Author

Sebastian Franz

Technical University of MunichORCID 0009-0002-0740-1571Unclaimed ORCID profile · follow to get notified of new preprints

Biology Disciplines

Click to filter author papers

Bioinformatics· 3

Signature Assays, Organisms & Methods

Click to filter · or open tag

Research Focus:benchmarking· 3 Assay:protein sequence· 3 Approach:statistical model· 2 Approach:experimental assay· 1 Research Focus:protein design· 1 Research Focus:protein structure prediction· 1 Research Focus:software / tool· 1

Frequent Co-Authors

Burkhard RostiD· 3 shared Maurice BrenneriD· 2 shared Michael HeinzingeriD· 2 shared Alexander P.iD· 1 shared Amine SmaouiiD· 1 shared Luisa F. Jiménez SotoiD· 1 shared MANUEL PLONERiD· 1 shared Paula Schloetermann· 1 shared

Activity by Year

2026-2026 · peak 3/yr

Co-Author Collaboration Network

10 top collaborators · 23 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

Burkhard RostORCID

Mutual co-authors in cluster

Author profile →

3 papers

Recent·Most cited

DeePEn - A Depth sensitive benchmark for Protein Engineering

Robert Schmirler, Maurice Brenner, Sebastian Franz, Michael Heinzinger, Burkhard Rost

DeePEn evaluates protein engineering models' ability to predict fitness of variants with increasing mutational distance from wildtype.

bioRxiv · Jun 11, 2026 · PreprintBioinformatics

Pseudoperplexity Probes Memorization in Protein Language Models

Alexander P., MANUEL PLONER, Zeno Sewald, Tobias Senoner, Sebastian Franz, Maurice Brenner, Michael Heinzinger, Burkhard Rost

This study uses pseudoperplexity to assess whether ProtT5 memorizes its training data, finding detectable but limited memorization.

bioRxiv · Jun 10, 2026 · PreprintBioinformatics

biocentral: embedding-based protein predictions

Sebastian Franz, Tobias Olenyi, Paula Schloetermann, Amine Smaoui, Luisa F. Jiménez Soto, Burkhard Rost

Biocentral provides an open embedding-based service for protein predictions, demonstrating its utility with a virus database analysis and training module.

Journal of Molecular Biology · Jan 30, 2026Peer-reviewedBioinformatics