[Microbiome] New tutorial: Annotate MGEs in metagenomics data using custom database

CONTRIBUTORS.yaml

@@ -581,6 +581,10 @@ dbrites:
     name: Daniela Brites
     joined: 2022-03
 
+debroas:
+    name: Didier Debroas
+    joined: 2024-12
+
 dechendb:
     name: Dechen Bhuming
     joined: 2023-06

topics/microbiome/tutorials/metaplasmidome_query/faqs/index.md

@@ -0,0 +1,3 @@
+---
+layout: faq-page
+---

topics/microbiome/tutorials/metaplasmidome_query/tutorial.bib

@@ -0,0 +1,186 @@
+@article{antipov2020metaviral,
+  title={Metaviral SPAdes: assembly of viruses from metagenomic data},
+  author={Antipov, Dmitry and Raiko, Mikhail and Lapidus, Alla and Pevzner, Pavel A},
+  journal={Bioinformatics},
+  volume={36},
+  number={14},
+  pages={4126--4129},
+  year={2020},
+  publisher={Oxford University Press},
+  doi={10.1093/bioinformatics/btaa490}
+}
+
+
+@article{danko2021global,
+  title={A global metagenomic map of urban microbiomes and antimicrobial resistance},
+  author={Danko, David and Bezdan, Daniela and Afshin, Evan E and Ahsanuddin, Sofia and Bhattacharya, Chandrima and Butler, Daniel J and Chng, Kern Rei and Donnellan, Daisy and Hecht, Jochen and Jackson, Katelyn and others},
+  journal={Cell},
+  volume={184},
+  number={13},
+  pages={3376--3393},
+  year={2021},
+  publisher={Elsevier},
+  doi={10.1016/j.cell.2021.05.002}
+}
+
+
+@dataset{debroas_2024_11124657,
+  author       = {DEBROAS, Didier},
+  title        = {Plasmids Identified in Air Metagenomes},
+  month        = may,
+  year         = 2024,
+  publisher    = {Zenodo},
+  doi          = {10.5281/zenodo.11124657},
+  url          = {https://doi.org/10.5281/zenodo.11124657}
+}
+
+@article{hennequin2022plasmidome,
+  title={Plasmidome analysis of a hospital effluent biofilm: Status of antibiotic resistance},
+  author={Hennequin, Claire and Forestier, Christiane and Traore, Ousmane and Debroas, Didier and Bricheux, Genevi{\`e}ve},
+  journal={Plasmid},
+  volume={122},
+  pages={102638},
+  year={2022},
+  publisher={Elsevier},
+  doi={10.1016/j.plasmid.2022.102638}
+}
+
+
+@article{hilpert2021reconstruction,
+  title={Reconstruction of plasmids by shotgun sequencing from environmental DNA: which bioinformatic workflow?},
+  author={Hilpert, C{\'e}cile and Bricheux, Genevi{\`e}ve and Debroas, Didier},
+  journal={Briefings in bioinformatics},
+  volume={22},
+  number={3},
+  pages={bbaa059},
+  year={2021},
+  publisher={Oxford University Press},
+  doi={10.1093/bib/bbaa059}
+}
+
+@article{kanehisa2016kegg,
+  title={KEGG as a reference resource for gene and protein annotation},
+  author={Kanehisa, Minoru and Sato, Yoko and Kawashima, Masayuki and Furumichi, Miho and Tanabe, Mao},
+  journal={Nucleic acids research},
+  volume={44},
+  number={D1},
+  pages={D457--D462},
+  year={2016},
+  publisher={Oxford University Press},
+  doi={10.1093/nar/gkv1070}
+}
+
+@article{krawczyk2018plasflow,
+  title={PlasFlow: predicting plasmid sequences in metagenomic data using genome signatures},
+  author={Krawczyk, Pawel S and Lipinski, Leszek and Dziembowski, Andrzej},
+  journal={Nucleic acids research},
+  volume={46},
+  number={6},
+  pages={e35--e35},
+  year={2018},
+  publisher={Oxford University Press},
+  doi={10.1093/nar/gkx1321}
+}
+
+
+@article{li2015,
+	title = {{MEGAHIT}: an ultra-fast single-node solution for large and complex metagenomics assembly via succinct de {Bruijn} graph},
+	volume = {31},
+	issn = {1367-4803},
+	shorttitle = {{MEGAHIT}},
+	doi = {10.1093/bioinformatics/btv033},
+	abstract = {Summary: MEGAHIT is a NGS de novo assembler for assembling large and complex metagenomics data in a time- and cost-efficient manner. It finished assembling a soil metagenomics dataset with 252 Gbps in 44.1 and 99.6 h on a single computing node with and without a graphics processing unit, respectively. MEGAHIT assembles the data as a whole, i.e. no pre-processing like partitioning and normalization was needed. When compared with previous methods on assembling the soil data, MEGAHIT generated a three-time larger assembly, with longer contig N50 and average contig length; furthermore, 55.8\% of the reads were aligned to the assembly, giving a fourfold improvement.Availability and implementation: The source code of MEGAHIT is freely available at https://github.com/voutcn/megahit under GPLv3 license.Contact:[email protected] or [email protected] information: Supplementary data are available at Bioinformatics online.},
+	number = {10},
+	journal = {Bioinformatics},
+	author = {Li, Dinghua and Liu, Chi-Man and Luo, Ruibang and Sadakane, Kunihiko and Lam, Tak-Wah},
+	month = may,
+	year = {2015},
+	pages = {1674--1676},
+}
+
+@article{li2018minimap2,
+  title={Minimap2: pairwise alignment for nucleotide sequences},
+  author={Li, Heng},
+  journal={Bioinformatics},
+  volume={34},
+  number={18},
+  pages={3094--3100},
+  year={2018},
+  publisher={Oxford University Press},
+  doi={10.1093/bioinformatics/bty191},
+}
+
+@article{mirdita2019mmseqs2,
+  title={MMseqs2 desktop and local web server app for fast, interactive sequence searches},
+  author={Mirdita, Milot and Steinegger, Martin and S{\"o}ding, Johannes},
+  journal={Bioinformatics},
+  volume={35},
+  number={16},
+  pages={2856--2858},
+  year={2019},
+  publisher={Oxford University Press},
+  doi={10.1093/bioinformatics/bty1057}
+}
+
+@article{mistry2021pfam,
+  title={Pfam: The protein families database in 2021},
+  author={Mistry, Jaina and Chuguransky, Sara and Williams, Lowri and Qureshi, Matloob and Salazar, Gustavo A and Sonnhammer, Erik LL and Tosatto, Silvio CE and Paladin, Lisanna and Raj, Shriya and Richardson, Lorna J and others},
+  journal={Nucleic acids research},
+  volume={49},
+  number={D1},
+  pages={D412--D419},
+  year={2021},
+  publisher={Oxford University Press},
+  doi={10.1093/nar/gkaa913}
+}
+
+
+@article{pellow2020plasclass,
+  title={PlasClass improves plasmid sequence classification},
+  author={Pellow, David and Mizrahi, Itzik and Shamir, Ron},
+  journal={PLoS computational biology},
+  volume={16},
+  number={4},
+  pages={e1007781},
+  year={2020},
+  publisher={Public Library of Science San Francisco, CA USA},
+  doi={10.1371/journal.pcbi.1007781}
+}
+
+
+@article{quast2012silva,
+  title={The SILVA ribosomal RNA gene database project: improved data processing and web-based tools},
+  author={Quast, Christian and Pruesse, Elmar and Yilmaz, Pelin and Gerken, Jan and Schweer, Timmy and Yarza, Pablo and Peplies, J{\"o}rg and Gl{\"o}ckner, Frank Oliver},
+  journal={Nucleic acids research},
+  volume={41},
+  number={D1},
+  pages={D590--D596},
+  year={2012},
+  publisher={Oxford University Press},
+  doi={10.1093/nar/gks1219}
+}
+
+
+@article{robertson2018mob,
+  title={MOB-suite: software tools for clustering, reconstruction and typing of plasmids from draft assemblies},
+  author={Robertson, James and Nash, John HE},
+  journal={Microbial genomics},
+  volume={4},
+  number={8},
+  pages={e000206},
+  year={2018},
+  publisher={Microbiology Society},
+  doi={10.1099/mgen.0.000206}
+}
+
+@article{wu2013systematic,
+  title={Systematic identification of gene families for use as “markers” for phylogenetic and phylogeny-driven ecological studies of bacteria and archaea and their major subgroups},
+  author={Wu, Dongying and Jospin, Guillaume and Eisen, Jonathan A},
+  journal={PloS one},
+  volume={8},
+  number={10},
+  pages={e77033},
+  year={2013},
+  publisher={Public Library of Science San Francisco, USA},
+  doi={10.1371/journal.pone.0077033}
+}