%0 Journal Article %1 Pucker:2017:BMC-Res-Notes:29202864 %A Pucker, B %A Holtgräwe, D %A Weisshaar, B %D 2017 %J BMC Res Notes %K myown %N 1 %P 667-667 %R 10.1186/s13104-017-2985-y %T Consideration of non-canonical splice sites improves gene prediction on the Arabidopsis thaliana Niederzenz-1 genome sequence %U https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5716242/ %V 10 %X The Arabidopsis thaliana Niederzenz-1 genome sequence was recently published with an ab initio gene prediction. In depth analysis of the predicted gene set revealed some errors involving genes with non-canonical splice sites in their introns. Since non-canonical splice sites are difficult to predict ab initio, we checked for options to improve the annotation by transferring annotation information from the recently released Columbia-0 reference genome sequence annotation Araport11.Incorporation of hints generated from Araport11 enabled the precise prediction of non-canonical splice sites. Manual inspection of RNA-Seq read mapping and RT-PCR were applied to validate the structural annotations of non-canonical splice sites. Predictions of untranslated regions were also updated by harnessing the potential of Araport11's information, which was generated by using high coverage RNA-Seq data. The improved gene set of the Nd-1 genome assembly (GeneSet\_Nd-1\_v1.1) was evaluated via comparison to the initial gene prediction (GeneSet\_Nd-1\_v1.0) as well as against Araport11 for the Col-0 reference genome sequence. GeneSet\_Nd-1\_v1.1 contains previously missed non-canonical splice sites in 1256 genes. Reciprocal best hits for 24,527 (89.4%) of all nuclear Col-0 genes against the GeneSet\_Nd-1\_v1.1 indicate a high gene prediction quality.

@article{Pucker:2017:BMC-Res-Notes:29202864, abstract = {The Arabidopsis thaliana Niederzenz-1 genome sequence was recently published with an ab initio gene prediction. In depth analysis of the predicted gene set revealed some errors involving genes with non-canonical splice sites in their introns. Since non-canonical splice sites are difficult to predict ab initio, we checked for options to improve the annotation by transferring annotation information from the recently released Columbia-0 reference genome sequence annotation Araport11.Incorporation of hints generated from Araport11 enabled the precise prediction of non-canonical splice sites. Manual inspection of RNA-Seq read mapping and RT-PCR were applied to validate the structural annotations of non-canonical splice sites. Predictions of untranslated regions were also updated by harnessing the potential of Araport11's information, which was generated by using high coverage RNA-Seq data. The improved gene set of the Nd-1 genome assembly (GeneSet\_Nd-1\_v1.1) was evaluated via comparison to the initial gene prediction (GeneSet\_Nd-1\_v1.0) as well as against Araport11 for the Col-0 reference genome sequence. GeneSet\_Nd-1\_v1.1 contains previously missed non-canonical splice sites in 1256 genes. Reciprocal best hits for 24,527 (89.4%) of all nuclear Col-0 genes against the GeneSet\_Nd-1\_v1.1 indicate a high gene prediction quality.}, added-at = {2018-11-08T06:37:43.000+0100}, author = {Pucker, B and Holtgräwe, D and Weisshaar, B}, biburl = {https://www.bibsonomy.org/bibtex/20901528c921639f18e765322a3e7ac6c/bpucker}, description = {Consideration of non-canonical splice sites improves gene prediction on the Arabidopsis thaliana Niederzenz-1 genome sequence}, doi = {10.1186/s13104-017-2985-y}, interhash = {a41f87c73a3610dce50af2a49550e3fd}, intrahash = {0901528c921639f18e765322a3e7ac6c}, journal = {BMC Res Notes}, keywords = {myown}, month = dec, number = 1, pages = {667-667}, pmid = {29202864}, timestamp = {2018-11-08T06:37:43.000+0100}, title = {Consideration of non-canonical splice sites improves gene prediction on the Arabidopsis thaliana Niederzenz-1 genome sequence}, url = {https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5716242/}, volume = 10, year = 2017 }