/tools

DeepCriticalLearning implements various deep learning methods for protein function prediction and classification. It provides tools for training models that can be used in the context of protein design and analysis.

The AlphaFold MCP Server is a comprehensive tool that allows users to access and analyze protein structure predictions from the AlphaFold Protein Structure Database. It offers features such as structure retrieval, confidence score analysis, and batch processing for multiple proteins, making it valuable for researchers in molecular biology and bioinformatics.

Knowledge-based-BERT (K-BERT) is a model that utilizes BERT architecture to extract molecular features and predict properties of molecules. It employs various pre-training tasks to enhance its ability to generalize across different representations of molecular data.

The SIMG repository introduces a novel approach to molecular representation by infusing stereoelectronic effects into molecular graphs. This enhances the performance of molecular machine learning models and enables the evaluation and design of complex molecular systems, including proteins.

GSCDB is a comprehensive benchmark database containing 137 datasets with detailed molecular properties such as reaction energies and barrier heights. It serves as a platform for validating density functional approximations and supports the development of machine-learned functionals in computational chemistry.

LeMat-GenBench is a comprehensive benchmarking framework designed to evaluate crystal generative models across various metrics such as validity, diversity, and stability. It facilitates the assessment of material generation models, making it relevant for molecular design and optimization in computational chemistry.

Chemprop benchmarking scripts and data provide a framework for evaluating the performance of Chemprop, a message passing neural network designed for predicting molecular properties. The repository includes various benchmarks and datasets that facilitate the assessment of molecular property prediction models.

pylj is a teaching utility designed for classical atomistic simulations, primarily aimed at educational purposes in computational chemistry. It provides tools for running simulations and is intended for use within Jupyter notebooks, making it accessible for teaching and learning.

The OpenMM Example Plugin demonstrates how to write a plugin for the OpenMM molecular simulation toolkit. It includes a specific force implementation and supports various platforms like OpenCL and CUDA, facilitating molecular dynamics simulations.

Gau2Grid is a computational tool designed for fast computation of Gaussian functions and their derivatives on a grid. It offers various algorithms for optimization and can be utilized in molecular simulations and quantum chemistry applications.

`allegro-pol` is an extension of the `nequip` framework designed for predicting the electric response of materials, including properties like polarization and polarizability, using machine learning models. It provides tools for training and processing data related to these predictions.

The ccpbiosim-2023 repository provides educational materials for a workshop on molecular simulations and force fields, including notebooks for working with protein-ligand systems and other molecular types. It serves as a tutorial resource for users interested in molecular modeling and simulation techniques.

EquivariantMultipoleGNN is a repository that implements a Graph Neural Network model designed to predict atomic multipoles, which are essential for calculating electrostatic potentials in molecular systems. The model is based on research published in a scientific paper and utilizes a specific dataset for training.

HELM-GPT is a tool designed for the de novo generation of macrocyclic peptides using a generative pre-trained transformer model. It allows users to train models and generate new peptide structures, contributing to drug discovery efforts.

BLIP is a framework for training and fine-tuning machine learning interatomic potentials, providing reliable uncertainty estimates and minimal computational overhead. It allows users to convert existing machine learning interatomic potentials into Bayesian models, enhancing their robustness and interpretability.

vcmsa is a Python library designed for vector clustering of Multiple Sequence Alignments (MSA) using protein language models. It allows for the alignment of protein sets that have conserved functions or structures but poorly conserved sequences, making it useful for protein design and analysis.

MDVWhole is a tool designed for density-based object completion in molecular simulations, specifically handling periodic boundary conditions. It utilizes a graph-based approach to efficiently manage memory while completing molecular structures across boundaries.

MetaScreener is a collection of scripts that integrates various molecular modeling and docking programs to facilitate virtual screening and analysis of molecular interactions. It automates the processing of data and results, making it a valuable tool for computational chemistry and drug discovery.

CodonMPNN is a tool for organism-specific and codon optimal inverse folding, producing codon sequences based on trained models from the AlphaFold database. It facilitates the design of codon-optimized sequences for proteins, making it relevant in the field of molecular biology.

MoBioTools is a versatile toolkit designed to automate the setup of quantum mechanics/molecular mechanics (QM/MM) calculations from molecular dynamics trajectories. It generates input files for various quantum chemistry programs based on MD trajectories, facilitating advanced molecular simulations.

HyMD is a massively parallel Python package for Hamiltonian hybrid particle-field molecular dynamics simulations of coarse-grained bio- and soft-matter systems. It allows for various types of molecular simulations, including canonical and filtered density Hamiltonian simulations, and supports accurate modeling of protein conformational dynamics.

The RDKit MCP Server allows language models to interact with RDKit through natural language, providing agent-level access to its functions. It facilitates molecular property prediction and manipulation, making it a valuable tool for drug discovery and cheminformatics applications.