/tools

DiffSBDD is an implementation of an equivariant diffusion model aimed at structure-based drug design. It allows users to generate new ligands, optimize existing molecules, and benchmark performance using various datasets, making it a comprehensive tool for molecular design and analysis.

The RFDiffusionAA repository provides tools for designing small molecule binders and proteins using a diffusion-based approach. It includes functionalities for generating molecular structures and optimizing their properties, making it a valuable resource in molecular design.

RFantibody is a pipeline for the structure-based design of de novo antibodies and nanobodies. It utilizes methods for protein backbone design, sequence design, and in silico filtering of designs, making it a comprehensive tool for antibody engineering.

GeoDiff implements a geometric diffusion model for generating molecular conformations, which is crucial for understanding molecular structures. It also provides tools for property prediction and includes datasets for training and evaluation, making it a valuable resource in computational chemistry and molecular biology.

RFdiffusion2 is an open-source tool designed for enzyme design and molecular generation using advanced inference techniques. It supports the creation of protein structures from atomic motifs and includes benchmarking capabilities for evaluating design performance.

Pocket2Mol is a tool designed for efficient molecular sampling based on the 3D structures of protein pockets. It employs equivariant graph neural networks to improve the quality and efficiency of molecular generation, making it useful for structure-based drug design.

GT4SD is an open-source library designed to accelerate hypothesis generation in scientific discovery, particularly in the fields of molecular design and property prediction. It includes generative models for creating molecules and tools for predicting molecular properties, making it a valuable resource for researchers in computational chemistry and molecular biology.

ReLeaSE is a tool that utilizes deep reinforcement learning to facilitate the de-novo design of drug molecules. It includes functionalities for optimizing molecular properties and generating new molecular structures based on learned patterns.

REINVENT is a tool designed for the de novo design of molecules using reinforcement learning techniques. It provides a framework for generating molecular structures and optimizing their properties, making it a valuable resource in the field of drug discovery.

This repository provides a Tensorflow implementation of a Graph Convolutional Policy Network aimed at goal-directed molecular graph generation. It allows for the generation of molecules based on desired properties, utilizing reinforcement learning techniques.

PyXtal is an open-source Python library that facilitates the generation of atomic and molecular structures while adhering to symmetry constraints. It includes features for geometry optimization and supports various structural formats for further analysis.

The `exmol` package is designed to explain black-box predictions of molecular properties using model agnostic methods. It includes functionalities for generating counterfactuals and descriptor attributions, helping users understand the influence of molecular structures on predicted properties.

REINVENT is a tool for molecular de novo design that employs recurrent neural networks and reinforcement learning techniques. It allows users to explore chemical space and generate novel molecular structures based on learned representations.

ProteinGenerator is a tool that generates sequence-structure pairs using a diffusion model based on RoseTTAFold. It allows users to explore and create new protein sequences conditioned on structural motifs, facilitating advancements in protein design.

CBGBench is a benchmark tool for generative target-aware molecule design, integrating multiple state-of-the-art methods for generating molecules. It supports tasks such as linker design, fragment growing, and scaffold hopping, making it a valuable resource for researchers in drug discovery.

torch-molecule is a deep learning package designed for molecular discovery, featuring an sklearn-style interface for property prediction, inverse design, and representation learning. It supports various molecular tasks and includes datasets for training models on molecular properties.

The DPLM repository provides implementations of diffusion protein language models that excel in generating and predicting protein sequences and structures. It includes features for unconditional and conditional protein generation, as well as representation learning for various protein-related tasks.

Mol-Instructions is a dataset that contains a large collection of instructions for biomolecular tasks, including molecule-oriented and protein-oriented tasks. It aims to facilitate the development of large language models for generating and understanding molecular and protein-related information.

The Ersilia Model Hub is a platform that hosts pre-trained AI/ML models aimed at drug discovery, particularly for infectious and neglected diseases. It includes models for predicting antibiotic activity, ADMET properties, and generative chemistry, facilitating research in molecular biology and computational chemistry.

The All-atom Diffusion Transformers repository provides an implementation of a generative model that can create new molecular and material structures using a unified latent diffusion framework. It supports the generation of both small molecules and periodic materials, making it a valuable tool for molecular design and materials science.

IBM's FM4M is a multi-modal foundation model designed to support research in materials science and chemistry. It includes various pre-trained models for predicting molecular properties and generating molecular representations, making it a versatile tool for computational chemistry applications.

Chemformer is a repository that implements a pre-trained transformer model for generating and predicting molecular properties, including reaction and retrosynthetic predictions. It utilizes SMILES strings for molecular representation and is aimed at enhancing molecular design and optimization tasks.

The 'stk' library is designed for the construction and manipulation of complex molecules, facilitating automatic molecular design and the creation of molecular databases. It serves as a framework for researchers in computational chemistry and materials science to explore molecular structures and properties.

The 'torsional-diffusion' repository provides an implementation of a state-of-the-art method for generating molecular conformers using a diffusion framework. It outperforms traditional software in generating diverse molecular structures, making it a valuable tool for molecular design and optimization.