/tools

DrugGPT is a tool that employs a GPT-based strategy to design potential ligands for specific proteins. It utilizes deep learning to explore chemical space and optimize ligand design, enhancing the drug development process.

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.

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.

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.

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.

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.

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.

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.

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.

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.

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.

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.

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.

DrugHIVE is a software tool that implements a deep hierarchical variational autoencoder for structure-based drug design. It allows for the generation and optimization of ligands, making it a valuable resource in the field of molecular design and drug discovery.

PepGLAD is a tool for full-atom peptide design that utilizes geometric latent diffusion models to co-design peptide sequences and structures. It supports binding conformation generation and provides datasets for benchmarking the models.

SELFormer is a molecular representation learning tool that utilizes SELFIES language models to generate high-quality molecular embeddings. It is pre-trained on drug-like compounds and fine-tuned for various molecular property prediction tasks, making it a valuable resource for drug discovery and cheminformatics.

APPT is a state-of-the-art model designed to predict protein-protein binding affinity using transformer architectures and the ESM protein language model. It supports drug discovery and protein engineering by providing precise predictions based on protein sequence pairs.

BitBIRCH-Lean is a memory-efficient implementation of the BitBIRCH clustering algorithm designed for high-throughput clustering of large molecular libraries. It allows users to generate molecular fingerprints from SMILES files and cluster them efficiently, making it a valuable tool for drug discovery and cheminformatics applications.

MEAN is a tool for conditional antibody design utilizing a multi-channel equivariant attention network. It provides functionalities for redesigning antibody CDRs and optimizing binding affinities, making it a valuable resource in the field of molecular design and drug discovery.

This repository provides code for predicting molecular properties using neural networks on raw molecular graphs. It includes implementations of various models designed for bioactivity and physical-chemical property prediction, making it a valuable resource for drug discovery applications.

USearchMolecules is a comprehensive dataset containing over 7 billion small molecules, designed for efficient searching and clustering of molecular structures. It utilizes various molecular fingerprints and is aimed at facilitating drug discovery and cheminformatics research.

This repository implements a method for predicting drug-drug interactions by utilizing knowledge graph embeddings and a convolutional-LSTM network. It extracts features from various drug databases and trains models to predict potential interactions, making it a valuable tool in the field of drug discovery.