@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{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} } @article {Sanger5463, author = {Sanger, F. and Nicklen, S. and Coulson, A. R.}, title = {DNA sequencing with chain-terminating inhibitors}, volume = 74, number = 12, pages = {5463--5467}, year = 1977, doi = {10.1073/pnas.74.12.5463}, publisher = {National Academy of Sciences}, abstract = {A new method for determining nucleotide sequences in DNA is described. It is similar to the {\textquotedblleft}plus and minus{\textquotedblright} method [Sanger, F. \& Coulson, A. R. (1975) J. Mol. Biol. 94, 441-448] but makes use of the 2',3'-dideoxy and arabinonucleoside analogues of the normal deoxynucleoside triphosphates, which act as specific chain-terminating inhibitors of DNA polymerase. The technique has been applied to the DNA of bacteriophage ϕX174 and is more rapid and more accurate than either the plus or the minus method.}, issn = {0027-8424}, URL = {https://www.pnas.org/content/74/12/5463}, eprint = {https://www.pnas.org/content/74/12/5463.full.pdf}, journal = {Proceedings of the National Academy of Sciences} }  @Article{InternationalHumanGenomeSequencingConsortium2004, author = {Consortium, International Human Genome Sequencing}, title = {Finishing the euchromatic sequence of the human genome}, journal = {Nature}, year = 2004, month = {Oct}, day = 01, volume = 431, number = 7011, pages = {931-945}, abstract = {The sequence of the human genome encodes the genetic instructions for human physiology, as well as rich information about human evolution. In 2001, the International Human Genome Sequencing Consortium reported a draft sequence of the euchromatic portion of the human genome. Since then, the international collaboration has worked to convert this draft into a genome sequence with high accuracy and nearly complete coverage. Here, we report the result of this finishing process. The current genome sequence (Build 35) contains 2.85 billion nucleotides interrupted by only 341 gaps. It covers ∼99{\%} of the euchromatic genome and is accurate to an error rate of ∼1 event per 100,000 bases. Many of the remaining euchromatic gaps are associated with segmental duplications and will require focused work with new methods. The near-complete sequence, the first for a vertebrate, greatly improves the precision of biological analyses of the human genome including studies of gene number, birth and death. Notably, the human genome seems to encode only 20,000--25,000 protein-coding genes. The genome sequence reported here should serve as a firm foundation for biomedical research in the decades ahead.}, issn = {1476-4687}, doi = {10.1038/nature03001}, url = {https://doi.org/10.1038/nature03001} }  @Article{Schloss2008, author = {Schloss, Jeffery A.}, title = {How to get genomes at one ten-thousandth the cost}, journal = {Nature Biotechnology}, year = 2008, month = {Oct}, day = 01, volume = 26, number = 10, pages = {1113-1115}, abstract = {The NHGRI's Advanced DNA Sequencing Technology program is spearheading the development of platforms that will bring routine whole-genome sequencing closer to reality.}, issn = {1546-1696}, doi = {10.1038/nbt1008-1113}, url = {https://doi.org/10.1038/nbt1008-1113} } @Article{Shugay2014, author = {Shugay, Mikhail and Britanova, Olga V. and Merzlyak, Ekaterina M. and Turchaninova, Maria A. and Mamedov, Ilgar Z. and Tuganbaev, Timur R. and Bolotin, Dmitriy A. and Staroverov, Dmitry B. and Putintseva, Ekaterina V. and Plevova, Karla and Linnemann, Carsten and Shagin, Dmitriy and Pospisilova, Sarka and Lukyanov, Sergey and Schumacher, Ton N. and Chudakov, Dmitriy M.}, title = {Towards error-free profiling of immune repertoires}, journal = {Nature Methods}, year = 2014, month = {Jun}, day = 01, volume = 11, number = 6, pages = {653-655}, abstract = {A two-step error correction process for high throughput--sequenced T- and B-cell receptors allows the elimination of most errors while not diminishing the natural complexity of the repertoires.}, issn = {1548-7105}, doi = {10.1038/nmeth.2960}, url = {https://doi.org/10.1038/nmeth.2960} } @Article{Ma2019, author = {Ma, Xiaotu and Shao, Ying and Tian, Liqing and Flasch, Diane A. and Mulder, Heather L. and Edmonson, Michael N. and Liu, Yu and Chen, Xiang and Newman, Scott and Nakitandwe, Joy and Li, Yongjin and Li, Benshang and Shen, Shuhong and Wang, Zhaoming and Shurtleff, Sheila and Robison, Leslie L. and Levy, Shawn and Easton, John and Zhang, Jinghui}, title = {Analysis of error profiles in deep next-generation sequencing data}, journal = {Genome Biology}, year = 2019, month = {Mar}, day = 14, volume = 20, number = 1, pages = 50, abstract = {Sequencing errors are key confounding factors for detecting low-frequency genetic variants that are important for cancer molecular diagnosis, treatment, and surveillance using deep next-generation sequencing (NGS). However, there is a lack of comprehensive understanding of errors introduced at various steps of a conventional NGS workflow, such as sample handling, library preparation, PCR enrichment, and sequencing. In this study, we use current NGS technology to systematically investigate these questions.}, issn = {1474-760X}, doi = {10.1186/s13059-019-1659-6}, } @mastersthesis{BenítezCantos-Master, author = "María Soledad Benítez Cantos", title = "Análisis de repertorios de receptores de células T a partir de datos de secuenciación masiva", school = "Universidad de Granada", year = "2019", month = "{Jul}", } @inbook{abbas_lichtman_pillai_2017, place = {Philadelphia, PA}, edition = {9th}, booktitle = {Cellular and molecular immunology}, publisher = {Elsevier}, author = {Abbas, Abul K. and Lichtman, Andrew H. and Pillai, Shiv}, year = 2017, pages = 204 }  @Article{CRICK1970, author = {Crick, Francis}, title = {Central Dogma of Molecular Biology}, journal = {Nature}, year = 1970, month = {Aug}, day = 01, volume = 227, number = 5258, pages = {561-563}, abstract = {The central dogma of molecular biology deals with the detailed residue-by-residue transfer of sequential information. It states that such information cannot be transferred from protein to either protein or nucleic acid.}, issn = {1476-4687}, doi = {10.1038/227561a0}, url = {https://doi.org/10.1038/227561a0} } @Article{Salk2018, author = {Salk, Jesse J. and Schmitt, Michael W. and Loeb, Lawrence A.}, title = {Enhancing the accuracy of next-generation sequencing for detecting rare and subclonal mutations}, journal = {Nature Reviews Genetics}, year = 2018, month = {May}, day = 01, volume = 19, number = 5, pages = {269-285}, abstract = {The ability to identify low-frequency genetic variants among heterogeneous populations of cells or DNA molecules is important in many fields of basic science, clinical medicine and other applications, yet current high-throughput DNA sequencing technologies have an error rate between 1 per 100 and 1 per 1,000 base pairs sequenced, which obscures their presence below this level.As next-generation sequencing technologies evolved over the decade, throughput has improved markedly, but raw accuracy has remained generally unchanged. Researchers with a need for high accuracy developed data filtering methods and incremental biochemical improvements that modestly improve low-frequency variant detection, but background errors remain limiting in many fields.The most profoundly impactful means for reducing errors, first developed approximately 7 years ago, has been the concept of single-molecule consensus sequencing. This entails redundant sequencing of multiple copies of a given specific DNA molecule and discounting of variants that are not present in all or most of the copies as likely errors.Consensus sequencing can be achieved by labelling each molecule with a unique molecular barcode before generating copies, which allows subsequent comparison of these copies or schemes whereby copies are physically joined and sequenced together. Because of trade-offs in cost, time and accuracy, no single method is optimal for every application, and each method should be considered on a case-by-case basis.Major applications for high-accuracy DNA sequencing include non-invasive cancer diagnostics, cancer screening, early detection of cancer relapse or impending drug resistance, infectious disease applications, prenatal diagnostics, forensics and mutagenesis assessment.Future advances in ultra-high-accuracy sequencing are likely to be driven by an emerging generation of single-molecule sequencers, particularly those that allow independent sequence comparison of both strands of native DNA duplexes.}, issn = {1471-0064}, doi = {10.1038/nrg.2017.117}, url = {https://doi.org/10.1038/nrg.2017.117} } @book{book:lehninger, title = {Lehninger-Principles of Biochemistry}, author = {Albert Lehninger, David L. Nelson, Michael M. Cox}, publisher = {W. H. Freeman}, isbn = {9781429224161,1429224169}, year = 2008, edition = {5th Edition}, pages = 276 } @inproceedings{crick1958protein, title = {On protein synthesis}, author = {Crick, Francis HC}, booktitle = {Symp Soc Exp Biol}, volume = 12, number = {138-63}, pages = 8, year = 1958 } @article{10.1093/bioinformatics/btg109, author = {Lee, Christopher}, title = "{Generating consensus sequences from partial order multiple sequence alignment graphs}", journal = {Bioinformatics}, volume = 19, number = 8, pages = {999-1008}, year = 2003, month = 05, abstract = "{Motivation: Consensus sequence generation is important in many kinds of sequence analysis ranging from sequence assembly to profile-based iterative search methods. However, how can a consensus be constructed when its inherent assumption—that the aligned sequences form a single linear consensus—is not true?Results: Partial Order Alignment (POA) enables construction and analysis of multiple sequence alignments as directed acyclic graphs containing complex branching structure. Here we present a dynamic programming algorithm (heaviest\_bundle) for generating multiple consensus sequences from such complex alignments. The number and relationships of these consensus sequences reveals the degree of structural complexity of the source alignment. This is a powerful and general approach for analyzing and visualizing complex alignment structures, and can be applied to any alignment. We illustrate its value for analyzing expressed sequence alignments to detect alternative splicing, reconstruct full length mRNA isoform sequences from EST fragments, and separate paralog mixtures that can cause incorrect SNP predictions.Availability: The heaviest\_bundle source code is available at http://www.bioinformatics.ucla.edu/poaContact: leec@mbi.ucla.edu*To whom correspondence should be addressed.}", issn = {1367-4803}, doi = {10.1093/bioinformatics/btg109}, url = {https://doi.org/10.1093/bioinformatics/btg109}, eprint = {https://academic.oup.com/bioinformatics/article-pdf/19/8/999/642375/btg109.pdf}, } @Article{Nagar2013, author = {Nagar, Anurag and Hahsler, Michael}, title = {Fast discovery and visualization of conserved regions in DNA sequences using quasi-alignment}, journal = {BMC Bioinformatics}, year = 2013, month = {Sep}, day = 13, volume = 14, number = 11, pages = {S2}, abstract = {Next Generation Sequencing techniques are producing enormous amounts of biological sequence data and analysis becomes a major computational problem. Currently, most analysis, especially the identification of conserved regions, relies heavily on Multiple Sequence Alignment and its various heuristics such as progressive alignment, whose run time grows with the square of the number and the length of the aligned sequences and requires significant computational resources. In this work, we present a method to efficiently discover regions of high similarity across multiple sequences without performing expensive sequence alignment. The method is based on approximating edit distance between segments of sequences using p-mer frequency counts. Then, efficient high-throughput data stream clustering is used to group highly similar segments into so called quasi-alignments. Quasi-alignments have numerous applications such as identifying species and their taxonomic class from sequences, comparing sequences for similarities, and, as in this paper, discovering conserved regions across related sequences.}, issn = {1471-2105}, doi = {10.1186/1471-2105-14-S11-S2}, url = {https://doi.org/10.1186/1471-2105-14-S11-S2} } @book{book:771224, title = {Artificial Intelligence: A Modern Approach}, author = {Stuart Russell, Peter Norvig}, publisher = {Prentice Hall}, isbn = {0136042597, 9780136042594}, year = 2010, series = {Prentice Hall Series in Artificial Intelligence}, edition = {3rd}, pages = {38-45, 55-56} } @article{McCarthy_Minsky_Rochester_Shannon_2006, title = {A Proposal for the Dartmouth Summer Research Project on Artificial Intelligence, August 31, 1955}, volume = 27, url = {https://ojs.aaai.org/index.php/aimagazine/article/view/1904}, DOI = {10.1609/aimag.v27i4.1904}, abstractNote = {The 1956 Dartmouth summer research project on artificial intelligence was initiated by this August 31, 1955 proposal, authored by John McCarthy, Marvin Minsky, Nathaniel Rochester, and Claude Shannon. The original typescript consisted of 17 pages plus a title page. Copies of the typescript are housed in the archives at Dartmouth College and Stanford University. The first 5 papers state the proposal, and the remaining pages give qualifications and interests of the four who proposed the study. In the interest of brevity, this article reproduces only the proposal itself, along with the short autobiographical statements of the proposers.}, number = 4, journal = {AI Magazine}, author = {McCarthy, John and Minsky, Marvin L. and Rochester, Nathaniel and Shannon, Claude E.}, year = 2006, month = {Dec.}, pages = 12 } @book{book:80129, title = {Computational Intelligence. An Introduction}, author = {Andries P. Engelbrecht}, publisher = {Wiley}, isbn = {9780470035610,0470035617}, year = 2007, edition = 2, pages = {39-40} }