@article{prjibelski_using_2020, title = {Using {SPAdes} De Novo Assembler}, volume = {70}, issn = {1934-3396, 1934-340X}, url = {https://onlinelibrary.wiley.com/doi/10.1002/cpbi.102}, doi = {10.1002/cpbi.102}, number = {1}, journaltitle = {Current Protocols in Bioinformatics}, shortjournal = {Current Protocols in Bioinformatics}, author = {Prjibelski, Andrey and Antipov, Dmitry and Meleshko, Dmitry and Lapidus, Alla and Korobeynikov, Anton}, urldate = {2021-05-26}, date = {2020-06}, langid = {english}, } @article{li_fast_2009, title = {Fast and accurate short read alignment with Burrows-Wheeler transform}, volume = {25}, issn = {1367-4811}, doi = {10.1093/bioinformatics/btp324}, abstract = {{MOTIVATION}: The enormous amount of short reads generated by the new {DNA} sequencing technologies call for the development of fast and accurate read alignment programs. A first generation of hash table-based methods has been developed, including {MAQ}, which is accurate, feature rich and fast enough to align short reads from a single individual. However, {MAQ} does not support gapped alignment for single-end reads, which makes it unsuitable for alignment of longer reads where indels may occur frequently. The speed of {MAQ} is also a concern when the alignment is scaled up to the resequencing of hundreds of individuals. {RESULTS}: We implemented Burrows-Wheeler Alignment tool ({BWA}), a new read alignment package that is based on backward search with Burrows-Wheeler Transform ({BWT}), to efficiently align short sequencing reads against a large reference sequence such as the human genome, allowing mismatches and gaps. {BWA} supports both base space reads, e.g. from Illumina sequencing machines, and color space reads from {AB} {SOLiD} machines. Evaluations on both simulated and real data suggest that {BWA} is approximately 10-20x faster than {MAQ}, while achieving similar accuracy. In addition, {BWA} outputs alignment in the new standard {SAM} (Sequence Alignment/Map) format. Variant calling and other downstream analyses after the alignment can be achieved with the open source {SAMtools} software package. {AVAILABILITY}: http://maq.sourceforge.net.}, pages = {1754--1760}, number = {14}, journaltitle = {Bioinformatics (Oxford, England)}, shortjournal = {Bioinformatics}, author = {Li, Heng and Durbin, Richard}, date = {2009-07-15}, pmid = {19451168}, pmcid = {PMC2705234}, keywords = {Algorithms, Genomics, Sequence Alignment, Sequence Analysis, {DNA}, Software}, file = {Full Text:/home/thomas/Zotero/storage/RAZYFYCS/Li and Durbin - 2009 - Fast and accurate short read alignment with Burrow.pdf:application/pdf}, } @article{altschul_basic_1990, title = {Basic local alignment search tool}, volume = {215}, issn = {0022-2836}, doi = {10.1016/S0022-2836(05)80360-2}, abstract = {A new approach to rapid sequence comparison, basic local alignment search tool ({BLAST}), directly approximates alignments that optimize a measure of local similarity, the maximal segment pair ({MSP}) score. Recent mathematical results on the stochastic properties of {MSP} scores allow an analysis of the performance of this method as well as the statistical significance of alignments it generates. The basic algorithm is simple and robust; it can be implemented in a number of ways and applied in a variety of contexts including straightforward {DNA} and protein sequence database searches, motif searches, gene identification searches, and in the analysis of multiple regions of similarity in long {DNA} sequences. In addition to its flexibility and tractability to mathematical analysis, {BLAST} is an order of magnitude faster than existing sequence comparison tools of comparable sensitivity.}, pages = {403--410}, number = {3}, journaltitle = {Journal of Molecular Biology}, shortjournal = {J Mol Biol}, author = {Altschul, S. F. and Gish, W. and Miller, W. and Myers, E. W. and Lipman, D. J.}, date = {1990-10-05}, pmid = {2231712}, keywords = {Algorithms, Software, Amino Acid Sequence, Base Sequence, Databases, Factual, Mutation, Sensitivity and Specificity, Sequence Homology, Nucleic Acid}, } @article{quinlan_bedtools_2010, title = {{BEDTools}: a flexible suite of utilities for comparing genomic features}, volume = {26}, issn = {1460-2059, 1367-4803}, url = {https://academic.oup.com/bioinformatics/article-lookup/doi/10.1093/bioinformatics/btq033}, doi = {10.1093/bioinformatics/btq033}, shorttitle = {{BEDTools}}, pages = {841--842}, number = {6}, journaltitle = {Bioinformatics}, author = {Quinlan, Aaron R. and Hall, Ira M.}, urldate = {2021-05-26}, date = {2010-03-15}, langid = {english}, file = {Full Text:/home/thomas/Zotero/storage/9QFL3W2J/Quinlan and Hall - 2010 - BEDTools a flexible suite of utilities for compar.pdf:application/pdf}, } @article{chen_fastp_2018, title = {fastp: an ultra-fast all-in-one {FASTQ} preprocessor}, volume = {34}, issn = {1367-4803, 1460-2059}, url = {https://academic.oup.com/bioinformatics/article/34/17/i884/5093234}, doi = {10.1093/bioinformatics/bty560}, shorttitle = {fastp}, pages = {i884--i890}, number = {17}, journaltitle = {Bioinformatics}, author = {Chen, Shifu and Zhou, Yanqing and Chen, Yaru and Gu, Jia}, urldate = {2021-05-26}, date = {2018-09-01}, langid = {english}, file = {Full Text:/home/thomas/Zotero/storage/6R62R2P4/Chen et al. - 2018 - fastp an ultra-fast all-in-one FASTQ preprocessor.pdf:application/pdf}, } @article{faust_samblaster_2014, title = {{SAMBLASTER}: fast duplicate marking and structural variant read extraction}, volume = {30}, issn = {1367-4803, 1460-2059}, url = {https://academic.oup.com/bioinformatics/article-lookup/doi/10.1093/bioinformatics/btu314}, doi = {10.1093/bioinformatics/btu314}, shorttitle = {{SAMBLASTER}}, pages = {2503--2505}, number = {17}, journaltitle = {Bioinformatics}, shortjournal = {Bioinformatics}, author = {Faust, G. G. and Hall, I. M.}, urldate = {2021-05-26}, date = {2014-09-01}, langid = {english}, file = {Full Text:/home/thomas/Zotero/storage/5PRKXKZP/Faust and Hall - 2014 - SAMBLASTER fast duplicate marking and structural .pdf:application/pdf}, }