Author

Lukas Beierle

Justus-Liebig-Universität GießenORCID 0009-0009-3830-5006Unclaimed ORCID profile · follow to get notified of new preprints

Biology Disciplines

Click to filter author papers

Bioinformatics· 1 Systems Biology· 1

Signature Assays, Organisms & Methods

Click to filter · or open tag

Approach:deep learning· 1 Organism:human· 1 Research Focus:protein design· 1 Assay:protein sequence· 1 Approach:statistical model· 1 Approach:transformer / foundation model· 1 Research Focus:variant effect prediction· 1 Approach:variational autoencoder· 1

Frequent Co-Authors

Reihaneh MostolizadehiD· 2 shared Alexander GoesmanniD· 1 shared Bernd SchmeckiD· 1 shared Franz CemičiD· 1 shared Julian M. HahnfeldiD· 1 shared Syed Mushahid HussainiD· 1 shared

Activity by Year

2026-2026 · peak 2/yr

Co-Author Collaboration Network

6 top collaborators · 9 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 papersSystems Biology

Reihaneh MostolizadehORCID

Mutual co-authors in cluster

Author profile →

2 papers

Recent·Most cited

Systems BiologybioRxivPreprintJun 14, 2026

First Genome-Scale Metabolic Model for Understanding HMPV-Host Interaction

Syed Mushahid Hussain, Lukas Beierle, Bernd Schmeck, Reihaneh Mostolizadeh

The paper constructs the first genome-scale metabolic model for HMPV, identifies antiviral targets, and highlights UDP-GlcNAc as a critical metabolic hub for viral replication.

DOI 10.64898/2026.06.10.731436

humanstatistical model

𝕏 PostBluesky

BioinformaticsBioData MiningPeer-reviewedMay 9, 2026

Generative models for antimicrobial peptide design: auto-encoders and beyond

Lukas Beierle, Julian M. Hahnfeld, Alexander Goesmann…·Franz Cemič

This study compares deep learning models for generating antimicrobial peptides, finding that auto-encoders, especially Wasserstein auto-encoders, produce more diverse sequences than other models.

2 citationstop 4%

protein sequencedeep learning

𝕏 PostBluesky