Merge pull request #4064 from BiodataAnalysisGroup/metagenomics-binning

Metagenomics binning tutorial

CONTRIBUTORS.yaml

@@ -1253,6 +1253,13 @@ npalopoli:
     name: Nicolas Palopoli
     joined: 2021-09
 
+npechl:
+    name: Nikolaos Pechlivanis
+    email: [email protected]
+    twitter: npechl
+    joined: 2023-05
+    orcid: 0000-0003-2502-612X
+
 nsoranzo:
     name: Nicola Soranzo
     matrix: 'nsoranzo:matrix.org'

bin/schema-tutorial.yaml

@@ -187,6 +187,12 @@ mapping:
             link on Zenodo to the input data for the tutorial
         examples:
             - "https://zenodo.org/record/3706539"
+    extra:
+        type: map
+        description: |
+            Any additional variables you want to set on the page
+        mapping:
+          '=': {}
     tags:
         type: seq
         sequence:

topics/metagenomics/tutorials/metagenomics-binning/tutorial.bib

@@ -0,0 +1,148 @@
+@article{maxbin2015,
+    author = {Wu, Yu-Wei and Simmons, Blake A. and Singer, Steven W.},
+    title = "{MaxBin 2.0: an automated binning algorithm to recover genomes from multiple metagenomic datasets}",
+    journal = {Bioinformatics},
+    volume = {32},
+    number = {4},
+    pages = {605-607},
+    year = {2015},
+    month = {10},
+    abstract = "{Summary: The recovery of genomes from metagenomic datasets is a critical step to defining the functional roles of the underlying uncultivated populations. We previously developed MaxBin, an automated binning approach for high-throughput recovery of microbial genomes from metagenomes. Here we present an expanded binning algorithm, MaxBin 2.0, which recovers genomes from co-assembly of a collection of metagenomic datasets. Tests on simulated datasets revealed that MaxBin 2.0 is highly accurate in recovering individual genomes, and the application of MaxBin 2.0 to several metagenomes from environmental samples demonstrated that it could achieve two complementary goals: recovering more bacterial genomes compared to binning a single sample as well as comparing the microbial community composition between different sampling environments.Availability and implementation: MaxBin 2.0 is freely available at http://sourceforge.net/projects/maxbin/ under BSD license.Contact:  [email protected] information:  Supplementary data are available at Bioinformatics online.}",
+    issn = {1367-4803},
+    doi = {10.1093/bioinformatics/btv638},
+    url = {https://doi.org/10.1093/bioinformatics/btv638},
+    eprint = {https://academic.oup.com/bioinformatics/article-pdf/32/4/605/49017620/btv638.pdf},
+}
+
+@article{Wu2014,
+  doi = {10.1186/2049-2618-2-26},
+  url = {https://doi.org/10.1186/2049-2618-2-26},
+  year = {2014},
+  month = aug,
+  publisher = {Springer Science and Business Media {LLC}},
+  volume = {2},
+  number = {1},
+  author = {Yu-Wei Wu and Yung-Hsu Tang and Susannah G Tringe and Blake A Simmons and Steven W Singer},
+  title = {{MaxBin}: an automated binning method to recover individual genomes from metagenomes using an expectation-maximization algorithm},
+  journal = {Microbiome}
+}
+
+@article{Kang2019,
+  doi = {10.7717/peerj.7359},
+  url = {https://doi.org/10.7717/peerj.7359},
+  year = {2019},
+  month = jul,
+  publisher = {{PeerJ}},
+  volume = {7},
+  pages = {e7359},
+  author = {Dongwan D. Kang and Feng Li and Edward Kirton and Ashleigh Thomas and Rob Egan and Hong An and Zhong Wang},
+  title = {{MetaBAT} 2: an adaptive binning algorithm for robust and efficient genome reconstruction from metagenome assemblies},
+  journal = {{PeerJ}}
+}
+
+@article{Alneberg2014,
+  doi = {10.1038/nmeth.3103},
+  url = {https://doi.org/10.1038/nmeth.3103},
+  year = {2014},
+  month = sep,
+  publisher = {Springer Science and Business Media {LLC}},
+  volume = {11},
+  number = {11},
+  pages = {1144--1146},
+  author = {Johannes Alneberg and Brynjar Sm{\'{a}}ri Bjarnason and Ino de Bruijn and Melanie Schirmer and Joshua Quick and Umer Z Ijaz and Leo Lahti and Nicholas J Loman and Anders F Andersson and Christopher Quince},
+  title = {Binning metagenomic contigs by coverage and composition},
+  journal = {Nature Methods}
+}
+
+@article{Lin2016,
+  doi = {10.1038/srep24175},
+  url = {https://doi.org/10.1038/srep24175},
+  year = {2016},
+  month = apr,
+  publisher = {Springer Science and Business Media {LLC}},
+  volume = {6},
+  number = {1},
+  author = {Hsin-Hung Lin and Yu-Chieh Liao},
+  title = {Accurate binning of metagenomic contigs via automated clustering sequences using information of genomic signatures and marker genes},
+  journal = {Scientific Reports}
+}
+
+@article{Imelfort2014,
+  doi = {10.7717/peerj.603},
+  url = {https://doi.org/10.7717/peerj.603},
+  year = {2014},
+  month = sep,
+  publisher = {{PeerJ}},
+  volume = {2},
+  pages = {e603},
+  author = {Michael Imelfort and Donovan Parks and Ben J. Woodcroft and Paul Dennis and Philip Hugenholtz and Gene W. Tyson},
+  title = {{GroopM}: an automated tool for the recovery of population genomes from related metagenomes},
+  journal = {{PeerJ}}
+}
+
+@article{Uritskiy2018,
+  doi = {10.1186/s40168-018-0541-1},
+  url = {https://doi.org/10.1186/s40168-018-0541-1},
+  year = {2018},
+  month = sep,
+  publisher = {Springer Science and Business Media {LLC}},
+  volume = {6},
+  number = {1},
+  author = {Gherman V. Uritskiy and Jocelyne DiRuggiero and James Taylor},
+  title = {{MetaWRAP}{\textemdash}a flexible pipeline for genome-resolved metagenomic data analysis},
+  journal = {Microbiome}
+}
+
+@article{Eren2015,
+  doi = {10.7717/peerj.1319},
+  url = {https://doi.org/10.7717/peerj.1319},
+  year = {2015},
+  month = oct,
+  publisher = {{PeerJ}},
+  volume = {3},
+  pages = {e1319},
+  author = {A. Murat Eren and \"{O}zcan C. Esen and Christopher Quince and Joseph H. Vineis and Hilary G. Morrison and Mitchell L. Sogin and Tom O. Delmont},
+  title = {Anvi'o: an advanced analysis and visualization platform for `omics data},
+  journal = {{PeerJ}}
+}
+
+@article{Pan2022,
+  doi = {10.1038/s41467-022-29843-y},
+  url = {https://doi.org/10.1038/s41467-022-29843-y},
+  year = {2022},
+  month = apr,
+  publisher = {Springer Science and Business Media {LLC}},
+  volume = {13},
+  number = {1},
+  author = {Shaojun Pan and Chengkai Zhu and Xing-Ming Zhao and Luis Pedro Coelho},
+  title = {A deep siamese neural network improves metagenome-assembled genomes in microbiome datasets across different environments},
+  journal = {Nature Communications}
+}
+
+@article{Parks2015,
+  doi = {10.1101/gr.186072.114},
+  url = {https://doi.org/10.1101/gr.186072.114},
+  year = {2015},
+  month = may,
+  publisher = {Cold Spring Harbor Laboratory},
+  volume = {25},
+  number = {7},
+  pages = {1043--1055},
+  author = {Donovan H. Parks and Michael Imelfort and Connor T. Skennerton and Philip Hugenholtz and Gene W. Tyson},
+  title = {{CheckM}: assessing the quality of microbial genomes recovered from isolates,  single cells,  and metagenomes},
+  journal = {Genome Research}
+}
+
+@article{Sczyrba2017,
+  doi = {10.1038/nmeth.4458},
+  url = {https://doi.org/10.1038/nmeth.4458},
+  year = {2017},
+  month = oct,
+  publisher = {Springer Science and Business Media {LLC}},
+  volume = {14},
+  number = {11},
+  pages = {1063--1071},
+  author = {Alexander Sczyrba and Peter Hofmann and Peter Belmann and David Koslicki and Stefan Janssen and Johannes Dr\"{o}ge and Ivan Gregor and Stephan Majda and Jessika Fiedler and Eik Dahms and Andreas Bremges and Adrian Fritz and Ruben Garrido-Oter and Tue Sparholt J{\o}rgensen and Nicole Shapiro and Philip D Blood and Alexey Gurevich and Yang Bai and Dmitrij Turaev and Matthew Z DeMaere and Rayan Chikhi and Niranjan Nagarajan and Christopher Quince and Fernando Meyer and Monika Balvo{\v{c}}i{\={u}}t{\.{e}} and Lars Hestbjerg Hansen and S{\o}ren J S{\o}rensen and Burton K H Chia and Bertrand Denis and Jeff L Froula and Zhong Wang and Robert Egan and Dongwan Don Kang and Jeffrey J Cook and Charles Deltel and Michael Beckstette and Claire Lemaitre and Pierre Peterlongo and Guillaume Rizk and Dominique Lavenier and Yu-Wei Wu and Steven W Singer and Chirag Jain and Marc Strous and Heiner Klingenberg and Peter Meinicke and Michael D Barton and Thomas Lingner and Hsin-Hung Lin and Yu-Chieh Liao and Genivaldo Gueiros Z Silva and Daniel A Cuevas and Robert A Edwards and Surya Saha and Vitor C Piro and Bernhard Y Renard and Mihai Pop and Hans-Peter Klenk and Markus G\"{o}ker and Nikos C Kyrpides and Tanja Woyke and Julia A Vorholt and Paul Schulze-Lefert and Edward M Rubin and Aaron E Darling and Thomas Rattei and Alice C McHardy},
+  title = {Critical Assessment of Metagenome Interpretation{\textemdash}a benchmark of metagenomics software},
+  journal = {Nature Methods}
+}