@article {Hart307868, author = {Alexander J. Hart and Samuel Ginzburg and Muyang (Sam) Xu and Cera R. Fisher and Nasim Rahmatpour and Jeffry B. Mitton and Robin Paul and Jill L. Wegrzyn}, title = {EnTAP: Bringing Faster and Smarter Functional Annotation to Non-Model Eukaryotic Transcriptomes}, elocation-id = {307868}, year = {2019}, doi = {10.1101/307868}, publisher = {Cold Spring Harbor Laboratory}, abstract = {EnTAP (Eukaryotic Non-Model Transcriptome Annotation Pipeline) was designed to improve the accuracy, speed, and flexibility of functional gene annotation for de novo assembled transcriptomes in non-model eukaryotes. This software package addresses the fragmentation and related assembly issues that result in inflated transcript estimates and poor annotation rates, while focusing primarily on protein-coding transcripts. Following filters applied through assessment of true expression and frame selection, open-source tools are leveraged to functionally annotate the translated proteins. Downstream features include fast similarity search across three repositories, protein domain assignment, orthologous gene family assessment, and Gene Ontology term assignment. The final annotation integrates across multiple databases and selects an optimal assignment from a combination of weighted metrics describing similarity search score, taxonomic relationship, and informativeness. Researchers have the option to include additional filters to identify and remove contaminants, identify associated pathways, and prepare the transcripts for enrichment analysis. This fully featured pipeline is easy to install, configure, and runs significantly faster than comparable annotation packages. EnTAP is optimized to generate extensive functional information for the gene space of organisms with limited or poorly characterized genomic resources.}, URL = {https://www.biorxiv.org/content/early/2019/08/13/307868}, eprint = {https://www.biorxiv.org/content/early/2019/08/13/307868.full.pdf}, journal = {bioRxiv} }