Short-length peptides contact map prediction using Convolution Neural Networks

A. Maminov

АБВ
АБВ
АБВ

Обычная версия сайта

Priority areas

by year

Subject

News

June 5, 2026

Neural Network Maps as a Method for Constructing Mathematical Models

Scientists from HSE University–Nizhny Novgorod and the Institute of Physics Belgrade, Serbia, are jointly exploring the application of machine learning techniques and neural networks to the study of nonlinear dynamics. Natalya Stankevich, Leading Research Fellow at the Laboratory of Topological Methods in Dynamics of the Faculty of Informatics, Mathematics, and Computer Science at HSE University–Nizhny Novgorod, spoke to the HSE News Service about this international project.

June 5, 2026

‘In the Age of Technology, It Is Interesting to Look into the Past and Think about What We Can Take from It

Polina Tabakova decided to apply for a Philology degree at HSE in Nizhny Novgorod because she grew up in Mari El and did not want to move far away from the Russian forests. In an interview for the Young Scientists of HSE University project, she spoke about the genre of the campus novel, the existential drama of Kolobok, and a blackout version of Eugene Onegin.

June 5, 2026

HSE Scientists Develop Method to Compress Large Language Models Without Losing Quality

Researchers from the AI and Digital Science Institute at the HSE Faculty of Computer Science have developed a new compression method for large language models such as GPT and LLaMA that reduces their size by 25–36% without additional training or significant loss of accuracy. This is the first approach to use mathematical transformations—specifically, rotations of model weights—to make models more amenable to compression with structured matrices. The study results have been published in ACL Findings 2025. The code is available on GitHub.

Have you spotted a typo?
Highlight it, click Ctrl+Enter and send us a message. Thank you for your help!

Publications

?

Short-length peptides contact map prediction using Convolution Neural Networks

Maminov A.

Inthisarticle, it isconsideredanapproachforpredictingthecontactmatrix(contactmap) for short-lengthpeptides. Contactmatrixis two-dimensional representationof theprotein. Itcan beusedfortertiarystructurereconstructionorforstartingapproximationinenergyminimization models.Forthiswork,peptideswithachainlengthfrom15upto30werechosentotestthemodel andsimplifythecalculations. Convolutionalneuralnetworks(CNNs)wereusedasaprediction toolaccordingtothefactthatthefeaturespaceofeachpeptideispresentedasatwo-dimensional matrix. SCRATCHtoolwasusedtogeneratethesecondarystructure,solventaccessibility,and profilematrix(PSSM) foreachpeptide. CNNwas implementedinthePythonprogramming languageusingtheKeras library. ToworkwiththecommonPDB-format,whichpresents the structureinformationofproteins,theBioPythonmodulewasused.Asaresult,training,validation andtestsamplesweregenerated, themultilayermulti-outputconvolutionalneuralnetworkwas constructed,whichwastrainedandvalidated.Theexperimentswereconductedonatestsample topredictthecontactmatrixandcompareitwithnativeone.Toassessthequalityofprediction, conjunctionmatricesfor thethresholdof8and12𝐴wereformed, themetricsF1-score, recall andprecisionwerecalculated. According toF1-score,wecanobserve, that evenwithsmall neuralnetworkwecanachevequitegoodresults.AtthefinalstepFT-COMARtoolwasusedto reconstruct tertiarystructureoftheproteinsfromitscontactmatrix. Theresultsshows, thatfor reconstructedstructuresfrom12threshholdcontactmatrix,RMSDmetricisbetter

Language: English

Keywords: Folding

In book

Proceedings of Science, volume 429. The 6th International Workshop on Deep Learning in Computational Physics

[б.и.], 2023.