Author

Krešimir Friganović

Agency for Science, Technology and ResearchORCID 0000-0002-6053-5539Unclaimed 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

Approach:deep learning· 2 Research Focus:benchmarking· 1 Research Focus:database / resource· 1 Assay:long-read sequencing· 1 Assay:metagenomics· 1 Research Focus:software / tool· 1 Approach:transformer / foundation model· 1

Frequent Co-Authors

Mile ŠikićiD· 2 shared Bryan HooiiD· 1 shared Dominik StanojevićiD· 1 shared Po-Shen Benson CheniD· 1 shared Sara BakićiD· 1 shared

Activity by Year

2026-2026 · peak 2/yr

Co-Author Collaboration Network

5 top collaborators · 6 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

Mile ŠikićORCID

Mutual co-authors in cluster

Author profile →

2 papers

Recent·Most cited

Metaxa: A Transformer-Based Deep Learning Model for Taxonomic Classification of Long Nanopore Reads

Krešimir Friganović, Dominik Stanojević, Po-Shen Benson Chen, Mile Šikić

Metaxa is a transformer-based model for classifying long Nanopore reads, outperforming existing tools on out-of-sample data and across different sequencing chemistries.

bioRxiv · Apr 23, 2026 · PreprintBioinformatics

Campolina: A Deep Neural Framework for Accurate Segmentation of Nanopore Signals

Sara Bakić, Krešimir Friganović, Bryan Hooi, Mile Šikić

Campolina improves nanopore signal segmentation accuracy using deep learning, outperforming traditional methods on real datasets.

Genome biology · Jan 27, 2026Peer-reviewedBioinformatics