@inbook{459e72b0126e4cbc8e59d2618080face,
title = "Atlas of the Radical SAM Superfamily: Divergent Evolution of Function Using a “Plug and Play” Domain",
abstract = "The radical SAM superfamily contains over 100,000 homologous enzymes that catalyze a remarkably broad range of reactions required for life, including metabolism, nucleic acid modification, and biogenesis of cofactors. While the highly conserved SAM-binding motif responsible for formation of the key 5′-deoxyadenosyl radical intermediate is a key structural feature that simplifies identification of superfamily members, our understanding of their structure–function relationships is complicated by the modular nature of their structures, which exhibit varied and complex domain architectures. To gain new insight about these relationships, we classified the entire set of sequences into similarity-based subgroups that could be visualized using sequence similarity networks. This superfamily-wide analysis reveals important features that had not previously been appreciated from studies focused on one or a few members. Functional information mapped to the networks indicates which members have been experimentally or structurally characterized, their known reaction types, and their phylogenetic distribution. Despite the biological importance of radical SAM chemistry, the vast majority of superfamily members have never been experimentally characterized in any way, suggesting that many new reactions remain to be discovered. In addition to 20 subgroups with at least one known function, we identified additional subgroups made up entirely of sequences of unknown function. Importantly, our results indicate that even general reaction types fail to track well with our sequence similarity-based subgroupings, raising major challenges for function prediction for currently identified and new members that continue to be discovered. Interactive similarity networks and other data from this analysis are available from the Structure-Function Linkage Database.",
author = "Holliday, {Gemma L.} and Eyal Akiva and Meng, {Elaine C.} and Brown, {Shoshana D.} and Sara Calhoun and Ursula Pieper and Andrej Sali and Booker, {Squire J.} and Babbitt, {Patricia C.}",
note = "Funding Information: Support for this work acknowledges NIH R01 GM60595 (P. Babbitt), NIH R01 GM-122595 (S. Booker), and NSF DBI-1356193 (P. Babbitt and G. Holliday). Some of the results described in this chapter were initially developed as part of a workshop on the RSS sponsored by the Enzyme Function Initiative with support from NIH U54GM093342 (J. Gerlt). The SFLD was developed as a joint project of the Babbitt lab with support by NIH R01GM60595 and NSF Grants DBI-0234768 and DBI-0640476 (P. Babbitt), NSF DBI-1356193 (P. Babbitt and G. Holliday), and The Resource for Biocomputing, Visualization, & Informatics (T. Ferrin) with support from NIGMS P41GM103311. Support for development of the SFLD was also provided NIH U54GM093342 and P01GM07790 (J. Gerlt). The authors thank David Mischel and Benjamin Polacco for technical support of the SFLD, including implementation of new code required of the back-end and graphical user interface, and Kathy Clement for help with generating graphics images of SSNs. Publisher Copyright: {\textcopyright} 2018 Elsevier Inc.",
year = "2018",
doi = "10.1016/bs.mie.2018.06.004",
language = "English (US)",
isbn = "9780128127940",
series = "Methods in Enzymology",
publisher = "Academic Press Inc.",
pages = "1--71",
editor = "Vahe Bandarian",
booktitle = "Methods in Enzymology",
address = "United States",
}