A ligand-based approach for the in silico discovery of multi-target inhibitors for proteins associated with HIV infection

A review of machine learning-based methods for predicting drug-target interactions

The prediction of drug-target interactions (DTI) is a crucial preliminary stage in drug discovery and development, given the substantial risk of failure and the prolonged validation period associated with in vitro and in vivo experiments. In the contemporary landscape, various machine learning-based methods have emerged as indispensable tools for DTI prediction. This paper begins by placing emphasis on the data representation employed by these methods, delineating five representations for drugs and four for proteins. The methods are then categorized into traditional machine learning-based approaches and deep learning-based ones, with a discussion of representative approaches in each category and the introduction of a novel taxonomy for deep neural network models in DTI prediction. Additionally, we present a synthesis of commonly used datasets and evaluation metrics to facilitate practical implementation. In conclusion, we address current challenges and outline potential future directions in this research field.

HBCVTr: an end-to-end transformer with a deep neural network hybrid model for anti-HBV and HCV activity predictor from SMILES

Hepatitis B and C viruses (HBV and HCV) are significant causes of chronic liver diseases, with approximately 350 million infections globally. To accelerate the finding of effective treatment options, we introduce HBCVTr, a novel ligand-based drug design (LBDD) method for predicting the inhibitory activity of small molecules against HBV and HCV. HBCVTr employs a hybrid model consisting of double encoders of transformers and a deep neural network to learn the relationship between small molecules' simplified molecular-input line-entry system (SMILES) and their antiviral activity against HBV or HCV. The prediction accuracy of HBCVTr has surpassed baseline machine learning models and existing methods, with R-squared values of 0.641 and 0.721 for the HBV and HCV test sets, respectively. The trained models were successfully applied to virtual screening against 10 million compounds within 240 h, leading to the discovery of the top novel inhibitor candidates, including IJN04 for HBV and IJN12 and IJN19 for HCV. Molecular docking and dynamics simulations identified IJN04, IJN12, and IJN19 target proteins as the HBV core antigen, HCV NS5B RNA-dependent RNA polymerase, and HCV NS3/4A serine protease, respectively. Overall, HBCVTr offers a new and rapid drug discovery and development screening method targeting HBV and HCV.

The design of compounds with desirable properties - The anti-HIV case study

Efficacy and safety are among the most desirable characteristics of an ideal drug. The tremendous increase in computing power and the entry of artificial intelligence into the field of computational drug design are accelerating the process of identifying, developing, and optimizing potential drugs. Here, we present novel approach to design new molecules with desired properties. We combined various neural networks and linear regression algorithms to build models for cytotoxicity and anti-HIV activity based on Continual Molecular Interior analysis (CoMIn) and Cinderella's Shoe (CiS) derived molecular descriptors. After validating the reliability of the models, a genetic algorithm was coupled with the Des-Pot Grid algorithm to generate new molecules from a predefined pool of molecular fragments and predict their bioactivity and cytotoxicity. This combination led to the proposal of 16 hit molecules with high anti-HIV activity and low cytotoxicity. The anti-SARS-CoV-2 activity of the hits was predicted.

PTML modeling for peptide discovery: in silico design of non-hemolytic peptides with antihypertensive activity

Hypertension is a medical condition that affects millions of people worldwide. Despite the high efficacy of the current antihypertensive drugs, they are associated with serious side effects. Peptides constitute attractive options for chemical therapy against hypertension, and computational models can accelerate the design of antihypertensive peptides. Yet, to the best of our knowledge, all the in silico models predict only the antihypertensive activity of peptides while neglecting their inherent toxic potential to red blood cells. In this work, we report the first sequence-based model that combines perturbation theory and machine learning through multilayer perceptron networks (SB-PTML-MLP) to enable the simultaneous screening of antihypertensive activity and hemotoxicity of peptides. We have interpreted the molecular descriptors present in the model from a physicochemical and structural point of view. By strictly following such interpretations as guidelines, we performed two tasks. First, we selected amino acids with favorable contributions to both the increase of the antihypertensive activity and the diminution of hemotoxicity. Then, we assembled those suitable amino acids, virtually designing peptides that were predicted by the SB-PTML-MLP model as antihypertensive agents exhibiting low hemotoxicity. The potentiality of the SB-PTML-MLP model as a tool for designing potent and safe antihypertensive peptides was confirmed by predictions performed by online computational tools reported in the scientific literature. The methodology presented here can be extended to other pharmacological applications of peptides.

QSAR Modeling for Multi-Target Drug Discovery: Designing Simultaneous Inhibitors of Proteins in Diverse Pathogenic Parasites

Parasitic diseases remain as unresolved health issues worldwide. While for some parasites the treatments involve drug combinations with serious side effects, for others, chemical therapies are inefficient due to the emergence of drug resistance. This urges the search for novel antiparasitic agents able to act through multiple mechanisms of action. Here, we report the first multi-target model based on quantitative structure-activity relationships and a multilayer perceptron neural network (mt-QSAR-MLP) to virtually design and predict versatile inhibitors of proteins involved in the survival and/or infectivity of different pathogenic parasites. The mt-QSAR-MLP model exhibited high accuracy (>80%) in both training and test sets for the classification/prediction of protein inhibitors. Several fragments were directly extracted from the physicochemical and structural interpretations of the molecular descriptors in the mt-QSAR-MLP model. Such interpretations enabled the generation of four molecules that were predicted as multi-target inhibitors against at least three of the five parasitic proteins reported here with two of the molecules being predicted to inhibit all the proteins. Docking calculations converged with the mt-QSAR-MLP model regarding the multi-target profile of the designed molecules. The designed molecules exhibited drug-like properties, complying with Lipinski’s rule of five, as well as Ghose’s filter and Veber’s guidelines.

The system of self-consistent semi-correlations as one of the tools of cheminformatics for designing antiviral drugs

The development of antiviral agents against SARS-CoV-2 is necessary.

Cell-based multi-target QSAR model for design of virtual versatile inhibitors of liver cancer cell lines

Liver cancers are one of the leading fatal diseases among malignant neoplasms. Current chemotherapeutic treatments used to fight these illnesses have become less efficient in terms of both efficacy and safety. Therefore, there is a great need of search for new anti-liver cancer agents and this can be accelerated by using computer-aided drug discovery approaches. In this work, we report the development of the first cell-based multi-target model based on quantitative structure-activity relationships (CBMT-QSAR) for the design and prediction of chemicals as anticancer agents against 17 liver cancer cell lines. While having a good quality and predictive power (accuracy higher than 80%) in the training and test sets, respectively, the CBMT-QSAR model was employed as a tool to directly extract suitable fragments from the physicochemical and structural interpretations of the molecular descriptors. Some of these desirable fragments were assembled, leading to the virtual design of eight molecules with drug-like properties, with six of them being predicted as versatile anticancer agents against the 17 liver cancer cell lines reported here.

Molecular topology and QSAR multi-target analysis to boost the in silico research for fungicides in agricultural chemistry

The aim of the present study is to show how molecular topology can be a powerful in silico tool for the prediction of the fungicidal activity of several diphenylamine derivatives against three fungal species (cucumber downy mildew, rice blast and cucumber gray mold). A multi-target QSAR model was developed, and two strategies were followed. First is the construction of a virtual library of molecules using DesMol2 program and a subsequent selection of potential active ones. Second is the selection of molecules from the literature on the basis of molecular scaffolds. More than 700 diphenylamine derivatives designed and other 60 fluazinam's derivatives with structural similarity higher than 80% were studied. Almost twenty percent of the molecules analyzed show potential activity against the three fungal species.

First Multitarget Chemo-Bioinformatic Model To Enable the Discovery of Antibacterial Peptides against Multiple Gram-Positive Pathogens

Antimicrobial peptides (AMPs) have emerged as promising therapeutic alternatives to fight against the diverse infections caused by different pathogenic microorganisms. In this context, theoretical approaches in bioinformatics have paved the way toward the creation of several in silico models capable of predicting antimicrobial activities of peptides. All current models have several significant handicaps, which prevent the efficient search for highly active AMPs. Here, we introduce the first multitarget (mt) chemo-bioinformatic model devoted to performing alignment-free prediction of antibacterial activity of peptides against multiple Gram-positive bacterial strains. The model was constructed from a data set containing 2488 cases of AMPs sequences assayed against at least 1 out of 50 Gram-positive bacterial strains. This mt-chemo-bioinformatic model displayed percentages of correct classification higher than 90.00% in both training and prediction (test) sets. For the first time, two computational approaches derived from basic concepts in genetics and molecular biology were applied, allowing the calculations of the relative contributions of any amino acid (in a defined position) to the antibacterial activity of an AMP and depending on the bacterial strain used in the biological assay. The present mt-chemo-bioinformatic model constitutes a powerful tool to enable the discovery of potent and versatile AMPs.

Mapping chemical structure-activity information of HAART-drug cocktails over complex networks of AIDS epidemiology and socioeconomic data of U.S. counties

Using computational algorithms to design tailored drug cocktails for highly active antiretroviral therapy (HAART) on specific populations is a goal of major importance for both pharmaceutical industry and public health policy institutions. New combinations of compounds need to be predicted in order to design HAART cocktails. On the one hand, there are the biomolecular factors related to the drugs in the cocktail (experimental measure, chemical structure, drug target, assay organisms, etc.); on the other hand, there are the socioeconomic factors of the specific population (income inequalities, employment levels, fiscal pressure, education, migration, population structure, etc.) to study the relationship between the socioeconomic status and the disease. In this context, machine learning algorithms, able to seek models for problems with multi-source data, have to be used. In this work, the first artificial neural network (ANN) model is proposed for the prediction of HAART cocktails, to halt AIDS on epidemic networks of U.S. counties using information indices that codify both biomolecular and several socioeconomic factors. The data was obtained from at least three major sources. The first dataset included assays of anti-HIV chemical compounds released to ChEMBL. The second dataset is the AIDSVu database of Emory University. AIDSVu compiled AIDS prevalence for >2300 U.S. counties. The third data set included socioeconomic data from the U.S. Census Bureau. Three scales or levels were employed to group the counties according to the location or population structure codes: state, rural urban continuum code (RUCC) and urban influence code (UIC). An analysis of >130,000 pairs (network links) was performed, corresponding to AIDS prevalence in 2310 counties in U.S. vs. drug cocktails made up of combinations of ChEMBL results for 21,582 unique drugs, 9 viral or human protein targets, 4856 protocols, and 10 possible experimental measures. The best model found with the original data was a linear neural network (LNN) with AUROC>0.80 and accuracy, specificity, and sensitivity≈77% in training and external validation series. The change of the spatial and population structure scale (State, UIC, or RUCC codes) does not affect the quality of the model. Unbalance was detected in all the models found comparing positive/negative cases and linear/non-linear model accuracy ratios. Using synthetic minority over-sampling technique (SMOTE), data pre-processing and machine-learning algorithms implemented into the WEKA software, more balanced models were found. In particular, a multilayer perceptron (MLP) with AUROC=97.4% and precision, recall, and F-measure >90% was found.

Simultaneous virtual prediction of anti-Escherichia coli activities and ADMET profiles: A chemoinformatic complementary approach for high-throughput screening

Escherichia coli remains one of the principal pathogens that cause nosocomial infections, medical conditions that are increasingly common in healthcare facilities. E. coli is intrinsically resistant to many antibiotics, and multidrug-resistant strains have emerged recently. Chemoinformatics has been a great ally of experimental methodologies such as high-throughput screening, playing an important role in the discovery of effective antibacterial agents. However, there is no approach that can design safer anti-E. coli agents, because of the multifactorial nature and complexity of bacterial diseases and the lack of desirable ADMET (absorption, distribution, metabolism, elimination, and toxicity) profiles as a major cause of disapproval of drugs. In this work, we introduce the first multitasking model based on quantitative-structure biological effect relationships (mtk-QSBER) for simultaneous virtual prediction of anti-E. coli activities and ADMET properties of drugs and/or chemicals under many experimental conditions. The mtk-QSBER model was developed from a large and heterogeneous data set of more than 37800 cases, exhibiting overall accuracies of >95% in both training and prediction (validation) sets. The utility of our mtk-QSBER model was demonstrated by performing virtual prediction of properties for the investigational drug avarofloxacin (AVX) under 260 different experimental conditions. Results converged with the experimental evidence, confirming the remarkable anti-E. coli activities and safety of AVX. Predictions also showed that our mtk-QSBER model can be a promising computational tool for virtual screening of desirable anti-E. coli agents, and this chemoinformatic approach could be extended to the search for safer drugs with defined pharmacological activities.

S. Cordeiro MN, Yañez M, González-Díaz H, García-Mera X. Model for high-throughput screening of multitarget drugs in chemical neurosciences: synthesis, assay, and theoretic study of rasagiline carbamates

The disappointing results obtained in recent clinical trials renew the interest in experimental/computational techniques for the discovery of neuroprotective drugs. In this context, multitarget or multiplexing QSAR models (mt-QSAR/mx-QSAR) may help to predict neurotoxicity/neuroprotective effects of drugs in multiple assays, on drug targets, and in model organisms. In this work, we study a data set downloaded from CHEMBL; each data point (>8000) contains the values of one out of 37 possible measures of activity, 493 assays, 169 molecular or cellular targets, and 11 different organisms (including human) for a given compound. In this work, we introduce the first mx-QSAR model for neurotoxicity/neuroprotective effects of drugs based on the MARCH-INSIDE (MI) method. First, we used MI to calculate the stochastic spectral moments (structural descriptors) of all compounds. Next, we found a model that classified correctly 2955 out of 3548 total cases in the training and validation series with Accuracy, Sensitivity, and Specificity values>80%. The model also showed excellent results in Computational-Chemistry simulations of High-Throughput Screening (CCHTS) experiments, with accuracy=90.6% for 4671 positive cases. Next, we reported the synthesis, characterization, and experimental assays of new rasagiline derivatives. We carried out three different experimental tests: assay (1) in the absence of neurotoxic agents, assay (2) in the presence of glutamate, and assay (3) in the presence of H2O2. Compounds 11 with 27.4%, 8 with 11.6%, and 9 with 15.4% showed the highest neuroprotective effects in assays (1), (2), and (3), respectively. After that, we used the mx-QSAR model to carry out a CCHTS of the new compounds in >400 unique pharmacological tests not carried out experimentally. Consequently, this model may become a promising auxiliary tool for the discovery of new drugs for the treatment of neurodegenerative diseases.

Fragment-based optimization of small molecule CXCL12 inhibitors for antagonizing the CXCL12/CXCR4 interaction

The chemokine CXCL12 and its G protein-coupled receptor (GPCR) CXCR4 are high-priority clinical targets because of their involvement in metastatic cancers (also implicated in autoimmune disease and cardiovascular disease). Because chemokines interact with two distinct sites to bind and activate their receptors, both the GPCRs and chemokines are potential targets for small molecule inhibition. A number of chemokines have been validated as targets for drug development, but virtually all drug discovery efforts focus on the GPCRs. However, all CXCR4 receptor antagonists with the exception of MSX-122 have failed in clinical trials due to unmanageable toxicities, emphasizing the need for alternative strategies to interfere with CXCL12/CXCR4-guided metastatic homing. Although targeting the relatively featureless surface of CXCL12 was presumed to be challenging, focusing efforts at the sulfotyrosine (sY) binding pockets proved successful for procuring initial hits. Using a hybrid structure-based in silico/NMR screening strategy, we recently identified a ligand that occludes the receptor recognition site. From this initial hit, we designed a small fragment library containing only nine tetrazole derivatives using a fragment-based and bioisostere approach to target the sY binding sites of CXCL12. Compound binding modes and affinities were studied by 2D NMR spectroscopy, X-ray crystallography, molecular docking and cell-based functional assays. Our results demonstrate that the sY binding sites are conducive to the development of high affinity inhibitors with better ligand efficiency (LE) than typical protein-protein interaction inhibitors (LE ≤ 0.24). Our novel tetrazole-based fragment 18 was identified to bind the sY21 site with a K(d) of 24 μM (LE = 0.30). Optimization of 18 yielded compound 25 which specifically inhibits CXCL12-induced migration with an improvement in potency over the initial hit 9. The fragment from this library that exhibited the highest affinity and ligand efficiency (11: K(d) = 13 μM, LE = 0.33) may serve as a starting point for development of inhibitors targeting the sY12 site.