Author

Vincentius Jeremy Suhardi

Hospital for Special SurgeryORCID 0000-0002-5783-5434Unclaimed 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 Assay:GWAS summary statistics· 2 Research Focus:database / resource· 1 Approach:deep learning· 1 Assay:electronic health records· 1 Research Focus:gene regulatory network inference· 1 Approach:large language model· 1 Approach:transformer / foundation model· 1

Frequent Co-Authors

Anastasia OktarinaiD· 2 shared Mathias P. BostromiD· 2 shared Nicolas Matthew SuhardiiD· 2 shared Yang XuiD· 2 shared Damanpreet Dhillon· 1 shared Dona Ninan· 1 shared Julia S. RetzkyiD· 1 shared

Activity by Year

2025-2025 · peak 2/yr

Co-Author Collaboration Network

7 top collaborators · 21 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 papersGenetics

Anastasia OktarinaORCID

Mutual co-authors in cluster

Author profile →

2 papers

Recent·Most cited

GeneticsbioRxivPreprintJun 11, 2025

Evaluating Large Language Models for Gene-to-Phenotype Mapping: The Critical Role of Full-Text Database Access

Nicolas Matthew Suhardi, Anastasia Oktarina, Julia S. Retzky…·Vincentius Jeremy Suhardi

This study evaluates LLMs for gene-to-phenotype mapping, finding that models with dedicated databases achieve >80% accuracy and provide supporting literature.

DOI 10.1101/2025.06.11.659165

GWAS summary statisticslarge language model

𝕏 PostBluesky

GenomicsbioRxivPreprintJan 28, 2025

Database-Augmented Transformer-Based Large Language Models Achieve High Accuracy in Mapping Gene-Phenotype Relationships

Nicolas Matthew Suhardi, Anastasia Oktarina, Mathias P. Bostrom…·Vincentius Jeremy Suhardi

This study evaluates LLMs for gene-phenotype mapping, finding that fine-tuned models with dedicated databases achieve high accuracy (>80%) in mapping 102 genes to four phenotypes.

DOI 10.1101/2025.01.28.635344

GWAS summary statisticselectronic health records

𝕏 PostBluesky