2026-04-18T13:54:55Zhttps://riubu.ubu.es/oai/requestoai:riubu.ubu.es:10259/114302026-02-26T01:05:59Zcom_10259_5377com_10259_5086com_10259_2604com_10259_4219col_10259_5378col_10259_4220
Olivares Gil, Alicia
749
600
0000-0002-3378-197X
Barbero Aparicio, José Antonio
819
600
0000-0002-3269-0806
Rodríguez Diez, Juan José
477
600
0000-0002-3291-2739
Diez Pastor, José Francisco
156
600
0000-0001-5013-7505
García Osorio, César
212
600
0000-0002-1206-1084
Davari, Mehdi D.
71abb1c5-df2b-4933-8544-b775dd0c354d
2026-02-25T12:25:39Z
2026-02-25T12:25:39Z
2025-12
1758-2946
https://hdl.handle.net/10259/11430
10.1186/s13321-025-01029-w
1758-2946
Protein fitness prediction plays a crucial role in the advancement of protein engineering endeavours. However, the combinatorial complexity of the protein sequence space and the limited availability of assay-labelled data hinder the efficient optimization of protein properties. Data-driven strategies utilizing machine learning methods have emerged as a promising solution, yet their dependence on labelled training datasets poses a significant obstacle. To overcome this challenge, in this work, we explore various ways of introducing the latent information present in evolutionarily related sequences (homologous sequences) into the training process. To do so, we establish several strategies based on semi-supervised learning (unsupervised pre-processing and wrapper methods) and perform a comprehensive comparison using 19 datasets containing protein-fitness pairs. Our findings reveal that using the information present in the homologous sequences can improve the performance of the models, especially when the number of available labelled sequences is considerably low. Specifically, the combination of a sequence encoding method based on Direct Coupling Analysis (DCA), with MERGE (a hybrid regression framework that combines evolutionary information with supervised learning) and an SVM regressor, outperforms other encodings (PAM250, UniRep, eUniRep) and other semi-supervised wrapper methods (Tri-Training Regressor, Co-Training Regressor). In summary, the demonstrated performance gains of this strategy mark a substantial leap towards more robust and reliable predictive models for protein engineering tasks. This advancement holds the potential to streamline the design and optimisation of proteins for diverse applications in biotechnology and therapeutics.
This work is supported by the Junta de Castilla León under project BU055P20 (JCyL/FEDER, UE), and the Ministry of Science and Innovation of Spain under the project PID2020-119894GB-I00/AEI/10.13039/501100011033, co-financed through FEDER funds from the European Union. M.D. Davari acknowledges funding by the Deutsche Forschungsgemeinschaft (DFG, German Research Foundation) (SPP2363). A. Olivares-Gil is supported through Consejería de Educación of the Junta de Castilla y León and the European Social Fund through a pre-doctoral grant (EDU/875/2021). The research stay of A. Olivares-Gil and J.A. Barbero-Aparicio was financed by the Mobility grants for doctoral students of the University of Burgos, co-financed by Banco Santander S.A (2021/00001/007/001/018).
application/pdf
eng
BioMed Central
Journal of Cheminformatics. 2025, V. 17, n. 1, 88
https://doi.org/10.1186/s13321-025-01029-w
Attribution-NonCommercial-NoDerivatives 4.0 Internacional
http://creativecommons.org/licenses/by-nc-nd/4.0/
info:eu-repo/semantics/openAccess
Machine learning
Protein engineering
Directed evolution
Semi-supervised learning
Protein design
Tritraining regressor
Generalized MERGE
Proteínas
Bioinformática
Proteins
Bioinformatics
Semi-supervised prediction of protein fitness for data-driven protein engineering
info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
Journal of Cheminformatics
17
1
THUMBNAIL
Olivares-jc_2025.pdf.jpg
Olivares-jc_2025.pdf.jpg
IM Thumbnail
image/jpeg
4835
https://riubu.ubu.es/bitstream/10259/11430/4/Olivares-jc_2025.pdf.jpg
3dabd98d18eff8d18e61dbfd6cb1ca93
MD5
4
LICENSE
license.txt
license.txt
text/plain; charset=utf-8
999
https://riubu.ubu.es/bitstream/10259/11430/3/license.txt
b295bcbce42e2caabeb0c623d3860c06
MD5
3
CC-LICENSE
license_rdf
license_rdf
application/rdf+xml; charset=utf-8
805
https://riubu.ubu.es/bitstream/10259/11430/2/license_rdf
4460e5956bc1d1639be9ae6146a50347
MD5
2
ORIGINAL
Olivares-jc_2025.pdf
Olivares-jc_2025.pdf
application/pdf
2188067
https://riubu.ubu.es/bitstream/10259/11430/1/Olivares-jc_2025.pdf
fc0bbf0d7d4f0f76581c0fde3f5f247a
MD5
1
10259/11430
oai:riubu.ubu.es:10259/11430
2026-02-26 02:05:59.294
Repositorio Institucional de la Universidad de Burgos
bubrep@ubu.es
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