A stacked meta-ensemble for protein inter-residue distance prediction
File version
Author(s)
Newton, MAH
Hasan, MAM
Sattar, A
Griffith University Author(s)
Primary Supervisor
Other Supervisors
Editor(s)
Date
Size
File type(s)
Location
License
Abstract
Predicted inter-residue distances are a key behind recent success in high quality protein structure prediction (PSP). However, prediction of both short and long distance values together is challenging. Consequently, predicted short distances are mostly used by existing PSP methods. In this paper, we use a stacked meta-ensemble method to combine deep learning models trained for different ranges of real-valued distances. On five benchmark sets of proteins, our proposed inter-residue distance prediction method improves mean Local Distance Different Test (LDDT) scores at least by 5% over existing such methods. Moreover, using a real-valued distance based conformational search algorithm, we also show that predicted long distances help obtain significantly better protein conformations than when only predicted short distances are used. Our method is named meta-ensemble for distance prediction (MDP) and its program is available from https://gitlab.com/mahnewton/mdp.
Journal Title
Computers in Biology and Medicine
Conference Title
Book Title
Edition
Volume
148
Issue
Thesis Type
Degree Program
School
Publisher link
Patent number
Funder(s)
Grant identifier(s)
Rights Statement
Rights Statement
Item Access Status
Note
Access the data
Related item(s)
Subject
Information and computing sciences
Engineering
Clinical sciences
Deep learning
Ensemble learning
Inter-residue distance
Protein structure prediction
Real-valued distance
Persistent link to this record
Citation
Rahman, J; Newton, MAH; Hasan, MAM; Sattar, A, A stacked meta-ensemble for protein inter-residue distance prediction, Computers in Biology and Medicine, 2022, 148, pp. 105824