/tools

HoloBench is a benchmarking tool for discrete sequence optimization algorithms, specifically designed for biophysical applications. It allows users to optimize sequences using evolutionary strategies, making it relevant for protein design and optimization tasks.

Syndirella is a tool designed for generating and scoring synthetically tractable elaborations of molecules derived from fragment screens. It utilizes retrosynthetic analysis and energy minimization to produce viable synthetic routes for small molecules.

The ProteinLM-TDG2-Mutation repository provides code for optimizing a uracil-N-glycosylase variant using protein language models. It facilitates the generation of mutations and benchmarking of models in the context of programmable base editing.

MSIBI is a Python package designed for managing and running coarse-grain potential optimizations through the MultiState Iterative Boltzmann Inversion method. It facilitates the optimization of both intra-molecular and inter-molecular potentials, making it a valuable tool for molecular dynamics simulations.

MoleculeMO is a tool for multiobjective de novo drug design that utilizes recurrent neural networks to generate and optimize molecules based on various properties. It includes data preprocessing, model training, and validation of generated molecules for their pharmacokinetic properties.

The Flexible Topology project develops a machine learning-based tool for dynamically designing potential drug molecules. It utilizes PyTorch to create models that predict molecular structures and poses, and incorporates molecular dynamics simulations to optimize these designs toward drug-like candidates.

Hotpot is a Python package designed to facilitate communication among various chemical and materials calculation tools. It integrates deep learning with traditional cheminformatics to predict molecular properties, generate new molecules, and optimize experimental conditions.

ChemBounce is a Python tool that facilitates scaffold hopping by generating new molecular structures based on input SMILES. It uses pre-computed fingerprints for efficient similarity searches and allows users to customize scaffold databases for enhanced performance.

De-Novo-Drug-Design is a tool that utilizes Deep Reinforcement Learning to optimize the permeation of drugs across the blood-brain barrier. It aims to facilitate the design of new drug candidates by improving their molecular properties.

PRO-LDM is a framework that utilizes a conditional latent diffusion model to design and optimize protein sequences. It enables the generation of natural-like sequences with tailored properties, making it a valuable tool for protein engineering and molecular design.

Conformer-Search is a workflow designed for minimum energy conformer search of molecules using force field optimization methods like UFF and MMFF94. It allows users to import molecules from SMILES, generate conformers, optimize them, and select the minimum energy conformer for further analysis.

GA4AMOEBA is a genetic algorithm program designed to optimize parameters of the AMOEBA polarizable force field. It is intended for use in molecular simulations, particularly in high-performance computing environments.

moo-denovo is a tool for automated de novo design of drug-like molecular libraries, leveraging deep learning and multi-objective optimization techniques. It allows users to optimize molecular descriptors and generate new molecular structures based on specified criteria.

MCHammer is a Monte Carlo-based molecular optimizer that focuses on optimizing the lengths of specified bonds in molecules towards target values. It employs a simple Metropolis Monte-Carlo algorithm to navigate the potential energy surface defined by bonded and nonbonded interactions.

QSARtuna is a library for building predictive QSAR models with optimized hyperparameters using machine learning. It facilitates the optimization of molecular descriptors and algorithms to enhance the accuracy of molecular property predictions.

ProteinTuneRL is a framework designed for optimizing protein sequences using infilling language models and reinforcement learning. It specifically supports antibody design by modifying regions of protein sequences to enhance properties like stability and binding affinity.

The 'idp-design' repository provides tools for optimizing intrinsically disordered proteins by simulating their properties and designing sequences that meet specific functional criteria. It includes various optimization examples, such as targeting the radius of gyration and designing binders for specific substrates.

This tool provides a pipeline for designing and optimizing single chain variable fragment (scFv) antibodies targeting specific peptides and histone modifications. It automates the process of identifying CDR regions and optimizing antibody frameworks using AI models.

OptADMET is a webserver designed for ADMET optimization in drug discovery, providing a platform to analyze and optimize compounds based on 32 important ADMET properties. It utilizes a large database of experimental data and transformation rules to guide medicinal chemists in lead optimization.

The tqchem library is a Python tool designed for efficient manipulation and optimization of molecular structures. It allows users to perform high accuracy conformer optimization and convert molecular data formats, facilitating molecular design and analysis.

TorchMMFF94 provides a PyTorch implementation of the MMFF94 force field, enabling molecular energy minimization both in isolation and in the context of protein pockets. It offers a simple interface for testing and running examples related to molecular optimization.

This repository contains implementations for protein structure prediction using various optimization techniques, including molecular dynamics simulations and genetic algorithms. It aims to explore different approaches to improve the accuracy and efficiency of predicting protein folding.

QRCI is a tool that calculates the Quantitative Ring Complexity Index, which profiles the topology and diversity of ring systems in molecules. It is useful for molecular design and optimization by providing insights into the complexity and characteristics of chemical structures.

This repository contains designs and evaluations for protein binders created during the AdaptyvBio competition. It utilizes various tools and models, including AlphaFold, to generate and assess the stability and binding potential of protein designs.