SeqImprove: Machine-Learning-Assisted Curation of Genetic Circuit Sequence Information

• DOI: 10.1021/acssynbio.4c00392
• Publication Date: 2024-09-04T15:50:49Z
• Authors: Jeanet Mante; Zach Sents; Duncan Britt; William Mo; Chunxiao Liao; Ryan Greer; Chris J. Myers
• Keywords: Sequence (biology)

The progress and utility of synthetic biology is currently hindered by the lengthy process studying literature replicating poorly documented work. Reconstruction crucial design information through post hoc curation highly noisy error-prone. To combat this, author participation during crucial. encourage without overburdening them, an ML-assisted tool called SeqImprove has been developed. Using named entity recognition, normalization, sequence matching, creates machine-accessible data metadata annotations, which authors can then review edit before submitting a final file. makes it easier for to submit that FAIR (findable, accessible, interoperable, reusable).