/tools

The 'protein-ligand-benchmark' repository offers a comprehensive dataset designed for testing parameters and methods of free energy calculations in protein-ligand interactions. It includes detailed metadata for various protein targets and ligands, facilitating research in molecular property prediction and computational chemistry.

Matbench Discovery is an evaluation framework that ranks machine learning models on tasks related to high-throughput discovery of stable inorganic crystals. It predicts material properties such as thermodynamic stability and thermal conductivity, providing insights for building large-scale materials databases.

PocketGen is a tool that generates full-atom ligand-binding protein pockets using generative models. It benchmarks its performance against established datasets like CrossDocked and Binding MOAD, providing processed datasets for training and evaluation of pocket generation methods.

PoseBench is a comprehensive benchmarking tool designed for evaluating protein-ligand structure prediction methods. It facilitates the comparison of various inference methods and provides datasets for benchmarking, making it a valuable resource in computational chemistry and molecular biology.

ProteinInvBench is an open-source project that benchmarks structure-based protein design methods. It integrates various models, datasets, and evaluation metrics into a unified framework, facilitating the analysis and development of protein design algorithms.

Dockstring is a Python package designed for easy molecular docking, allowing users to dock molecules from SMILES strings. It includes a highly-curated dataset and realistic benchmark tasks to aid in drug discovery efforts.

FLEXS is an open-source environment for developing and comparing algorithms for biological sequence design. It allows users to explore fitness landscapes and implement exploration algorithms to optimize sequences based on model-guided predictions.

DrugOOD is a dataset curator and benchmark tool designed for AI-aided drug discovery, focusing on generating datasets for ligand and structure-based affinity prediction. It supports various noise levels and domain annotations, making it a valuable resource for researchers in molecular property prediction.

DeeplyTough is a tool designed for learning structural comparisons of protein binding sites using deep learning techniques. It provides built-in support for several benchmark datasets and allows users to evaluate custom datasets, making it a valuable resource for drug discovery and protein design.

FAPLM is an efficient PyTorch implementation of state-of-the-art protein language models, designed to optimize memory usage and inference time. It supports various protein sequence tasks and can be utilized for protein design and benchmarking against official implementations.

IntelliFold is a controllable foundation model that predicts the structures of biomolecules, particularly proteins. It provides a framework for evaluating its performance against other leading methods and offers a server for convenient predictions.

FLAb is a dataset designed for training and benchmarking AI models in therapeutic antibody design, offering extensive data on properties such as binding affinity and thermostability. It serves as a centralized resource for researchers in protein design, facilitating the development of optimized antibody candidates.

PINDER is a comprehensive dataset and evaluation resource for protein-protein interactions, aimed at enhancing the training and evaluation of docking algorithms. It includes a large collection of protein structures and associated metadata, making it a valuable resource for researchers in molecular biology and computational chemistry.

ProSST is an advanced hybrid language model designed for directed protein evolution, enabling zero-shot prediction of mutant effects. It utilizes a pre-trained transformer model to analyze protein sequences and structures, making it a valuable tool for protein design and benchmarking in computational biology.

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.

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.

MolRep is a Python library designed for deep representation learning aimed at predicting molecular properties. It includes a comprehensive evaluation of state-of-the-art models across multiple benchmark datasets, facilitating advancements in molecular property prediction.

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.

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.

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.

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.

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.

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.

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.