/tools

GraphChem is an open-source Python package designed for constructing graph-based machine learning models aimed at predicting chemical properties, particularly for fuels. It utilizes advanced techniques such as graph neural networks to facilitate accurate predictions in computational chemistry.

The PaccMann^RL repository provides a pipeline for predicting drug sensitivity and generating hit-like anticancer molecules using reinforcement learning. It includes tools for training multimodal predictors and generative models for both omic profiles and molecular structures.

CG2AT is a tool designed for converting coarse-grained molecular models into atomistic representations, facilitating further molecular dynamics simulations. It allows users to input coarse-grained structures and outputs the necessary files for atomistic simulations, enhancing the analysis and refinement of molecular systems.

structRFM is an open-source structure-guided RNA foundation model designed for robust structural and functional inference. It integrates sequence and structural knowledge to achieve state-of-the-art performance in RNA secondary and tertiary structure prediction, as well as function prediction tasks.

The Point Edge Transformer (PET) is a graph neural network designed for interatomic machine learning potentials, achieving state-of-the-art performance on various datasets. It facilitates molecular simulations by providing a framework for fitting energies and forces, making it useful for molecular dynamics applications.

VESPA is a tool that predicts the effects of single amino acid variants (SAVs) using embeddings from the Protein Language Model ProtT5. It provides a multistage pipeline for generating predictions based on protein sequences, making it useful for understanding protein mutations and their impacts.

CoPRA is a tool designed for predicting protein-RNA binding affinity using pretrained sequence models. It includes datasets for training and evaluation, as well as model weights for users to implement and fine-tune their predictions.

BACPI is a bi-directional attention neural network designed for predicting compound-protein interactions and binding affinities. It allows users to classify interactions and predict continuous binding affinity values based on molecular data.

PlaNet is a geometric deep learning tool designed to predict population responses to drugs by utilizing a clinical knowledge graph. It integrates disease biology, drug chemistry, and population characteristics to forecast drug efficacy and safety in clinical trials.

HOOMD-TF is a plugin that allows the use of TensorFlow within the HOOMD-blue molecular dynamics engine, facilitating online machine learning during simulations. It supports various tasks such as calculating forces and collective variables, making it a valuable tool for molecular simulations and machine learning integration.

ESM-Ezy is a tool designed for training and inference on protein sequences using a pre-trained model. It facilitates the retrieval and analysis of candidate sequences, making it relevant for applications in protein design and bioinformatics.

OpenMM TensorFlow is a plugin that enables the definition of forces in molecular simulations using neural networks. It allows users to create TensorFlow graphs that compute forces and energy based on particle positions, facilitating advanced molecular dynamics simulations.

PyPLIF-HIPPOS is an advanced molecular interaction fingerprinting tool that enhances the analysis of docking results from AutoDock Vina and PLANTS. It generates customized interaction bitstrings from the 3D coordinates of ligands and proteins, facilitating molecular docking post-analysis.

PDBench is a dataset and software package that evaluates fixed-backbone sequence design algorithms for proteins. It includes a benchmark set of protein structures and provides metrics for assessing the performance of various design models.

DEL QSAR is a tool for predicting enrichment from molecular structures using DNA-encoded libraries and machine learning. It includes scripts for training and evaluating models, optimizing hyperparameters, and visualizing results, making it relevant for molecular property prediction.

This repository provides a variational autoencoder for generating and optimizing molecular structures using SMILES data. It includes preprocessing steps, training procedures, and notebooks for visualizing and analyzing the learned latent space of molecular representations.

PyMOL-MCP connects PyMOL with Claude AI, enabling users to control molecular visualization and perform structural analyses through natural language commands. This integration facilitates interactive exploration of molecular structures and enhances the usability of PyMOL for structural biology applications.

QM9nano4USTC is a repository that introduces the QM9 dataset, which contains information on 130,462 organic molecules and their properties. It includes preprocessed features for molecular property prediction, making it useful for data-driven experiments in computational chemistry.

Stspeckmol is a Streamlit component designed for creating and visualizing Speck molecular structures within a web application. It allows users to easily integrate molecular visualization into their Streamlit apps, making it a useful tool for bioinformatics and molecular biology applications.

Trident Chemwidgets is a set of Jupyter widgets that enhance data visibility in cheminformatics and molecular machine learning. It allows users to interact with molecular datasets through various visualization tools, including histograms and scatter plots, as well as an interactive molecule viewer.

ChemInformatics Model Explorer (CIME) is a web application that enables users to explore chemical compounds through interactive visualizations. It supports the analysis of molecular properties and allows users to upload and visualize datasets, making it a valuable tool for cheminformatics.

Modof is a software implementation for optimizing molecules through fragment-based generative models. It allows users to train models on pairs of molecules to generate optimized structures based on specific properties, making it a valuable tool in molecular design and optimization.

AlphaPPImd utilizes transformer-based generative neural networks to explore and generate new conformations of protein-protein complexes. It enhances molecular dynamics simulations by providing a method to sample unsampled conformations, thereby aiding in the analysis of protein interactions.