Virtual Screening Pipeline Research Articles

Computational screening of umami tastants using deep learning.

Umami, a fundamental human taste modality, refers to the savory flavors in meats and broths, often associated with monosodium glutamate and protein richness. With limited knowledge of umami molecules, the food industry seeks efficient approaches for identifying novel tastants. In this study, we have devised a virtual screening pipeline for identifying highly potent umami tastants from large molecular databases. We curated the most extensive classification dataset containing 439 umami and 428 non-umami molecules and trained a transformer-based architecture to differentiate between the two classes, achieving 93% accuracy. Additionally, we built a neural network model for predicting the potency of umami compounds, the first effort of its kind. The classification and potency prediction models were combined with similarity analysis and toxicity screening to build an end-to-end virtual framework for the rational discovery of novel tastants. We applied this framework to the FooDB database containing around 70,000 molecules as an illustrative use case for screening potent umami compounds. The screened molecules were validated using molecular docking with the umami taste receptor. This study demonstrates the potential of data-driven methods in discovering new tastants from structural and chemical features of molecules and proposes an efficient implementation for industrial applications.

Discovery of novel BfmR inhibitors restoring carbapenem susceptibility against carbapenem-resistant Acinetobacter baumannii by structure-based virtual screening and biological evaluation

ABSTRACT The emergence and spread of Acinetobacter baumannii pose a severe threat to public health, highlighting the urgent need for the next generation of therapeutics due to its increasing resistance to existing antibiotics. BfmR, a response regulator modulating virulence and antimicrobial resistance, shows a promising potential as a novel antimicrobial target. Developing BfmR inhibitors may propel a new therapeutic direction for intractable infection of resistant strains. In this study, we conducted a structure-based hierarchical virtual screening pipeline combining molecular docking, molecular dynamic simulation, and MM/GBSA calculation to sift the Specs chemical library and finally discover three novel potential BfmR inhibitors. The three hits can reduce the MIC of meropenem for the carbapenem-resistant Acinetobacter baumannii (CRAB) strain ZJ06. Similar to the BfmR knockout strain, Cmp-98 was demonstrated to downregulate the expression of K locus genes, indicating it as a BfmR inhibitor. Bacteria underwent harmful morphological changes after treatment with these inhibitors. Molecular dynamic simulations found that all the hits tend to dynamically bind to different positions of the phosphorylation site of BfmR. Wherein we identified a potential inhibitory-binding cleft, beside a possible activated binding cleft at the edge of the phosphorylation site. Restraining the ligand binding poses may help exert inhibitory effects. This study reports a group of new scaffold BfmR inhibitors, offering new insights for novel antibiotic therapeutics against CRAB.

The potential of Chlorella spp. as antiviral source against African swine fever virus through a virtual screening pipeline

African swine fever (ASF) causes high mortality in pigs and threatens global swine production. There is still a lack of therapeutics available, with two vaccines under scrutiny and no approved small-molecule drugs. Eleven (11) viral proteins were used to identify potential antivirals in in silico screening of secondary metabolites (127) from Chlorella spp. The metabolites were screened for affinity and binding selectivity. High-scoring compounds were assessed through in silico ADMET (Absorption, Distribution, Metabolism, Excretion, Toxicity) predictions, compared to structurally similar drugs, and checked for off-target docking with prepared swine receptors. Molecular dynamics (MD) simulations determined binding stability while binding energy was measured in Molecular Mechanics - Generalized Born Surface Area (MMGBSA) or Poisson-Boltzmann Surface Area (MMPBSA). Only six (6) compounds passed until MD analyses, of which five (5) were stable after 100 ns of MD runs. Of these five compounds, only three had binding affinities that were comparable to or stronger than controls. Specifically, phytosterols 24,25-dihydrolanosterol and CID 4206521 that interact with the RNA capping enzyme (pNP868R), and ergosterol which bound to the Erv-like thioreductase (pB119L). The compounds identified in this study can be used as a theoretical basis for in vitro screening to develop potent antiviral drugs against ASFV.

In Silico Drug Repurposing Uncovered the Antiviral Potential of the Antiparasitic Drug Oxibendazole Against the Chikungunya Virus.

Chikungunya virus (CHIKV) has been reported in over 120 countries and is the causative agent of Chikungunya fever. The debilitating nature of this disease, which can persist months to years after acute infection, drastically impacts the quality of life of patients. Yet, specific antivirals are lacking for the treatment of this disease, which makes the search for new drugs necessary. In this context, the nsP2 protease emerges as an attractive therapeutic target, and drug repurposing strategies have proven to be valuable. Therefore, we combined in silico and in vitro methods to identify known drugs as potential CHIKV nsP2 protease inhibitors with antiviral properties within DrugBank. Herein, we developed a hybrid virtual screening pipeline comprising pharmacophore- and target-based screening, drug-like, and pharmaceutical filtering steps. Six virtual hits were obtained, and two of them, capecitabine (CPB) and oxibendazole (OBZ), were evaluated against CHIKV replication in Vero cells. CPB did not present antiviral activity, whereas OBZ inhibited the replication of two different strains of CHIKV, namely, 181-25 (Asian genotype) and BRA/RJ/18 (clinical isolate from ECSA genotype). OBZ showed potent antiviral activity against the CHIKV BRA/RJ/18 (EC50 = 11.4 μM) with a high selectivity index (>44). Analogs of OBZ (albendazole, fenbendazole, and mebendazole) were also evaluated, but none exhibited anti-CHIKV activity, and further, their stereoelectronic features were analyzed. Additionally, we observed that OBZ acts mainly at post-entry steps. Hence, our results support further in vivo studies to investigate the antiviral potential of OBZ, which offers a new alternative to fight CHIKV infections.

Geometry Optimization Algorithms in Conjunction with the Machine Learning Potential ANI-2x Facilitate the Structure-Based Virtual Screening and Binding Mode Prediction.

Structure-based virtual screening utilizes molecular docking to explore and analyze ligand-macromolecule interactions, crucial for identifying and developing potential drug candidates. Although there is availability of several widely used docking programs, the accurate prediction of binding affinity and binding mode still presents challenges. In this study, we introduced a novel protocol that combines our in-house geometry optimization algorithm, the conjugate gradient with backtracking line search (CG-BS), which is capable of restraining and constraining rotatable torsional angles and other geometric parameters with a highly accurate machine learning potential, ANI-2x, renowned for its precise molecular energy predictions reassembling the wB97X/6-31G(d) model. By integrating this protocol with binding pose prediction using the Glide, we conducted additional structural optimization and potential energy prediction on 11 small molecule-macromolecule and 12 peptide-macromolecule systems. We observed that ANI-2x/CG-BS greatly improved the docking power, not only optimizing binding poses more effectively, particularly when the RMSD of the predicted binding pose by Glide exceeded around 5 Å, but also achieving a 26% higher success rate in identifying those native-like binding poses at the top rank compared to Glide docking. As for the scoring and ranking powers, ANI-2x/CG-BS demonstrated an enhanced performance in predicting and ranking hundreds or thousands of ligands over Glide docking. For example, Pearson's and Spearman's correlation coefficients remarkedly increased from 0.24 and 0.14 with Glide docking to 0.85 and 0.69, respectively, with the addition of ANI-2x/CG-BS for optimizing and ranking small molecules binding to the bacterial ribosomal aminoacyl-tRNA receptor. These results suggest that ANI-2x/CG-BS holds considerable potential for being integrated into virtual screening pipelines due to its enhanced docking performance.

A deep learning based multi-model approach for predicting drug-like chemical compound’s toxicity

Ensuring the safety and efficacy of chemical compounds is crucial in small-molecule drug development. In the later stages of drug development, toxic compounds pose a significant challenge, losing valuable resources and time. Early and accurate prediction of compound toxicity using deep learning models offers a promising solution to mitigate these risks during drug discovery. In this study, we present the development of several deep-learning models aimed at evaluating different types of compound toxicity, including acute toxicity, carcinogenicity, hERG_cardiotoxicity (the human ether-a-go-go related gene caused cardiotoxicity), hepatotoxicity, and mutagenicity. To address the inherent variations in data size, label type, and distribution across different types of toxicity, we employed diverse training strategies. Our first approach involved utilizing a graph convolutional network (GCN) regression model to predict acute toxicity, which achieved notable performance with Pearson R 0.76, 0.74, and 0.65 for intraperitoneal, intravenous, and oral administration routes, respectively. Furthermore, we trained multiple GCN binary classification models, each tailored to a specific type of toxicity. These models exhibited high area under the curve (AUC) scores, with an impressive AUC of 0.69, 0.77, 0.88, and 0.79 for predicting carcinogenicity, hERG_cardiotoxicity, mutagenicity, and hepatotoxicity, respectively. Additionally, we have used the approved drug dataset to determine the appropriate threshold value for the prediction score in model usage. We integrated these models into a virtual screening pipeline to assess their effectiveness in identifying potential low-toxicity drug candidates. Our findings indicate that this deep learning approach has the potential to significantly reduce the cost and risk associated with drug development by expediting the selection of compounds with low toxicity profiles. Therefore, the models developed in this study hold promise as critical tools for early drug candidate screening and selection.

Abstract 4945: Computational modeling-based discovery of novel anticancer drug candidates targeting centromere-associated protein E

Abstract Purpose: Centromere-associated protein E (CENP-E), a mitotic motor protein, is crucial for cell division. Inhibition of CENP-E can lead to chromosome misalignment and aneuploidy. Our recent studies revealed that the CENP-E inhibitor (CENP-Ei), Compound A, induces aneuploid-mediated cGAS-STING pathway activation in cancer cell lines, which is expected to trigger innate immune response and induce immunological conversion of the tumor microenvironment from cold to hot. However, known CENP-Eis exhibited limited efficacy, and none have gone beyond phase I trials since 2012. The aim of this study is to develop a workflow integrating structure and artificial intelligence-based modeling approaches to accelerate the discovery of novel CENP-Eis with improved efficacy and overcome related challenges. Method: The inhibitor-bound CENP-E structure was modeled using chimeric homology modeling followed by induced fit docking with known CENP-Eis. Structure-based virtual screening (VS) was performed on large compound libraries in Enamine REAL, Synthetically Accessible Virtual Inventory, and MolPort databases. Consensus scoring methods were applied by averaging ranks of individual molecules obtained from VS against different CENP-E conformations. An active learning-enhanced VS pipeline was developed using ATOM Modeling PipeLine (AMPL) to find the best-ranked ligands more efficiently. CENP-E ligand candidates were further filtered based on their safety properties predicted by machine learning models trained with curated databases of adverse drug reactions using AMPL. The success of this study was measured by its ability to reveal novel chemotypes that could modulate CENP-E in kinesin ATPase assays. Result: Conformations of CENP-E’s ligand binding site were predicted for VS using the homology model. Structure-based VS was performed to select high-ranked compounds based on consensus scoring. The active learning-enhanced VS pipeline achieved 75% accuracy in ranking the top 20% of hit compounds. The graph convolutional network model with a ROCAUC, 0.76, was created using AMPL to filter ligand candidates based on their predicted safety properties. Seventy-three potential CENP-E ligands computationally prioritized from the Molport database were experimentally tested using kinesin ATPase assays from which 4 potential inhibitors and 8 potential activators were identified indicating overlapping binding sites of inhibitors and activators. Conclusion: Our integrated workflow is effective in discovering novel CENP-E modulators. The discovery of CENP-E activators provides an opportunity to identify novel therapeutics in hepatocellular carcinoma malignancies known to experience decreased CENP-E activity leading to aneuploidy. The predictions generated by computational models combined with experimental validations could further accelerate anticancer drug discovery. Citation Format: Pinyi Lu, Ryo Kamata, Michael R. Weil, Naomi Ohashi, Akihiro Ohashi, Eric A. Stahlberg. Computational modeling-based discovery of novel anticancer drug candidates targeting centromere-associated protein E [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 1 (Regular Abstracts); 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84(6_Suppl):Abstract nr 4945.

BioProtIS: Streamlining protein-ligand interaction pipeline for analysis in genomic and transcriptomic exploration

The identification of protein-ligand interactions plays a pivotal role in elucidating biological processes and discovering potential bioproducts. Harnessing the capabilities of computational methods in drug discovery, we introduce an innovative Inverted Virtual Screening (IVS) pipeline. This pipeline Integrated molecular dynamics and docking analyses to ensure that protein structures are not only energetically favorable but also representative of stable conformations. The primary objective of this pipeline is to automate and streamline the analysis of protein-ligand interactions at both genomic and transcriptomic scales. In the contemporary post-genomic era, high-throughput computational screening for bioproducts, biological systems, and therapeutic drugs has become a cornerstone practice. This approach offers the promise of cost-effectiveness, time efficiency, and optimization of laboratory work. Nevertheless, a notable deficiency persists in the availability of efficient pipelines capable of automating the virtual screening process, seamlessly integrating input and output, and leveraging the full potential of open-source tools. To bridge this critical gap, we have developed a versatile pipeline known as BioProtIS. This tool seamlessly integrates a suite of state-of-the-art tools, including Modeller, AlphaFold, Gromacs, FPOCKET, and AutoDock Vina, thus facilitating the streamlined docking of ligands with an expansive repertoire of proteins sourced from genomes and transcriptomes, and substrates. To assess the pipeline's performance, we employed the transcriptomes of Cereus jamacaru (a cactus species) and Aspisoma lineatum (firefly), along with the genome of Homo sapiens. This integration not only improves the accuracy of ligand-protein interactions by minimizing replicability deviations but also optimizes the discovery process by enabling the simultaneous evaluation of multiple substrates. Furthermore, our pipeline accommodates distinct testing scenarios, such as blind docking or site-specific targeting, which are invaluable in applications ranging from drug repositioning to the exploration of new allosteric binding sites and toxicity assessments. BioProtIS has been designed with modularity at its core. This inherent flexibility empowers users to make custom modifications directly within the source code, tailoring the pipeline to their specific research needs. Moreover, it lays the foundation for seamless integration of diverse docking algorithms in future iterations, promising ongoing advancements in the field of computational biology. This pipeline is available for free distribution and can be download at: https://github.com/BBMDO/BioProtIS.

Targeting PDE4A for therapeutic potential: exploiting drug repurposing approach through virtual screening and molecular dynamics

cAMP-specific 3′,5′-cyclic phosphodiesterase 4 A (PDE4A) holds a pivotal role in modulating intracellular levels of cyclic adenosine monophosphate (cAMP). Targeting PDE4A with novel therapeutic agents shows promise in addressing neurological disorders (e.g. Alzheimer’s and Parkinson’s diseases), mood disorders (depression, anxiety), inflammatory conditions (asthma, chronic obstructive pulmonary disease), and even cancer. In this study, we present a comprehensive approach that integrates virtual screening and molecular dynamics (MD) simulations to identify potential inhibitors of PDE4A from the existing pool of FDA-approved drugs. The initial compound selection was conducted focusing on binding affinity scores, which led to the identification of several high-affinity compounds with potential PDE4A binding properties. From the refined selection process, two promising compounds, Fluspirilene and Dihydroergocristine, emerged as strong candidates, displaying substantial affinity and specificity for the PDE4A binding site. Interaction analysis provided robust evidence of their binding capabilities. To gain deeper insights into the dynamic behavior of Fluspirilene and Dihydroergocristine in complex with PDE4A, we conducted 300 ns MD simulations, principal components analysis (PCA), and free energy landscape (FEL) analysis. These analyses revealed that Fluspirilene and Dihydroergocristine binding stabilized the PDE4A structure and induced minimal conformational changes, highlighting their potential as potent binders. In conclusion, our study systematically explores repurposing existing FDA-approved drugs as PDE4A inhibitors through a comprehensive virtual screening pipeline. The identified compounds, Fluspirilene and Dihydroergocristine, exhibit a strong affinity for PDE4A, displaying characteristics that support their suitability for further development as potential therapeutic agents for conditions associated with PDE4A dysfunction. Communicated by Ramaswamy H. Sarma

Crystallographic mining driven computer-guided approach to identify the ASK1 inhibitor likely to perturb the catalytic region

The pathological levels of reactive oxygen species (ROS) and oxidative stress has been recognized as a critical driver for inflammatory disorders. Apoptosis signal-regulating kinase 1 (ASK1) has been reported to be activated by intracellular ROS and its inhibition leads to a down regulation of p38-and JNK-dependent signaling. ASK1 inhibitors are reported to have the potential to treat clinically important inflammatory pathologies including liver, pulmonary and renal disorders. In view of its biological and pathological significance, inhibition of ASK1 with small molecules has been pursued as an attractive strategy to combat human diseases such as non-alcoholic steatohepatitis (NASH). Despite several ASK1 inhibitors being developed, the failure in Phase 3 clinical trials of most advanced candidate selonsertib’s, underscores to discover therapeutic agents with diverse chemical moiety. Here, by using structural pharmacophore and enumeration strategy on mining co-crystals of ASK1, different scaffolds were generated to enhance the chemical diversity keeping the critical molecular interaction in the catalytic site intact. A total of 15,772 compounds were generated from diverse chemical scaffolds and were evaluated using a virtual screening pipeline. Based on docking and MM-GBSA scores, a lead candidate, S3C-1-D424 was identified from top hits. A comparative molecular dynamics simulations (MD) of APO, Selonsertib and shortlisted potential candidates combined with pharmacokinetics profiling and thermodynamic analysis, demonstrating their suitability as potential ASK1 inhibitors to explore further for establishment towards hit-to-lead campaign.Communicated by Ramaswamy H. Sarma

Discovery and biological evaluation of novel dual PTP1B and ACP1 inhibitors for the treatment of insulin resistance

In this study, a virtual screening pipeline comprising ligand-based and structure-based approaches was established and applied for the identification of dual PTP1B and ACP1 inhibitors. As a result, a series of benzoic acid derivatives was discovered, and compound H3 and S6 demonstrated PTP1B and ACP1 inhibitory activity, with IC50 values of 3.5 and 8.2 μM for PTP1B, and 2.5 and 5.2 μM for ACP1, respectively. Molecular dynamics simulations illustrated that H3 interacted with critical residues in the active site, such as Cys215 and Arg221 for PTP1B, and Cys17 and Arg18 for ACP1. Enzymatic kinetic research indicated that identified inhibitors competitively inhibited PTP1B and ACP1. Additionally, cellular assays demonstrated that H3 and S6 effectively increased glucose uptake in insulin-resistant HepG2 cells while displaying very limited cytotoxicity at their effective concentrations. In summary, H3 and S6 represent novel dual-target inhibitors for PTP1B and ACP1, warranting further investigation as potential agents for the treatment of diabetes.

Discovery of high‐affinity amyloid ligands using a ligand‐based virtual screening pipeline

AbstractBackgroundA ligand‐based virtual screening pipeline was developed to discover structurally novel ligands for Aβ(1‐42) fibrils.MethodA database of ligands that bind to Aβ(1‐42) fibrils was used to develop a two‐step ligand‐based virtual screening pipeline. The first step involved developing machine learnings models that use relatively simple chemical descriptors to predict ligand dissociation constants (Kd ). The second step involved constructing 3D models based on field points that describe the surface, shape, and electronic properties of ligands. The combined pipeline was then used to screen 63 million compounds from the ZINC15 database.1 The most promising compounds were experimentally evaluated using binding assays.ResultFor the first chemical descriptor model, a support vector machine model was found to predict the ‐log(Kd /M) of Aβ(1‐42) fibril ligands with a mean absolute error of only 0.41. An ensemble of four 3D models were then developed that each predicted ‐log(Kd /M) with a cross‐validation regression coefficient of 0.48–0.56. The ZINC15 database compounds were screened through the first chemical descriptor model, and the 10,000 compounds with the highest predicted affinities were then screened through the 3D models. The 46 highest‐ranked ligands were then evaluated using Thioflavin T competition assays, resulting in five new Aβ(1‐42) ligands with novel structures that exhibited nanomolar binding.ConclusionA ligand‐based virtual screening pipeline has been developed to discover new fibril‐binding ligands. Using Aβ(1‐42) fibrils as a target, five new structurally diverse ligands were found that exhibit nanomolar binding affinities.1. Sterling and J. J. Irwin, J. Chem. Inf. Model. 2015, 55, 2324‐2337.

Streamlining pipeline efficiency: a novel model-agnostic technique for accelerating conditional generative and virtual screening pipelines

The discovery of potential therapeutic agents for life-threatening diseases has become a significant problem. There is a requirement for fast and accurate methods to identify drug-like molecules that can be used as potential candidates for novel targets. Existing techniques like high-throughput screening and virtual screening are time-consuming and inefficient. Traditional molecule generation pipelines are more efficient than virtual screening but use time-consuming docking software. Such docking functions can be emulated using Machine Learning models with comparable accuracy and faster execution times. However, we find that when pre-trained machine learning models are employed in generative pipelines as oracles, they suffer from model degradation in areas where data is scarce. In this study, we propose an active learning-based model that can be added as a supplement to enhanced molecule generation architectures. The proposed method uses uncertainty sampling on the molecules created by the generator model and dynamically learns as the generator samples molecules from different regions of the chemical space. The proposed framework can generate molecules with high binding affinity with sima 70% improvement in runtime compared to the baseline model by labeling only sim30% of molecules compared to the baseline oracle.

Optimal decision-making in high-throughput virtual screening pipelines

The need for efficient computational screening of molecular candidates that possess desired properties frequently arises in various scientific and engineering problems, including drug discovery and materials design. However, the enormous search space containing the candidates and the substantial computational cost of high-fidelity property prediction models make screening practically challenging. In this work, we propose a general framework for constructing and optimizing a high-throughput virtual screening (HTVS) pipeline that consists of multi-fidelity models. The central idea is to optimally allocate the computational resources to models with varying costs and accuracy to optimize the return on computational investment. Based on both simulated and real-world data, we demonstrate that the proposed optimal HTVS framework can significantly accelerate virtual screening without any degradation in terms of accuracy. Furthermore, it enables an adaptive operational strategy for HTVS, where one can trade accuracy for efficiency.

Virtual Screening and Binding Analysis of Potential CD58 Inhibitors in Colorectal Cancer (CRC).

Human cell surface receptor CD58, also known as lymphocyte function-associated antigen 3 (LFA-3), plays a critical role in the early stages of immune response through interacting with CD2. Recent research identified CD58 as a surface marker of colorectal cancer (CRC), which can upregulate the Wnt pathway and promote self-renewal of colorectal tumor-initiating cells (CT-ICs) by degradation of Dickkopf 3. In addition, it was also shown that knockdown of CD58 significantly impaired tumor growth. In this study, we developed a structure-based virtual screening pipeline using Autodock Vina and binding analysis and identified a group of small molecular compounds having the potential to bind with CD58. Five of them significantly inhibited the growth of the SW620 cell line in the following in vitro studies. Their proposed binding models were further verified by molecular dynamics (MD) simulations, and some pharmaceutically relevant chemical and physical properties were predicted. The hits described in this work may be considered interesting leads or structures for the development of new and more efficient CD58 inhibitors.

ML-PLIC: a web platform for characterizing protein-ligand interactions and developing machine learning-based scoring functions.

Cracking the entangling code of protein-ligand interaction (PLI) is of great importance to structure-based drug design and discovery. Different physical and biochemical representations can be used to describe PLI such as energy terms and interaction fingerprints, which can be analyzed by machine learning (ML) algorithms to create ML-based scoring functions (MLSFs). Here, we propose the ML-based PLI capturer (ML-PLIC), a web platform that automatically characterizes PLI and generates MLSFs to identify the potential binders of a specific protein target through virtual screening (VS). ML-PLIC comprises five modules, including Docking for ligand docking, Descriptors for PLI generation, Modeling for MLSF training, Screening for VS and Pipeline for the integration of the aforementioned functions. We validated the MLSFs constructed by ML-PLIC in three benchmark datasets (Directory of Useful Decoys-Enhanced, Active as Decoys and TocoDecoy), demonstrating accuracy outperforming traditional docking tools and competitive performance to the deep learning-based SF, and provided a case study of the Serine/threonine-protein kinase WEE1 in which MLSFs were developed by using the ML-based VS pipeline in ML-PLIC. Underpinning the latest version of ML-PLIC is a powerful platform that incorporates physical and biological knowledge about PLI, leveraging PLI characterization and MLSF generation into the design of structure-based VS pipeline. The ML-PLIC web platform is now freely available at http://cadd.zju.edu.cn/plic/.

Discovery of High-Affinity Amyloid Ligands Using a Ligand-Based Virtual Screening Pipeline.

Fibrillar protein aggregates are characteristic of neurodegenerative diseases but represent difficult targets for ligand design, because limited structural information about the binding sites is available. Ligand-based virtual screening has been used to develop a computational method for the selection of new ligands for Aβ(1-42) fibrils, and five new ligands have been experimentally confirmed as nanomolar affinity binders. A database of ligands for Aβ(1-42) fibrils was assembled from the literature and used to train models for the prediction of dissociation constants based on chemical structure. The virtual screening pipeline consists of three steps: a molecular property filter based on charge, molecular weight, and logP; a machine learning model based on simple chemical descriptors; and machine learning models that use field points as a 3D description of shape and surface properties in the Forge software. The three-step pipeline was used to virtually screen 698 million compounds from the ZINC15 database. From the top 100 compounds with the highest predicted affinities, 46 compounds were experimentally investigated by using a thioflavin T fluorescence displacement assay. Five new Aβ(1-42) ligands with dissociation constants in the range 20-600 nM and novel structures were identified, demonstrating the power of this ligand-based approach for discovering new structurally unique, high-affinity amyloid ligands. The experimental hit rate using this virtual screening approach was 10.9%.

Virtual Screening and Biological Evaluation of Novel Low Molecular Weight Protein Tyrosine Phosphatase Inhibitor for the Treatment of Insulin Resistance.

Protein tyrosine phosphatases (PTPs) play an essential way in diseases including cancer, obesity, diabetes and autoimmune disorders. As a member of PTPs, low molecular weight PTP (LMPTP) has been a well-recognized anti-insulin resistance target in obesity. However, the number of reported LMPTP inhibitors is limited. Our research aims to discover a novel LMPTP inhibitor and evaluate its biological activity against insulin resistance. A virtual screening pipeline based on the X-ray co-crystal complex of LMPTP was constructed. Enzyme inhibition assay and cellular bioassay were used to evaluate the activity of screened compounds. The screening pipeline rendered 15 potential hits from Specs chemical library. Enzyme inhibition assay identified compound F9 (AN-465/41163730) as a potential LMPTP inhibitor with a K i value of 21.5 ± 7.3 μM. Cellular bioassay showed F9 could effectively increase the glucose consumption of HepG2 cells as a result of releasing insulin resistance by regulating PI3K-Akt pathway. In summary, this study presents a versatile virtual screening pipeline for potential LMPTP inhibitor discovery and provides a novel-scaffold lead compound that is worthy of further modification to get more potent LMPTP inhibitors.

Ringtail: A Python Tool for Efficient Management and Storage of Virtual Screening Results.

Virtual screening using molecular docking is now routinely used for the rapid evaluation of very large ligand libraries in early stage drug discovery. As the size of compound libraries which can feasibly be screened grows, so do the challenges in result management and storage. Here we introduce Ringtail, a new Python tool in the AutoDock Suite for efficient storage and analysis of virtual screening data based on portable SQLite databases. Ringtail is designed to work with AutoDock-GPU and AutoDock Vina out-of-the-box. Its modular design also allows for easy extension to support input file types from other docking software, different storage solutions, and incorporation into other applications. Ringtail's SQLite database output can dramatically reduce the required disk storage (36-46 fold) by selecting individual poses to store and by taking advantage of the relational database format. Filtering times are also dramatically reduced, requiring minutes to filter millions of ligands. Thus, Ringtail is a tool that can immediately integrate into existing virtual screening pipelines using AutoDock-GPU and Vina, and is scriptable and modifiable to fit specific user needs.

Optimal high-throughput virtual screening pipeline for efficient selection of redox-active organic materials

As global interest in renewable energy continues to increase, there has been a pressing need for developing novel energy storage devices based on organic electrode materials that can overcome the shortcomings of the current lithium-ion batteries. One critical challenge for this quest is to find materials whose redox potential (RP) meets specific design targets. In this study, we propose a computational framework for addressing this challenge through the effective design and optimal operation of a high-throughput virtual screening (HTVS) pipeline that enables rapid screening of organic materials that satisfy the desired criteria. Starting from a high-fidelity model for estimating the RP of a given material, we show how a set of surrogate models with different accuracy and complexity may be designed to construct a highly accurate and efficient HTVS pipeline. We demonstrate that the proposed HTVS pipeline construction and operation strategies substantially enhance the overall screening throughput.