Author

Aleksei Shmelev

National Research University Higher School of EconomicsORCID 0009-0007-9223-4558Unclaimed ORCID profile · follow to get notified of new preprints

Biology Disciplines

Click to filter author papers

Bioinformatics· 2

Signature Assays, Organisms & Methods

Click to filter · or open tag

Assay:whole-genome sequencing· 2 Research Focus:benchmarking· 1 Approach:deep learning· 1 Organism:multiple species· 1 Research Focus:software / tool· 1 Approach:statistical model· 1 Approach:transformer / foundation model· 1

Frequent Co-Authors

Mikhail BurtseviD· 2 shared Olga L. KardymoniD· 2 shared Veniamin FishmaniD· 2 shared Yuri KuratoviD· 2 shared Artem ShadskiyiD· 1 shared Denis ShepeliniD· 1 shared Dmitry PenzariD· 1 shared Maxim PetroviD· 1 shared

Activity by Year

2024-2026 · peak 1/yr

Co-Author Collaboration Network

9 top collaborators · 32 mutual co-author links

Click any collaborator node to inspect or filter shared papers

Focal author (center)Selected co-authorORCID co-authorUnlinked name

Curved chords = mutual co-authorship

2 shared papersBioinformatics

Mikhail BurtsevORCID

Mutual co-authors in cluster

Author profile →

2 papers

Recent·Most cited

BioinformaticsbioRxivPreprintJun 21, 2026

GENATATORs: ab initio Gene Annotation With DNA Language Models

Aleksei Shmelev, Artem Shadskiy, Yuri Kuratov…·Veniamin Fishman

The paper benchmarks gene annotation methods, showing fine-tuned DNA language models outperform existing tools and generalize across species and annotate non-coding transcripts.

DOI 10.64898/2026.06.17.732686

whole-genome sequencingdeep learning

𝕏 PostBluesky

BioinformaticsNucleic Acids ResearchPeer-reviewedDec 26, 2024

GENA-LM: A Family of Open-Source Foundational DNA Language Models for Long Sequences

Veniamin Fishman, Yuri Kuratov, Aleksei Shmelev…·Mikhail Burtsev

GENA-LM introduces transformer-based DNA language models for long sequences, capable of handling up to 36,000 base pairs and supporting multispecies and taxon-specific applications.

137 citationstop 1%

multiple specieswhole-genome sequencing

𝕏 PostBluesky