Author

Nikolaos Rafailidis

University of DelawarePrimary ORCID profile (0009-0002-2988-7533 · 1 paper)Unclaimed ORCID profile · follow to get notified of new preprints

Listed by name: these papers carry no ORCID for this author, so different people with the same name may be mixed together.

Same name, identified by ORCID

Nikolaos RafailidisiD1 paper · University of Delaware;

Biology Disciplines

Click to filter author papers

Bioinformatics· 3

Signature Assays, Organisms & Methods

Click to filter · or open tag

Assay:protein sequence· 3 Approach:transformer / foundation model· 2 Research Focus:benchmarking· 1 Research Focus:cell-cell communication· 1 Approach:deep learning· 1 Research Focus:differential expression· 1 Research Focus:gene regulatory network inference· 1 Approach:machine learning (classical)· 1

Frequent Co-Authors

Jason P. GleghorniD· 3 shared Logan HalleeiD· 3 shared Colin Horger· 1 shared David Ke HongiD· 1 shared Tamar Peleg· 1 shared

Activity by Year

2023-2026 · peak 1/yr

Co-Author Collaboration Network

5 top collaborators · 8 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

3 shared papersBioinformatics

Jason P. GleghornORCID

Mutual co-authors in cluster

Author profile →

3 papers

Recent·Most cited

Protein Language Models are Accidental Taxonomists

Logan Hallee, Tamar Peleg, Nikolaos Rafailidis, Jason P. Gleghorn

The paper shows that protein language models can exploit taxonomic information rather than true interaction features in PPI datasets, leading to inflated performance.

BMC Bioinformatics · Jun 12, 2026Peer-reviewedBioinformatics

Annotation Vocabulary (Might Be) All You Need

Logan Hallee, Nikolaos Rafailidis, Colin Horger, David Ke Hong, Jason P. Gleghorn

The paper introduces Annotation Vocabulary to enhance protein embeddings using structured ontologies, demonstrating its effectiveness through various downstream tasks and generative models.

bioRxiv · Jul 30, 2024 · PreprintBioinformatics

cdsBERT - Extending Protein Language Models with Codon Awareness

Logan Hallee, Nikolaos Rafailidis, Jason P. Gleghorn

This paper introduces cdsBERT, a protein language model trained on codon sequences, which outperforms amino acid-based models in enzyme prediction and reveals codon usage patterns in embeddings.

bioRxiv · Sep 15, 2023 · PreprintBioinformatics