Author

Vahid Atabaigi Elmi

Helmholtz Centre for Infection ResearchORCID 0009-0002-0045-2683Unclaimed 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

Research Focus:benchmarking· 2 Approach:deep learning· 1 Research Focus:drug response / drug discovery· 1 Approach:machine learning (classical)· 1 Research Focus:protein design· 1 Research Focus:protein structure prediction· 1 Approach:transformer / foundation model· 1

Frequent Co-Authors

Olga V. KalininaiD· 2 shared Roman JoeresiD· 2 shared

Activity by Year

2025-2026 · peak 1/yr

Co-Author Collaboration Network

2 top collaborators · 1 mutual co-author link

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

Olga V. KalininaORCID

Mutual co-authors in cluster

Author profile →

2 papers

Recent·Most cited

BioinformaticsBioinformaticsPeer-reviewedSep 30, 2026

Information Leakage in Enzyme Substrate Prediction

Vahid Atabaigi Elmi, Roman Joeres, Olga V. Kalinina

This study identifies information leakage in enzyme-substrate prediction models and datasets, showing performance drops when leakage is removed.

1 citation

deep learningbenchmarking

𝕏 PostBluesky

BioinformaticsbioRxivPreprintOct 9, 2025

A General Transformer-Based Multi-Task Learning Framework for Predicting Interaction Types between Enzyme and Small Molecule

Vahid Atabaigi Elmi, Roman Joeres, Olga V. Kalinina

This paper introduces EMMA, a transformer-based multi-task learning framework for predicting enzyme-small molecule interactions, showing strong performance across different data-splitting regimes.

DOI 10.1101/2025.10.09.681419

transformer / foundation modelmachine learning (classical)

𝕏 PostBluesky