Software - Gene Sequence Analysis Snekmer: A scalable pipeline for protein sequence fingerprinting using amino acid recoding (AAR)

Last updated on 2023-02-23T19:37:46+00:00 by LN Anderson

Snekmer: A scalable pipeline for protein sequence fingerprinting using amino acid recoding (AAR)

Snekmer is a software package designed to reduce the representation of protein sequences by combining amino acid reduction (AAR) with the kmer approach. Based on the AAR-kmer representations, Snekmer subsequently (1) clusters sequences using various unsupervised clustering algorithms, (2) generates supervised machine learning models, or (3) searches sequences against pre-trained models to determine probabilistic annotations.

Data Reuse Citation Policy

When referencing and reusing linked PerCon SFA project digital data assets listed at the PNNL DataHub institutional repository, we ask that users please cite the dataset digital object identifier provided at the download page and any corresponding journal article publications. Reference citations, where applicable, should provide the necessary metadata information required to support, corroborate, verify, and otherwise determine the legitimacy of the research findings provided (data and code) from scholarly publications and corresponding project data releases.

Cite as

1. McDermott, Jason E., Chang, Christine H., Jerger, Abby, Nelson, William B., & Jacobson, Jeremy R. (2023). Snekmer: A scalable pipeline for protein sequence fingerprinting using amino acid recoding (AAR) (v1.0.3). Zenodo. doi: https://doi.org/10.5281/zenodo.7662597. url: https://github.com/PNNL-CompBio/Snekmer
2. Christine H Chang, William C Nelson, Abby Jerger, Aaron T Wright, Robert G Egbert, Jason E McDermott, Snekmer: a scalable pipeline for protein sequence fingerprinting based on amino acid recoding, Bioinformatics Advances, Volume 3, Issue 1, 2023, vbad005, https://doi.org/10.1093/bioadv/vbad005.