/tools

GPT_protein_design is a pipeline for de novo protein design that utilizes a GPT-based generator and a transfer learning-based discriminator. It aims to generate novel proteins, such as antimicrobial peptides, by leveraging advanced machine learning techniques.

ProfileBFN is an implementation for steering protein family design through Profile Bayesian Flow. It allows for the generation and evaluation of protein sequences, making it a valuable tool in the field of molecular design.

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.

This repository provides an introduction to small molecule drug design using structure-based techniques and interactive Jupyter notebooks. It covers ligand-based analysis, generative design with REINVENT4, and docking to analyze interactions with the Zika virus protease.

Rxitect is a de-novo drug design library that utilizes deep reinforcement learning and generative flow networks to create molecules with a focus on synthetic accessibility. It aims to improve the practicality of generated molecules by incorporating retrosynthesis-aware models into the design process.

This repository contains code for evaluating reinforcement learning techniques applied to transformer-based molecular design. It includes predictive models and configurations for running experiments related to molecular generation and optimization.

TrDesign_partialhall is a tool that supports the design of protein structures with partial hallucination capabilities. It allows users to modify and generate protein sequences based on provided PDB files, facilitating the optimization and design of molecular structures.

TED-Gen is a framework designed for generating and analyzing atomic structures at van der Waals interfaces using a generative model. It utilizes experimental and simulated data to create high-quality training datasets and offers tools for training models to analyze stacking patterns in materials.