AI for science topic
AI for science is the application of machine learning and artificial intelligence methods to accelerate research and discovery across scientific domains. It encompasses work in protein structure prediction, climate modeling, drug discovery, materials design, and particle physics, among others.
Rather than replacing traditional scientific methods, AI for science augments them by learning patterns from experimental and simulation data to generate hypotheses, design experiments, and build fast surrogate models. Landmark examples include AlphaFold for protein structure prediction, GraphCast for weather forecasting, and FermiNet for quantum chemistry.
SciMLBenchmarks.jl
Scientific machine learning (SciML) benchmarks, AI for science, and (differential) equation solvers. Covers Julia, Python (PyTorch, Jax), MATLAB, R
Mol-Instructions
[ICLR 2024] Mol-Instructions: A Large-Scale Biomolecular Instruction Dataset for Large Language Models
graph-gpt
Graph Learning with Generative Pretrained Transformers
DrugAssist
DrugAssist: A Large Language Model for Molecule Optimization
chemgymrl
targetdiff
The official implementation of 3D Equivariant Diffusion for Target-Aware Molecule Generation and Affinity Prediction (ICLR 2023)
equiformer
[ICLR 2023 Spotlight] Equiformer: Equivariant Graph Attention Transformer for 3D Atomistic Graphs
equiformer_v2
[ICLR 2024] EquiformerV2: Improved Equivariant Transformer for Scaling to Higher-Degree Representations
Awesome-LWMs
🌍 A Collection of Awesome Large Weather Models (LWMs) | AI for Earth (AI4Earth) | AI for Science (AI4Science)