Implementation of Geometric Vector Perceptron, a simple circuit for 3d rotation equivariance for learning over large biomolecules, in Pytorch. Idea proposed and accepted at ICLR 2021

Related tags

Deep Learning deep-learning protein-structure artficial-intelligence biomolecule equivariance
Overview

Geometric Vector Perceptron

Implementation of Geometric Vector Perceptron, a simple circuit with 3d rotation equivariance for learning over large biomolecules, in Pytorch. The repository may also contain experimentation to see if this could be easily extended to self-attention.

Install

$ pip install geometric-vector-perceptron

Functionality

  • GVP: Implementing the basic geometric vector perceptron.
  • GVPDropout: Adapted dropout for GVP in MPNN context
  • GVPLayerNorm: Adapted LayerNorm for GVP in MPNN context
  • GVP_MPNN: Adapted instance of Message Passing class from torch-geometric package. Still not tested.

Usage

import torch
from geometric_vector_perceptron import GVP

model = GVP(
    dim_vectors_in = 1024,
    dim_feats_in = 512,
    dim_vectors_out = 256,
    dim_feats_out = 512
)

feats, vectors = (torch.randn(1, 512), torch.randn(1, 1024, 3))

feats_out, vectors_out = model( (feats, vectors) ) # (1, 256), (1, 512, 3)

With the specialized dropout and layernorm as described in the paper

import torch
from torch import nn
from geometric_vector_perceptron import GVP, GVPDropout, GVPLayerNorm

model = GVP(
    dim_vectors_in = 1024,
    dim_feats_in = 512,
    dim_vectors_out = 256,
    dim_feats_out = 512
)

dropout = GVPDropout(0.2)
norm = GVPLayerNorm(512)

feats, vectors = (torch.randn(1, 512), torch.randn(1, 1024, 3))

feats, vectors = model( (feats, vectors) )
feats, vectors = dropout(feats, vectors)
feats, vectors = norm(feats, vectors)  # (1, 256), (1, 512, 3)

TF implementation:

The original implementation in TF by the paper authors can be found here: https://github.com/drorlab/gvp/

Citations

@inproceedings{
    anonymous2021learning,
    title={Learning from Protein Structure with Geometric Vector Perceptrons},
    author={Anonymous},
    booktitle={Submitted to International Conference on Learning Representations},
    year={2021},
    url={https://openreview.net/forum?id=1YLJDvSx6J4},
    note={under review}
}
You might also like...
PyTorch reimplementation of the Smooth ReLU activation function proposed in the paper
PyTorch reimplementation of the Smooth ReLU activation function proposed in the paper "Real World Large Scale Recommendation Systems Reproducibility and Smooth Activations" [arXiv 2022].

Smooth ReLU in PyTorch Unofficial PyTorch reimplementation of the Smooth ReLU (SmeLU) activation function proposed in the paper Real World Large Scale

Christoph Reich 10 Jan 2, 2023
Seach Losses of our paper 'Loss Function Discovery for Object Detection via Convergence-Simulation Driven Search', accepted by ICLR 2021.
Seach Losses of our paper 'Loss Function Discovery for Object Detection via Convergence-Simulation Driven Search', accepted by ICLR 2021.

CSE-Autoloss Designing proper loss functions for vision tasks has been a long-standing research direction to advance the capability of existing models

Peidong Liu(εˆ˜ζ²›δΈœ) 54 Dec 17, 2022
Neuralnetwork - Basic Multilayer Perceptron Neural Network for deep learning

Neural Network Just a basic Neural Network module Usage Example Importing Module

andreecy 0 Nov 1, 2022
This repo contains the implementation of the algorithm proposed in Off-Belief Learning, ICML 2021.

Off-Belief Learning Introduction This repo contains the implementation of the algorithm proposed in Off-Belief Learning, ICML 2021. Environment Setup

Facebook Research 32 Jan 5, 2023
From Perceptron model to Deep Neural Network from scratch in Python.

Neural-Network-Basics Aim of this Repository: From Perceptron model to Deep Neural Network (from scratch) in Python. ** Currently working on a basic N

Aditya Kahol 1 Jan 14, 2022
[ICLR 2021, Spotlight] Large Scale Image Completion via Co-Modulated Generative Adversarial Networks
[ICLR 2021, Spotlight] Large Scale Image Completion via Co-Modulated Generative Adversarial Networks

Large Scale Image Completion via Co-Modulated Generative Adversarial Networks, ICLR 2021 (Spotlight) Demo | Paper [NEW!] Time to play with our interac

Shengyu Zhao 373 Jan 2, 2023
A PyTorch implementation of Mugs proposed by our paper
A PyTorch implementation of Mugs proposed by our paper "Mugs: A Multi-Granular Self-Supervised Learning Framework".

Mugs: A Multi-Granular Self-Supervised Learning Framework This is a PyTorch implementation of Mugs proposed by our paper "Mugs: A Multi-Granular Self-

Sea AI Lab 62 Nov 8, 2022
An attempt at the implementation of Glom, Geoffrey Hinton's new idea that integrates neural fields, predictive coding, top-down-bottom-up, and attention (consensus between columns)

GLOM - Pytorch (wip) An attempt at the implementation of Glom, Geoffrey Hinton's new idea that integrates neural fields, predictive coding,

Phil Wang 173 Dec 14, 2022
Official Pytorch implementation of 6DRepNet: 6D Rotation representation for unconstrained head pose estimation.
Official Pytorch implementation of 6DRepNet: 6D Rotation representation for unconstrained head pose estimation.

6D Rotation Representation for Unconstrained Head Pose Estimation (Pytorch) Paper Thorsten Hempel and Ahmed A. Abdelrahman and Ayoub Al-Hamadi, "6D Ro

Thorsten Hempel 284 Dec 23, 2022
Comments
  • Adds MPNN wrapper

    Adds MPNN wrapper

    Could you double check it?

    I've tried to follow the original implementation ( https://github.com/drorlab/gvp/ see src/models.py ) but it's weird since they seem to mix the edge_attrs and the node features and return a mix of them, but later they seem to discard them so :man_shrugging: (whereas i only return node features - bc idk how to modify edge_attrs in an easy way -> the aggregation is always node-based)

    opened by hypnopump 3
  • Fixes edge issues and distinguishes between covalent and proximity bonds

    Fixes edge issues and distinguishes between covalent and proximity bonds

    • Gets all covalent bonds for a protein conformation (different than proximity)
    • Reduces unused computations
    • Fixes edges (now undirected graph)
    • Adapts denoising example accordingly (not in reconstruction example yet)
    opened by hypnopump 0
Owner
Phil Wang
Working with Attention. It's all we need.
Phil Wang
GitHub
Geometric Vector Perceptrons --- a rotation-equivariant GNN for learning from biomolecular structure

Geometric Vector Perceptron Implementation of equivariant GVP-GNNs as described in Learning from Protein Structure with Geometric Vector Perceptrons b

Dror Lab 142 Dec 29, 2022
The official implementation of our CVPR 2021 paper - Hybrid Rotation Averaging: A Fast and Robust Rotation Averaging Approach

Graph Optimizer This repo contains the official implementation of our CVPR 2021 paper - Hybrid Rotation Averaging: A Fast and Robust Rotation Averagin

Chenyu 109 Dec 23, 2022
Implementation of 'lightweight' GAN, proposed in ICLR 2021, in Pytorch. High resolution image generations that can be trained within a day or two

512x512 flowers after 12 hours of training, 1 gpu 256x256 flowers after 12 hours of training, 1 gpu Pizza 'Lightweight' GAN Implementation of 'lightwe

Phil Wang 1.5k Jan 2, 2023
This repo contains the pytorch implementation for Dynamic Concept Learner (accepted by ICLR 2021).

DCL-PyTorch Pytorch implementation for the Dynamic Concept Learner (DCL). More details can be found at the project page. Framework Grounding Physical

Zhenfang Chen 31 Jan 6, 2023
PiCIE: Unsupervised Semantic Segmentation using Invariance and Equivariance in clustering (CVPR2021)

PiCIE: Unsupervised Semantic Segmentation using Invariance and Equivariance in Clustering Jang Hyun Cho1, Utkarsh Mall2, Kavita Bala2, Bharath Harihar

Jang Hyun Cho 164 Dec 30, 2022
A Research-oriented Federated Learning Library and Benchmark Platform for Graph Neural Networks. Accepted to ICLR'2021 - DPML and MLSys'21 - GNNSys workshops.

FedGraphNN: A Federated Learning System and Benchmark for Graph Neural Networks A Research-oriented Federated Learning Library and Benchmark Platform

FedML-AI 175 Dec 1, 2022
This project is the official implementation of our accepted ICLR 2021 paper BiPointNet: Binary Neural Network for Point Clouds.

BiPointNet: Binary Neural Network for Point Clouds Created by Haotong Qin, Zhongang Cai, Mingyuan Zhang, Yifu Ding, Haiyu Zhao, Shuai Yi, Xianglong Li

Haotong Qin 59 Dec 17, 2022
Vector AI β€” A platform for building vector based applications. Encode, query and analyse data using vectors.

Vector AI is a framework designed to make the process of building production grade vector based applications as quickly and easily as possible. Create

Vector AI 267 Dec 23, 2022
Implementation of GeoDiff: a Geometric Diffusion Model for Molecular Conformation Generation (ICLR 2022).

GeoDiff: a Geometric Diffusion Model for Molecular Conformation Generation [OpenReview] [arXiv] [Code] The official implementation of GeoDiff: A Geome

Minkai Xu 155 Dec 26, 2022
MLP-Numpy - A simple modular implementation of Multi Layer Perceptron in pure Numpy.

MLP-Numpy A simple modular implementation of Multi Layer Perceptron in pure Numpy. I used the Iris dataset from scikit-learn library for the experimen

Soroush Omranpour 1 Jan 1, 2022