Short-length peptides contact map prediction using Convolution Neural Networks

A. Maminov

АБВ
АБВ
АБВ

Обычная версия сайта

Priority areas

by year

Subject

News

October 14, 2026

At HSE University–St Petersburg, Experts Discuss How AI Changes Tourist Routes and Cultural Heritage

Neural networks are no longer simple travel assistants; now they decide what to include on the route and what to skip. Artificial intelligence changes how people perceive a place and shapes the image of tourist centres. At the II International Scientific and Practical Conference ’Information Technologies in the Preservation and Promotion of Cultural Heritage,’ researchers discussed who controls algorithmic solutions and in what ways, and whether authentic traditions get lost in them.

October 12, 2026

Road Injuries Leading Cause of Death Among Men Aged 10 to 39

Worldwide, road injuries are the leading cause of death among males aged 10–39. An international team of researchers reached this conclusion as part of the Global Burden of Disease Study 2023, analysing data from 204 countries between 1990 and 2023. Their findings have been published in The Lancet Public Health, with HSE University Professor Vasily Vlassov listed among the collaborators.

October 8, 2026

HSE Experts Take Part in 23rd Annual Meeting of Valdai Discussion Club

The 23rd Annual Meeting of the Valdai Discussion Club was held from September 28 to October 1, 2026 under the theme ‘Responsibility for the Future: Limits of the Possible, or Limitless Possibilities?’ The forum brought together 120 experts from 40 countries, including representatives of China, the United States, India, Brazil, the United Kingdom, Germany, Egypt, Iran, and Japan.

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.