Correcting base-assignment errors in repeat regions of shotgun assembly. Export

@article{citeulike:3515054, abstract = {Accurate base-assignment in repeat regions of a whole genome shotgun assembly is an unsolved problem. Since reads in repeat regions cannot be easily attributed to a unique location in the genome, current assemblers may place these reads arbitrarily. As a result, the base-assignment error rate in repeats is likely to be much higher than that in the rest of the genome. We developed an iterative algorithm, EULER-AIR, that is able to correct base-assignment errors in finished genome sequences in public databases. The Wolbachia genome is among the best finished genomes. Using this genome project as an example, we demonstrated that EULER-AIR can 1) discover and correct base-assignment errors, 2) provide accurate read assignments, 3) utilize finishing reads for accurate base-assignment, and 4) provide guidance for designing finishing experiments. In the genome of Wolbachia, EULER-AIR found 16 positions with ambiguous base-assignment and two positions with erroneous bases. Besides Wolbachia, many other genome sequencing projects have significantly fewer finishing reads and, hence, are likely to contain more base-assignment errors in repeats. We demonstrate that EULER-AIR is a software tool that can be used to find and correct base-assignment errors in a genome assembly project.}, author = {Zhi, Degui and Keich, Uri and Pevzner, Pavel and Heber, Steffen and Tang, Haixu}, citeulike-article-id = {3515054}, citeulike-linkout-0 = {http://dx.doi.org/10.1109/TCBB.2007.1005}, citeulike-linkout-1 = {http://view.ncbi.nlm.nih.gov/pubmed/17277413}, citeulike-linkout-2 = {http://www.hubmed.org/display.cgi?uids=17277413}, doi = {10.1109/TCBB.2007.1005}, issn = {1545-5963}, journal = {IEEE/ACM transactions on computational biology and bioinformatics / IEEE, ACM}, keywords = {assembly, euler, repeats, sequencing, tandem-repeats}, number = {1}, pages = {54--64}, posted-at = {2009-10-13 20:22:18}, priority = {5}, title = {Correcting base-assignment errors in repeat regions of shotgun assembly.}, url = {http://dx.doi.org/10.1109/TCBB.2007.1005}, volume = {4}, year = {2007} }

TY - JOUR ID - citeulike:3515054 L3 - citeulike-article-id:3515054 N2 - Accurate base-assignment in repeat regions of a whole genome shotgun assembly is an unsolved problem. Since reads in repeat regions cannot be easily attributed to a unique location in the genome, current assemblers may place these reads arbitrarily. As a result, the base-assignment error rate in repeats is likely to be much higher than that in the rest of the genome. We developed an iterative algorithm, EULER-AIR, that is able to correct base-assignment errors in finished genome sequences in public databases. The Wolbachia genome is among the best finished genomes. Using this genome project as an example, we demonstrated that EULER-AIR can 1) discover and correct base-assignment errors, 2) provide accurate read assignments, 3) utilize finishing reads for accurate base-assignment, and 4) provide guidance for designing finishing experiments. In the genome of Wolbachia, EULER-AIR found 16 positions with ambiguous base-assignment and two positions with erroneous bases. Besides Wolbachia, many other genome sequencing projects have significantly fewer finishing reads and, hence, are likely to contain more base-assignment errors in repeats. We demonstrate that EULER-AIR is a software tool that can be used to find and correct base-assignment errors in a genome assembly project. IS - 1 JF - IEEE/ACM transactions on computational biology and bioinformatics / IEEE, ACM SN - 1545-5963 EP - 64 TI - Correcting base-assignment errors in repeat regions of shotgun assembly. VL - 4 SP - 54 KW - assembly KW - euler KW - repeats KW - sequencing KW - tandem-repeats AU - Zhi, Degui AU - Keich, Uri AU - Pevzner, Pavel AU - Heber, Steffen AU - Tang, Haixu PY - 2007///r UR - http://dx.doi.org/10.1109/TCBB.2007.1005 ER -