RiRPSSP: A unified deep learning method for prediction of regular and irregular protein secondary structures

Authors: Sofi, M.A. and Wani, M.A.

Journal: Journal of Bioinformatics and Computational Biology

Volume: 21

Issue: 1

eISSN: 1757-6334

ISSN: 0219-7200

DOI: 10.1142/S0219720023500014

Abstract:

Protein secondary structure prediction (PSSP) is an important and challenging task in protein bioinformatics. Protein secondary structures (SSs) are categorized in regular and irregular structure classes. Regular SSs, representing nearly 50% of amino acids consist of helices and sheets, whereas the remaining amino acids represent irregular SSs. β-turns and γ-turns are the most abundant irregular SSs present in proteins. Existing methods are well developed for separate prediction of regular and irregular SSs. However, for more comprehensive PSSP, it is essential to develop a uniform model to predict all types of SSs simultaneously. In this work, using a novel dataset comprising dictionary of secondary structure of protein (DSSP)-based SSs and PROMOTIF-based β-turns and γ-turns, we propose a unified deep learning model consisting of convolutional neural networks (CNNs) and long short-term memory networks (LSTMs) for simultaneous prediction of regular and irregular SSs. To the best of our knowledge, this is the first study in PSSP covering both regular and irregular structures. The protein sequences in our constructed datasets, RiR6069 and RiR513, have been borrowed from benchmark CB6133 and CB513 datasets, respectively. The results are indicative of increased PSSP accuracy.

Source: Scopus

RiRPSSP: A unified deep learning method for prediction of regular and irregular protein secondary structures.

Authors: Sofi, M.A. and Wani, M.A.

Journal: J Bioinform Comput Biol

Volume: 21

Issue: 1

Pages: 2350001

eISSN: 1757-6334

DOI: 10.1142/S0219720023500014

Abstract:

Protein secondary structure prediction (PSSP) is an important and challenging task in protein bioinformatics. Protein secondary structures (SSs) are categorized in regular and irregular structure classes. Regular SSs, representing nearly 50% of amino acids consist of helices and sheets, whereas the remaining amino acids represent irregular SSs. [Formula: see text]-turns and [Formula: see text]-turns are the most abundant irregular SSs present in proteins. Existing methods are well developed for separate prediction of regular and irregular SSs. However, for more comprehensive PSSP, it is essential to develop a uniform model to predict all types of SSs simultaneously. In this work, using a novel dataset comprising dictionary of secondary structure of protein (DSSP)-based SSs and PROMOTIF-based [Formula: see text]-turns and [Formula: see text]-turns, we propose a unified deep learning model consisting of convolutional neural networks (CNNs) and long short-term memory networks (LSTMs) for simultaneous prediction of regular and irregular SSs. To the best of our knowledge, this is the first study in PSSP covering both regular and irregular structures. The protein sequences in our constructed datasets, RiR6069 and RiR513, have been borrowed from benchmark CB6133 and CB513 datasets, respectively. The results are indicative of increased PSSP accuracy.

Source: PubMed

RiRPSSP: A unified deep learning method for prediction of regular and irregular protein secondary structures

Authors: Sofi, M.A. and Wani, M.A.

Journal: JOURNAL OF BIOINFORMATICS AND COMPUTATIONAL BIOLOGY

Volume: 21

Issue: 01

eISSN: 1757-6334

ISSN: 0219-7200

DOI: 10.1142/S0219720023500014

Source: Web of Science (Lite)

RiRPSSP: A unified deep learning method for prediction of regular and irregular protein secondary structures.

Authors: Sofi, M.A. and Wani, M.A.

Journal: Journal of bioinformatics and computational biology

Volume: 21

Issue: 1

Pages: 2350001

eISSN: 1757-6334

ISSN: 0219-7200

DOI: 10.1142/s0219720023500014

Abstract:

Protein secondary structure prediction (PSSP) is an important and challenging task in protein bioinformatics. Protein secondary structures (SSs) are categorized in regular and irregular structure classes. Regular SSs, representing nearly 50% of amino acids consist of helices and sheets, whereas the remaining amino acids represent irregular SSs. [Formula: see text]-turns and [Formula: see text]-turns are the most abundant irregular SSs present in proteins. Existing methods are well developed for separate prediction of regular and irregular SSs. However, for more comprehensive PSSP, it is essential to develop a uniform model to predict all types of SSs simultaneously. In this work, using a novel dataset comprising dictionary of secondary structure of protein (DSSP)-based SSs and PROMOTIF-based [Formula: see text]-turns and [Formula: see text]-turns, we propose a unified deep learning model consisting of convolutional neural networks (CNNs) and long short-term memory networks (LSTMs) for simultaneous prediction of regular and irregular SSs. To the best of our knowledge, this is the first study in PSSP covering both regular and irregular structures. The protein sequences in our constructed datasets, RiR6069 and RiR513, have been borrowed from benchmark CB6133 and CB513 datasets, respectively. The results are indicative of increased PSSP accuracy.

Source: Europe PubMed Central