/tools

DeepSMILES is a Python module that converts standard SMILES notation to a modified version suitable for machine learning applications. It simplifies the representation of molecular structures, making it easier to work with in generative models and other computational chemistry tasks.

ConPLex is a tool that utilizes deep learning and protein language models to predict interactions between drugs and protein targets. It aims to enhance drug discovery by providing accurate predictions at scale, leveraging contrastive learning techniques.

G-SchNet is a generative model that creates 3D molecular structures in an autoregressive manner. It is designed to work with datasets like QM9, allowing for the generation and analysis of small molecules based on their atomic positions and types.

BindFlow is a snakemake-based workflow that facilitates the calculation of absolute and relative binding free energies using GROMACS. It is particularly useful for researchers in drug design and molecular simulations, providing a structured approach to perform complex calculations efficiently.

The ATOM Modeling PipeLine (AMPL) is an open-source software pipeline that facilitates data curation, model building, and molecular property prediction to enhance in silico drug discovery efforts. It supports various machine learning techniques and has been benchmarked on extensive pharmaceutical datasets.

This repository provides an implementation of a denoising diffusion probabilistic model tailored for the conditional generation of protein distograms. It utilizes advanced generative modeling techniques to potentially enhance protein structure prediction and design.

chemCPA is a tool designed to predict cellular responses to novel drug perturbations at a single-cell resolution. It includes code for model training, data processing, and utilizes various molecular embedding models to enhance drug discovery efforts.

OAReactDiff is a diffusion-based generative model designed to generate 3D chemical reactions efficiently. It accelerates the search for transition states and explores new chemical reactions, making it a significant contribution to molecular design and optimization.

OpenMM-ML is a high-level API designed for utilizing machine learning models in OpenMM simulations. It supports various pretrained models to represent molecular interactions, facilitating advanced molecular dynamics and simulations.

The Flex ddG Tutorial provides a framework for modeling and predicting changes in binding free energies of proteins upon mutation using the Rosetta software. It includes example scripts for running the protocol and analyzing results, making it a valuable resource for researchers in computational biology and molecular design.

Uni-3DAR is an autoregressive model designed for unified 3D generation and understanding of molecular structures, proteins, and crystals. It supports diverse tasks including molecular property prediction and generation, utilizing pretrained models and datasets for training and inference.

E3FP is a tool for generating extended 3-dimensional molecular fingerprints, which are useful for representing molecular structures in cheminformatics. It integrates with RDKit and can be applied in various molecular property prediction tasks.

MolCRAFT is a series of projects aimed at developing deep learning models for structure-based drug design and molecule optimization. It introduces novel methodologies for generating molecules with high binding affinity and stable 3D conformations, addressing critical challenges in the field.

Foyer is an open-source Python package that facilitates atom-typing and the application of force fields in molecular simulations. It generates input files for various simulation engines and aims to improve reproducibility in computational research.

Summit is a set of tools designed for optimizing chemical processes, particularly reactions, using machine learning techniques. It includes various optimization strategies and benchmarks to enhance the efficiency of reaction optimization in the fine chemicals industry.

Vermouth and Martinize2 are tools for generating coarse-grained structures and topologies from atomistic molecular structures. They utilize graph algorithms to describe and apply transformations, primarily aimed at enhancing molecular dynamics simulations.

Psiflow is a scalable molecular simulation engine designed for chemistry and materials science applications. It facilitates complex molecular simulations using quantum mechanical calculations and supports a variety of sampling algorithms, allowing users to define and execute intricate workflows efficiently.

CRISPR-GPT is a Large Language Model agent designed to automate and streamline gene-editing experiments, particularly using CRISPR technology. It assists researchers in planning, executing, and analyzing various gene-editing tasks, enhancing efficiency and accuracy in molecular biology applications.

The 'gmxtools' repository provides a collection of scripts and utilities for GROMACS, facilitating various molecular dynamics simulations and analyses. It includes tools for calculating properties, adjusting simulation parameters, and analyzing molecular structures.

DrugFlow is a generative model designed for structure-based drug design, integrating advanced techniques to learn chemical and physical properties from protein-ligand data. It allows for the generation of novel molecules tailored to specific protein targets, enhancing the drug discovery process.

DrugAssist is a large language model aimed at optimizing molecules, making it a valuable tool in drug discovery. It includes a dataset for training and facilitates the generation and optimization of molecular structures.

NBodySimulator.jl is a differentiable simulator designed for scientific machine learning, specifically for simulating N-body problems, including molecular dynamics. It allows users to model and visualize the interactions of multiple bodies, making it applicable in the field of molecular simulations.

ScanNet is an interpretable geometric deep learning model that predicts binding sites on proteins. It identifies functional sites such as protein-protein and protein-antibody interactions, leveraging the three-dimensional structure of proteins to enhance predictions.

SLICES is an innovative tool for encoding and decoding crystal structures, enabling the inverse design of solid-state materials with specific properties. It utilizes generative deep learning techniques to facilitate the creation of new materials, making it a valuable resource in computational chemistry and materials science.