@article{10.1093/molbev/msy224, author = {Flagel, Lex and Brandvain, Yaniv and Schrider, Daniel R}, title = "{The Unreasonable Effectiveness of Convolutional Neural Networks in Population Genetic Inference}", journal = {Molecular Biology and Evolution}, volume = 36, number = 2, pages = {220-238}, year = 2018, month = 12, abstract = "{Population-scale genomic data sets have given researchers incredible amounts of information from which to infer evolutionary histories. Concomitant with this flood of data, theoretical and methodological advances have sought to extract information from genomic sequences to infer demographic events such as population size changes and gene flow among closely related populations/species, construct recombination maps, and uncover loci underlying recent adaptation. To date, most methods make use of only one or a few summaries of the input sequences and therefore ignore potentially useful information encoded in the data. The most sophisticated of these approaches involve likelihood calculations, which require theoretical advances for each new problem, and often focus on a single aspect of the data (e.g., only allele frequency information) in the interest of mathematical and computational tractability. Directly interrogating the entirety of the input sequence data in a likelihood-free manner would thus offer a fruitful alternative. Here, we accomplish this by representing DNA sequence alignments as images and using a class of deep learning methods called convolutional neural networks (CNNs) to make population genetic inferences from these images. We apply CNNs to a number of evolutionary questions and find that they frequently match or exceed the accuracy of current methods. Importantly, we show that CNNs perform accurate evolutionary model selection and parameter estimation, even on problems that have not received detailed theoretical treatments. Thus, when applied to population genetic alignments, CNNs are capable of outperforming expert-derived statistical methods and offer a new path forward in cases where no likelihood approach exists.}", issn = {0737-4038}, doi = {10.1093/molbev/msy224}, url = {https://doi.org/10.1093/molbev/msy224}, eprint = {https://academic.oup.com/mbe/article-pdf/36/2/220/27736968/msy224.pdf}, } @Article{pmid19706884, Author = "Robins, H. S. and Campregher, P. V. and Srivastava, S. K. and Wacher, A. and Turtle, C. J. and Kahsai, O. and Riddell, S. R. and Warren, E. H. and Carlson, C. S. ", Title = "{{C}omprehensive assessment of {T}-cell receptor beta-chain diversity in alphabeta {T} cells}", Journal = "Blood", Year = 2009, Volume = 114, Number = 19, Pages = "4099--4107", Month = "Nov" } @article {Nurk2021.05.26.445798, author = {Nurk, Sergey and Koren, Sergey and Rhie, Arang and Rautiainen, Mikko and Bzikadze, Andrey V. and Mikheenko, Alla and Vollger, Mitchell R. and Altemose, Nicolas and Uralsky, Lev and Gershman, Ariel and Aganezov, Sergey and Hoyt, Savannah J. and Diekhans, Mark and Logsdon, Glennis A. and Alonge, Michael and Antonarakis, Stylianos E. and Borchers, Matthew and Bouffard, Gerard G. and Brooks, Shelise Y. and Caldas, Gina V. and Cheng, Haoyu and Chin, Chen-Shan and Chow, William and de Lima, Leonardo G. and Dishuck, Philip C. and Durbin, Richard and Dvorkina, Tatiana and Fiddes, Ian T. and Formenti, Giulio and Fulton, Robert S. and Fungtammasan, Arkarachai and Garrison, Erik and Grady, Patrick G.S. and Graves-Lindsay, Tina A. and Hall, Ira M. and Hansen, Nancy F. and Hartley, Gabrielle A. and Haukness, Marina and Howe, Kerstin and Hunkapiller, Michael W. and Jain, Chirag and Jain, Miten and Jarvis, Erich D. and Kerpedjiev, Peter and Kirsche, Melanie and Kolmogorov, Mikhail and Korlach, Jonas and Kremitzki, Milinn and Li, Heng and Maduro, Valerie V. and Marschall, Tobias and McCartney, Ann M. and McDaniel, Jennifer and Miller, Danny E. and Mullikin, James C. and Myers, Eugene W. and Olson, Nathan D. and Paten, Benedict and Peluso, Paul and Pevzner, Pavel A. and Porubsky, David and Potapova, Tamara and Rogaev, Evgeny I. and Rosenfeld, Jeffrey A. and Salzberg, Steven L. and Schneider, Valerie A. and Sedlazeck, Fritz J. and Shafin, Kishwar and Shew, Colin J. and Shumate, Alaina and Sims, Yumi and Smit, Arian F. A. and Soto, Daniela C. and Sovi{\'c}, Ivan and Storer, Jessica M. and Streets, Aaron and Sullivan, Beth A. and Thibaud-Nissen, Fran{\c c}oise and Torrance, James and Wagner, Justin and Walenz, Brian P. and Wenger, Aaron and Wood, Jonathan M. D. and Xiao, Chunlin and Yan, Stephanie M. and Young, Alice C. and Zarate, Samantha and Surti, Urvashi and McCoy, Rajiv C. and Dennis, Megan Y. and Alexandrov, Ivan A. and Gerton, Jennifer L. and O{\textquoteright}Neill, Rachel J. and Timp, Winston and Zook, Justin M. and Schatz, Michael C. and Eichler, Evan E. and Miga, Karen H. and Phillippy, Adam M.}, title = {The complete sequence of a human genome}, elocation-id = {2021.05.26.445798}, year = 2021, doi = {10.1101/2021.05.26.445798}, publisher = {Cold Spring Harbor Laboratory}, abstract = {In 2001, Celera Genomics and the International Human Genome Sequencing Consortium published their initial drafts of the human genome, which revolutionized the field of genomics. While these drafts and the updates that followed effectively covered the euchromatic fraction of the genome, the heterochromatin and many other complex regions were left unfinished or erroneous. Addressing this remaining 8\% of the genome, the Telomere-to-Telomere (T2T) Consortium has finished the first truly complete 3.055 billion base pair (bp) sequence of a human genome, representing the largest improvement to the human reference genome since its initial release. The new T2T-CHM13 reference includes gapless assemblies for all 22 autosomes plus Chromosome X, corrects numerous errors, and introduces nearly 200 million bp of novel sequence containing 2,226 paralogous gene copies, 115 of which are predicted to be protein coding. The newly completed regions include all centromeric satellite arrays and the short arms of all five acrocentric chromosomes, unlocking these complex regions of the genome to variational and functional studies for the first time.Competing Interest StatementAF and CSC are employees of DNAnexus; IS, JK, MWH, PP, and AW are employees of Pacific Biosciences; FJS has received travel funds to speak at events hosted by Pacific Biosciences; SK and FJS have received travel funds to speak at events hosted by Oxford Nanopore Technologies. WT has licensed two patents to Oxford Nanopore Technologies (US 8748091 and 8394584).}, URL = {https://www.biorxiv.org/content/early/2021/05/27/2021.05.26.445798}, eprint = {https://www.biorxiv.org/content/early/2021/05/27/2021.05.26.445798.full.pdf}, journal = {bioRxiv} } @ARTICLE{10.3389/fgene.2020.00900, AUTHOR = {Wang, Luotong and Qu, Li and Yang, Longshu and Wang, Yiying and Zhu, Huaiqiu}, TITLE = {NanoReviser: An Error-Correction Tool for Nanopore Sequencing Based on a Deep Learning Algorithm}, JOURNAL = {Frontiers in Genetics}, VOLUME = 11, PAGES = 900, YEAR = 2020, URL = {https://www.frontiersin.org/article/10.3389/fgene.2020.00900}, DOI = {10.3389/fgene.2020.00900}, ISSN = {1664-8021}, ABSTRACT = {Nanopore sequencing is regarded as one of the most promising third-generation sequencing (TGS) technologies. Since 2014, Oxford Nanopore Technologies (ONT) has developed a series of devices based on nanopore sequencing to produce very long reads, with an expected impact on genomics. However, the nanopore sequencing reads are susceptible to a fairly high error rate owing to the difficulty in identifying the DNA bases from the complex electrical signals. Although several basecalling tools have been developed for nanopore sequencing over the past years, it is still challenging to correct the sequences after applying the basecalling procedure. In this study, we developed an open-source DNA basecalling reviser, NanoReviser, based on a deep learning algorithm to correct the basecalling errors introduced by current basecallers provided by default. In our module, we re-segmented the raw electrical signals based on the basecalled sequences provided by the default basecallers. By employing convolution neural networks (CNNs) and bidirectional long short-term memory (Bi-LSTM) networks, we took advantage of the information from the raw electrical signals and the basecalled sequences from the basecallers. Our results showed NanoReviser, as a post-basecalling reviser, significantly improving the basecalling quality. After being trained on standard ONT sequencing reads from public E. coli and human NA12878 datasets, NanoReviser reduced the sequencing error rate by over 5% for both the E. coli dataset and the human dataset. The performance of NanoReviser was found to be better than those of all current basecalling tools. Furthermore, we analyzed the modified bases of the E. coli dataset and added the methylation information to train our module. With the methylation annotation, NanoReviser reduced the error rate by 7% for the E. coli dataset and specifically reduced the error rate by over 10% for the regions of the sequence rich in methylated bases. To the best of our knowledge, NanoReviser is the first post-processing tool after basecalling to accurately correct the nanopore sequences without the time-consuming procedure of building the consensus sequence. The NanoReviser package is freely available at https://github.com/pkubioinformatics/NanoReviser.} }  @Article{Davis2021, author = {Davis, Eric M. and Sun, Yu and Liu, Yanling and Kolekar, Pandurang and Shao, Ying and Szlachta, Karol and Mulder, Heather L. and Ren, Dongren and Rice, Stephen V. and Wang, Zhaoming and Nakitandwe, Joy and Gout, Alexander M. and Shaner, Bridget and Hall, Salina and Robison, Leslie L. and Pounds, Stanley and Klco, Jeffery M. and Easton, John and Ma, Xiaotu}, title = {SequencErr: measuring and suppressing sequencer errors in next-generation sequencing data}, journal = {Genome Biology}, year = 2021, month = {Jan}, day = 25, volume = 22, number = 1, pages = 37, abstract = {There is currently no method to precisely measure the errors that occur in the sequencing instrument/sequencer, which is critical for next-generation sequencing applications aimed at discovering the genetic makeup of heterogeneous cellular populations.}, issn = {1474-760X}, doi = {10.1186/s13059-020-02254-2}, url = {https://doi.org/10.1186/s13059-020-02254-2} } @article{HEATHER20161, title = {The sequence of sequencers: The history of sequencing DNA}, journal = {Genomics}, volume = 107, number = 1, pages = {1-8}, year = 2016, issn = {0888-7543}, doi = {https://doi.org/10.1016/j.ygeno.2015.11.003}, url = {https://www.sciencedirect.com/science/article/pii/S0888754315300410}, author = {James M. Heather and Benjamin Chain}, keywords = {DNA, RNA, Sequencing, Sequencer, History}, abstract = {Determining the order of nucleic acid residues in biological samples is an integral component of a wide variety of research applications. Over the last fifty years large numbers of researchers have applied themselves to the production of techniques and technologies to facilitate this feat, sequencing DNA and RNA molecules. This time-scale has witnessed tremendous changes, moving from sequencing short oligonucleotides to millions of bases, from struggling towards the deduction of the coding sequence of a single gene to rapid and widely available whole genome sequencing. This article traverses those years, iterating through the different generations of sequencing technology, highlighting some of the key discoveries, researchers, and sequences along the way.} }  @Article{vanDijk2014, author = {van Dijk, Erwin L. and Auger, H{\'e}l{\`e}ne and Jaszczyszyn, Yan and Thermes, Claude}, title = {Ten years of next-generation sequencing technology}, journal = {Trends in Genetics}, year = 2014, month = {Sep}, day = 01, publisher = {Elsevier}, volume = 30, number = 9, pages = {418-426}, issn = {0168-9525}, doi = {10.1016/j.tig.2014.07.001}, url = {https://doi.org/10.1016/j.tig.2014.07.001} }