Abstract Protein–protein interactions (PPIs) play an important role in the different functions of cells, but accurate prediction three-dimensional structures for PPIs is still a notoriously difficult task. In this study, HawkDock, free and open accessed web server, was developed to predict analyze PPIs. HawkDock ATTRACT docking algorithm, HawkRank scoring function our group MM/GBSA energy decomposition analysis were seamlessly integrated into multi-functional platform. The predicted by...

Abstract Proteolysis-targeting chimeras (PROTACs), which selectively degrade targeted proteins by the ubiquitin-proteasome system, have emerged as a novel therapeutic technology with potential advantages over traditional inhibition strategies. In past few years, this has achieved substantial progress and two PROTACs been advanced into phase I clinical trials. However, is still maturing design of remains great challenge. order to promote rational PROTACs, we present PROTAC-DB, web-based...

Proteolysis targeting chimeras (PROTACs), which harness the ubiquitin-proteasome system to selectively induce targeted protein degradation, represent an emerging therapeutic technology with potential modulate traditional undruggable targets. Over past few years, this has moved from academia industry and more than 10 PROTACs have been advanced into clinical trials. However, designing potent desirable drug-like properties still remains a great challenge. Here, we report updated online...

A large number of protein–protein interactions (PPIs) are mediated by the between proteins and peptide segments binding partners, therefore determination protein–peptide (PpIs) is quite crucial to elucidate important biological processes design peptides or peptidomimetic drugs that can modulate PPIs. Nowadays, as a powerful computation tool, molecular docking has been widely utilized predict structures complexes. However, although programs have available, systematic study on assessment their...

A significant number of protein-protein interactions (PPIs) are mediated through the between proteins and peptide segments, therefore determination protein-peptide (PpIs) is critical to gain an in-depth understanding PPI network even design peptides or small molecules capable modulating PPIs. Computational approaches, especially molecular docking, provide efficient way model PpIs, a reliable scoring function that can recognize correct binding conformations for complexes one most important...

Enhanced sampling has been extensively used to capture the conformational transitions in protein folding, but it attracts much less attention studies of protein-protein recognition. In this study, we evaluated impact enhanced methods and solute dielectric constants on overall accuracy molecular mechanics/Poisson-Boltzmann surface area (MM/PBSA) mechanics/generalized Born (MM/GBSA) approaches for binding free energy calculations. Here, two widely methods, including aMD GaMD, conventional...

Proteolysis-targeting chimeras (PROTACs), which selectively induce targeted protein degradation, represent an emerging drug discovery technology. Although numerous PROTACs have been reported, designing potent still remains a great challenge, to some extent, due insufficient structural data of Target-PROTAC-E3 ternary complexes. In this work, PROTAC-Model, integrative computational method by combining the FRODOCK-based protocol and RosettaDock-based refinement, was developed predict...

Deep learning (DL)-based de novo molecular design has recently gained considerable traction. Many DL-based generative models have been successfully developed to novel molecules, but most of them are ligand-centric and the role 3D geometries target binding pockets in generation not well-exploited. Here, we proposed a new 3D-based model called RELATION. In RELATION model, BiTL algorithm was specifically designed extract transfer desired geometric features protein-ligand complexes latent space...

Deep learning-based molecular generative models have garnered emerging attention for their capability to generate molecules with novel structures and desired physicochemical properties. However, the evaluation of these models, particularly in a biological context, remains insufficient. To address limitations existing metrics emulate practical application scenarios, we construct RediscMol benchmark that comprises active extracted from 5 kinase 3 GPCR data sets. A set rediscovery-...

Abstract Inhibitors that form covalent bonds with their targets have traditionally been considered highly adventurous due to potential off-target effects and toxicity concerns. However, the clinical validation approval of many inhibitors during past decade, design discovery novel attracted increasing attention. A large amount scattered experimental data for reported, but a resource by integrating information inhibitor is still lacking. In this study, we presented Covalent Inhibitor Database...

Proteolysis-targeting chimera (PROTAC) is an emerging therapeutic technology that leverages the ubiquitin-proteasome system to target protein degradation. Due its event-driven mechanistic characteristics, PROTAC has potential regulate traditionally non-druggable targets. Recently, AI-aided drug design accelerated development of drugs. However, rational PROTACs remains a considerable challenge. Here, we present updated online database, PROTAC-DB 3.0. In this third version, have expanded...

In structure-based drug design (SBDD), the molecular mechanics generalized Born surface area (MM/GBSA) approach has been widely used in ranking binding affinity of small molecule ligands. However, an accurate estimation protein-ligand still remains a challenge due to intrinsic limitation standard (GB) model MM/GBSA. this study, we proposed and evaluated MM/GBSA based on variable dielectric (VDGB) using residue-type-based constants. VDGB model, different values were assigned for three types...

The molecular mechanics/generalized Born surface area (MM/GBSA) has been widely used in end-point binding free energy prediction structure-based drug design (SBDD). However, practice, it is usually being treated as a disputed method mostly because of its system dependence. Here, combining with machine-learning optimization, we developed novel version MM/GBSA, named variable atomic dielectric MM/GBSA (VAD-MM/GBSA), by assigning constants directly to the protein/ligand atoms. new strategy...

Machine-learning (ML)-based scoring functions (MLSFs) have gradually emerged as a promising alternative for protein-ligand binding affinity prediction and structure-based virtual screening. However, clouds of doubts still been raised against the benefits this novel type (SFs). In study, to benchmark performance target-specific MLSFs on relatively unbiased dataset, trained from three representative interaction representations were assessed LIT-PCBA classical Glide SP SF types ligand-based...

Deep learning-based

The aberrant expression of HER2 is highly associated with tumour occurrence and metastasis, therefore extensively targeted for immunotherapy. For example, trastuzumab pertuzumab are FDA-approved monoclonal antibodies that target HER2-positive cells. Despite their advances in clinical applications, emerging resistance to these two HER2-targeting has hindered further application. Somatic mutations receptor have been identified as one the major reasons anti-HER2 antibodies.We analysed frequency...

DNA methyltransferase 3A (DNMT3A) has been regarded as a potential epigenetic target for the development of cancer therapeutics. A number DNMT3A inhibitors have reported, but most them do not good potency, high selectivity and/or low cytotoxicity. It suggested that non-conserved region around recognition domain (TRD) loop is implicated in activity under allosteric regulation ATRX-DNMT3-DNMT3L (ADD) domain, molecular mechanism TRD on needs to be elucidated. In this study, based reported...

Abstract Virtual screening (VS) based on molecular docking has emerged as one of the mainstream technologies drug discovery due to its low cost and high efficiency. However, scoring functions (SFs) implemented in most programs are not always accurate enough how improve their prediction accuracy is still a big challenge. Here, we propose an integrated platform called ASFP, web server for development customized SFs structure-based VS. There three main modules ASFP: (1) descriptor generation...

Deep learning (DL) and machine contribute significantly to basic biology research drug discovery in the past few decades. Recent advances DL-based generative models have led superior developments de novo design. However, data availability, deep processing, lack of user-friendly DL tools interfaces make it difficult apply these techniques We hereby present ReMODE (Receptor-based MOlecular DEsign), a new web server based on algorithm for target-specific ligand design, which integrates...

Three-dimensional (3D) molecular generation models employ deep neural networks to simultaneously generate both topological representation and conformations. Due their advantages in utilizing the structural interaction information on targets, as well reduced reliance existing bioactivity data, these have attracted widespread attention. However, limited training testing data sets unexpected biases inherent single evaluation metrics pose a significant challenge comparing practical settings. In...

Abstract Virtual screening (VS) based on molecular docking has emerged as one of the mainstream technologies drug discovery due to its low cost and high efficiency. However, scoring functions (SFs) implemented in most programs are not always accurate enough how improve their prediction accuracy is still a big challenge. Here, we propose an integrated platform called ASFP, web server for development customized SFs structure-based VS. There three main modules ASFP: 1) descriptor generation...