Persistent spectral based ensemble learning (PerSpect-EL) for protein-protein binding affinity prediction

Protein-protein interactions (PPIs) play a significant role in nearly all cellular and biological activities. Data-driven machine learning models have demonstrated great power in PPIs. However, the design of efficient molecular featurization poses a great challenge for all learning models for PPIs....

Full description

Saved in:
Bibliographic Details
Main Authors: Wee, Junjie, Xia, Kelin
Other Authors: School of Physical and Mathematical Sciences
Format: Article
Language:English
Published: 2022
Subjects:
Online Access:https://hdl.handle.net/10356/162232
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-162232
record_format dspace
spelling sg-ntu-dr.10356-1622322023-06-27T01:20:01Z Persistent spectral based ensemble learning (PerSpect-EL) for protein-protein binding affinity prediction Wee, Junjie Xia, Kelin School of Physical and Mathematical Sciences Science::Mathematics Science::Mathematics Protein–Protein Interaction Hodge Laplacian Protein-protein interactions (PPIs) play a significant role in nearly all cellular and biological activities. Data-driven machine learning models have demonstrated great power in PPIs. However, the design of efficient molecular featurization poses a great challenge for all learning models for PPIs. Here, we propose persistent spectral (PerSpect) based PPI representation and featurization, and PerSpect-based ensemble learning (PerSpect-EL) models for PPI binding affinity prediction, for the first time. In our model, a sequence of Hodge (or combinatorial) Laplacian (HL) matrices at various different scales are generated from a specially designed filtration process. PerSpect attributes, which are statistical and combinatorial properties of spectrum information from these HL matrices, are used as features for PPI characterization. Each PerSpect attribute is input into a 1D convolutional neural network (CNN), and these CNN networks are stacked together in our PerSpect-based ensemble learning models. We systematically test our model on the two most commonly used datasets, i.e. SKEMPI and AB-Bind. It has been found that our model can achieve state-of-the-art results and outperform all existing models to the best of our knowledge. Ministry of Education (MOE) Nanyang Technological University This work was supported in part by Nanyang Technological University Startup Grant M4081842.110, Singapore Ministry of Education Academic Research fund Tier 1 RG109/19, Tier 2 MOE-T2EP20120-0013 and MOE-T2EP20220-0010. 2022-10-10T08:20:05Z 2022-10-10T08:20:05Z 2022 Journal Article Wee, J. & Xia, K. (2022). Persistent spectral based ensemble learning (PerSpect-EL) for protein-protein binding affinity prediction. Briefings in Bioinformatics, 23(2). https://dx.doi.org/10.1093/bib/bbac024 1467-5463 https://hdl.handle.net/10356/162232 10.1093/bib/bbac024 35189639 2-s2.0-85127436516 2 23 en M4081842.110 RG109/19 MOE-T2EP20120-0013 MOE-T2EP20220-0010 Briefings in Bioinformatics © 2022 The Author(s). All rights reserved.
institution Nanyang Technological University
building NTU Library
continent Asia
country Singapore
Singapore
content_provider NTU Library
collection DR-NTU
language English
topic Science::Mathematics
Science::Mathematics
Protein–Protein Interaction
Hodge Laplacian
spellingShingle Science::Mathematics
Science::Mathematics
Protein–Protein Interaction
Hodge Laplacian
Wee, Junjie
Xia, Kelin
Persistent spectral based ensemble learning (PerSpect-EL) for protein-protein binding affinity prediction
description Protein-protein interactions (PPIs) play a significant role in nearly all cellular and biological activities. Data-driven machine learning models have demonstrated great power in PPIs. However, the design of efficient molecular featurization poses a great challenge for all learning models for PPIs. Here, we propose persistent spectral (PerSpect) based PPI representation and featurization, and PerSpect-based ensemble learning (PerSpect-EL) models for PPI binding affinity prediction, for the first time. In our model, a sequence of Hodge (or combinatorial) Laplacian (HL) matrices at various different scales are generated from a specially designed filtration process. PerSpect attributes, which are statistical and combinatorial properties of spectrum information from these HL matrices, are used as features for PPI characterization. Each PerSpect attribute is input into a 1D convolutional neural network (CNN), and these CNN networks are stacked together in our PerSpect-based ensemble learning models. We systematically test our model on the two most commonly used datasets, i.e. SKEMPI and AB-Bind. It has been found that our model can achieve state-of-the-art results and outperform all existing models to the best of our knowledge.
author2 School of Physical and Mathematical Sciences
author_facet School of Physical and Mathematical Sciences
Wee, Junjie
Xia, Kelin
format Article
author Wee, Junjie
Xia, Kelin
author_sort Wee, Junjie
title Persistent spectral based ensemble learning (PerSpect-EL) for protein-protein binding affinity prediction
title_short Persistent spectral based ensemble learning (PerSpect-EL) for protein-protein binding affinity prediction
title_full Persistent spectral based ensemble learning (PerSpect-EL) for protein-protein binding affinity prediction
title_fullStr Persistent spectral based ensemble learning (PerSpect-EL) for protein-protein binding affinity prediction
title_full_unstemmed Persistent spectral based ensemble learning (PerSpect-EL) for protein-protein binding affinity prediction
title_sort persistent spectral based ensemble learning (perspect-el) for protein-protein binding affinity prediction
publishDate 2022
url https://hdl.handle.net/10356/162232
_version_ 1772826631536115712