PT  - JOURNAL ARTICLE
AU  - Laraib I. Malik
AU  - Shravya Thatipally
AU  - Nikhil Junneti
AU  - Rob Patro
TI  - Graph regularized, semi-supervised learning improves annotation of <em>de novo</em> transcriptomes
AID  - 10.1101/089417
DP  - 2016 Jan 01
TA  - bioRxiv
PG  - 089417
4099  - http://biorxiv.org/content/early/2016/11/25/089417.short
4100  - http://biorxiv.org/content/early/2016/11/25/089417.full
AB  - We present a new method, GRASS, for improving an initial annotation of de novo transcriptomes. GRASS makes the shared-sequence relationships between assembled contigs explicit in the form of a graph, and applies an algorithm that performs label propagation to transfer annotations between related contigs and modifies the graph topology iteratively. We demonstrate that GRASS increases the completeness and accuracy of the initial annotation, allows for improved differential analysis, and is very efficient, typically taking 10s of minutes.