/tools

The smina-docking-benchmark repository provides tools for evaluating molecular docking models and optimizing generated molecules. It includes benchmarks for various models and allows users to generate and assess molecules based on their docking scores.

LaMBO is a tool that accelerates Bayesian optimization for biological sequence design using denoising autoencoders. It allows for efficient exploration of protein sequences to optimize properties such as stability and surface area, outperforming traditional genetic algorithms in its evaluations.

BO-ICL is a tool that utilizes Bayesian optimization and in-context learning to predict molecular properties and generate new molecular data. It allows users to perform regression with uncertainties and supports inverse design for proposing new molecular structures based on desired properties.

DeepFMPO is a tool designed for optimizing drug design through deep reinforcement learning. It allows users to generate and modify molecules based on lead compounds, facilitating the exploration of new drug candidates.

Delete is a tool for deep lead optimization that generates new molecular structures by utilizing a structure-aware network and deleting specific fragments from lead compounds. It is designed to assist in drug discovery by suggesting new ligands that fit within protein pockets.

Optimas is a framework designed for the end-to-end optimization of compound AI systems, utilizing Globally Aligned Local Reward Functions to enhance the performance of various components. It supports the generation of preference data, training of reward models, and optimization of system variables, making it applicable to molecular design and optimization tasks.

MOFDiff is a diffusion model designed for generating coarse-grained structures of metal-organic frameworks (MOFs). It includes functionalities for optimizing these structures based on specific properties and simulating their behavior in gas adsorption scenarios.

PepINVENT is a generative reinforcement learning framework for designing peptides, including both natural and non-natural amino acids. It allows users to specify objectives for peptide generation and optimization, making it applicable for peptide-based drug design and development.

Wazy is a tool for Bayesian optimization of amino acid sequences, allowing users to design peptides that bind to specific proteins. It utilizes pretrained models to predict the properties of sequences and optimize their design through an interactive interface.

Origin-1 is a generative AI platform designed for the de novo design of antibodies targeting novel epitopes. It includes data on binding affinity and optimization results, making it a valuable resource for antibody development in molecular biology.

This repository implements a machine learning-guided framework for protein design through directed evolution. It utilizes large language models to predict fitness scores and generate novel protein sequences, streamlining the optimization process in protein engineering.

Swarm-CG automates the optimization of bonded terms in MARTINI-based coarse-grained molecular models by using a reference all-atom trajectory. It includes modules for evaluating parametrization, optimizing parameters, and monitoring the optimization process, making it a valuable tool for molecular modeling and simulations.

Modof is a tool designed for molecule optimization through fragment-based generative models. It allows users to train models on pairs of molecules to generate new molecules with improved properties, making it useful for applications in drug discovery and molecular design.

AliDiff implements a method for aligning target-aware molecule diffusion models with exact energy optimization. It provides tools for data generation, training, and evaluation, including molecular docking capabilities, making it useful for molecular design and drug discovery applications.

moldrug is a Python package that focuses on drug-oriented optimization within the chemical space. It employs a Genetic Algorithm as a search engine and integrates with the CReM library for generating chemical structures.

LatentDE is a tool for protein sequence design that utilizes a latent-based directed evolution approach. It employs a variational autoencoder to optimize biological functionalities by exploring high-fitness mutants in the latent space, making it suitable for protein engineering tasks.

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.

FRAME is a tool for fragment-based molecular expansion that utilizes geometric deep learning techniques to aid in structure-based ligand design. It allows for the addition of molecular fragments to a seed ligand, optimizing the design process for drug discovery.

DeepBioisostere is a tool that utilizes deep learning to perform bioisosteric replacements, optimizing various molecular properties such as molecular weight and logP. It allows users to generate and optimize molecules based on specified criteria, making it relevant for molecular design and property prediction.

LEADD is a tool that employs a Lamarckian evolutionary algorithm for the design and optimization of molecules in drug discovery. It utilizes a population-based approach to evolve molecular structures by combining fragments and optimizing them based on user-defined scoring functions.

GraphRelax is a drop-in replacement for Rosetta Relax that utilizes graph neural networks for residue repacking and design. It combines LigandMPNN for sequence design with OpenMM for energy minimization, enabling efficient protein structure optimization.

This repository contains a tool for optimizing crystal structures using machine learning models. It allows users to perform structure optimization and single point evaluations, making it useful for researchers in materials science and computational chemistry.

Chemtools is a Python toolbox that facilitates advanced computations in quantum chemistry, enabling users to manipulate and optimize basis sets for various electronic structure programs. It supports computations with popular software like Dalton, Gamess-US, and MolPro, making it a valuable resource for computational chemists.

PMGen is a comprehensive pipeline designed for predicting peptide-MHC complex structures and optimizing peptide sequences. It utilizes advanced techniques like AlphaFold for structure prediction and includes features for iterative peptide optimization and mutation screening.