Merge pull request #278 from ncsa/paper

Paper

Author: keshav-gandhi

.github/workflows/paper-pdf.yml

@@ -0,0 +1,32 @@
+name: Paper PDF
+on:
+  push:
+    paths:
+      - paper.md
+      - paper.bib
+      - .github/workflows/paper-pdf.yml
+
+jobs:
+  paper:
+    runs-on: ubuntu-latest
+    name: Paper Draft
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+      - name: Open Journals PDF Generator
+        uses: openjournals/openjournals-draft-action@v.1.0
+        with:
+          journal: joss
+          # This is the path to the paper within the repo
+          paper-path: paper.md
+      - name: Upload
+        uses: actions/upload-artifact@v4
+        with:
+          name: paper
+          # This is the output path where Pandoc will write the compiled
+          # PDF (should be the same directory as the input paper.md)
+          path: paper.pdf
+
+      - name: Debug list files
+        run: ls -R
+      # Double-check to find the actual path of the generated PDF

paper.bib

@@ -0,0 +1,270 @@
+@article{Stephens:2016,
+    author = {Stephens, Z. D. and Hudson, M. E. and Mainzer, L. S. and Taschuk, M. and Weber, M. R. and Iyer, R. K.},
+    title = {Simulating Next-Generation Sequencing Datasets from Empirical Mutation and Sequencing Models},
+    journal = {PLOS ONE},
+    year = {2016},
+    volume = {11},
+    number = {11},
+    pages = {e0167047},
+    doi = {10.1371/journal.pone.0167047}
+}
+
+@article{Benjamini:2012,
+    author = {Benjamini, Y. and Speed, T. P.},
+    title = {Summarizing and correcting the {GC} content bias in high-throughput sequencing},
+    journal = {Nucleic Acids Research},
+    year = {2012},
+    volume = {40},
+    number = {10},
+    pages = {e72},
+    doi = {10.1093/nar/gks001}
+}
+
+@article{Ross:2013,
+    author = {Ross, M. G. and Russ, C. and Costello, M. and Hollinger, A. and Lennon, N. J. and Hegarty, R. and Nusbaum, C. and Jaffe, D. B.},
+    title = {Characterizing and measuring bias in sequence data},
+    journal = {Genome Biology},
+    year = {2013},
+    volume = {14},
+    number = {5},
+    pages = {R51},
+    doi = {10.1186/gb-2013-14-5-r51}
+}
+
+@article{Escalona:2016,
+    author = {Escalona, M. and Rocha, S. and Posada, D.},
+    title = {A comparison of tools for the simulation of genomic next-generation sequencing data},
+    journal = {Nature Reviews Genetics},
+    year = {2016},
+    volume = {17},
+    number = {8},
+    pages = {459--469},
+    doi = {10.1038/nrg.2016.57}
+}
+
+@article{Zhao:2017,
+    author = {Zhao, M. and Liu, D. and Qu, H.},
+    title = {Systematic review of next-generation sequencing simulators: computational tools, features and perspectives},
+    journal = {Briefings in Functional Genomics},
+    year = {2017},
+    volume = {16},
+    number = {3},
+    pages = {121--128},
+    doi = {10.1093/bfgp/elw012}
+}
+
+@article{Alosaimi:2020,
+    author = {Alosaimi, Shatha and Bandiang, Armand and {van Biljon}, Noelle and Awany, Denis and Thami, Prisca K. and Tchamga, Milaine S. S. and Kiran, Anmol and Messaoud, Olfa and Hassan, Radia Ismaeel Mohammed and Mugo, Jacquiline and Ahmed, Azza and Bope, Christian D. and Allali, Imane and Mazandu, Gaston K. and Mulder, Nicola J. and Chimusa, Emile R.},
+    title = {A broad survey of {DNA} sequence data simulation tools},
+    journal = {Briefings in Functional Genomics},
+    year = {2020},
+    volume = {19},
+    number = {1},
+    pages = {49--59},
+    doi = {10.1093/bfgp/elz033}
+}
+
+@article{Milhaven:2023,
+    author = {Milhaven, M. and Pfeifer, S. P.},
+    title = {Performance evaluation of six popular short-read simulators},
+    journal = {Heredity},
+    year = {2023},
+    volume = {130},
+    pages = {55--63},
+    doi = {10.1038/s41437-022-00577-3}
+}
+
+@article{Schmeing:2021,
+    author = {Schmeing, S. and Robinson, M. D.},
+    title = {{ReSeq} simulates realistic {Illumina} high-throughput sequencing data},
+    journal = {Genome Biology},
+    year = {2021},
+    volume = {22},
+    pages = {67},
+    doi = {10.1186/s13059-021-02265-7}
+}
+
+@article{Huang:2012,
+    author = {Huang, W. and Li, L. and Myers, J. R. and Marth, G. T.},
+    title = {{ART}: a next-generation sequencing read simulator},
+    journal = {Bioinformatics},
+    year = {2012},
+    volume = {28},
+    number = {4},
+    pages = {593--594},
+    doi = {10.1093/bioinformatics/btr708}
+}
+
+@article{Caboche:2014,
+    author = {Caboche, S. and Audebert, C. and Lemoine, Y. and Hot, D.},
+    title = {Comparison of mapping algorithms used in high-throughput sequencing: application to {Ion Torrent} data},
+    journal = {BMC Genomics},
+    year = {2014},
+    volume = {15},
+    pages = {264},
+    doi = {10.1186/1471-2164-15-264}
+}
+
+@misc{Homer:2010,
+    author = {Homer, N.},
+    title = {{DWGSIM}: Whole Genome Simulator for Next-Generation Sequencing},
+    year = {2010},
+    howpublished = {GitHub repository},
+    url = {https://github.com/nh13/DWGSIM}
+}
+
+@article{McElroy:2012,
+    author = {McElroy, K. E. and Luciani, F. and Thomas, T.},
+    title = {{GemSIM}: general, error-model based simulator of next-generation sequencing data},
+    journal = {BMC Genomics},
+    year = {2012},
+    volume = {13},
+    pages = {74},
+    doi = {10.1186/1471-2164-13-74}
+}
+
+@article{Gourle:2019,
+    author = {Gourl{\'e}, H. and Karlsson-Lindsj{\"o}, O. and Hayer, J. and Bongcam-Rudloff, E.},
+    title = {Simulating {Illumina} metagenomic data with {InSilicoSeq}},
+    journal = {Bioinformatics},
+    year = {2019},
+    volume = {35},
+    number = {3},
+    pages = {521--522},
+    doi = {10.1093/bioinformatics/bty630}
+}
+
+@misc{Holtgrewe:2010,
+    author = {Holtgrewe, M.},
+    title = {Mason -- {A} Read Simulator for Second Generation Sequencing Data},
+    year = {2010},
+    howpublished = {Technical Report TR-B-10-06},
+    institution = {Freie Universit{\"a}t Berlin, Fachbereich Mathematik und Informatik},
+    number = {B-10-06},
+    url = {https://publications.imp.fu-berlin.de/962/2/mason201009.pdf}
+}
+
+@article{Hu:2012,
+    author = {Hu, Xuesong and Yuan, Jianying and Shi, Yujian and Lu, Jianliang and Liu, Binghang and Li, Zhenyu and Chen, Yanxiang and Mu, Desheng and Zhang, Hao and Li, Nan and Yue, Zhen and Bai, Fan and Li, Heng and Fan, Wei},
+    title = {{pIRS}: Profile-based {Illumina} paired-end reads simulator},
+    journal = {Bioinformatics},
+    year = {2012},
+    volume = {28},
+    number = {11},
+    pages = {1533--1535},
+    doi = {10.1093/bioinformatics/bts187}
+}
+
+@article{Pattnaik:2014,
+    author = {Pattnaik, S. and Gupta, S. and Rao, A. A. and Panda, B.},
+    title = {{SInC}: an accurate and fast error-model based simulator for {SNPs}, {Indels} and {CNVs} coupled with a read generator for short-read sequence data},
+    journal = {BMC Bioinformatics},
+    year = {2014},
+    volume = {15},
+    pages = {40},
+    doi = {10.1186/1471-2105-15-40}
+}
+
+@misc{Li:2011,
+  author = {Li, Heng},
+  title = {{wgsim}-{Read} simulator for next generation sequencing},
+  year = {2011},
+  howpublished = {GitHub repository},
+  url = {https://github.com/lh3/wgsim}
+}
+
+@article{Rhie:2023,
+    author = {Rhie, Arang and Nurk, Sergey and Cechova, Monika and Hoyt, Savannah J. and Taylor, Dylan J. and Altemose, Nicolas and Hook, Paul W. and Koren, Sergey and Rautiainen, Mikko and Alexandrov, Ivan A. and Allen, Jamie and Asri, Mobin and Bzikadze, Andrey V. and Chen, Nae-Chyun and Chin, Chen-Shan and Diekhans, Mark and Flicek, Paul and Formenti, Giulio and Fungtammasan, Arkarachai and Giron, Carlos Garcia and Garrison, Erik and Gershman, Ariel and Gerton, Jennifer L. and Grady, Patrick G. S. and Guarracino, Andrea and Haggerty, Leanne and Halabian, Reza and Hansen, Nancy F. and Harris, Robert and Hartley, Gabrielle A. and Harvey, William T. and Haukness, Marina and Heinz, Jakob and Hourlier, Thibaut and Hubley, Robert M. and Hunt, Sarah E. and Hwang, Stephen and Jain, Miten and Kesharwani, Rupesh K. and Lewis, Alexandra P. and Li, Heng and Logsdon, Glennis A. and Lucas, Julian K. and Makalowski, Wojciech and Markovic, Christopher and Martin, Fergal J. and {Mc Cartney}, Ann M. and McCoy, Rajiv C. and McDaniel, Jennifer and McNulty, Brandy M. and Medvedev, Paul and Mikheenko, Alla and Munson, Katherine M. and Murphy, Terence D. and Olsen, Hugh E. and Olson, Nathan D. and Paulin, Luis F. and Porubsky, David and Potapova, Tamara and Ryabov, Fedor and Salzberg, Steven L. and Sauria, Michael E. G. and Sedlazeck, Fritz J. and Shafin, Kishwar and Shepelev, Valery A. and Shumate, Alaina and Storer, Jessica M. and Surapaneni, Likhitha and {Taravella Oill}, Angela M. and Thibaud-Nissen, Fran\c{c}oise and Timp, Winston and Tomaszkiewicz, Marta and Vollger, Mitchell R. and Walenz, Brian P. and Watwood, Allison C. and Weissensteiner, Matthias H. and Wenger, Aaron M. and Wilson, Melissa A. and Zarate, Samantha and Zhu, Yiming and Zook, Justin M. and Eichler, Evan E. and O'Neill, Rachel J. and Schatz, Michael C. and Miga, Karen H. and Makova, Kateryna D. and Phillippy, Adam M.},
+    title = {The complete sequence of a human {Y} chromosome},
+    journal = {Nature},
+    year = {2023},
+    volume = {621},
+    number = {7978},
+    pages = {344--354},
+    doi = {10.1038/s41586-023-06457-y}
+}
+
+@article{Lefouili:2022,
+    author = {Lefouili, M. and Nam, K.},
+    title = {The evaluation of {Bcftools} mpileup and {GATK} {HaplotypeCaller} for variant calling in non-human species},
+    journal = {Scientific Reports},
+    year = {2022},
+    volume = {12},
+    pages = {11331},
+    doi = {10.1038/s41598-022-15563-2}
+}
+
+@article{Zhao:2020,
+    author = {Zhao, S. and Agafonov, O. and Azab, A. and Stokowy, T. and Hovig, E.},
+    title = {Accuracy and efficiency of germline variant calling pipelines for human genome data},
+    journal = {Scientific Reports},
+    year = {2020},
+    volume = {10},
+    pages = {20222},
+    doi = {10.1038/s41598-020-77218-4}
+}
+
+@article{Ahmed:2019,
+  author = {Ahmed, A. E. and Heldenbrand, J. and Asmann, Y. and Fadlelmola, F. M. and Katz, D. S. and Kendig, K. and Kendzior, M. C. and Li, T. and Ren, Y. and Rodriguez, E. and Weber, M. R. and Wozniak, J. M. and Zermeno, J. and Mainzer, L. S.},
+  title = {Managing genomic variant calling workflows with {Swift/T}},
+  journal = {PLOS ONE},
+  year = {2019},
+  volume = {14},
+  number = {7},
+  pages = {e0211608},
+  doi = {10.1371/journal.pone.0211608}
+}
+
+@article{Kendig:2019,
+  author = {Kendig, Katherine I. and Baheti, Saurabh and Bockol, Matthew A. and Drucker, Travis M. and Hart, Steven N. and Heldenbrand, Jacob R. and Hernaez, Mikel and Hudson, Matthew E. and Kalmbach, Michael T. and Klee, Eric W. and Mattson, Nathan R. and Ross, Christian A. and Taschuk, Morgan and Wieben, Eric D. and Wiepert, Mathieu and Wildman, Derek E. and Mainzer, Liudmila S.},
+  title = {Sentieon {DNASeq} Variant Calling Workflow Demonstrates Strong Computational Performance and Accuracy},
+  journal = {Frontiers in Genetics},
+  year = {2019},
+  volume = {10},
+  pages = {736},
+  doi = {10.3389/fgene.2019.00736}
+}
+
+@article{RuizSchultz:2021,
+  author = {{Ruiz-Schultz}, Nicole and Sant, David and Norcross, Stevie and Dansithong, Warunee and Hart, Kim and Asay, Bryce and Little, Jordan and Chung, Krystal and Oakeson, Kelly F. and Young, Erin L. and Eilbeck, Karen and Rohrwasser, Andreas},
+  title = {Methods and feasibility study for exome sequencing as a universal second-tier test in newborn screening},
+  journal = {Genetics in Medicine},
+  year = {2021},
+  volume = {23},
+  number = {4},
+  pages = {767--776},
+  doi = {10.1038/s41436-020-01058-w}
+}
+
+@article{Jandrasits:2019,
+  author = {Jandrasits, C. and Kr{\"o}ger, S. and Haas, W. and Renard, B. Y.},
+  title = {Computational pan-genome mapping and pairwise {SNP}-distance improve detection of {\textit{Mycobacterium tuberculosis}} transmission clusters},
+  journal = {PLOS Computational Biology},
+  year = {2019},
+  volume = {15},
+  number = {12},
+  pages = {e1007527},
+  doi = {10.1371/journal.pcbi.1007527}
+}
+
+@article{Shah:2021,
+  author = {Shah, R. N. and Ruthenburg, A. J.},
+  title = {Sequence deeper without sequencing more: Bayesian resolution of ambiguously mapped reads},
+  journal = {PLOS Computational Biology},
+  year = {2021},
+  volume = {17},
+  number = {4},
+  pages = {e1008926},
+  doi = {10.1371/journal.pcbi.1008926}
+}
+
+@article{Delhomme:2020,
+  author = {Delhomme, Tiffany M. and Avogbe, Patrice H. and Gabriel, Aur{\'e}lie A. G. and Alcala, Nicolas and Leblay, Noemie and Voegele, Catherine and Vall{\'e}e, Maxime and Chopard, Priscilia and Chabrier, Am{\'e}lie and Abedi-Ardekani, Behnoush and Gaborieau, Val{\'e}rie and Holcatova, Ivana and Janout, Vladimir and Foretov{\'a}, Lenka and Milosavljevic, Sasa and Zaridze, David and Mukeriya, Anush and Brambilla, Elisabeth and Brennan, Paul and Scelo, Ghislaine and Fernandez-Cuesta, Lynnette and Byrnes, Graham and Calvez-Kelm, Florence L. and McKay, James D. and Foll, Matthieu},
+  title = {Needlestack: an ultra-sensitive variant caller for multi-sample next generation sequencing data},
+  journal = {NAR Genomics and Bioinformatics},
+  year = {2020},
+  volume = {2},
+  number = {2},
+  pages = {lqaa021},
+  doi = {10.1093/nargab/lqaa021}
+}