/tools

iBenchmark is a collection of datasets and performance metrics for evaluating the structural interpretation of QSAR models. It includes synthetic datasets designed for regression and classification tasks, focusing on the contributions of atoms in molecular structures.

gmx_ffconv is a semi-automated force field converter for GROMACS that allows users to convert molecular systems between different all-atom force fields. It requires topology files for the molecules and facilitates the conversion process without needing extensive programming knowledge.

LaplacianNB is a Python module for a Laplacian-modified Naive Bayes classifier optimized for binary/boolean molecular data. It integrates with RDKit for molecular fingerprint conversion and includes features for performance benchmarking and large-scale processing of molecular datasets.

dftio is a tool designed to assist machine learning communities by transcribing and manipulating DFT output into a format suitable for machine learning models. It supports various DFT software and provides functionalities for parsing different molecular properties from the output data.

LAMBench provides a comprehensive suite of benchmarks to evaluate the performance of machine learning interatomic potentials across various atomic systems. It aims to facilitate the understanding of model generalizability and performance in real-world applications.

DualBind is a deep learning model designed for accurate and fast prediction of protein-ligand binding affinities. It includes a benchmark dataset, ToxBench, which provides a large-scale collection of protein-ligand complexes and their binding free energies.

AlphaFold Analyser is a command line tool designed for rapid visualization of predictions made by AlphaFold2 and AlphaFold3. It generates publication-quality plots for predicted aligned error (PAE) and pLDDT scores, as well as creating PyMol sessions for structural analysis.

xyz2svg is a lightweight Python script designed to create vector images of molecules from XYZ file formats. It offers various customization options for visual representation, making it a valuable tool for molecular visualization in computational chemistry.

AutoGrid is a software tool designed to precalculate grids used by docking programs like AutoDock. It helps predict the binding of small molecules to proteins, facilitating structure-based drug design and virtual screening.

PDB-CAT is a Jupyter Notebook tool designed to automatically categorize PDB structures based on the type of interaction between proteins and ligands, while also checking for mutations in the protein sequence. It facilitates decision-making in drug discovery by providing clear classifications and outputs for protein-ligand interactions.

OEOMMTools is a collection of tools designed to integrate the OpenEye Toolkit with the OpenMM API, facilitating molecular simulations and conformer generation. It includes functionalities for solvation and molecular packing, making it useful for computational chemistry applications.

TBPLaS (Tight-Binding Package for Large-scale Simulation) is a software package designed for building and solving tight-binding models, emphasizing large systems. It provides various methods for electronic structure calculations and simulations, including exact diagonalization and tight-binding propagation methods.

FABFlex is a tool designed for fast and accurate blind flexible docking of molecules, particularly proteins and ligands. It includes functionalities for inference and training of models to predict molecular interactions and structures.

libgmxfort is a modern Fortran library designed for reading and analyzing GROMACS simulation trajectory files. It includes utilities for handling periodic boundary conditions and distance calculations, making it useful for molecular dynamics analysis.

KIMMDY is a reactive molecular dynamics pipeline designed for use with GROMACS, utilizing Kinetic Monte Carlo methods to simulate molecular reactions. It includes various plugins for different types of reactions and allows for on-the-fly parametrization of molecular systems.

Molecule-Generator is a Variational Autoencoder-based tool that generates synthetic SMILES strings for molecules composed of specific repeat units. It allows for the creation of a large dataset of molecular representations and facilitates the generation of new molecular structures through perturbation in the latent space.

Denoise-Pretrain-ML-Potential provides an implementation for denoise pretraining on non-equilibrium molecular conformations to enhance the accuracy and transferability of neural potentials. It utilizes graph neural networks and includes datasets for training and fine-tuning models for molecular potential predictions.

SGNN-EBM is a tool designed for structured multi-task learning aimed at predicting molecular properties. It includes a novel dataset for drug discovery and proposes a state graph neural network-energy based model for effective task modeling.

AntiFormer is a graph-enhanced large language model designed to predict antibody binding affinity. It incorporates sequence information into a graph framework, allowing for accurate predictions that can aid in therapeutic development and diagnostics.

QADD is a software tool designed for de novo drug design that utilizes iterative multi-objective deep reinforcement learning. It incorporates a graph-based molecular quality assessment model to generate high-quality drug-like molecules while considering their potential drug properties.

De-Novo-Drug-Design is a tool that utilizes Deep Reinforcement Learning to optimize the permeation of drugs across the blood-brain barrier. It aims to facilitate the design of new drug candidates by improving their molecular properties.

Multi-eGO is a set of tools designed to generate a multi-eGO force field for performing molecular dynamics simulations. It facilitates the setup and analysis of simulations involving proteins and self-assembly processes.

CAPSIF is a deep learning tool designed to predict carbohydrate-binding residues in proteins based on their structure. It utilizes two models, CAPSIF:Voxel and CAPSIF:Graph, to analyze protein structures and identify binding sites, making it a valuable resource for researchers in molecular biology and computational chemistry.