A5035098555- Computational Drug Discovery Methods
- Machine Learning in Materials Science
- Single-cell and spatial transcriptomics
- Click Chemistry and Applications
- Cell Image Analysis Techniques
- Microbial Natural Products and Biosynthesis
- vaccines and immunoinformatics approaches
- AI in cancer detection
- Metabolomics and Mass Spectrometry Studies
- Protein Structure and Dynamics
- Software Engineering Research
- Adenosine and Purinergic Signaling
- Microbial Metabolism and Applications
- Scientific Computing and Data Management
- Data Quality and Management
- Machine Learning in Bioinformatics
- Natural Language Processing Techniques
- Signaling Pathways in Disease
- Topic Modeling
- Biochemical and Molecular Research
- Synthesis and biological activity
- Advanced Proteomics Techniques and Applications
- Genomics and Phylogenetic Studies
- Chemical Synthesis and Analysis
University of Pittsburgh
2021-2025
Indiana University – Purdue University Indianapolis
2020-2023
Indiana University School of Medicine
2020-2023
International Institute of Information Technology, Hyderabad
2021
University of Oxford
2021
Abstract Molecular docking computationally predicts the conformation of a small molecule when binding to receptor. Scoring functions are vital piece any molecular pipeline as they determine fitness sampled poses. Here we describe and evaluate 1.0 release Gnina software, which utilizes an ensemble convolutional neural networks (CNNs) scoring function. We also explore array parameter values for optimize performance computational cost. Docking performance, evaluated by percentage targets where...
Conformer generation, the assignment of realistic 3D coordinates to a small molecule, is fundamental structure-based drug design. Conformational ensembles are required for rigid-body matching algorithms, such as shape-based or pharmacophore approaches, and even methods that treat ligand flexibly, docking, dependent on quality provided conformations due not sampling all degrees freedom (e.g., only torsions). Here, we empirically elucidate some general principles about size, diversity,...
TNFα inhibitor (TNFi) immunogenicity in rheumatoid arthritis (RA) is a major obstacle to its therapeutic effectiveness. Although methotrexate (MTX) can mitigate TNFi immunogenicity, adverse effects necessitate alternative strategies. Targeting nuclear factor of activated T cells (NFAT) transcription factors may protect against biologic immunogenicity. Therefore, developing potent NFAT suppress this offer an MTX. We performed structure-based virtual screen the NFATC2 crystal structure...
Natural products have long been a rich source of diverse and clinically effective drug candidates. Non-ribosomal peptides (NRPs), polyketides (PKs), NRP-PK hybrids are three classes natural that display broad range bioactivities, including antibiotic, antifungal, anticancer, immunosuppressant activities. However, discovering these compounds through traditional bioactivity-guided techniques is costly time-consuming, often resulting in the rediscovery known molecules. Consequently, genome...
Abstract Computer-aided drug design has the potential to significantly reduce astronomical costs of development, and molecular docking plays a prominent role in this process. Molecular is an silico technique that predicts bound 3D conformations two molecules, necessary step for other structure-based methods. Here, we describe version 1.3 open-source software Gnina . This release updates underlying deep learning framework PyTorch, resulting more computationally efficient paving way seamless...
Abstract To understand the physiology and pathology of disease, capturing heterogeneity cell types within their tissue environment is fundamental. In such an endeavor, human kidney presents a formidable challenge because its complex organizational structure tightly linked to key physiological functions. Advances in imaging‐based classification may be limited by need incorporate specific markers that can link function. Multiplex imaging mitigate these limitations, but requires cumulative...
Knowledge of the bound protein-ligand structure is critical to many drug discovery tasks. One tool for in silico elucidation molecular docking, which samples and scores ligand binding conformations. Recent work has demonstrated that convolutional neural networks (CNNs) pose scoring outperform conventional functions. Scoring performance can be further increased by taking average multiple CNN models, termed ensembles. However, ensembles large parameter models require significant computational...
Molecular docking computationally predicts the conformation of a small molecule when binding to receptor. Scoring functions are vital piece any molecular pipeline as they determine fitness sampled poses. Here we describe and evaluate 1.0 release Gnina software, which utilizes an ensemble convolutional neural networks (CNNs) scoring function. We also explore array parameter values for optimize performance computational cost. Docking performance, evaluated by percentage targets where top pose...
Abstract The human kidney is a complex organ with various cell types that are intricately organized to perform key physiological functions and maintain homeostasis. New imaging modalities such as mesoscale highly multiplexed fluorescence microscopy increasingly applied tissue create single resolution datasets both spatially large multi-dimensional. These high-content have great potential uncover the spatial organization cellular make-up of kidney. Tissue cytometry novel approach used for...
Virtual screening of small molecules against protein targets can accelerate drug discovery and development by predicting drug-target interactions (DTIs). However, structure-based methods like molecular docking are too slow to allow for broad proteome-scale screens, limiting their application in off-target effects or new mechanisms. Recently, vector-based using language models (PLMs) have emerged as a complementary approach that bypasses explicit 3D structure modeling. Here, we develop...
Determination of the bound pose a ligand is critical first step in many silico drug discovery tasks. Molecular docking main tool for prediction non-covalent binding protein and system. pipelines often only utilize information one to despite commonly held hypothesis that different ligands share interactions when same receptor. Here we describe Open-ComBind, an easy-to-use, open-source version ComBind molecular pipeline leverages from multiple without known structures enhance selection. We...
Molecular docking computationally predicts the conformation of a small molecule when binding to receptor. Scoring functions are vital piece any molecular pipeline as they determine fitness sampled poses. Here we describe and evaluate 1.0 release Gnina software, which utilizes an ensemble convolutional neural networks (CNNs) scoring function. We also explore array parameter values for optimize performance computational cost. Docking performance, evaluated by percentage targets where top pose...
Abstract To understand the physiology and pathology of disease, capturing heterogeneity cell types within their tissue environment is fundamental. In such an endeavor, human kidney presents a formidable challenge because its complex organizational structure tightly linked to key physiological functions. Advances in imaging-based classification may be limited by need incorporate specific markers that can link function. Multiplex imaging mitigate these limitations, but requires cumulative...
Conformer generation, the assignment of realistic 3D coordinates to a small molecule, is fundamental structure based drug design. Conformational ensembles are required for rigid-body matching algorithms, such as shape-based or pharmacophore approaches, and even methods that treat ligand flexibly, docking, dependent on quality provided conformations due not sampling all degrees freedom (e.g. only torsions). Our goal here comprehensively evaluate expansive suite available conformer generation...
Determination of the bound pose a ligand is critical first step in many silico drug discovery tasks. Molecular docking main tool for prediction non-covalent binding protein and system. pipelines often only utilize information one to despite commonly held hypothesis that different ligands share interactions when same receptor. Here we describe Open-ComBind, an easy-to-use, open-source version ComBind molecular pipeline leverages from multiple without known structures enhance selection. We...
The lead optimization phase of drug discovery refines an initial hit molecule for desired properties, especially potency. Synthesis and experimental testing the small perturbations during this refinement can be quite costly time consuming. Relative binding free energy (RBFE, also referred to as ∆∆G) methods allow estimation changes after a ligand scaffold. Here we propose evaluate Convolutional Neural Network (CNN) Siamese network prediction RBFE between two bound ligands. We show that our...