Emulating Docking Results Using a Deep Neural Network: A New Perspective for Virtual Screening.

Targeting OPA1 protein for therapeutic intervention in autosomal dominant optic atrophy: In silico drug discovery.

RNAs are a vast reservoir of untapped drug targets. Structure-based virtual screening (VS) identifies candidate molecules by leveraging binding site information, traditionally using molecular docking simulations. However, docking struggles to scale with large compound libraries and RNA targets. Machine learning offers a solution but remains underdeveloped for RNA due to limited data and practical evaluations. We introduce a data-driven VS pipeline tailored for RNA, utilizing coarse-grained 3D modeling, synthetic data augmentation, and RNA-specific self-supervision. Our model achieves a 10,000x speedup over docking while ranking active compounds in the top 2.8% on structurally distinct test sets. It is robust to binding site variations and successfully screens unseen RNA riboswitches in a 20,000-compound in-vitro microarray, with a mean enrichment factor of 2.93 at 1%. This marks the first experimentally validated success of structure-based deep learning for RNA VS.

Predicting accurate protein-ligand binding affinities is an important task in drug discovery but remains a challenge even with computationally expensive biophysics-based energy scoring methods and state-of-the-art deep learning approaches. Despite the recent advances in the application of deep convolutional and graph neural network-based approaches, it remains unclear what the relative advantages of each approach are and how they compare with physics-based methodologies that have found more mainstream success in virtual screening pipelines. We present fusion models that combine features and inference from complementary representations to improve binding affinity prediction. This, to our knowledge, is the first comprehensive study that uses a common series of evaluations to directly compare the performance of three-dimensional (3D)-convolutional neural networks (3D-CNNs), spatial graph neural networks (SG-CNNs), and their fusion. We use temporal and structure-based splits to assess performance on novel protein targets. To test the practical applicability of our models, we examine their performance in cases that assume that the crystal structure is not available. In these cases, binding free energies are predicted using docking pose coordinates as the inputs to each model. In addition, we compare these deep learning approaches to predictions based on docking scores and molecular mechanic/generalized Born surface area (MM/GBSA) calculations. Our results show that the fusion models make more accurate predictions than their constituent neural network models as well as docking scoring and MM/GBSA rescoring, with the benefit of greater computational efficiency than the MM/GBSA method. Finally, we provide the code to reproduce our results and the parameter files of the trained models used in this work. The software is available as open source at https://github.com/llnl/fast. Model parameter files are available at ftp://gdo-bioinformatics.ucllnl.org/fast/pdbbind2016_model_checkpoints/.

Equivariant graph neural network-based accurate and ultra-fast virtual screening of small molecules targeting miRNA-protein complex

The interplay between life sciences and advancing technology drives a continuous cycle of chemical data growth; these data are most often stored in open or partially open databases. In parallel, many different types of algorithms are being developed to manipulate these chemical objects and associated bioactivity data. Virtual screening methods are among the most popular computational approaches in pharmaceutical research. Today, user-friendly web-based tools are available to help scientists perform virtual screening experiments. This article provides an overview of internet resources enabling and supporting chemical biology and early drug discovery with a main emphasis on web servers dedicated to virtual ligand screening and small-molecule docking. This survey first introduces some key concepts and then presents recent and easily accessible virtual screening and related target-fishing tools as well as briefly discusses case studies enabled by some of these web services. Notwithstanding further improvements, already available web-based tools not only contribute to the design of bioactive molecules and assist drug repositioning but also help to generate new ideas and explore different hypotheses in a timely fashion while contributing to teaching in the field of drug development.

Researchers have adopted model-centric artificial intelligence (AI) approaches in cheminformatics by using newer, more sophisticated AI methods to take advantage of growing chemical libraries. It has been shown that complex deep learning methods outperform conventional machine learning (ML) methods in QSAR and ligand-based virtual screening– but such approaches generally lack explanability. Hence, instead of developing more sophisticated AI methods (i.e., pursuing a model-centric approach), we wanted to explore the potential of a data-centric AI paradigm for virtual screening. A data-centric AI is an intelligent system that would automatically identify the right type of data to collect, clean and curate for later use by a predictive AI and this is required given the large volumes of chemical data that exist in chemical databases – PubChem alone has over 100 million unique compounds. However, a systematic assessment of the attributes and properties of suitable data is needed. We show here that it is not the result of deficiencies in current AI algorithms but rather, poor understanding and erroneous use of chemical data that ultimately leads to poor predictive performance. Using a new benchmark dataset of BRAF ligands that we developed, we show that our best performing predictive model can achieve an unprecedented accuracy of 99% with a conventional ML algorithm (SVM) using a merged molecular representation (Extended+ ECFP6 fingerprints), far surpassing past performances of virtual screening platforms using sophisticated deep learning methods. Thus, we demonstrate that it is not necessary to resort to the use of sophisticated deep learning algorithms for virtual screening because conventional ML can perform exceptionally well if given the right data and representation. We also show that the common use of decoys for training leads to high false positive rates and its use for testing will result in an over-optimistic estimation of a model’s predictive performance. Another common practice in virtual screening is defining compounds that are above a certain pharmacological threshold as inactives. Here, we show that the use of these so-called inactive compounds lowers a model’s sensitivity/recall. Considering that some target proteins have a limited number of known ligands, we wanted to also observe how the size and composition of the training data impact predictive performance. We found that an imbalance training dataset where inactives outnumber actives led to a decrease in recall but an increase in precision, regardless of the model or molecular representation used; and overall, we observed a decrease in the model’s accuracy. We highlight in this study some of the considerations that one needs to take into account in future development of data-centric AI for CADD.

Chapter 10 - Other Related Techniques

Aims: The research work aims to apply the current virtual screening approaches for rapid screening of available compounds as inhibitors of the novel coronavirus (COVID-19). Background: The worldwide pandemic, uncontrolled spread, and lack of effective therapeutics demand novel SARS-CoV-2 inhibitory anti-viral agents. Objective: The major objectives of the present work are – i) effective utilization of open-source computer- aided drug design (CADD) tools; ii) to prepare a database according to chemical structure similarity to the reported anti-viral drug, Favipiravir; and iii) to investigate potential inhibitors of the novel coronavirus. Methods: The dataset was prepared based on the chemical structure similarity feature of ChemSpider. The virtual screening was carried out using molecular docking and ADMET properties. For performing molecular docking studies, the standard docking protocol of iGEMDOCK was used. Result: Based on chemical structure similarity search to Favipiravir, a small library of 40 compounds was designed. The docking score and ADMET properties were analyzed to prioritize the compounds. Conclusion: The virtual screening resulted in the identification of potential anti-viral compounds. Among the designed library of compounds based on structural similarity to Favipiravir, 70% of compounds were found to possess docking scores more than that of Favipiravir. The amino acid residues involved in binding at the RNA dependent RNA polymerase (RdRp) were identified. The compounds have shown acceptable ADME properties and are potentially non-toxic. Other: The study has successfully applied the open source CADD tools to investigate novel SARS-CoV-2 polymerase inhibitors.

BackgroundIn a structure-based virtual screening, the choice of the docking program is essential for the success of a hit identification. Benchmarks are meant to help in guiding this choice, especially when undertaken on a large variety of protein targets. Here, the performance of four popular virtual screening programs, Gold, Glide, Surflex and FlexX, is compared using the Directory of Useful Decoys-Enhanced database (DUD-E), which includes 102 targets with an average of 224 ligands per target and 50 decoys per ligand, generated to avoid biases in the benchmarking. Then, a relationship between these program performances and the properties of the targets or the small molecules was investigated.ResultsThe comparison was based on two metrics, with three different parameters each. The BEDROC scores with α = 80.5, indicated that, on the overall database, Glide succeeded (score > 0.5) for 30 targets, Gold for 27, FlexX for 14 and Surflex for 11. The performance did not depend on the hydrophobicity nor the openness of the protein cavities, neither on the families to which the proteins belong. However, despite the care in the construction of the DUD-E database, the small differences that remain between the actives and the decoys likely explain the successes of Gold, Surflex and FlexX. Moreover, the similarity between the actives of a target and its crystal structure ligand seems to be at the basis of the good performance of Glide. When all targets with significant biases are removed from the benchmarking, a subset of 47 targets remains, for which Glide succeeded for only 5 targets, Gold for 4 and FlexX and Surflex for 2.ConclusionThe performance dramatic drop of all four programs when the biases are removed shows that we should beware of virtual screening benchmarks, because good performances may be due to wrong reasons. Therefore, benchmarking would hardly provide guidelines for virtual screening experiments, despite the tendency that is maintained, i.e., Glide and Gold display better performance than FlexX and Surflex. We recommend to always use several programs and combine their results.Graphical Summary of the results obtained by virtual screening with the four programs, Glide, Gold, Surflex and FlexX, on the 102 targets of the DUD-E database. The percentage of targets with successful results, i.e., with BDEROC(α = 80.5) > 0.5, when the entire database is considered are in Blue, and when targets with biased chemical libraries are removed are in Red.Electronic supplementary materialThe online version of this article (doi:10.1186/s13321-016-0167-x) contains supplementary material, which is available to authorized users.

A Molecular Dynamics-Shared Pharmacophore Approach to Boost Early-Enrichment Virtual Screening: A Case Study on Peroxisome Proliferator-Activated Receptor α.

Virtual Screening (VS) based on molecular docking is an efficient method used for retrieving novel hit compounds in drug discovery. However, the accuracy of the current docking scoring function (SF) is usually insufficient. In this study, in order to improve the screening power of SF, a novel approach named EAT-Score was proposed by directly utilizing the energy auxiliary terms (EAT) provided by molecular docking scoring through eXtreme Gradient Boosting (XGBoost). Here, EAT specifically refers to the output of the Molecular Operating Environment (MOE) scoring, including the energy scores of five different classical SFs and the Protein-Ligand Interaction Fingerprint (PLIF) terms. The performance of EAT-Score to discriminate actives from decoys was strictly validated on the DUD-E diverse subset by using different performance metrics. The results showed that EAT-Score performed much better than classical SFs in VS, with its AUC values exhibiting an improvement of around 0.3. Meanwhile, EAT-Score could achieve comparable even better prediction performance compared with other state-of-the-art VS methods, such as some machine learning (ML)-based SFs and classical SFs implemented in docking programs, in terms of AUC, LogAUC, or BEDROC. Furthermore, the EAT-Score model can capture important binding pattern information from protein-ligand complexes by Shapley additive explanations (SHAP) analysis, which may be very helpful in interpreting the ligand binding mechanism for a certain target and thereby guiding drug design.

Virtual screening of small molecule databases against macromolecular targets was used to identify binding ligands and predict their lowest energy bound conformation (i.e., pose). AutoDock4-generated poses were rescored using mean-field pathway decoupling free energy of binding calculations and evaluated if these calculations improved virtual screening discrimination between bound and nonbound ligands. Two small molecule databases were used to evaluate the effectiveness of the rescoring algorithm in correctly identifying binders of L99A T4 lysozyme. Self-dock calculations of a database containing compounds with known binding free energies and cocrystal structures largely reproduced experimental measurements, although the mean difference between calculated and experimental binding free energies increased as the predicted bound poses diverged from the experimental poses. In addition, free energy rescoring was more accurate than AutoDock4 scores in discriminating between known binders and nonbinders, suggesting free energy rescoring could be a useful approach to reduce false positive predictions in virtual screening experiments.

BackgroundVirtual screening in the form of similarity rankings is often applied in the early drug discovery process to rank and prioritize compounds from a database. This similarity ranking can be achieved with structural similarity measures. However, their general nature can lead to insufficient performance in some application cases. In this paper, we provide a link between ranking-based virtual screening and fragment-based data mining methods. The inclusion of binding-relevant background knowledge into a structural similarity measure improves the quality of the similarity rankings. This background knowledge in the form of binding relevant substructures can either be derived by hand selection or by automated fragment-based data mining methods.ResultsIn virtual screening experiments we show that our approach clearly improves enrichment factors with both applied variants of our approach: the extension of the structural similarity measure with background knowledge in the form of a hand-selected relevant substructure or the extension of the similarity measure with background knowledge derived with data mining methods.ConclusionOur study shows that adding binding relevant background knowledge can lead to significantly improved similarity rankings in virtual screening and that even basic data mining approaches can lead to competitive results making hand-selection of the background knowledge less crucial. This is especially important in drug discovery and development projects where no receptor structure is available or more frequently no verified binding mode is known and mostly ligand based approaches can be applied to generate hit compounds.

The overexpression of dihydroorotate dehydrogenase (DHODH) in various malignant tumor cells is significantly associated with ferroptosis, making DHODH inhibition a promising strategy for cancer therapy. In this study, we employed an integrated approach to screen and optimize DHODH inhibitor candidates. First, virtual screening of the FDA-approved drug library identified 20 potential compounds (with the positive control AG-636 as a benchmark, docking score: 133.166). Subsequent pharmacophore modeling (ROC curve value >0.8) further narrowed the candidates to six compounds, which underwent fragment displacement optimization. All optimized compounds were evaluated for absorption, distribution, metabolism, excretion, and toxicity (ADMET) properties. Molecular docking identified compounds 65:[(4S)-2,2-dimethyl-1,3-dioxolan-4-yl]methyl 3-(4-{[(2S)-2-hydroxypropyl]oxy}phenyl) (docking score: 197.362) and 66: [(4S)-2,2-dimethyl-1,3-dioxolan-4-yl]methyl 4-(4-{[(2S)-2-hydroxypropyl]oxy}phenyl) (docking score: 202.623) as high-affinity candidates. Molecular dynamics (MD) simulations, principal component analysis (PCA), and free energy landscape (FEL) analyses confirmed stable binding conformations for both compounds. Notably, compound 66: [(4S)-2,2-dimethyl-1,3-dioxolan-4-yl]methyl 4-(4-{[(2S)-2-hydroxypropyl]oxy}phenyl) exhibited minimal conformational changes, suggesting superior binding stability. This study advances compound 66: [(4S)-2,2-dimethyl-1,3-dioxolan-4-yl]methyl 4-(4-{[(2S)-2-hydroxypropyl]oxy}phenyl) as a promising DHODH inhibitor candidate through a multimodal workflow integrating structure-based pharmacophore design, fragment optimization, ADMET profiling, and advanced molecular simulations, providing a novel avenue for DHODH-targeted antitumor therapies.

Amid the rise of multi-drug resistance among bacterial pathogens, the drying of the development pipeline of new antibiotics is worrisome. In search of new effective alternatives, phytocompounds can be considered a good one because of their immense antimicrobial property, low toxicity and huge structural diversity. In the present study, 200 phytocompounds were targeted against two Metallo β-lactamase (MBL) enzymes (NDM-1 and VIM-1) through molecular docking and meropenem was used as a reference drug. The phytocompounds with docking score ≤–8.0 kcal/mol were screened for their pharmacokinetic properties. The three best selected phytocompounds are Coriandrinonediol, Oleanderolide and Uzarigenin. Molecular docking helps to understand binding affinity. The selected phytocompounds showed better result than meropenem. Molecular interaction study reveals their competitive mechanism of inhibition against the target proteins. Coriandrinonediol has docking score −8.3 kcal/mol (NDM-1) and −8.9 kcal/mol (VIM-1), and oleanderolide has docking score −8.2 kcal/mol (NDM-1) and −9.3 kcal/mol (VIM-1). Uzarigenin has the highest binding affinity (–10.4 kcal/mol) among the three against VIM-1 and the lowest binding affinity (–8.1 kcal/mol) against NDM-1. Molecular dynamic (MD) simulation study also supports the stability and flexibility of the above phytocompounds during the MD run. Among the abovementioned three phytocompounds, oleanderolide has given the best result against both target proteins. These phytocompounds are first time reported as MBL inhibitors and their promising in silico results encourage to promote them for further investigation for in vitro and in vivo clinical trials. Communicated by Ramaswamy H. Sarma