross-validation and independent test sets. The models were applied to screen a virtual chemical library, which was designed to have MDR-TB activity. The seven most promising compounds were identified, synthesized and tested. All of them showed activity against the H37Rv strain, and three molecules demonstrated activity against the MDR-TB strain. The docking analysis indicated that the discovered molecules could bind enoyl reductase, InhA, which is required in mycobacterial cell wall development. The models are freely available online (http://ochem.eu/article/103868) and can be used to predict potential anti-TB activity of new chemicals.

Anticancer evaluation of di- and trifunctional substituted 1,3-thiazoles

“…1,3-Thiazoles 8, 9 containing the 4-chlorophenylsulfonyl group at position C 5 and a substituted amino group at position C 4 are somewhat more active than compound 4 with the morpholino group at position C 5 . Thus, 1,3-thiazole Advanced in vitro study of compounds 5, 19, 21 at five concentrations of the 10-fold dilution (10 -4 -10 -8 М) was also performed towards 60 human cancer cell lines, the set of which was identical to that for the pre-screening stage (Table 2).…”

“…It has been demonstrated that 1,3-thiazoles are widely used for creation of dyes, insecticides, herbicides, and pharmaceuticals. Di-and trisubstituted 1,3-thiazole are effective anti-inflammatory, anthelmintic, antiviral, and bactericidal agents [1][2][3][4][5][6]. The nature of the chemical groups in the heterocycle can significantly affect their pharmacological properties.…”

“…sulfonyl]-2-phenyl-1,3thiazoles 1-4, 6-9[11], 5-Chloro-2-(furan-2-yl)-4-((4methylphenyl)sulfonyl)-1,3-thiazole (10)[12], 2,4-Disubstituted 5-(4-chlorophenyl)sulfonyl-1,3-thiazoles 11-16[13], 2-(3,5-Dimethyl-1H-pyrazol-1-yl)-4-((4-methylphenyl)sulfonyl)-1,3-thiazoles 17, 18[14] were synthesized following the procedures described in the corresponding sources cited.1-(4-((4-Methylphenyl)sulfonyl)-2-phenyl-1,3-thiazol-5yl)piperazine(5) was synthesized similarly to compound 4.Yield 67%, mp 112-113 °C (EtOH).1 H NMR (500 MHz, CDCl3) δ 2.45 (s, 3H, CH3), 3.20-3.35 (m, 4H, 2CH2), 3.82-3.94 (m, 4H, 2CH2), 7.33-7.45 (m, 5H, Ar), 7.78 (d, J 7.5 Hz, 2H, Ar), 8.05 (d, J 7.5 Hz, 2H, Ar). Anal.…”

Use of Artificial Intelligence and Machine Learning for Discovery of Drugs for Neglected Tropical Diseases

“…Traditional ML methods, AsNN, RF, kNN, and XGBoost, were also used to generate models predicting antitubercular activities using a training set of 6,337 compounds (Kovalishyn et al, 2018). These molecules were derivatives of azoles, isoniazids, indoles, and others that exhibited MIC values from 1.5 nM to 100 μM.…”

The role of machine learning method in the synthesis and biological ınvestigation of heterocyclic compounds

“…In 2018, novel isonicotinic acid hydrazide derivatives as antitubercular agents determined by ML methods were synthesized by Kovalishyn and coauthors [25]. In this research, 6337 compounds from the various publications which have MIC values ranged from 0.0015 μM to 99.9 μM were selected as initial data set 1.…”