GLTM: A Global-Local Attention LSTM Model to Locate Dimer Motif of Single-Pass Membrane Proteins

Single-pass membrane proteins, which constitute up to 50% of all transmembrane proteins, are typically active in significant conformational changes, such as a dimer or other oligomers, which is essential for understanding the function of transmembrane proteins. Finding the key motifs of oligomers th...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Frontiers in genetics 2022-03, Vol.13, p.854571-854571
Hauptverfasser: Ma, Quanchao, Zou, Kai, Zhang, Zhihai, Yang, Fan
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Single-pass membrane proteins, which constitute up to 50% of all transmembrane proteins, are typically active in significant conformational changes, such as a dimer or other oligomers, which is essential for understanding the function of transmembrane proteins. Finding the key motifs of oligomers through experimental observation is a routine method used in the field to infer the potential conformations of other members of the transmembrane protein family. However, approaches based on experimental observation need to consume a lot of time and manpower costs; moreover, they are hard to reveal the potential motifs. A proposed approach is to build an accurate and efficient transmembrane protein oligomer prediction model to screen the key motifs. In this paper, an attention-based Global-Local structure LSTM model named GLTM is proposed to predict dimers and screen potential dimer motifs. Different from traditional motifs screening based on highly conserved sequence search frame, a self-attention mechanism has been employed in GLTM to locate the highest dimerization score of subsequence fragments and has been proven to locate most known dimer motifs well. The proposed GLTM can reach 97.5% accuracy on the benchmark dataset collected from Membranome2.0. The three characteristics of GLTM can be summarized as follows: First, the original sequence fragment was converted to a set of subsequences which having the similar length of known motifs, and this additional step can greatly enhance the capability of capturing motif pattern; Second, to solve the problem of sample imbalance, a novel data enhancement approach combining improved one-hot encoding with random subsequence windows has been proposed to improve the generalization capability of GLTM; Third, position penalization has been taken into account, which makes a self-attention mechanism focused on special TM fragments. The experimental results in this paper fully demonstrated that the proposed GLTM has a broad application perspective on the location of potential oligomer motifs, and is helpful for preliminary and rapid research on the conformational change of mutants.
ISSN:1664-8021
1664-8021
DOI:10.3389/fgene.2022.854571