Home
Login
Deutsch
Advanced Search
Browse by ...
Publication overview
Contact persons
Help
Publ. Version/Full Text
Research data
DOI
 |
Open Access Gold |
|
as soon as is submitted to ZB.
seqme : A Python library for evaluating biological sequence design from generative models.
Bioinfo. Adv. 6:vbag212 (2026)
Summary: Recent advances in computational methods for designing biological sequences have sparked the developmentof metrics to evaluate these methods performance in terms of the fidelity of the designed sequences to a target distribu-tion and their attainment of desired properties. However, a software library implementing these metrics was lacking. Inthis work we introduce seqme, a modular and highly extendable open-source Python library, containing model-agnosticmetrics for evaluating computational methods for biological sequence design. seqme considers three groups of metrics:sequence-based, embedding-based, and property-based, and is applicable to a wide range of biological sequences: smallmolecules, DNA, ncRNA, mRNA, peptides and proteins. The library offers a number of embedding and property models forbiological sequences, as well as diagnostics and visualization functions to inspect the results. seqme can be used to evalu-ate both one-shot generation and iterative optimization. We show the utility of seqme by performing an antimicrobialpeptide benchmark and acquiring mRNA data.
Altmetric
Additional Metrics?
Edit extra informations
Login
Publication type
Article: Journal article
Document type
Scientific Article
Keywords
Python (programming Language) ; Modular Design ; Visualization ; Software ; Embedding ; Biological Database ; Fidelity
ISSN (print) / ISBN
2635-0041
e-ISSN
2635-0041
Journal
Bioinformatics Advances
Quellenangaben
Volume: 6,
Issue: 1,
Article Number: vbag212
Publisher
Oxford University Press
Reviewing status
Peer reviewed
Institute(s)
Institute of AI for Health (AIH)