Navigating bioactivity space in anti-tubercular drug discovery through the deployment of advanced machine learning models and cheminformatics tools: a molecular modeling based retrospective study

Abstract

Mycobacterium tuberculosis is the bacterial strain that causes tuberculosis (TB). However, multidrug-resistant and extensively drug-resistant tuberculosis are significant obstacles to effective treatment. As a result, novel therapies against various strains of M. tuberculosis have been developed. Drug development is a lengthy procedure that includes identifying target protein and isolation, preclinical testing of the drug, and various phases of a clinical trial, etc., can take decades for a molecule to reach the market. Computational approaches such as QSAR, molecular docking techniques, and pharmacophore modeling have aided drug development. In this review article, we have discussed the various techniques in tuberculosis drug discovery by briefly introducing them and their importance. Also, the different databases, methods, approaches, and software used in conducting QSAR, pharmacophore modeling, and molecular docking have been discussed. The other targets targeted by these techniques in tuberculosis drug discovery have also been discussed, with important molecules discovered using these computational approaches. This review article also presents the list of drugs in a clinical trial for tuberculosis found drugs. Finally, we concluded with the challenges and future perspectives of these techniques in drug discovery.

WITHDRAWN: Neural Network and Random Forest Algorithms as Catalysts in QSAR/QSAAR Modeling: Targeting Carbonic Anhydrase for Antituberculosis Drug Design

“…These layers are responsible for assigning weights and biases, which are used to construct a predictive model based on the training data provided. The input layer receives molecular descriptor information as input for the model, which is further processed in the concealed layer and released as a result in the output layer [27][28][29] . In the ANN, the number of neurons in the input layer corresponds to the number of descriptors along with the pKi value of an MtbCA subtype, while one neuron in the output layer represents the predicted pKi of the other MtbCA subtype.…”

WITHDRAWN: Mechanistic modeling of Mycobacterium tuberculosis β-carbonic anhydrase inhibitors using integrated systems biology and the QSAR approach

“…Moreover, the bootstrap aggregation or bagging approach is used to train random forests. In bagging, training data subsets are randomly sampled (with replacement), a model is fitted to the updated training sets, and the predictions are aggregated [23,24,36,37]. Therefore, we developed universal random forest-based nonlinear prediction (ML-QSAR) models for Mtb β-CA inhibitors by implementing diverse molecular properties that can predict the activity of any new molecule against Mtb β-CA.…”

“…The objective of our QSAR model was to identify crucial molecular features of small-molecule modulators that strongly correlate with their inhibitory activity against Mtb β-CA, which might effectively halt the progression of TB and offer valuable insights for the design and discovery of anti-TB drugs. In this study, we propose a novel cheminformatics pipeline to generate multiple machine learning-assisted quantitative structural activity relationship (ML-QSAR) prediction models with diverse molecular features to explore the chemical space of Mtb β-CA inhibitors [22][23][24]. In this pursuit, we employed a random forest (RF) ML algorithm to generate each of our multidiverse molecular feature-based ML-QSAR models (PubChem fingerprints, substructure fingerprints, and 1D and 2D molecular descriptors).…”

WITHDRAWN: Mechanistic modelling of Mycobacterium Tuberculosis beta carbonic anhydrase 3 inhibitors

“…However, TB can also spread to other regions, such as the lymph nodes, urinary tract, and brain. According to the Global Tuberculosis Report 2023 in 2023, the total number of TB cases was approximately around 9.9 million, among which approximately 5.6 million (57%) were male whereas approximately 3.2 million (32%) were female and approximately 1.1 million (11%) were children [3,4] [5]. Another highly concerning fact about Mtb infection is that multi-drug resistant (MDR) TB and extended drug-resistant (XDR) TB are difficult-to-treat due to their ability to evade currently used drugs.…”