Open-source alternatives to Alphafold

Biopython is a bioinformatics library for Python providing tools to parse, manipulate, and analyze biological sequences, molecular structures, and phylogenetic trees. It serves as a biological sequence parser for genomic and proteomic data across multiple industry-standard file formats and acts as an interface for querying biological data and citations from NCBI Entrez repositories. The project distinguishes itself through specialized toolkits for protein structure analysis and phylogenetic tree construction. It includes a protein structure analyzer for processing PDB and mmCIF files to calcu

This project is a collection of pretrained transformer protein language models designed for sequence embedding, structure prediction, variant effect estimation, and generative inverse folding. It provides a framework for transforming amino acid sequences into high-dimensional numerical vectors and predicting biological properties through these embeddings. The system includes a generative model for inverse folding that designs amino acid sequences to fit a specific target protein backbone structure. It also features tools for protein variant analysis that use zero-shot prediction to estimate t

This project provides a comprehensive educational curriculum and research resource for deep learning, focusing on the theoretical and technical foundations of neural network implementation. It serves as a structured academic guide for building and training complex models from scratch, covering the essential mathematical primitives, computational graph construction, and automatic differentiation mechanisms required for modern machine learning. The repository distinguishes itself through its extensive coverage of generative modeling and specialized neural architectures. It includes practical im

This project is a collection of educational notebooks and computational workflows designed for cheminformatics and molecular data science. It provides a structured environment for processing chemical structures, performing scaffold identification, and executing reaction enumeration through standardized data representations. The toolkit distinguishes itself by integrating statistical clustering and visualization techniques to interpret chemical diversity within large datasets. It supports advanced research workflows by enabling structure-activity relationship analysis and the evaluation of pro

This project is a computer vision library designed for facial landmark detection and alignment. It provides a framework for identifying and mapping specific points on a human face in both two-dimensional and three-dimensional space, enabling the normalization of facial geometry and orientation across diverse images. The system utilizes a deep learning approach to extract precise facial coordinates, supporting tasks such as expression analysis and geometric modeling. By employing a stacked hourglass architecture, the model performs multi-stage feature refinement to capture spatial relationship

BoltzDesign1 is a molecular design tool powered by the Boltz model for designing protein-protein interactions and biomolecular complexes.

This repository presents an approach for ligand discovery for protein bindign pockets, by combining Monte Carlo (MC) simulations with the model Chai-1 (Chai-1 github, Chai-1 technical report). There are two types of simulations presented here: - The basic simulation explores chemical space by…

Structure prediction and design of proteins with noncanonical amino acids.

Fast and accurate protein structure prediction

Official repository for DeepAb: Antibody structure prediction using interpretable deep learning. The code, data, and weights for this work are made available under the Rosetta-DL license as part of the Rosetta-DL bundle.

The code for FvHallucinator is made available under the Rosetta-DL license as part of the Rosetta-DL bundle.

English | 简体中文

DSPy is a declarative programming framework designed for building complex language model applications. It treats model interactions as modular, composable programs, allowing developers to define task logic through typed class schemas rather than relying on manually written prompts. By organizing workflows into hierarchical, reusable Python objects, the framework enables the construction of sophisticated AI systems that manage state and execution flow independently. The framework distinguishes itself through an automated optimization engine that iteratively refines prompt instructions and few-