-
Massachusetts Institute of Technology
- aksub99.github.io
- @AkshaySubraman9
Highlights
- Pro
Stars
Calculate Root-mean-square deviation (RMSD) of two molecules, using rotation, in xyz or pdb format
A generative model for programmable protein design
A text-guided diffusion model for crystal structure generation
Official implementation of MatterGen -- a generative model for inorganic materials design across the periodic table that can be fine-tuned to steer the generation towards a wide range of property c…
Official repository for our work on micro-budget training of large-scale diffusion models.
A python module for manipulating cartesian and internal coordinates.
cuEquivariance is a math library that is a collective of low-level primitives and tensor ops to accelerate widely-used models, like DiffDock, MACE, Allegro and NEQUIP, based on equivariant neural n…
GFlowNet library specialized for graph & molecular data
DFTB+ general package for performing fast atomistic simulations
Timewarp is a research project using deep learning to accelerate molecular dynamics simulation.
Official repository for the Boltz-1 biomolecular interaction model
MatterSim: A deep learning atomistic model across elements, temperatures and pressures.
Estimates the size of a PyTorch model in memory
An SE(3)-invariant autoencoder for generating the periodic structure of materials [ICLR 2022]
Crystal graph convolutional neural networks for predicting material properties.
[NeurIPS 2023] The implementation for the paper "Crystal Structure Prediction by Joint Equivariant Diffusion"
Riemannian Adaptive Optimization Methods with pytorch optim
This repository is the official code source of PPFlow: Target-Aware Peptide Design with Torsional Flow Matching (ICML2024)
code for "Riemannian Flow Matching on General Geometries".
Code for “FlowMM Generating Materials with Riemannian Flow Matching” and "FlowLLM: Flow Matching for Material Generation with Large Language Models as Base Distributions"
TorchCFM: a Conditional Flow Matching library
Example scripts using the CSD Python API
A concise and easy-to-customize reimplementation of "ChemProp" (Yang et al, 2019) in PyTorch Geometric.
A library for building equivariant neural networks and a zoo of implementations & examples.
Graph Neural Network Library for PyTorch