Current advances in ligand‐based target prediction

Exploring natural products potential: A similarity-based target prediction tool for natural products

Natural products are invaluable resources in drug discovery due to their substantial structural diversity. However, predicting their interactions with druggable protein targets remains a challenge, primarily due to the limited availability of bioactivity data. This study introduces CTAPred (Compound-Target Activity Prediction), an open-source command-line tool designed to predict potential protein targets for natural products. CTAPred employs a two-stage approach, combining fingerprinting and similarity-based search techniques to identify likely drug targets for these bioactive compounds. Despite its simplicity, the tool's performance is comparable to that of more complex methods, demonstrating proficiency in target retrieval for natural product compounds. Furthermore, this study explores the optimal number of reference compounds most similar to the query compound, aiming to refine target prediction accuracy. The findings demonstrated the superior performance of considering only the most similar reference compounds for target prediction. CTAPred is freely available at https://github.com/Alhasbary/CTAPred, offering a valuable resource for deciphering natural product-target associations and advancing drug discovery.

Advanced AI and ML frameworks for transforming drug discovery and optimization: With innovative insights in polypharmacology, drug repurposing, combination therapy and nanomedicine

Artificial Intelligence (AI) and Machine Learning (ML) are transforming drug discovery by overcoming traditional challenges like high costs, time-consuming, and frequent failures. AI-driven approaches streamline key phases, including target identification, lead optimization, de novo drug design, and drug repurposing. Frameworks such as deep neural networks (DNNs), convolutional neural networks (CNNs), and deep reinforcement learning (DRL) models have shown promise in identifying drug targets, optimizing delivery systems, and accelerating drug repurposing. Generative adversarial networks (GANs) and variational autoencoders (VAEs) aid de novo drug design by creating novel drug-like compounds with desired properties. Case studies, such as DDR1 kinase inhibitors designed using generative models and CDK20 inhibitors developed via structure-based methods, highlight AI's ability to produce highly specific therapeutics. Models like SNF-CVAE and DeepDR further advance drug repurposing by uncovering new therapeutic applications for existing drugs. Advanced ML algorithms enhance precision in predicting drug efficacy, toxicity, and ADME-Tox properties, reducing development costs and improving drug-target interactions. AI also supports polypharmacology by optimizing multi-target drug interactions and enhances combination therapy through predictions of drug synergies and antagonisms. In nanomedicine, AI models like CURATE.AI and the Hartung algorithm optimize personalized treatments by predicting toxicological risks and real-time dosing adjustments with high accuracy. Despite its potential, challenges like data quality, model interpretability, and ethical concerns must be addressed. High-quality datasets, transparent models, and unbiased algorithms are essential for reliable AI applications. As AI continues to evolve, it is poised to revolutionize drug discovery and personalized medicine, advancing therapeutic development and patient care.

Testing the predictive power of reverse screening to infer drug targets, with the help of machine learning

Estimating protein targets of compounds based on the similarity principle-similar molecules are likely to show comparable bioactivity-is a long-standing strategy in drug research. Having previously quantified this principle, we present here a large-scale evaluation of its predictive power for inferring macromolecular targets by reverse screening an unprecedented vast external test set of more than 300,000 active small molecules against another bioactivity set of more than 500,000 compounds. We show that machine-learning can predict the correct targets, with the highest probability among 2069 proteins, for more than 51% of the external molecules. The strong enrichment thus obtained demonstrates its usefulness in supporting phenotypic screens, polypharmacology, or repurposing. Moreover, we quantified the impact of the bioactivity knowledge available for proteins in terms of number and diversity of actives. Finally, we advise that developers of such approaches follow an application-oriented benchmarking strategy and use large, high-quality, non-overlapping datasets as provided here.

Water Network-Augmented Two-State Model for Protein-Ligand Binding Affinity Prediction

Water network rearrangement from the ligand-unbound state to the ligand-bound state is known to have significant effects on the protein-ligand binding interactions, but most of the current machine learning-based scoring functions overlook these effects. In this study, we endeavor to construct a comprehensive and realistic deep learning model by incorporating water network information into both ligand-unbound and -bound states. In particular, extended connectivity interaction features were integrated into graph representation, and graph transformer operator was employed to extract features of the ligand-unbound and -bound states. Through these efforts, we developed a water network-augmented two-state model called ECIFGraph::HM-Holo-Apo. Our new model exhibits satisfactory performance in terms of scoring, ranking, docking, screening, and reverse screening power tests on the CASF-2016 benchmark. In addition, it can achieve superior performance in large-scale docking-based virtual screening tests on the DEKOIS2.0 data set. Our study highlights that the use of a water network-augmented two-state model can be an effective strategy to bolster the robustness and applicability of machine learning-based scoring functions, particularly for targets with hydrophilic or solvent-exposed binding pockets.

Prediction of compound-target interaction using several artificial intelligence algorithms and comparison with a consensus-based strategy

For understanding a chemical compound's mechanism of action and its side effects, as well as for drug discovery, it is crucial to predict its possible protein targets. This study examines 15 developed target-centric models (TCM) employing different molecular descriptions and machine learning algorithms. They were contrasted with 17 third-party models implemented as web tools (WTCM). In both sets of models, consensus strategies were implemented as potential improvement over individual predictions. The findings indicate that TCM reach f1-score values greater than 0.8. Comparing both approaches, the best TCM achieves values of 0.75, 0.61, 0.25 and 0.38 for true positive/negative rates (TPR, TNR) and false negative/positive rates (FNR, FPR); outperforming the best WTCM. Moreover, the consensus strategy proves to have the most relevant results in the top 20 % of target profiles. TCM consensus reach TPR and FNR values of 0.98 and 0; while on WTCM reach values of 0.75 and 0.24. The implemented computational tool with the TCM and their consensus strategy at: https://bioquimio.udla.edu.ec/tidentification01/ . Scientific Contribution: We compare and discuss the performances of 17 public compound-target interaction prediction models and 15 new constructions. We also explore a compound-target interaction prioritization strategy using a consensus approach, and we analyzed the challenging involved in interactions modeling.

Diarylpentanoids, the privileged scaffolds in antimalarial and anti-infectives drug discovery: A review

Asia is a hotspot for infectious diseases, including malaria, dengue fever, tuberculosis, and the pandemic COVID-19. Emerging infectious diseases have taken a heavy toll on public health and the economy and have been recognized as a major cause of morbidity and mortality, particularly in Southeast Asia. Infectious disease control is a major challenge, but many surveillance systems and control strategies have been developed and implemented. These include vector control, combination therapies, vaccine development, and the development of new anti-infectives. Numerous newly discovered agents with pharmacological anti-infective potential are being actively and extensively studied for their bioactivity, toxicity, selectivity, and mode of action, but many molecules lose their efficacy over time due to resistance developments. These facts justify the great importance of the search for new, effective, and safe anti-infectives. Diarylpentanoids, a curcumin derivative, have been developed as an alternative with better bioavailability and metabolism as a therapeutic agent. In this review, the mechanisms of action and potential targets of antimalarial drugs as well as the classes of antimalarial drugs are presented. The bioactivity of diarylpentanoids as a potential scaffold for a new class of anti-infectives and their structure-activity relationships are also discussed in detail.

PepScaf: Harnessing Machine Learning with In Vitro Selection toward De Novo Macrocyclic Peptides against IL-17C/IL-17RE Interaction

The combination of library-based screening and artificial intelligence (AI) has been accelerating the discovery and optimization of hit ligands. However, the potential of AI to assist in de novo macrocyclic peptide ligand discovery has yet to be fully explored. In this study, an integrated AI framework called PepScaf was developed to extract the critical scaffold relative to bioactivity based on a vast dataset from an initial in vitro selection campaign against a model protein target, interleukin-17C (IL-17C). Taking the generated scaffold, a focused macrocyclic peptide library was rationally constructed to target IL-17C, yielding over 20 potent peptides that effectively inhibited IL-17C/IL-17RE interaction. Notably, the top two peptides displayed exceptional potency with IC50 values of 1.4 nM. This approach presents a viable methodology for more efficient macrocyclic peptide discovery, offering potential time and cost savings. Additionally, this is also the first report regarding the discovery of macrocyclic peptides against IL-17C/IL-17RE interaction.

TB-IECS: an accurate machine learning-based scoring function for virtual screening

Machine learning-based scoring functions (MLSFs) have shown potential for improving virtual screening capabilities over classical scoring functions (SFs). Due to the high computational cost in the process of feature generation, the numbers of descriptors used in MLSFs and the characterization of protein-ligand interactions are always limited, which may affect the overall accuracy and efficiency. Here, we propose a new SF called TB-IECS (theory-based interaction energy component score), which combines energy terms from Smina and NNScore version 2, and utilizes the eXtreme Gradient Boosting (XGBoost) algorithm for model training. In this study, the energy terms decomposed from 15 traditional SFs were firstly categorized based on their formulas and physicochemical principles, and 324 feature combinations were generated accordingly. Five best feature combinations were selected for further evaluation of the model performance in regard to the selection of feature vectors with various length, interaction types and ML algorithms. The virtual screening power of TB-IECS was assessed on the datasets of DUD-E and LIT-PCBA, as well as seven target-specific datasets from the ChemDiv database. The results showed that TB-IECS outperformed classical SFs including Glide SP and Dock, and effectively balanced the efficiency and accuracy for practical virtual screening.

Pinostrobin, a fingerroot compound, regulates miR-181b-5p and induces acute leukemic cell apoptosis

Pinostrobin (PN) is the most abundant flavonoid found in fingerroot. Although the anti-leukemic properties of PN have been reported, its mechanisms are still unclear. MicroRNAs (miRNAs) are small RNA molecules that function in posttranscriptional silencing and are increasingly being used in cancer therapy. The aims of this study were to investigate the effects of PN on proliferation inhibition and induction of apoptosis, as well as the involvement of miRNAs in PN-mediated apoptosis in acute leukemia. The results showed that PN reduced cell viability and induced apoptosis in acute leukemia cells via both intrinsic and extrinsic pathways. A bioinformatics approach and Protein-Protein Interaction (PPI) network analysis revealed that ataxia-telangiectasia mutated kinase (ATM), one of the p53 activators that responds to DNA damage-induced apoptosis, is a crucial target of PN. Four prediction tools were used to predict ATM-regulated miRNAs; miR-181b-5p was the most likely candidate. The reduction in miR-181b-5 after PN treatment was found to trigger ATM, resulting in cellular apoptosis. Therefore, PN could be developed as a drug for acute leukemia; in addition, miR-181b-5p and ATM may be promising therapeutic targets.

Target identification by structure-based computational approaches: Recent advances and perspectives

The use of computational techniques in the early stages of drug discovery has recently experienced a boost, especially in the target identification step. Finding the biological partner(s) for new or existing synthetic and/or natural compounds by "wet" approaches may be challenging; therefore, preliminary in silico screening is even more recommended. After a brief overview of some of the most known target identification techniques, recent advances in structure-based computational approaches for target identification are reported in this digest, focusing on Inverse Virtual Screening and its recent applications. Moreover, future perspectives concerning the use of such methodologies, coupled or not with other approaches, are analyzed.

Systematic Improvement of the Performance of Machine Learning Scoring Functions by Incorporating Features of Protein-Bound Water Molecules

Water molecules at the ligand-protein interfaces play crucial roles in the binding of the ligands, but the behavior of protein-bound water is largely ignored in many currently used machine learning (ML)-based scoring functions (SFs). In an attempt to improve the prediction performance of existing ML-based SFs, we estimated the water distribution with a HydraMap (HM) method and then incorporated the features extracted from protein-bound waters obtained in this way into three ML-based SFs: RF-Score, ECIF, and PLEC. It was found that a combination of HM-based features can consistently improve the performance of all three SFs, including their scoring, ranking, and docking power. HydraMap-based features show consistently good performance with both crystal structures and docked structures, demonstrating their robustness for SFs. Overall, HM-based features, which are a statistical representation of hydration sites at protein-ligand interfaces, are expected to improve the prediction performance for diverse SFs.

Thiophenes-Naturally Occurring Plant Metabolites: Biological Activities and In Silico Evaluation of Their Potential as Cathepsin D Inhibitors

Naturally, thiophenes represent a small family of natural metabolites featured by one to five thiophene rings. Numerous plant species belonging to the family Asteraceae commonly produce thiophenes. These metabolites possessed remarkable bioactivities, including antimicrobial, antiviral, anti-inflammatory, larvicidal, antioxidant, insecticidal, cytotoxic, and nematicidal properties. The current review provides an update over the past seven years for the reported natural thiophene derivatives, including their sources, biosynthesis, spectral data, and bioactivities since the last review published in 2015. Additionally, with the help of the SuperPred webserver, an AI (artificial intelligence) tool, the potential drug target for the compounds was predicted. In silico studies were conducted for Cathepsin D with thiophene derivatives, including ADMET (drug absorption/distribution/metabolism/excretion/and toxicity) properties prediction, molecular docking for the binding interaction, and molecular dynamics to evaluate the ligand-target interaction stability under simulated physiological conditions.

Deep learning in target prediction and drug repositioning: Recent advances and challenges

Drug repositioning is an attractive strategy for discovering new therapeutic uses for approved or investigational drugs, with potentially shorter development timelines and lower development costs. Various computational methods have been used in drug repositioning, promoting the efficiency and success rates of this approach. Recently, deep learning (DL) has attracted wide attention for its potential in target prediction and drug repositioning. Here, we provide an overview of the basic principles of commonly used DL architectures and their applications in target prediction and drug repositioning, and discuss possible ways of dealing with current challenges to help achieve its expected potential for drug repositioning.

Quantitative Polypharmacology Profiling Based on a Multifingerprint Similarity Predictive Approach

We present a new quantitative ligand-based bioactivity prediction approach employing a multifingerprint similarity search algorithm, enabling the polypharmacological profiling of small molecules. Quantitative bioactivity predictions are made on the basis of the statistical distributions of multiple Tanimoto similarity θ values, calculated through 13 different molecular fingerprints, and of the variation of the measured biological activity, reported as ΔpIC₅₀, for all of the ligands sharing a given protein drug target. The application data set comprises as much as 4241 protein drug targets as well as 418 485 ligands selected from ChEMBL (release 25) by employing a set of well-defined filtering rules. Several large internal and external validation studies were carried out to demonstrate the robustness and the predictive potential of the herein proposed method. Additional comparative studies, carried out on two freely available and well-known ligand-target prediction platforms, demonstrated the reliability of our proposed approach for accurate ligand-target matching. Moreover, two applicative cases were also discussed to practically describe how to use our predictive algorithm, which is freely available as a user-friendly web platform. The user can screen single or multiple queries at a time and retrieve the output as a terse html table or as a json file including all of the information concerning the explored similarities to obtain a deeper understanding of the results. High-throughput virtual reverse screening campaigns, allowing for a given query compound the quick detection of the potential drug target from a large collection of them, can be carried out in batch on demand.

Currently Available Strategies for Target Identification of Bioactive Natural Products

In recent years, biologically active natural products have gradually become important agents in the field of drug research and development because of their wide availability and variety. However, the target sites of many natural products are yet to be identified, which is a setback in the pharmaceutical industry and has seriously hindered the translation of research findings of these natural products as viable candidates for new drug exploitation. This review systematically describes the commonly used strategies for target identification via the application of probe and non-probe approaches. The merits and demerits of each method were summarized using recent examples, with the goal of comparing currently available methods and selecting the optimum techniques for identifying the targets of bioactive natural products.

Accurate Receptor-Ligand Binding Free Energies from Fast QM Conformational Chemical Space Sampling

Small molecule receptor-binding is dominated by weak, non-covalent interactions such as van-der-Waals hydrogen bonding or electrostatics. Calculating these non-covalent ligand-receptor interactions is a challenge to computational means in terms of accuracy and efficacy since the ligand may bind in a number of thermally accessible conformations. The conformational rotamer ensemble sampling tool (CREST) uses an iterative scheme to efficiently sample the conformational space and calculates energies using the semi-empirical 'Geometry, Frequency, Noncovalent, eXtended Tight Binding' (GFN2-xTB) method. This combined approach is applied to blind predictions of the modes and free energies of binding for a set of 10 drug molecule ligands to the cucurbit[n]urils CB[8] receptor from the recent 'Statistical Assessment of the Modeling of Proteins and Ligands' (SAMPL) challenge including morphine, hydromorphine, cocaine, fentanyl, and ketamine. For each system, the conformational space was sufficiently sampled for the free ligand and the ligand-receptor complexes using the quantum chemical Hamiltonian. A multitude of structures makes up the final conformer-rotamer ensemble, for which then free energies of binding are calculated. For those large and complex molecules, the results are in good agreement with experimental values with a mean error of 3 kcal/mol. The GFN2-xTB energies of binding are validated by advanced density functional theory calculations and found to be in good agreement. The efficacy of the automated QM sampling workflow allows the extension towards other complex molecular interaction scenarios.