12 open-source projects similar to aqlaboratory/genie2, ranked by how many features they have in common. Compare stars, activity and what each one does to find the best Genie2 alternative.
This repository contains the source code accompanying the paper:
This repository provides the implementation code for our ICML paper. Below provides an illustration of the sampling process.
Feynman-Kac guided protein design using RFdiffusion. This package implements particle filtering to optimize design objectives during the diffusion process.
B. Ni, D.L. Kaplan, M.J. Buehler, ForceGen: End-to-end de novo protein generation based on nonlinear mechanical unfolding responses using a language diffusion model. Sci. Adv. 10, eadl4000 (2024). DOI: 10.1126/sciadv.adl4000
This repository provides an interface for solving motif scaffolding problems with an unconditional diffusion model as a prior. It defines inverse problems for a variety of tasks and solves them by sampling the posterior via sequential Monte Carlo. This permits conditional sampling without…
This is the official code repository of the paper "TopoDiff: Improving Diffusion-Based Protein Backbone Generation with Global-Geometry-aware Latent Encoding".
We present a diffusion model for generating novel protein backbone structures. For more details, see our preprint on arXiv. We also host a trained version of our model on HuggingFace spaces and at SuperBio so you can get started with generating protein structures with just your browser!
FrameFlow is a SE(3) flow matching method for protein backbone generation and motif-scaffolding. The method is described in two papers:
Generation of Four Helix Backbones and Sequence Design via Deep Learning Pipeline
A text-to-protein backbone diffusion model. 1. Build Conda environment Run command: ` conda env create -n text2protein --file env.yaml `
Science: Built-in safeguards might stop AI from designing bioweapons - Nature Biotechnology: Watermarking generative AI for protein structure - Princeton AI Lab: Deep Dive Series: Building Biosecurity Safeguards into AI for Science