@article{Engström.2013.24185836, author = {Engström, PG and Steijger, T and Sipos, B and Grant, GR and Kahles, A and The RGASP Consortium and Alioto, T and Behr, J and Bertone, PBohnert, R and Campagna, D and Davis, CA and Dobin, A and Engström, PG and Gingeras, TR and Goldman, N and Grant, GR and Guigó, R and Harrow, J and Hubbard, TJ and Jean, G and Kahles, A and Kosarev, P and Li, S and Liu, J and Mason, CE and Molodtsov, V and Ning, Z and Ponstingl, H and Prins, JF and Rätsch, G and Ribeca, P and Seledtsov, I and Sipos, B and Solovyev, V and Steijger, T and Valle, G and Vitulo, N and Wang, K and Wu, TD and Zeller, G and Rätsch, G and Goldman, N and Hubbard, TJ and Harrow, J and Guigó, R and Bertone, P}, title = {{Systematic evaluation of spliced alignment programs for RNA-seq data}}, journal = {Nature methods}, pages = {}, year = {2013}, url = {http://www.ncbi.nlm.nih.gov/pubmed/24185836}, abstract = {{High-throughput RNA sequencing is an increasingly accessible method for studying gene structure and activity on a genome-wide scale. A critical step in RNA-seq data analysis is the alignment of partial transcript reads to a reference genome sequence. To assess the performance of current mapping software, we invited developers of RNA-seq aligners to process four large human and mouse RNA-seq data sets. In total, we compared 26 mapping protocols based on 11 programs and pipelines and found major performance differences between methods on numerous benchmarks, including alignment yield, basewise accuracy, mismatch and gap placement, exon junction discovery and suitability of alignments for transcript reconstruction. We observed concordant results on real and simulated RNA-seq data, confirming the relevance of the metrics employed. Future developments in RNA-seq alignment methods would benefit from improved placement of multimapped reads, balanced utilization of existing gene annotation and a reduced false discovery rate for splice junctions.}} }