/tools

CIGA is a framework designed to learn causally invariant representations from graph data, specifically addressing challenges in out-of-distribution generalization. It has applications in drug discovery, validating its relevance to molecular tools.

PyTrial is a Python package designed for artificial intelligence applications in drug development, providing off-the-shelf pipelines for various clinical trial tasks. It includes features for predicting patient outcomes, trial site selection, and trial data simulation, making it a comprehensive platform for researchers in the field.

Dense Homolog Retriever (DHR) is a tool designed for the ultra-fast detection of protein remote homologs using deep dense retrieval methods. It supports homolog retrieval benchmarks and includes functionalities for embedding and structure prediction of proteins.

ProteinLM is a pretrained protein language model that leverages deep learning techniques to evaluate protein embeddings on various biologically relevant tasks. It provides tools for pretraining and fine-tuning models, making it useful for researchers in molecular biology and bioinformatics.

Protenix-Dock is an end-to-end protein-ligand docking framework that utilizes empirical scoring functions for accurate docking tasks. It provides advanced features for conformation sampling and scoring, making it suitable for applications in drug discovery and molecular simulations.

The `graph-pes` framework is designed to accelerate the development of machine-learned potential energy surface models that utilize graph representations of atomic structures. It allows researchers to train, fine-tune, and deploy models for molecular dynamics simulations and energy calculations.

PLAID is a multimodal generative model designed for generating protein sequences and all-atom structures based on specific prompts. It includes features for both unconditional and conditional sampling, making it a valuable tool for protein design and molecular generation.

FreeBindCraft is a modified version of the BindCraft pipeline that allows for protein design and optimization with an optional bypass of PyRosetta. It incorporates structural relaxation, shape complementarity calculations, and scoring metrics to enhance the design process for peptides and miniproteins.

AQME (Automated Quantum Mechanical Environments) offers workflows for generating molecular conformers and creating quantum mechanical input files. It also facilitates the post-processing of quantum mechanical output and the generation of molecular descriptors, making it a valuable tool for computational chemistry.

DQC is a differentiable quantum chemistry package that supports density functional theory and Hartree-Fock calculations. It enables applications such as learning exchange-correlation functionals and basis optimization, making it a valuable tool for molecular property prediction and simulations.

The 'geometric-gnns' repository provides a curated list of Geometric Graph Neural Networks designed for 3D atomic systems. It includes various models, their characteristics, and a collection of datasets, facilitating research in molecular property prediction and simulations.

ProteinGCN is a tool designed for assessing the quality of protein models by generating protein graphs and using Graph Convolutional Networks to predict local and global quality scores. It utilizes datasets like Rosetta-300k for training and evaluation, making it a valuable resource in the field of protein modeling.

LSTM_Chem is a tool that implements generative recurrent networks for de novo drug design, allowing users to generate new molecular structures based on learned patterns from existing data. It utilizes SMILES representations for molecules and is built using TensorFlow and Keras.

The fep-benchmark repository offers a benchmark set specifically designed for evaluating relative free energy calculations. It is aimed at improving the accuracy of molecular property predictions in the context of drug discovery projects.

RareFold is a tool for predicting the structures of single-chain proteins that incorporate rare noncanonical amino acids. It also enables the design of novel peptide binders through its EvoBindRare framework, allowing for flexible and diverse peptide design without prior knowledge of binding sites.

Auto-QChem is an automated workflow designed for the generation and storage of density functional theory (DFT) calculations specifically for organic molecules. It facilitates the prediction of molecular properties by streamlining the computational chemistry process.

DiffBindFR is a diffusion model-based framework designed for flexible protein-ligand docking. It provides tools for both forward and reverse docking, allowing users to model interactions between proteins and ligands effectively.

CatLearn is a machine learning environment focused on atomic-scale modeling for surface science and catalysis. It provides utilities for building and testing machine learning models, including Gaussian Processes for predicting molecular properties and optimizing atomic structures.

BitBIRCH is an efficient clustering algorithm tailored for handling large molecular libraries, facilitating drug discovery and cheminformatics tasks. It allows researchers to perform similarity searches and analyze chemical space effectively.

OpenPathSampling is an open source Python framework designed for transition interface and path sampling calculations. It facilitates molecular dynamics simulations, allowing researchers to explore complex biomolecular systems.

Obsidian Chem is a plugin for Obsidian.md that allows users to render chemical structures from SMILES strings. It enhances note-taking in chemistry by enabling the visualization of molecular structures directly within notes.

ChemGAN challenge provides code for a study on using AI to reproduce natural chemical diversity for drug discovery. It employs generative models to design and generate molecules, making it a valuable resource in the field of computational chemistry.

Molecules_Dataset_Collection is a curated collection of datasets containing molecular structures and their associated physicochemical properties. It aims to facilitate the validation of machine learning models for predicting molecular properties, making it a valuable resource for researchers in computational chemistry and machine learning.

dxtb is a framework that implements the Extended Tight-Binding methods in PyTorch, allowing for efficient computation of molecular properties like energy and forces. It integrates machine learning with quantum chemistry, enabling automatic differentiation and facilitating molecular simulations.