Tianhao Yu

blatant-why. AI-powered biologics design campaign agent — multi-agent orchestration with BoltzGen, PXDesign, Protenix, and 200+ cloud tools. Antibodies, nanobodies, de novo binders, and beyond.

get-shit-done. A light-weight and powerful meta-prompting, context engineering and spec-driven development system for Claude Code by TÂCHES.

ColabDesign. Making Protein Design accessible to all via Google Colab!

dify. Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack.

ART. Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen3.6, GPT-OSS, Llama, and more!

ModelGenerator. GB.ModelGenerator is a software stack powering the development of an AI-driven Digital Organism (AIDO) by enabling researchers to adapt pretrained models and generate finetuned models for downstream tasks.

foldseek. Foldseek enables fast and sensitive comparisons of large structure sets.

robin. Robin: A multi-agent system for automating scientific discovery

info-nce-pytorch. PyTorch implementation of the InfoNCE loss for self-supervised learning.

AdaTask. AdaTask: A Task-Aware Adaptive Learning Rate Approach to Multi-Task Learning. AAAI, 2023.

gpt-assistants-api-ui. 💬 OpenAI Assistants API chat UI 🛠️ It works easily by setting the ASSISTANT ID 📁 Supports file upload and file download 🏃 Supports Streaming API 🪟 Support to Azure OpenAI

deepchem. Democratizing Deep-Learning for Drug Discovery, Quantum Chemistry, Materials Science and Biology

antibioticsai. Supporting code for the paper "Discovery of a structural class of antibiotics with explainable deep learning"

chemprop_abaucin. Personal branch of chemprop used to predict the antibiotics Abaucin

esmologs. Local homology search powered by ESM-2 language model, foldseek, hhsuite, and hmmer.

simpletransformers. Transformers for Information Retrieval, Text Classification, NER, QA, Language Modelling, Language Generation, T5, Multi-Modal, and Conversational AI

meaningful-protein-representations. Jupyter Notebook

CLIP. CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image

Transformer-M. [ICLR 2023] One Transformer Can Understand Both 2D & 3D Molecular Data (official implementation)

set2gaussian. code repo for Set2Gaussian

CLEAN. CLEAN: a contrastive learning model for high-quality functional prediction of proteins

EVcouplings. Evolutionary couplings from protein and RNA sequence alignments

bert-loves-chemistry. bert-loves-chemistry: a repository of HuggingFace models applied on chemical SMILES data for drug design, chemical modelling, etc.

rdkit. The official sources for the RDKit library

molformer. Repository for MolFormer

chemprop. Message Passing Neural Networks for Molecule Property Prediction

ColossalAI. Making large AI models cheaper, faster and more accessible

meta-learning-for-protein-engineering. Meta learning addresses noisy and under-labeled data in machine learning-guided antibody engineering (https://doi.org/10.1016/j.cels.2023.12.003)

PINNs. PyTorch Implementation of Physics-informed Neural Networks

PINN. Simple PyTorch Implementation of Physics Informed Neural Network (PINN)

Few-Shot-Regression. code for the paper "Few-Shot Regression via Learning Sparsifying Basis Functions

deep-kernel-transfer. Official pytorch implementation of the paper "Bayesian Meta-Learning for the Few-Shot Setting via Deep Kernels" (NeurIPS 2020)

biocatalysis-model. RXN for biochemical reactions

faiss. A library for efficient similarity search and clustering of dense vectors.

proteinfer. Deep networks for protein functional inference

DeepSequence. A generative latent variable model for biological sequence families.

EVmutation. Mutation effects predicted from sequence co-variation

MMseqs2. MMseqs2: ultra fast and sensitive search and clustering suite

combining-evolutionary-and-assay-labelled-data. Python

bio_embeddings. Get protein embeddings from protein sequences

EAT. Embedding-based annotation transfer (EAT) uses Euclidean distance between vector representations (embeddings) of proteins to transfer annotations from a set of labeled lookup protein embeddings to query protein embedding.

EPP. Code for the paper "Enzyme Promiscuity Prediction using hierarchy-informed multi-label classification"

SimCLR. PyTorch implementation of SimCLR: A Simple Framework for Contrastive Learning of Visual Representations

prototypical-networks. Code for the NeurIPS 2017 Paper "Prototypical Networks for Few-shot Learning"

Siamese-Networks-for-One-Shot-Learning. Implementation of Siamese Neural Networks for One-shot Image Recognition

alphafold. Open source code for AlphaFold 2.

imbalanced-learn. A Python Package to Tackle the Curse of Imbalanced Datasets in Machine Learning

evolocity. Evolutionary velocity with protein language models

esm. Evolutionary Scale Modeling (esm): Pretrained language models for proteins

SegLossOdyssey. A collection of loss functions for medical image segmentation

SPGen. Jupyter Notebook

ModAssistant. Simple Beat Saber Mod Installer

Machine-learning-for-proteins. Listing of papers about machine learning for proteins.

FADA-Pytorch. pytorch implement for the paper Few-Shot Adversarial Domain Adaptation

awesome-transfer-learning. Best transfer learning and domain adaptation resources (papers, tutorials, datasets, etc.)

jax-unirep. Reimplementation of the UniRep protein featurization model.

hh-suite. Remote protein homology detection suite.

tape-neurips2019. Tasks Assessing Protein Embeddings (TAPE), a set of five biologically relevant semi-supervised learning tasks spread across different domains of protein biology. (DEPRECATED)

LaTeX-Workshop. Boost LaTeX typesetting efficiency with preview, compile, autocomplete, colorize, and more.

machine-learning-uiuc. 🖥️ CS446: Machine Learning in Spring 2018, University of Illinois at Urbana-Champaign

tape. Tasks Assessing Protein Embeddings (TAPE), a set of five biologically relevant semi-supervised learning tasks spread across different domains of protein biology.

UniRep-analysis. Analysis and figure code from Alley et al. 2019.

UniRep. UniRep model, usage, and examples.

100-Days-Of-ML-Code. 100 Days of ML Coding

networkx. Network Analysis in Python