HN-PPISP: a hybrid network based on MLP-Mixer for protein–protein interaction site prediction

Abstract

Motivation Biological experimental approaches to protein–protein interaction (PPI) site prediction are critical for understanding the mechanisms of biochemical processes but are time-consuming and laborious. With the development of Deep Learning (DL) techniques, the most popular Convolutional Neural Networks (CNN)-based methods have been proposed to address these problems. Although significant progress has been made, these methods still have limitations in encoding the characteristics of each amino acid in protein sequences. Current methods cannot efficiently explore the nature of Position Specific Scoring Matrix (PSSM), secondary structure and raw protein sequences by processing them all together. For PPI site prediction, how to effectively model the PPI context with attention to prediction remains an open problem. In addition, the long-distance dependencies of PPI features are important, which is very challenging for many CNN-based methods because the innate ability of CNN is difficult to outperform auto-regressive models like Transformers. Results To effectively mine the properties of PPI features, a novel hybrid neural network named HN-PPISP is proposed, which integrates a Multi-layer Perceptron Mixer (MLP-Mixer) module for local feature extraction and a two-stage multi-branch module for global feature capture. The model merits Transformer, TextCNN and Bi-LSTM as a powerful alternative for PPI site prediction. On the one hand, this is the first application of an advanced Transformer (i.e. MLP-Mixer) with a hybrid network for sequence-based PPI prediction. On the other hand, unlike existing methods that treat global features altogether, the proposed two-stage multi-branch hybrid module firstly assigns different attention scores to the input features and then encodes the feature through different branch modules. In the first stage, different improved attention modules are hybridized to extract features from the raw protein sequences, secondary structure and PSSM, respectively. In the second stage, a multi-branch network is designed to aggregate information from both branches in parallel. The two branches encode the features and extract dependencies through several operations such as TextCNN, Bi-LSTM and different activation functions. Experimental results on real-world public datasets show that our model consistently achieves state-of-the-art performance over seven remarkable baselines. Availability The source code of HN-PPISP model is available at https://github.com/ylxu05/HN-PPISP.

Seq-InSite: sequence supersedes structure for protein interaction site prediction

“…More details are given in the Supplementary Material . The methods considered include sequence-based models: CRFPPI ( Wei et al 2015 ), DELPHI ( Li et al 2021 ), DLPred ( Zhang et al 2019 ), D-PPIsite ( Hu et al 2023 ), ISPRED-SEQ ( Manfredi et al 2023 ), LORIS ( Dhole et al 2014 ), PIPENN ( Stringer et al 2022 ), PITHIA ( Hosseini and Ilie 2022 ), PSIVER ( Murakami and Mizuguchi 2010 ), SCRIBER ( Zhang and Kurgan 2019 ), SPPIDER ( Porollo and Meller 2007 ), SPRINGS ( Singh et al 2014 ), SPRINT ( Taherzadeh et al 2016 ) and SSWRF ( Wei et al 2016 ); and structure-based models: AttentionCNN ( Lu et al 2021 ), DeepPPISP ( Zeng et al 2020 ), EGRET ( Mahbub and Bayzid 2022 ), GraphPPIS ( Yuan et al 2022 ), HN-PPISP ( Kang et al 2023 ), MaSIF ( Gainza et al 2020 ), ProB-site ( Khan et al 2022 ) and RGN ( Wang et al 2022 ).…”

Unveiling Hidden Connections in Omics DataviapyPARAGON: an Integrative Hybrid Approach for Disease Network Construction

“…First, reference interactomes are incomplete 65 . Notably, network-based methods strongly depend on features and coverage of reference networks 66 . As a result of incomplete knowledge in large reference interactomes, protein complexes tend to form more topological modules than metabolic pathways 67 .…”

Seq-InSite: sequence supersedes structure for protein interaction site prediction

“…We selected for comparison a number of methods based on the code availability, good performance reported in their papers, or having received significant attention in the literature. These include sequence-based models: CRFPPI [51], DELPHI [25], DLPred [54], ISPRED-SEQ [30], LORIS [11], PITHIA [18], PSIVER [32], SCRIBER [55], SPRINGS [43], SPRINT [48], and SSWRF [50]; and structure-based models: AttentionCNN [28], DeepPPISP [53], EGRET [29], GraphP-PIS [52], HN-PPISP [21], MaSIF [16], and RGN [49].…”