Author

Ronnie Rajan

ORCID 0000-0002-4982-0451Unclaimed ORCID profile · follow to get notified of new preprints

Biology Disciplines

Click to filter author papers

Signature Assays, Organisms & Methods

Click to filter · or open tag

Research Focus:benchmarking· 2 Approach:statistical model· 2 Assay:whole-genome sequencing· 2 Approach:deep learning· 1 Assay:DNA methylation· 1 Research Focus:gene regulatory network inference· 1 Organism:human· 1 Research Focus:variant effect prediction· 1

Frequent Co-Authors

Karthik Viswanathan· 2 shared Kirill Vishniakov· 2 shared Marco AF Pimentel· 2 shared Praveenkumar Kanithi· 2 shared Shadab KhaniD· 2 shared Александр Владимирович МедведевiD· 2 shared Clément Christophe· 1 shared Prateek Munjal· 1 shared

Activity by Year

2024-2025 · peak 1/yr

Co-Author Collaboration Network

9 top collaborators · 36 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 papersGenomics

Karthik Viswanathan

Mutual co-authors in cluster

Author profile →

2 papers

Recent·Most cited

BioToken and BioFM - Biologically-Informed Tokenization Enables Accurate and Efficient Genomic Foundation Models

Александр Владимирович Медведев, Karthik Viswanathan, Praveenkumar Kanithi, Kirill Vishniakov, Prateek Munjal, Clément Christophe, Tiago R Magalhães, Marco AF Pimentel, Ronnie Rajan, Shadab Khan

This paper introduces BioToken and BioFM, biologically-informed genomic models that improve performance and efficiency in genomic tasks by incorporating biological context into tokenization.

bioRxiv · Mar 27, 2025 · PreprintGenomics

Tokenization to Transfer: Do Genomic Foundation Models Learn Good Representations?

Kirill Vishniakov, Karthik Viswanathan, Александр Владимирович Медведев, Praveenkumar Kanithi, Marco AF Pimentel, Ronnie Rajan, Shadab Khan

This study evaluates seven Genomic Foundation Models across 52 genomic tasks, finding that random baselines are strong and tokenizer choices significantly impact performance.

bioRxiv · Dec 18, 2024 · PreprintGenomics