Decoding the Protein-ligand Interactions Using Parallel Graph Neural Networks

Overview

Decoding the Protein-ligand Interactions Using Parallel Graph Neural Networks

Requirements

  • python 0.10+
  • rdkit 2020.03.3.0
  • biopython 1.78
  • openbabel 2.4.1
  • numpy 1.19.2
  • scipy 1.5.2
  • torchvision 0.7.0

Conda enviroment is highly recommended for this implementation

Data Preparation for classification models

Data preperation requires the ligand and protein to be in a mol format readable by rdkit .mol, .mol2, and .pdb are readily handled by rdkit .sdf is easily handled with openbabel conversion, made convenient with the pybel wrapper

Both files can then be fed into extractM2.py where the cropping window can be adjusted on line 29 The extract method will operates best if the initial protein file is in pdbqt format. For easy model integration it is best to store the m2 protein window produced by the extract script along with the original protein ex: pickle.dump((m1,m2), file)

Once cropped complexes are stored, their numpy featurization files can be created. Files for the different models are labeled in the Data_Prep directory

The scripts are designed to use keys that reference the cropped and stored pairs from the previous step. Users will need to alter scripts to include their desired directories, as well as key traversal. Once these changes have been made, the scripts can be called with

python -W ignore gnn[f/p]_data_prep.py

Data Preparation for regression models

The data needs to be in mol format as similar to classification models. We have provided some sample mol files representing protein and ligand. Here the protein is cropped at 8Γ… window using the extract script as mentioned previously.

The cropped protein-ligand can be used to create features in numpy format. Sample training and test keys along with the corresponding pIC50 and experimental-binding-affinity (EBA) labels are provided in keys folder. All the files are saved in pickle format with train and test keys as list and the label files as disctionary with key corresponding to the train/test key and value corresponding to the label. The prepare_eba_data.py and prepapre_pic50_data.py uses the cropped protein-ligand mol files to create the correspnding features for the model and save them in compressed numpy file format in the corresponding numpy directory.

These scripts can be called as:

python repare_pic50_data.py <path to pkl-mol directory> <path to save numpy features>
python repare_eba_data.py <path to pkl-mol directory> <path to save numpy features>

Training

Below is an example of the training command. Additional options can be added to the argument parser here (learning rate, layer amount and dimension, etc). Defaults are in place for undeclared parameters including a save directory.

Classfication models

python -W ignore -u train.py --dropout_rate=0.3 --epoch=500 --ngpu=1 --batch_size=32 --num_workers=0  --train_keys=<your_training_keys.pkl>  --test_keys=<your_test_keys.pkl>

Regression models

python -W ignore -u train.py --dropout_rate=0.3 --epoch=500 --ngpu=1 --batch_size=1 --num_workers=0 --data_dir=<path to feature-numpy folder> --train_keys=<your_training_keys.pkl>  --test_keys=<your_test_keys.pkl>

The save directory stores each epoch as a .pt allowing the best model inatance to be loaded later on Training and test metrics such as loss and ROC are stored in the same directory for each GPU used. Ex 3 GPUS: log-rank1.csv, log-rank2.csv, and log-rank3.csv

Owner
Neeraj Kumar
Computational Biology/Chemistry and Bioinformatics.
Neeraj Kumar
YOLOv3 in PyTorch > ONNX > CoreML > TFLite

This repository represents Ultralytics open-source research into future object detection methods, and incorporates lessons learned and best practices

Ultralytics 9.3k Jan 07, 2023
ComPhy: Compositional Physical Reasoning ofObjects and Events from Videos

ComPhy This repository holds the code for the paper. ComPhy: Compositional Physical Reasoning ofObjects and Events from Videos, (Under review) PDF Pro

29 Dec 29, 2022
This is an unofficial PyTorch implementation of Meta Pseudo Labels

This is an unofficial PyTorch implementation of Meta Pseudo Labels. The official Tensorflow implementation is here.

Jungdae Kim 320 Jan 08, 2023
The personal repository of the work: *DanceNet3D: Music Based Dance Generation with Parametric Motion Transformer*.

DanceNet3D The personal repository of the work: DanceNet3D: Music Based Dance Generation with Parametric Motion Transformer. Dataset and Results Pleas

ε—ε˜‰Nanga 36 Dec 21, 2022
Apply Graph Self-Supervised Learning methods to graph-level task(TUDataset, MolculeNet Datset)

Graphlevel-SSL Overview Apply Graph Self-Supervised Learning methods to graph-level task(TUDataset, MolculeNet Dataset). It is unified framework to co

JunSeok 8 Oct 15, 2021
source code of Adversarial Feedback Loop Paper

Adversarial Feedback Loop [ArXiv] [project page] Official repository of Adversarial Feedback Loop paper Firas Shama, Roey Mechrez, Alon Shoshan, Lihi

17 Jul 20, 2022
Official repository for Hierarchical Opacity Propagation for Image Matting

HOP-Matting Official repository for Hierarchical Opacity Propagation for Image Matting 🚧 🚧 🚧 Under Construction 🚧 🚧 🚧 🚧 🚧 🚧   Coming Soon   

Li Yaoyi 54 Dec 30, 2021
Neural Caption Generator with Attention

Neural Caption Generator with Attention Tensorflow implementation of "Show

Taeksoo Kim 510 Nov 30, 2022
[ICML 2020] Prediction-Guided Multi-Objective Reinforcement Learning for Continuous Robot Control

PG-MORL This repository contains the implementation for the paper Prediction-Guided Multi-Objective Reinforcement Learning for Continuous Robot Contro

MIT Graphics Group 65 Jan 07, 2023
Codes accompanying the paper "Believe What You See: Implicit Constraint Approach for Offline Multi-Agent Reinforcement Learning" (NeurIPS 2021 Spotlight

Implicit Constraint Q-Learning This is a pytorch implementation of ICQ on Datasets for Deep Data-Driven Reinforcement Learning (D4RL) and ICQ-MA on SM

42 Dec 23, 2022
Official Implementation of "LUNAR: Unifying Local Outlier Detection Methods via Graph Neural Networks"

LUNAR Official Implementation of "LUNAR: Unifying Local Outlier Detection Methods via Graph Neural Networks" Adam Goodge, Bryan Hooi, Ng See Kiong and

Adam Goodge 25 Dec 28, 2022
Jiminy Cricket Environment (NeurIPS 2021)

Jiminy Cricket This is the repository for "What Would Jiminy Cricket Do? Towards Agents That Behave Morally" by Dan Hendrycks*, Mantas Mazeika*, Andy

Dan Hendrycks 15 Aug 29, 2022
LeetCode Solutions https://t.me/tenvlad

leetcode LeetCode Solutions groupped by common patterns YouTube: https://www.youtube.com/c/vladten Telegram: https://t.me/nilinterface Problems source

Vlad Ten 158 Dec 29, 2022
A self-supervised 3D representation learning framework named viewpoint bottleneck.

Pointly-supervised 3D Scene Parsing with Viewpoint Bottleneck Paper Created by Liyi Luo, Beiwen Tian, Hao Zhao and Guyue Zhou from Institute for AI In

63 Aug 11, 2022
Learning infinite-resolution image processing with GAN and RL from unpaired image datasets, using a differentiable photo editing model.

Exposure: A White-Box Photo Post-Processing Framework ACM Transactions on Graphics (presented at SIGGRAPH 2018) Yuanming Hu1,2, Hao He1,2, Chenxi Xu1,

Yuanming Hu 719 Dec 29, 2022
CTRL-C: Camera calibration TRansformer with Line-Classification

CTRL-C: Camera calibration TRansformer with Line-Classification This repository contains the official code and pretrained models for CTRL-C (Camera ca

57 Nov 14, 2022
Official implementation of the NeurIPS 2021 paper Online Learning Of Neural Computations From Sparse Temporal Feedback

Online Learning Of Neural Computations From Sparse Temporal Feedback This repository is the official implementation of the NeurIPS 2021 paper Online L

Lukas Braun 3 Dec 15, 2021
Implementation of "Debiasing Item-to-Item Recommendations With Small Annotated Datasets" (RecSys '20)

Debiasing Item-to-Item Recommendations With Small Annotated Datasets This is the code for our RecSys '20 paper. Other materials can be found here: Ful

Microsoft 34 Aug 10, 2022
Code & Data for the Paper "Time Masking for Temporal Language Models", WSDM 2022

Time Masking for Temporal Language Models This repository provides a reference implementation of the paper: Time Masking for Temporal Language Models

Guy Rosin 12 Jan 06, 2023
Lowest memory consumption and second shortest runtime in NTIRE 2022 challenge on Efficient Super-Resolution

FMEN Lowest memory consumption and second shortest runtime in NTIRE 2022 on Efficient Super-Resolution. Our paper: Fast and Memory-Efficient Network T

33 Dec 01, 2022