[ { "id": "authors:d7df6-3n859", "collection": "authors", "collection_id": "d7df6-3n859", "cite_using_url": "https://authors.library.caltech.edu/records/d7df6-3n859", "type": "publication_erratum", "title": "Correction to \"DeCOIL: Optimization of Degenerate Codon Libraries for Machine Learning-Assisted Protein Engineering\"", "author": [ { "family_name": "Yang", "given_name": "Jason", "orcid": "0000-0003-3184-1550", "clpid": "Yang-Jason" }, { "family_name": "Ducharme", "given_name": "Julie", "clpid": "Ducharme-Julie" }, { "family_name": "Johnston", "given_name": "Kadina E.", "orcid": "0000-0002-2214-3534", "clpid": "Johnston-Kadina-E" }, { "family_name": "Li", "given_name": "Francesca-Zhoufan", "orcid": "0000-0002-5710-9512", "clpid": "Li-Francesca-Zhoufan" }, { "family_name": "Yue", "given_name": "Yisong", "orcid": "0000-0001-9127-1989", "clpid": "Yue-Yisong" }, { "family_name": "Arnold", "given_name": "Frances H.", "orcid": "0000-0002-4027-364X", "clpid": "Arnold-F-H" } ], "abstract": "

Introduction, third paragraph, replace “Other studies take different approaches to bias libraries toward distributions of favorable variants, ranging from theoretical to more applied.16,51–55 Each study approaches the problem from a different angle, but none have been made both suitable and practical for the possible use cases encountered during MLPE (Figure 1A)” with “Other studies take different approaches to bias libraries toward distributions of favorable variants, ranging from theoretical to more applied.16,51–55 The most relevant to our work is Zhu et al.,16 which presents a method to maximize the diversity of a library, subject to a constraint on predicted variant fitness. In the future, it would be interesting to conduct a more detailed comparison to understand how suitable and practical each method is for different MLPE use cases (Figure 1A).

\n

Replace ref 16 with:

\n

(16) Zhu, D.; Brookes, D. H.; Busia, A.; Carneiro, A.; Fannjiang, C.; Popova, G.; Shin, D.; Donohue, K. C.; Chang, E. F.; Nowakowski, T. J.; Listgarten, J.; Schaffer, D. V. Optimal Trade-off Control in Machine Learning-Based Library Design, with Application to Adeno-Associated Virus (AAV) for Gene Therapy. Sci. Adv., in press.

", "doi": "10.1021/acssynbio.3c00751", "issn": "2161-5063", "publisher": "American Chemical Society", "publication": "ACS Synthetic Biology", "publication_date": "2024-01-17", "series_number": "2", "volume": "13", "issue": "2", "pages": "692" } ]