@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, 48-49, 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} } @Inbook{Zou2009, author = "Zou, Jinming and Han, Yi and So, Sung-Sau", editor = "Livingstone, David J.", title = "Overview of Artificial Neural Networks", bookTitle = "Artificial Neural Networks: Methods and Applications", year = 2009, publisher = "Humana Press", address = "Totowa, NJ", pages = "14--22", abstract = "The artificial neural network (ANN), or simply neural network, is a machine learning method evolved from the idea of simulating the human brain. The data explosion in modern drug discovery research requires sophisticated analysis methods to uncover the hidden causal relationships between single or multiple responses and a large set of properties. The ANN is one of many versatile tools to meet the demand in drug discovery modeling. Compared to a traditional regression approach, the ANN is capable of modeling complex nonlinear relationships. The ANN also has excellent fault tolerance and is fast and highly scalable with parallel processing. This chapter introduces the background of ANN development and outlines the basic concepts crucially important for understanding more sophisticated ANN. Several commonly used learning methods and network setups are discussed briefly at the end of the chapter.", isbn = "978-1-60327-101-1", doi = "10.1007/978-1-60327-101-1_2", url = "https://doi.org/10.1007/978-1-60327-101-1_2" } @book{book:2610592, title = {Principles of artificial neural networks}, author = {Graupe, Daniel}, publisher = {World Scientific Publ}, isbn = {9789814522731,9814522732}, year = 2013, edition = {3. ed}, pages = {28-31} } @Article{Cireşan2010, author = {Cire{\c{s}}an, Dan Claudiu and Meier, Ueli and Gambardella, Luca Maria and Schmidhuber, J{\"u}rgen}, title = {Deep, Big, Simple Neural Nets for Handwritten Digit Recognition}, journal = {Neural Computation}, year = 2010, month = {Dec}, day = 01, volume = 22, number = 12, pages = {3207-3220}, abstract = {Good old online backpropagation for plain multilayer perceptrons yields a very low 0.35{\%} error rate on the MNIST handwritten digits benchmark. All we need to achieve this best result so far are many hidden layers, many neurons per layer, numerous deformed training images to avoid overfitting, and graphics cards to greatly speed up learning.}, issn = {0899-7667}, doi = {10.1162/NECO_a_00052}, url = {https://doi.org/10.1162/NECO_a_00052} }  @Article{Rumelhart1986, author = {Rumelhart, David E. and Hinton, Geoffrey E. and Williams, Ronald J.}, title = {Learning representations by back-propagating errors}, journal = {Nature}, year = 1986, month = {Oct}, day = 01, volume = 323, number = 6088, pages = {533-536}, abstract = {We describe a new learning procedure, back-propagation, for networks of neurone-like units. The procedure repeatedly adjusts the weights of the connections in the network so as to minimize a measure of the difference between the actual output vector of the net and the desired output vector. As a result of the weight adjustments, internal `hidden' units which are not part of the input or output come to represent important features of the task domain, and the regularities in the task are captured by the interactions of these units. The ability to create useful new features distinguishes back-propagation from earlier, simpler methods such as the perceptron-convergence procedure1.}, issn = {1476-4687}, doi = {10.1038/323533a0}, url = {https://doi.org/10.1038/323533a0} } @book{book:2530718, title = {Machine Learning Refined: Foundations, Algorithms, and Applications}, author = {Jeremy Watt, Reza Borhani, Aggelos K. Katsaggelos}, publisher = {Cambridge University Press}, isbn = {1108480721,9781108480727}, year = 2020, edition = 2 } @article{ruder2016overview, title = {An overview of gradient descent optimization algorithms}, author = {Ruder, Sebastian}, journal = {arXiv preprint arXiv:1609.04747}, year = 2016 } @article{DBLP:journals/corr/WangRX17, author = {Haohan Wang and Bhiksha Raj and Eric P. Xing}, title = {On the Origin of Deep Learning}, journal = {CoRR}, volume = {abs/1702.07800}, year = 2017, url = {http://arxiv.org/abs/1702.07800}, archivePrefix = {arXiv}, eprint = {1702.07800}, timestamp = {Mon, 13 Aug 2018 16:46:19 +0200}, biburl = {https://dblp.org/rec/journals/corr/WangRX17.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} } @Inbook{Can2014, author = "Can, Tolga", editor = "Yousef, Malik and Allmer, Jens", title = "Introduction to Bioinformatics", bookTitle = "miRNomics: MicroRNA Biology and Computational Analysis", year = 2014, publisher = "Humana Press", address = "Totowa, NJ", pages = "51--71", abstract = "Bioinformatics is an interdisciplinary field mainly involving molecular biology and genetics, computer science, mathematics, and statistics. Data intensive, large-scale biological problems are addressed from a computational point of view. The most common problems are modeling biological processes at the molecular level and making inferences from collected data. A bioinformatics solution usually involves the following steps:Collect statistics from biological data.Build a computational model.Solve a computational modeling problem.Test and evaluate a computational algorithm.", isbn = "978-1-62703-748-8", doi = "10.1007/978-1-62703-748-8_4", url = "https://doi.org/10.1007/978-1-62703-748-8_4" }  @Article{Hagen2000, author = {Hagen, Joel B.}, title = {The origins of bioinformatics}, journal = {Nature Reviews Genetics}, year = 2000, month = {Dec}, day = 01, volume = 1, number = 3, pages = {231-236}, abstract = {Bioinformatics is often described as being in its infancy, but computers emerged as important tools in molecular biology during the early 1960s. A decade before DNA sequencing became feasible, computational biologists focused on the rapidly accumulating data from protein biochemistry. Without the benefits of supercomputers or computer networks, these scientists laid important conceptual and technical foundations for bioinformatics today.}, issn = {1471-0064}, doi = {10.1038/35042090}, url = {https://doi.org/10.1038/35042090} } @article{doi:10.1146/annurev-genom-090413-025358, author = {Reinert, Knut and Langmead, Ben and Weese, David and Evers, Dirk J.}, title = {Alignment of Next-Generation Sequencing Reads}, journal = {Annual Review of Genomics and Human Genetics}, volume = 16, number = 1, pages = {133-151}, year = 2015, doi = {10.1146/annurev-genom-090413-025358}, note = {PMID: 25939052}, URL = { https://doi.org/10.1146/annurev-genom-090413-025358 }, eprint = { https://doi.org/10.1146/annurev-genom-090413-025358 } , abstract = { High-throughput DNA sequencing has considerably changed the possibilities for conducting biomedical research by measuring billions of short DNA or RNA fragments. A central computational problem, and for many applications a first step, consists of determining where the fragments came from in the original genome. In this article, we review the main techniques for generating the fragments, the main applications, and the main algorithmic ideas for computing a solution to the read alignment problem. In addition, we describe pitfalls and difficulties connected to determining the correct positions of reads. } } @book{book:211898, title = {Mark's Basic Medical Biochemistry A Clinical Approach}, author = {Michael A. Lieberman, Allan Marks}, publisher = {Lippincott Williams & Wilkins}, isbn = {9780781770224,078177022X}, year = 2008, series = {Point Lippincott Williams & Wilkins}, edition = {Third}, pages = {209, 260}, } @article{ABIODUN2018e00938, title = {State-of-the-art in artificial neural network applications: A survey}, journal = {Heliyon}, volume = 4, number = 11, pages = {e00938}, year = 2018, issn = {2405-8440}, doi = {https://doi.org/10.1016/j.heliyon.2018.e00938}, url = {https://www.sciencedirect.com/science/article/pii/S2405844018332067}, author = {Oludare Isaac Abiodun and Aman Jantan and Abiodun Esther Omolara and Kemi Victoria Dada and Nachaat AbdElatif Mohamed and Humaira Arshad}, keywords = {Computer science}, abstract = {This is a survey of neural network applications in the real-world scenario. It provides a taxonomy of artificial neural networks (ANNs) and furnish the reader with knowledge of current and emerging trends in ANN applications research and area of focus for researchers. Additionally, the study presents ANN application challenges, contributions, compare performances and critiques methods. The study covers many applications of ANN techniques in various disciplines which include computing, science, engineering, medicine, environmental, agriculture, mining, technology, climate, business, arts, and nanotechnology, etc. The study assesses ANN contributions, compare performances and critiques methods. The study found that neural-network models such as feedforward and feedback propagation artificial neural networks are performing better in its application to human problems. Therefore, we proposed feedforward and feedback propagation ANN models for research focus based on data analysis factors like accuracy, processing speed, latency, fault tolerance, volume, scalability, convergence, and performance. Moreover, we recommend that instead of applying a single method, future research can focus on combining ANN models into one network-wide application.} } @article{LIU201711, title = {A survey of deep neural network architectures and their applications}, journal = {Neurocomputing}, volume = 234, pages = {11-26}, year = 2017, issn = {0925-2312}, doi = {https://doi.org/10.1016/j.neucom.2016.12.038}, url = {https://www.sciencedirect.com/science/article/pii/S0925231216315533}, author = {Weibo Liu and Zidong Wang and Xiaohui Liu and Nianyin Zeng and Yurong Liu and Fuad E. Alsaadi}, keywords = {Autoencoder, Convolutional neural network, Deep learning, Deep belief network, Restricted Boltzmann machine}, abstract = {Since the proposal of a fast learning algorithm for deep belief networks in 2006, the deep learning techniques have drawn ever-increasing research interests because of their inherent capability of overcoming the drawback of traditional algorithms dependent on hand-designed features. Deep learning approaches have also been found to be suitable for big data analysis with successful applications to computer vision, pattern recognition, speech recognition, natural language processing, and recommendation systems. In this paper, we discuss some widely-used deep learning architectures and their practical applications. An up-to-date overview is provided on four deep learning architectures, namely, autoencoder, convolutional neural network, deep belief network, and restricted Boltzmann machine. Different types of deep neural networks are surveyed and recent progresses are summarized. Applications of deep learning techniques on some selected areas (speech recognition, pattern recognition and computer vision) are highlighted. A list of future research topics are finally given with clear justifications.} } @misc{chervinskii_2015, title = {Autoencoder structure}, url = {https://commons.wikimedia.org/wiki/File:Autoencoder_structure.png}, journal = {Wikimedia}, author = {Chervinskii}, year = 2015, month = {Dec} } @book{Goodfellow-et-al-2016, title = {Deep Learning}, author = {Ian Goodfellow and Yoshua Bengio and Aaron Courville}, publisher = {MIT Press}, note = {\url{http://www.deeplearningbook.org}}, year = 2016 } @Article{Lewis_2020, author = {Lewis, Mike and Liu, Yinhan and Goyal, Naman and Ghazvininejad, Marjan and Mohamed, Abdelrahman and Levy, Omer and Stoyanov, Veselin and Zettlemoyer, Luke}, title = {BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension}, journal = {Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics}, year = 2020, doi = {10.18653/v1/2020.acl-main.703}, url = {http://dx.doi.org/10.18653/v1/2020.acl-main.703}, publisher = {Association for Computational Linguistics} } @article{bigdeli17_image_restor_using_autoen_prior, author = {Bigdeli, Siavash Arjomand and Zwicker, Matthias}, title = {Image Restoration Using Autoencoding Priors}, journal = {CoRR}, year = 2017, url = {http://arxiv.org/abs/1703.09964v1}, abstract = {We propose to leverage denoising autoencoder networks as priors to address image restoration problems. We build on the key observation that the output of an optimal denoising autoencoder is a local mean of the true data density, and the autoencoder error (the difference between the output and input of the trained autoencoder) is a mean shift vector. We use the magnitude of this mean shift vector, that is, the distance to the local mean, as the negative log likelihood of our natural image prior. For image restoration, we maximize the likelihood using gradient descent by backpropagating the autoencoder error. A key advantage of our approach is that we do not need to train separate networks for different image restoration tasks, such as non-blind deconvolution with different kernels, or super-resolution at different magnification factors. We demonstrate state of the art results for non-blind deconvolution and super-resolution using the same autoencoding prior.}, archivePrefix = {arXiv}, eprint = {1703.09964}, primaryClass = {cs.CV}, } @article{makhzani15_adver_autoen, author = {Makhzani, Alireza and Shlens, Jonathon and Jaitly, Navdeep and Goodfellow, Ian and Frey, Brendan}, title = {Adversarial Autoencoders}, journal = {CoRR}, year = 2015, url = {http://arxiv.org/abs/1511.05644v2}, abstract = {In this paper, we propose the "adversarial autoencoder" (AAE), which is a probabilistic autoencoder that uses the recently proposed generative adversarial networks (GAN) to perform variational inference by matching the aggregated posterior of the hidden code vector of the autoencoder with an arbitrary prior distribution. Matching the aggregated posterior to the prior ensures that generating from any part of prior space results in meaningful samples. As a result, the decoder of the adversarial autoencoder learns a deep generative model that maps the imposed prior to the data distribution. We show how the adversarial autoencoder can be used in applications such as semi-supervised classification, disentangling style and content of images, unsupervised clustering, dimensionality reduction and data visualization. We performed experiments on MNIST, Street View House Numbers and Toronto Face datasets and show that adversarial autoencoders achieve competitive results in generative modeling and semi-supervised classification tasks.}, archivePrefix = {arXiv}, eprint = {1511.05644v2}, primaryClass = {cs.LG}, } @Article{Yoo_2020, author = {Yoo, Jaeyoung and Lee, Hojun and Kwak, Nojun}, title = {Unpriortized Autoencoder For Image Generation}, journal = {2020 IEEE International Conference on Image Processing (ICIP)}, year = 2020, month = {Oct}, doi = {10.1109/icip40778.2020.9191173}, url = {http://dx.doi.org/10.1109/ICIP40778.2020.9191173}, ISBN = 9781728163956, publisher = {IEEE} } @article{kaiser18_discr_autoen_sequen_model, author = {Kaiser, Łukasz and Bengio, Samy}, title = {Discrete Autoencoders for Sequence Models}, journal = {CoRR}, year = 2018, url = {http://arxiv.org/abs/1801.09797v1}, abstract = {Recurrent models for sequences have been recently successful at many tasks, especially for language modeling and machine translation. Nevertheless, it remains challenging to extract good representations from these models. For instance, even though language has a clear hierarchical structure going from characters through words to sentences, it is not apparent in current language models. We propose to improve the representation in sequence models by augmenting current approaches with an autoencoder that is forced to compress the sequence through an intermediate discrete latent space. In order to propagate gradients though this discrete representation we introduce an improved semantic hashing technique. We show that this technique performs well on a newly proposed quantitative efficiency measure. We also analyze latent codes produced by the model showing how they correspond to words and phrases. Finally, we present an application of the autoencoder-augmented model to generating diverse translations.}, archivePrefix = {arXiv}, eprint = {1801.09797v1}, primaryClass = {cs.LG}, } @misc{brownlee_2020, title = {How Do Convolutional Layers Work in Deep Learning Neural Networks?}, url = {https://machinelearningmastery.com/convolutional-layers-for-deep-learning-neural-networks/}, journal = {Machine Learning Mastery}, author = {Brownlee, Jason}, year = 2020, month = {Apr} } @article{howard17_mobil, author = {Howard, Andrew G. and Zhu, Menglong and Chen, Bo and Kalenichenko, Dmitry and Wang, Weijun and Weyand, Tobias and Andreetto, Marco and Adam, Hartwig}, title = {Mobilenets: Efficient Convolutional Neural Networks for Mobile Vision Applications}, journal = {CoRR}, year = 2017, url = {http://arxiv.org/abs/1704.04861v1}, abstract = {We present a class of efficient models called MobileNets for mobile and embedded vision applications. MobileNets are based on a streamlined architecture that uses depth-wise separable convolutions to build light weight deep neural networks. We introduce two simple global hyper-parameters that efficiently trade off between latency and accuracy. These hyper-parameters allow the model builder to choose the right sized model for their application based on the constraints of the problem. We present extensive experiments on resource and accuracy tradeoffs and show strong performance compared to other popular models on ImageNet classification. We then demonstrate the effectiveness of MobileNets across a wide range of applications and use cases including object detection, finegrain classification, face attributes and large scale geo-localization.}, archivePrefix = {arXiv}, eprint = {1704.04861v1}, primaryClass = {cs.CV}, } @article{ronneberger15_u_net, author = {Ronneberger, Olaf and Fischer, Philipp and Brox, Thomas}, title = {U-Net: Convolutional Networks for Biomedical Image Segmentation}, journal = {CoRR}, year = 2015, url = {http://arxiv.org/abs/1505.04597v1}, abstract = {There is large consent that successful training of deep networks requires many thousand annotated training samples. In this paper, we present a network and training strategy that relies on the strong use of data augmentation to use the available annotated samples more efficiently. The architecture consists of a contracting path to capture context and a symmetric expanding path that enables precise localization. We show that such a network can be trained end-to-end from very few images and outperforms the prior best method (a sliding-window convolutional network) on the ISBI challenge for segmentation of neuronal structures in electron microscopic stacks. Using the same network trained on transmitted light microscopy images (phase contrast and DIC) we won the ISBI cell tracking challenge 2015 in these categories by a large margin. Moreover, the network is fast. Segmentation of a 512x512 image takes less than a second on a recent GPU. The full implementation (based on Caffe) and the trained networks are available at http://lmb.informatik.uni-freiburg.de/people/ronneber/u-net .}, archivePrefix = {arXiv}, eprint = {1505.04597v1}, primaryClass = {cs.CV}, } @article{yuan18_simpl_convol_gener_networ_next_item_recom, author = {Yuan, Fajie and Karatzoglou, Alexandros and Arapakis, Ioannis and Jose, Joemon M and He, Xiangnan}, title = {A Simple Convolutional Generative Network for Next Item Recommendation}, journal = {CoRR}, year = 2018, url = {http://arxiv.org/abs/1808.05163v4}, abstract = {Convolutional Neural Networks (CNNs) have been recently introduced in the domain of session-based next item recommendation. An ordered collection of past items the user has interacted with in a session (or sequence) are embedded into a 2-dimensional latent matrix, and treated as an image. The convolution and pooling operations are then applied to the mapped item embeddings. In this paper, we first examine the typical session-based CNN recommender and show that both the generative model and network architecture are suboptimal when modeling long-range dependencies in the item sequence. To address the issues, we introduce a simple, but very effective generative model that is capable of learning high-level representation from both short- and long-range item dependencies. The network architecture of the proposed model is formed of a stack of \emph{holed} convolutional layers, which can efficiently increase the receptive fields without relying on the pooling operation. Another contribution is the effective use of residual block structure in recommender systems, which can ease the optimization for much deeper networks. The proposed generative model attains state-of-the-art accuracy with less training time in the next item recommendation task. It accordingly can be used as a powerful recommendation baseline to beat in future, especially when there are long sequences of user feedback.}, archivePrefix = {arXiv}, eprint = {1808.05163v4}, primaryClass = {cs.IR}, } @article{sadr21_novel_deep_learn_method_textual_sentim_analy, author = {Sadr, Hossein and Solimandarabi, Mozhdeh Nazari and Pedram, Mir Mohsen and Teshnehlab, Mohammad}, title = {A Novel Deep Learning Method for Textual Sentiment Analysis}, journal = {CoRR}, year = 2021, url = {http://arxiv.org/abs/2102.11651v1}, abstract = {Sentiment analysis is known as one of the most crucial tasks in the field of natural language processing and Convolutional Neural Network (CNN) is one of those prominent models that is commonly used for this aim. Although convolutional neural networks have obtained remarkable results in recent years, they are still confronted with some limitations. Firstly, they consider that all words in a sentence have equal contributions in the sentence meaning representation and are not able to extract informative words. Secondly, they require a large number of training data to obtain considerable results while they have many parameters that must be accurately adjusted. To this end, a convolutional neural network integrated with a hierarchical attention layer is proposed which is able to extract informative words and assign them higher weight. Moreover, the effect of transfer learning that transfers knowledge learned in the source domain to the target domain with the aim of improving the performance is also explored. Based on the empirical results, the proposed model not only has higher classification accuracy and can extract informative words but also applying incremental transfer learning can significantly enhance the classification performance.}, archivePrefix = {arXiv}, eprint = {2102.11651}, primaryClass = {cs.CL}, } @book{book:930, title = {Bioinformatics: the machine learning approach}, author = {Pierre Baldi, Søren Brunak}, publisher = {The MIT Press}, isbn = {026202506X,9780585444666,9780262025065}, year = 2001, series = {Adaptive Computation and Machine Learning}, edition = 2, pages = 12, } @Article{Schneider_2011, author = {Schneider, Maria V. and Orchard, Sandra}, title = {Omics Technologies, Data and Bioinformatics Principles}, journal = {Bioinformatics for Omics Data}, year = 2011, pages = {3–30}, issn = {1940-6029}, doi = {10.1007/978-1-61779-027-0_1}, url = {http://dx.doi.org/10.1007/978-1-61779-027-0_1}, ISBN = 9781617790270, publisher = {Humana Press}, } @Article{Peri_2020, author = {Peri, Sateesh and Roberts, Sarah and Kreko, Isabella R. and McHan, Lauren B. and Naron, Alexandra and Ram, Archana and Murphy, Rebecca L. and Lyons, Eric and Gregory, Brian D. and Devisetty, Upendra K. and et al.}, title = {Read Mapping and Transcript Assembly: A Scalable and High-Throughput Workflow for the Processing and Analysis of Ribonucleic Acid Sequencing Data}, journal = {Frontiers in Genetics}, year = 2020, volume = 10, month = {Jan}, issn = {1664-8021}, doi = {10.3389/fgene.2019.01361}, url = {http://dx.doi.org/10.3389/fgene.2019.01361}, publisher = {Frontiers Media SA} } @Article{Zerbino_2008, author = {Zerbino, D. R. and Birney, E.}, title = {Velvet: Algorithms for de novo short read assembly using de Bruijn graphs}, journal = {Genome Research}, year = 2008, volume = 18, number = 5, month = {Feb}, pages = {821–829}, issn = {1088-9051}, doi = {10.1101/gr.074492.107}, url = {http://dx.doi.org/10.1101/gr.074492.107}, publisher = {Cold Spring Harbor Laboratory} } @Article{Spudich_2007, author = {Spudich, G. and Fernandez-Suarez, X. M. and Birney, E.}, title = {Genome browsing with Ensembl: a practical overview}, journal = {Briefings in Functional Genomics and Proteomics}, year = 2007, volume = 6, number = 3, month = {Aug}, pages = {202–219}, issn = {1477-4062}, doi = {10.1093/bfgp/elm025}, url = {http://dx.doi.org/10.1093/bfgp/elm025}, publisher = {Oxford University Press (OUP)} } @Article{Liu_2018, author = {Liu, Yang and Ye, Qing and Wang, Liwei and Peng, Jian}, title = {Learning structural motif representations for efficient protein structure search}, journal = {Bioinformatics}, year = 2018, volume = 34, number = 17, month = {Sep}, pages = {i773–i780}, issn = {1460-2059}, doi = {10.1093/bioinformatics/bty585}, url = {http://dx.doi.org/10.1093/bioinformatics/bty585}, publisher = {Oxford University Press (OUP)} } @Article{Salmela_2011, author = {Salmela, L. and Schroder, J.}, title = {Correcting errors in short reads by multiple alignments}, journal = {Bioinformatics}, year = 2011, volume = 27, number = 11, month = {Apr}, pages = {1455–1461}, issn = {1460-2059}, doi = {10.1093/bioinformatics/btr170}, url = {http://dx.doi.org/10.1093/bioinformatics/btr170}, publisher = {Oxford University Press (OUP)} } @Article{Yang_2012, author = {Yang, X. and Chockalingam, S. P. and Aluru, S.}, title = {A survey of error-correction methods for next-generation sequencing}, journal = {Briefings in Bioinformatics}, year = 2012, volume = 14, number = 1, month = {Apr}, pages = {56–66}, issn = {1477-4054}, doi = {10.1093/bib/bbs015}, url = {http://dx.doi.org/10.1093/bib/bbs015}, publisher = {Oxford University Press (OUP)} } @Article{Kelley_2010, author = {Kelley, David R and Schatz, Michael C and Salzberg, Steven L}, title = {Quake: quality-aware detection and correction of sequencing errors}, journal = {Genome Biology}, year = 2010, volume = 11, number = 11, pages = {R116}, issn = {1465-6906}, doi = {10.1186/gb-2010-11-11-r116}, url = {http://dx.doi.org/10.1186/gb-2010-11-11-r116}, publisher = {Springer Science and Business Media LLC} } @Article{Zhao_2017, author = {Zhao, Liang and Chen, Qingfeng and Li, Wencui and Jiang, Peng and Wong, Limsoon and Li, Jinyan}, title = {MapReduce for accurate error correction of next-generation sequencing data}, journal = {Bioinformatics}, year = 2017, editor = {Sahinalp, CenkEditor}, volume = 33, number = 23, month = {Feb}, pages = {3844–3851}, issn = {1460-2059}, doi = {10.1093/bioinformatics/btx089}, url = {http://dx.doi.org/10.1093/bioinformatics/btx089}, publisher = {Oxford University Press (OUP)} }