awesome-biochem-ai
github.com/ratthachat/awesome-biochem-ai ↗Curated list on Deep Transformers Applications on Biology and Chemistry
Use this list with your AI agent
Add the Context Awesome MCP server to Claude, Cursor, or any MCP client, then ask:
"Show me 3d resources from awesome-biochem-ai"
Installation instructions →What's inside
Molecule Retrosynthesis Pathways
- AiZynthFinder (2020)
- BioNavi-NP (2022)
- Graph-to-Graph Retrosynthesis (2020)
ICML 2020
- RetroXpert (2020)
Information Leak as noted in the Github repo.
- Root-aligned SMILES (2022)
Libraries on Molecule AI
Property and Interaction Prediction
Enzymatic Reaction
Protein-Protein Docking
Molecule Generation
- Equivariant Diffusion for Molecule Generation in 3D (ICML 2022)3D
- HGraph2Graph (ICML 2020)Graph-based Motif-level
An improved framework over JT-VAE by the same authors. The differences are (1) HGraph2Graph allows to use large motifs where as JT-VAE uses only small motifs such as rings. (2) HGraph2Graph is cleverly designed to avoid combinatorial problem in molecule generation e.g. it remembers specific atoms in each motif vocabulary which can be connect; hence, it avoids considering all connection possibilities in each motif. For details see this
- JunctionTree VAE (ICML 2018)Graph-based Motif-level
A classic work in graph-based molecule generation in tree-like manner. Unlike atom-level approaches, it can generate a ring into a molecule in one-step.
- MoLeR (ICLR 2022)Graph-based Motif-level
Molecule Similarity Metrics
- Graph Matching Network (ICML 2019)
- Levenshtein
- MAP4 (2020)
- maximum common substructure
m_i|$ is the total number of atoms of $m_i$. In the figure below, MCS between two molecules is draw as ablack backbone where differences between the two molecules are highlight in red. MCS distance is intuitive to interpret.
- MCS-distance
Showing a sample of 41 resources. View the full list on GitHub →