Codes and models for the paper "Learning Unknown from Correlations: Graph Neural Network for Inter-novel-protein Interaction Prediction".

Overview

GNN_PPI

Codes and models for the paper "Learning Unknown from Correlations: Graph Neural Network for Inter-novel-protein Interaction Prediction".

Learning Unknown from Correlations: Graph Neural Network for Inter-novel-protein Interaction Prediction
Authors: Guofeng Lv, Zhiqiang Hu, Yanguang Bi, Shaoting Zhang
Arxiv extended verison (arxiv: https://arxiv.org/abs/2105.06709)

Contact: [email protected]. Any questions or discussions are welcomed!

Abstract

The study of multi-type Protein-Protein Interaction (PPI) is fundamental for understanding biological processes from a systematic perspective and revealing disease mechanisms. Existing methods suffer from significant performance degradation when tested in unseen dataset. In this paper, we investigate the problem and find that it is mainly attributed to the poor performance for inter-novel-protein interaction prediction. However, current evaluations overlook the inter-novel-protein interactions, and thus fail to give an instructive assessment. As a result, we propose to address the problem from both the evaluation and the methodology. Firstly, we design a new evaluation framework that fully respects the inter-novel-protein interactions and gives consistent assessment across datasets. Secondly, we argue that correlations between proteins must provide useful information for analysis of novel proteins, and based on this, we propose a graph neural network based method (GNN-PPI) for better inter-novel-protein interaction prediction. Experimental results on real-world datasets of different scales demonstrate that GNN-PPI significantly outperforms state-of-the-art PPI prediction methods, especially for the inter-novel-protein interaction prediction.

Contribution

  1. We design a new evaluation framework that fully respects the inter-novel-protein interactions and give consistent assessment across datasets.

    An example of the testset construction strategies under the new evaluation framework. Random is the current scheme, while Breath-First Search (BFS) and Depth-First Search (DFS) are the proposed schemes.
  2. We propose to incorporate correlation between proteins into the PPI prediction problem. A graph neural network based method is presented to model the correlations.

    Development and evaluation of the GNN-PPI framework. Pairwise interaction data are firstly assembled to build the graph, where proteins serve as the nodes and interactions as the edges. The testset is constructed by firstly selecting the root node and then performing the proposed BFS or DFS strategy. The model is developed by firstly performing embedding for each protein to obtain predefined features, then processed by Convolution, Pooling, BiGRU and FC modules to extract protein-independent encoding (PIE) features, which are finally aggregated by graph convolutions and arrive at protein-graph encoding (PGE) features. Features of the pair proteins in interaction are multiplied and classified, supervised by the trainset labels.
  3. The proposed GNN-PPI model achieves state-of-the-art performance in real datasets of different scales, especially for the inter-novel-protein interaction prediction.

    For further investigation, we divide the testset into BS, ES and NS subsets, where BS denotes Both of the pair proteins in interaction were Seen during training, ES denotes Either (but not both) of the pair proteins was Seen, and NS denotes Neither proteins were Seen during training. We regard ES and NS as inter-novel-protein interactions. Existing methods suffer from significant performance degradation when tested on unseen Protein-protein interaction, especially inter-novel-protein interactions. On the contrary, GNN-PPI can handle this situation well, whether it is BS, ES or NS, the performance will not be greatly reduced.

Experimental Results

We evaluate the multi-label PPI prediction performance using micro-F1. This is because micro-averaging will emphasize the common labels in the dataset, which gives each sample the same importance.

Benchmark

  • Performance of GNN-PPI against comparative methods over different datasets and data partition schemes.

In-depth Analysis

  • In-depth analysis between PIPR and GNN-PPI over BS, ES and NS subsets.

Model Generalization

  • Testing on trainset-homologous testset vs. unseen testset, under different evaluations.

PPI Network Graph Construction

  • The impact of the PPI network graph construction method.

Using GNN_PPI

This repository contains:

  • Environment Setup
  • Data Processing
  • Training
  • Testing
  • Inference

Environment Setup

base environment: python 3.7, cuda 10.2, pytorch 1.6, torchvision 0.7.0, tensorboardX 2.1
pytorch-geometric:
pip install torch-scatter -f https://pytorch-geometric.com/whl/torch-1.6.0+cu102.html
pip install torch-sparse -f https://pytorch-geometric.com/whl/torch-1.6.0+cu102.html
pip install torch-cluster -f https://pytorch-geometric.com/whl/torch-1.6.0+cu102.html
pip install torch-spline-conv -f https://pytorch-geometric.com/whl/torch-1.6.0+cu102.html
pip install torch-geometric

Data Processing

The data processing codes in gnn_data.py (Class GNN_DATA), including:

  • data reading (def __init__)
  • protein vectorize (def get_feature_origin)
  • generate pyg data (def generate_data)
  • Data partition (def split_dataset)

Training

Training codes in gnn_train.py, and the run script in run.py.

"python -u gnn_train.py \
    --description={} \              # Description of the current training task
    --ppi_path={} \                 # ppi dataset
    --pseq_path={} \                # protein sequence
    --vec_path={} \                 # protein pretrained-embedding
    --split_new={} \                # whether to generate a new data partition, or use the previous
    --split_mode={} \               # data split mode
    --train_valid_index_path={} \   # Data partition json file path
    --use_lr_scheduler={} \         # whether to use training learning rate scheduler
    --save_path={} \                # save model, config and results dir path
    --graph_only_train={} \         # PPI network graph construction method, True: GCT, False: GCA
    --batch_size={} \               # Batch size
    --epochs={} \                   # Train epochs
    ".format(description, ppi_path, pseq_path, vec_path, 
            split_new, split_mode, train_valid_index_path,
            use_lr_scheduler, save_path, graph_only_train, 
            batch_size, epochs)

Dataset Download:

STRING(we use Homo sapiens subset):

SHS27k and SHS148k:

This repositorie uses the processed dataset download path:

Testing

Testing codes in gnn_test.py and gnn_test_bigger.py, and the run script in run_test.py and run_test_bigger.py.

gnn_test.py: It can test the overall performance, and can also make in-depth analysis to test the performance of different test data separately.
gnn_test_bigger.py: It can test the performance between the trainset-homologous testset and the unseen testset.
Running script run_test_bigger.py as above.

Inference

If you have your own dataset or want to save the prediction results, you can use inference.py. After execution, a ppi csv file will be generated to record the predicted PPI type of each pair of interacting proteins.

Running script run_inference.py as above.

Citation

If you find this project useful for your research, please use the following BibTeX entry.

@misc{lv2021learning,
    title={Learning Unknown from Correlations: Graph Neural Network for Inter-novel-protein Interaction Prediction}, 
    author={Guofeng Lv and Zhiqiang Hu and Yanguang Bi and Shaoting Zhang},
    year={2021},
    eprint={2105.06709},
    archivePrefix={arXiv},
    primaryClass={cs.LG}
}
You might also like...
Codes for NAACL 2021 Paper
Codes for NAACL 2021 Paper "Unsupervised Multi-hop Question Answering by Question Generation"

Unsupervised-Multi-hop-QA This repository contains code and models for the paper: Unsupervised Multi-hop Question Answering by Question Generation (NA

Codes for our paper "SentiLARE: Sentiment-Aware Language Representation Learning with Linguistic Knowledge" (EMNLP 2020)

SentiLARE: Sentiment-Aware Language Representation Learning with Linguistic Knowledge Introduction SentiLARE is a sentiment-aware pre-trained language

Source codes for the paper "Local Additivity Based Data Augmentation for Semi-supervised NER"

LADA This repo contains codes for the following paper: Jiaao Chen*, Zhenghui Wang*, Ran Tian, Zichao Yang, Diyi Yang: Local Additivity Based Data Augm

Official codes for the paper
Official codes for the paper "Learning Hierarchical Discrete Linguistic Units from Visually-Grounded Speech"

ResDAVEnet-VQ Official PyTorch implementation of Learning Hierarchical Discrete Linguistic Units from Visually-Grounded Speech What is in this repo? M

Codes for ACL-IJCNLP 2021 Paper
Codes for ACL-IJCNLP 2021 Paper "Zero-shot Fact Verification by Claim Generation"

Zero-shot-Fact-Verification-by-Claim-Generation This repository contains code and models for the paper: Zero-shot Fact Verification by Claim Generatio

Codes for paper "Towards Diverse Paragraph Captioning for Untrimmed Videos". CVPR 2021

Towards Diverse Paragraph Captioning for Untrimmed Videos This repository contains PyTorch implementation of our paper Towards Diverse Paragraph Capti

Implementation of CVPR 2021 paper
Implementation of CVPR 2021 paper "Spatially-invariant Style-codes Controlled Makeup Transfer"

SCGAN Implementation of CVPR 2021 paper "Spatially-invariant Style-codes Controlled Makeup Transfer" Prepare The pre-trained model is avaiable at http

Codes accompanying the paper "Learning Nearly Decomposable Value Functions with Communication Minimization" (ICLR 2020)

NDQ: Learning Nearly Decomposable Value Functions with Communication Minimization Note This codebase accompanies paper Learning Nearly Decomposable Va

Codes for CIKM'21 paper 'Self-Supervised Graph Co-Training for Session-based Recommendation'.

COTREC Codes for CIKM'21 paper 'Self-Supervised Graph Co-Training for Session-based Recommendation'. Requirements: Python 3.7, Pytorch 1.6.0 Best Hype

Releases(v1.0)
Owner
Ursa Zrimsek
Ursa Zrimsek
The source codes for ACL 2021 paper 'BoB: BERT Over BERT for Training Persona-based Dialogue Models from Limited Personalized Data'

BoB: BERT Over BERT for Training Persona-based Dialogue Models from Limited Personalized Data This repository provides the implementation details for

null 124 Dec 27, 2022
The codes and models in 'Gaze Estimation using Transformer'.

GazeTR We provide the code of GazeTR-Hybrid in "Gaze Estimation using Transformer". We recommend you to use data processing codes provided in GazeHub.

null 65 Dec 27, 2022
The official codes of "Semi-supervised Models are Strong Unsupervised Domain Adaptation Learners".

SSL models are Strong UDA learners Introduction This is the official code of paper "Semi-supervised Models are Strong Unsupervised Domain Adaptation L

Yabin Zhang 26 Dec 26, 2022
Codes to pre-train T5 (Text-to-Text Transfer Transformer) models pre-trained on Japanese web texts

t5-japanese Codes to pre-train T5 (Text-to-Text Transfer Transformer) models pre-trained on Japanese web texts. The following is a list of models that

Kimio Kuramitsu 1 Dec 13, 2021
Codes for our IJCAI21 paper: Dialogue Discourse-Aware Graph Model and Data Augmentation for Meeting Summarization

DDAMS This is the pytorch code for our IJCAI 2021 paper Dialogue Discourse-Aware Graph Model and Data Augmentation for Meeting Summarization [Arxiv Pr

xcfeng 55 Dec 27, 2022
codes for paper Combining Dynamic Local Context Focus and Dependency Cluster Attention for Aspect-level sentiment classification

DLCF-DCA codes for paper Combining Dynamic Local Context Focus and Dependency Cluster Attention for Aspect-level sentiment classification. submitted t

null 15 Aug 30, 2022
The codes reproduce the figures and statistics in the paper, "Controlling for multiple covariates," by Mark Tygert.

The accompanying codes reproduce all figures and statistics presented in "Controlling for multiple covariates" by Mark Tygert. This repository also pr

Meta Research 1 Dec 2, 2021
Codes for the paper Contrast and Mix: Temporal Contrastive Video Domain Adaptation with Background Mixing

Contrast and Mix (CoMix) The repository contains the codes for the paper Contrast and Mix: Temporal Contrastive Video Domain Adaptation with Backgroun

Computer Vision and Intelligence Research (CVIR) 13 Dec 10, 2022