/tools

DEEPScreen is a virtual screening tool that utilizes deep convolutional neural networks to predict drug-target interactions based on 2-D structural representations of compounds. It is aimed at enhancing early-stage drug discovery by providing accurate predictions from compound images.

OpenFermion-PySCF is a plugin that allows the electronic structure package PySCF to interface with OpenFermion, facilitating quantum simulations of fermionic systems. It is designed for researchers working in quantum chemistry and molecular simulations.

AbNumber is a Python library that offers convenience APIs for antibody numbering and alignment using the ANARCI method. It allows users to identify CDR regions, perform sequence alignments, and humanize antibodies through CDR grafting.

SynFlowNet is a GFlowNet model that generates molecules based on chemical reactions and available building blocks, allowing for the design of diverse and novel molecules while considering synthesis constraints. It includes functionalities for training the model and sampling molecules guided by user-defined rewards.

Vina-GPU 2.0 is a software tool that accelerates AutoDock Vina and its derivatives for molecular docking using GPU technology. It supports various docking methods and provides a graphical user interface for ease of use in virtual screening applications.

Interformer is a neural network designed for predicting protein-ligand interactions, specifically generating energy functions and scoring docking poses. It utilizes contrastive learning to assess the quality of docking poses and predict binding affinities, making it a valuable tool in drug discovery.

Alchemy is a repository that offers tools for predicting molecular properties using graph neural networks. It includes a dataset for benchmarking AI models in quantum chemistry and provides implementations for various models like SchNet and MGCN.

Folddisco is a tool for efficiently searching and indexing discontinuous motifs in protein structures across large-scale databases. It allows users to query protein structures for specific motifs, enabling insights into protein function and structure relationships.

RTMScore is a scoring function designed to predict protein-ligand interactions by utilizing residue-atom distance likelihood potentials and graph transformers. It processes proteins and ligands as 3D and 2D graphs, respectively, to calculate interaction probabilities and contributions.

ProGen is an implementation of a language model designed for generating protein sequences, akin to GPT for text. It utilizes deep learning techniques to facilitate the design and generation of proteins, making it a valuable tool in the field of molecular biology.

CDPKit is an open-source cheminformatics software toolkit designed for processing chemical data. It offers features for molecular representation, property prediction, pharmacophore generation, and integration with machine learning libraries, making it a valuable resource for computational drug discovery.

ShakeNBreak is a computational tool designed for defect structure-searching in solid materials, utilizing chemically-guided bond distortions to identify ground-state and metastable structures of point defects. It automates the generation of distorted structures and supports various geometry optimization codes, making it a valuable resource for materials design and analysis.

LobsterPy is a Python package that automates the analysis of bonding information from LOBSTER outputs, providing features for machine learning studies. It allows users to generate plots and summaries of chemical bonding, making it a useful tool in computational materials science.

GradDFT is a JAX-based library that enables the differentiable design and experimentation of exchange-correlation functionals using machine learning techniques. It allows for the training of neural functionals and performing DFT simulations, making it a valuable tool for predicting molecular properties and conducting quantum chemistry simulations.

ESM-GearNet is a codebase for joint representation learning on protein sequences and structures, combining sequence and structure encoders to enhance protein representation. It includes pre-training techniques and is designed for tasks related to protein structure analysis.

PLAPT is a state-of-the-art tool designed for predicting protein-ligand binding affinities, utilizing pretrained transformer models to enhance accuracy and efficiency in drug discovery processes. It allows users to input protein and ligand sequences to obtain binding affinity predictions, making it a valuable resource for researchers in the field.

ByteQC is a high-performance quantum chemistry package that supports various methods for quantum simulations, including mean-field calculations and many-body methods. It is optimized for GPU usage, enabling efficient simulations of complex molecular systems.

GPUSimilarity is a CUDA/Thrust implementation designed for efficient chemical fingerprint similarity searching using GPU acceleration. It integrates with RDKit for fingerprint generation and is intended for high-performance applications in cheminformatics.

PDGrapher is a tool for combinatorial prediction of therapeutic perturbations using causally-inspired neural networks. It leverages chemical datasets to train models that can predict the effects of drug combinations, contributing to the field of drug discovery.

sPyRMSD is a Python tool designed for symmetry-corrected RMSD calculations, which helps in comparing molecular structures. It can be used as a standalone tool or as a module, making it versatile for applications in drug discovery and computational biology.

FLIP is a collection of tasks designed to evaluate the effectiveness of protein sequence representations in modeling protein design aspects. It includes datasets and benchmarks for assessing machine learning models in the context of protein engineering.

CLAMP is a tool designed to enhance activity prediction models in drug discovery by leveraging natural language processing. It predicts relevant molecules based on textual descriptions of bioassays, enabling few-shot and zero-shot learning in the context of molecular properties.

Aboria is a C++ library that facilitates computations over a set of particles in N-dimensional space, enabling the implementation of particle-based numerical algorithms such as Molecular Dynamics and Smoothed Particle Hydrodynamics. It provides data structures and APIs for efficient spatial queries and kernel operator formation, making it suitable for simulations in molecular contexts.

CarsiDock is a deep learning framework that enhances the accuracy of protein-ligand docking and screening by leveraging a large-scale dataset of protein-ligand complexes. It employs innovative architectural designs and pre-training techniques to predict binding poses effectively.