Sequence-Based Prediction for Protein Solvent Accessibility
Yang, Yang ; Chen, Mengqi ; Liu, Congrui and Vihinen, Mauno LU
(2025)
In International Journal of Molecular Sciences
26(12).
- Abstract
When globular proteins fold into their characteristic three-dimensional structures, some amino acids are located on the surface, while others are situated in the protein core, where they cannot interact with molecules in the environment. Predicting the degree of solubility of amino acids provides insight into the function and relevance of residues. Residue accessibility is crucial for several protein functions, including enzymatic activity, allostery, multimer formation, binding to other molecules, and immunogenicity. We developed a novel sequence-based predictor for amino acid accessibility with features derived from three-dimensional protein structures. Several machine learning algorithms were tested, and the long short-term memory... (More)
When globular proteins fold into their characteristic three-dimensional structures, some amino acids are located on the surface, while others are situated in the protein core, where they cannot interact with molecules in the environment. Predicting the degree of solubility of amino acids provides insight into the function and relevance of residues. Residue accessibility is crucial for several protein functions, including enzymatic activity, allostery, multimer formation, binding to other molecules, and immunogenicity. We developed a novel sequence-based predictor for amino acid accessibility with features derived from three-dimensional protein structures. Several machine learning algorithms were tested, and the long short-term memory (LSTM) deep learning method demonstrated the best performance; thus, it was utilized to develop the freely available SolAcc tool. It showed superior performance compared to state-of-the-art predictors in a blind test.
(Less)
- author
- Yang, Yang
; Chen, Mengqi
; Liu, Congrui
and Vihinen, Mauno
LU
- organization
- publishing date
- 2025-06
- type
- Contribution to journal
- publication status
- published
- subject
- keywords
- amino acid accessibility, machine learning, protein structure, sequence-based prediction, solubility
- in
- International Journal of Molecular Sciences
- volume
- 26
- issue
- 12
- article number
- 5604
- publisher
- MDPI AG
- external identifiers
-
- pmid:40565067
- scopus:105009002645
- ISSN
- 1661-6596
- DOI
- 10.3390/ijms26125604
- language
- English
- LU publication?
- yes
- additional info
- Publisher Copyright: © 2025 by the authors.
- id
- 2089794d-fdb6-4e76-9451-1451034e22f2
- date added to LUP
- 2025-12-17 09:39:32
- date last changed
- 2025-12-18 03:00:15
@article{2089794d-fdb6-4e76-9451-1451034e22f2,
abstract = {{<p>When globular proteins fold into their characteristic three-dimensional structures, some amino acids are located on the surface, while others are situated in the protein core, where they cannot interact with molecules in the environment. Predicting the degree of solubility of amino acids provides insight into the function and relevance of residues. Residue accessibility is crucial for several protein functions, including enzymatic activity, allostery, multimer formation, binding to other molecules, and immunogenicity. We developed a novel sequence-based predictor for amino acid accessibility with features derived from three-dimensional protein structures. Several machine learning algorithms were tested, and the long short-term memory (LSTM) deep learning method demonstrated the best performance; thus, it was utilized to develop the freely available SolAcc tool. It showed superior performance compared to state-of-the-art predictors in a blind test.</p>}},
author = {{Yang, Yang and Chen, Mengqi and Liu, Congrui and Vihinen, Mauno}},
issn = {{1661-6596}},
keywords = {{amino acid accessibility; machine learning; protein structure; sequence-based prediction; solubility}},
language = {{eng}},
number = {{12}},
publisher = {{MDPI AG}},
series = {{International Journal of Molecular Sciences}},
title = {{Sequence-Based Prediction for Protein Solvent Accessibility}},
url = {{http://dx.doi.org/10.3390/ijms26125604}},
doi = {{10.3390/ijms26125604}},
volume = {{26}},
year = {{2025}},
}