Knots and $\theta$-curves identification in polymeric chains and native proteins using neural networks

da Silva, Fernando Bruno (author), Gabrovšek, Boštjan (author), Korpacz, Marta (author), Luczkiewicz, Kamil (author), Niewieczerzal, Szymon (author), Sikora, Maciej (author), Sulkowska, Joanna I. (author)

Entanglement in proteins is a fascinating structural motif that is neither easy to detect via traditional methods nor fully understood. Recent advancements in AI-driven models have predicted that millions of proteins could potentially have a nontrivial topology. Herein, we have shown that long short-term memory (LSTM)-based neural networks (NN) architecture can be applied to detect, classify, and predict entanglement not only in closed polymeric chains but also in polymers and protein-like structures with open knots, actual protein configurations, and also ▫$\theta$▫-curves motifs. The analysis revealed that the LSTM model can predict classes (up to the ▫$6_1$▫ knot) accurately for closed knots and open polymeric chains, resembling real proteins. In the case of open knots formed by protein-like structures, the model displays robust prediction capabilities with an accuracy of 99%. Moreover, the LSTM model with proper features, tested on hundreds of thousands of knotted and unknotted protein structures with different architectures predicted by AlphaFold 2, can distinguish between the trivial and nontrivial topology of the native state of the protein with an accuracy of 93%.

• Language: English
• Keywords: machine learning, topology, protein databases, entanglements, open knots, closed knots
• Work type: Article
• Typology: 1.01 - Original Scientific Article
• Organization: FS - Faculty of Mechanical Engineering; FMF - Faculty of Mathematics and Physics
• Publication status: Published
• Publication version: Version of Record
• Year: 2024
• Number of pages: Str. 4599-4608
• Numbering: Vol. 57, iss. 9
• PID: 20.500.12556/RUL-166791
• UDC: 004.85:004.725.4
• ISSN on article: 0024-9297
• DOI: 10.1021/acs.macromol.3c02479
• COBISS.SI-ID: 194735875
• Publication date in RUL: 24.01.2025

Record is a part of a journal

• Title: Macromolecules
• Shortened title: Macromolecules
• Publisher: American Chemical Society
• ISSN: 0024-9297
• COBISS.SI-ID: 25886464

Licences

• License: CC BY 4.0, Creative Commons Attribution 4.0 International
• Link: http://creativecommons.org/licenses/by/4.0/
• Description: This is the standard Creative Commons license that gives others maximum freedom to do what they want with the work as long as they credit the author.

Secondary language

• Language: Slovenian
• Keywords: strojno učenje, topologija, proteinska baza podatkov, zavozlanost, odprti vozli, sklenjeni vozli