Skip to content

Commit

Permalink
Add bulk_download to mg_toolkit suite (galaxyproject#6190)
Browse files Browse the repository at this point in the history 
* update .shed.yml

* Add bulk_download to mg_toolkit suite

* fix lint WARNINGs + review adjustments
  • Loading branch information
@RZ9082
RZ9082 authored Jul 30, 2024
1 parent fa0f3ca commit df500c2
Show file tree
Hide file tree
Showing 66 changed files with 5,378 additions and 0 deletions.
1 change: 1 addition & 0 deletions tools/mg_toolkit/.shed.yml
View file
Original file line number Diff line number Diff line change
Expand Up @@ -4,6 +4,7 @@ description: Metagenomics toolkit enables scientists to download all of the samp
homepage_url: https://github.com/EBI-Metagenomics/emg-toolkit
long_description: |
Metagenomics toolkit enables scientists to download all of the sample metadata for a given study or sequence to a single csv file.
also downloading study results categorized by group types.
remote_repository_url: https://github.com/galaxyproject/tools-iuc/tree/main/tools/mg_toolkit
type: unrestricted
categories:
Expand Down
859 changes: 859 additions & 0 deletions tools/mg_toolkit/bulk_download.xml
View file

Large diffs are not rendered by default.

120 changes: 120 additions & 0 deletions tools/mg_toolkit/macros.xml
View file
Original file line number Diff line number Diff line change
Expand Up @@ -16,6 +16,126 @@
<person givenName="Rand" familyName="Zoabi" url="https://github.com/RZ9082" />
</creator>
</xml>
<xml name="all_versions_result_group">
<option value="statistics">Statistics</option>
<option value="sequence_data">Sequence data</option>
<option value="functional_analysis">Functional analysis</option>
</xml>
<xml name="v1.0-v3.0_result_group">
<option value="taxonomic_analysis">Taxonomic analysis</option>
</xml>
<xml name="v4.0-v5.0_result_group">
<option value="taxonomic_analysis_ssu_rrna">Taxonomic analysis SSU</option>
<option value="taxonomic_analysis_lsu_rrna">Taxonomic analysis LSU</option>
<option value="non-coding_rnas">Non-coding RNAs</option>
</xml>
<xml name="v5.0_result_group">
<option value="taxonomic_analysis_itsonedb">Taxonomic analysis ITSoneDB</option>
<option value="taxonomic_analysis_unite">Taxonomic analysis ITS UNITE</option>
<option value="taxonomic_analysis_motu">Taxonomic analysis mOTU</option>
<option value="pathways_and_systems">Pathways and systems</option>
</xml>
<xml name="file_type_statistics">
<param name="file_type" type="select" label="File type" multiple="true" optional="false">
<option value="taxa_abundance_distribution">Taxa abundance distribution</option>
</param>
</xml>
<xml name="file_type_sequence_data">
<param name="file_type" type="select" label="File type" multiple="true" optional="false">
<option value="processed_contigs_nucleotide_reads">Processed contigs/nucleotide reads</option>
<option value="processed_contigs_reads_with_annotation">Processed contigs/reads with annotation</option>
<option value="processed_contigs_reads_without_annotation">Processed contigs/reads without annotation</option>
<option value="processed_contigs_reads_with_pcds">Processed contigs/reads with pCDS</option>
<option value="predicted_cds">Predicted CDS (aa)</option>
<option value="predicted_cds_with_annotation">Predicted CDS with annotation</option>
<option value="predicted_cds_without_annotation">Predicted CDS without annotation</option>
<option value="predicted_orf">Predicted ORF (nt)</option>
<option value="predicted_orf_with_annotation">Predicted ORF with annotation</option>
<option value="predicted_orf_without_annotation">Predicted ORF without annotation</option>
</param>
</xml>
<xml name="file_type_functional_analysis">
<param name="file_type" type="select" label="File type" multiple="true" optional="false">
<option value="complete_go_annotation">Complete GO annotation</option>
<option value="go_slim_annotation">GO slim annotation</option>
<option value="interpro_summary">InterPro summary</option>
<option value="interpro_matches">InterPro matches</option>
<option value="kegg_orthologues_annotation">KEGG orthologues annotation</option>
<option value="pfam_annotation">Pfam annotation</option>
<option value="combined_annotation">Combined (eggNOG, InterPro, antiSMASH) annotation</option>
<option value="diamond_annotation">Diamond annotation</option>
<option value="eggnog_annotation">eggNOG annotation</option>
<option value="eggnog_seed_orthologs">eggNOG seed orthologs</option>
</param>
</xml>
<xml name="file_type_taxonomic_analysis_ssu_rrna">
<param name="file_type" type="select" label="File type" multiple="true" optional="false">
<option value="reads_contigs_encoding_ssu">Reads/Contigs encoding SSU rRNA</option>
<option value="mapseq_ssu_assignments">MAPseq SSU assignments</option>
<option value="ssu_otu_tables">SSU OTU tables</option>
<option value="ssu_hdf5_biom">SSU HDF5 BIOM files</option>
<option value="ssu_json_biom">SSU JSON BIOM files</option>
</param>
</xml>
<xml name="file_type_taxonomic_analysis_lsu_rrna">
<param name="file_type" type="select" label="File type" multiple="true" optional="false">
<option value="reads_contigs_encoding_lsu">Reads/Contigs encoding LSU rRNA</option>
<option value="mapseq_lsu_assignments">MAPseq LSU assignments</option>
<option value="lsu_otu_tables">LSU OTU tables</option>
<option value="lsu_hdf5_biom">LSU HDF5 BIOM files</option>
<option value="lsu_json_biom">LSU JSON BIOM files</option>
</param>
</xml>
<xml name="file_type_non-coding_rnas">
<param name="file_type" type="select" label="File type" multiple="true" optional="false">
<option value="predicted_non_coding_rnas">Predicted non-coding RNAs</option>
</param>
</xml>
<xml name="file_type_taxonomic_analysis_itsonedb">
<param name="file_type" type="select" label="File type" multiple="true" optional="false">
<option value="mapseq_itsonedb_assignments">MAPseq ITSoneDB assignments</option>
<option value="itsonedb_otu_tables">ITSoneDB OTU tables</option>
<option value="itsonedb_hdf5_biom">ITSoneDB HDF5 BIOM files</option>
<option value="itsonedb_json_biom">ITSoneDB JSON BIOM files</option>
</param>
</xml>
<xml name="file_type_taxonomic_analysis_unite">
<param name="file_type" type="select" label="File type" multiple="true" optional="false">
<option value="mapseq_unite_assignments">MAPseq UNITE assignments</option>
<option value="unite_otu_tables">UNITE OTU tables</option>
<option value="unite_hdf5_biom">UNITE HDF5 BIOM files</option>
<option value="unite_json_biom">UNITE JSON BIOM files</option>
</param>
</xml>
<xml name="file_type_taxonomic_analysis_motu">
<param name="file_type" type="select" label="File type" multiple="true" optional="false">
<option value="motus_taxonomic_profile">mOTUs taxonomic profile</option>
</param>
</xml>
<xml name="file_type_pathways_and_systems">
<param name="file_type" type="select" label="File type" multiple="true" optional="false">
<option value="antismash_annotation_gff3">antiSMASH annotation (gff3)</option>
<option value="antismash_annotation_embl">antiSMASH annotation(embl)</option>
<option value="antismash_annotation_genbank">antiSMASH annotation(genbank)</option>
<option value="antismash_summary">antiSMASH summary</option>
<option value="genome_properties_annotation">Genome properties annotation</option>
<option value="kegg_pathway_annotation">KEGG pathway annotation</option>
<option value="kegg_pathway_annotation_contig">KEGG pathway annotation (contig)</option>
</param>
</xml>
<xml name="file_type_taxonomic_analysis">
<param name="file_type" type="select" label="File type" multiple="true" optional="false">
<option value="phylogenetic_tree"></option>
<option value="otus_counts_and_taxonomic_assignments_tsv">OTUs, counts and taxonomic assignments (table)</option>
<option value="otus_counts_and_taxonomic_assignments_biom1">OTUs, counts and taxonomic assignments (JSON)</option>
<option value="otus_counts_and_taxonomic_assignments_biom2">OTUs, counts and taxonomic assignments (HDF5)</option>
<option value="reads_encoding_5s_rrna">Reads enconding 5S rRNA</option>
<option value="reads_encoding_16s_rrna">Reads enconding 16S rRNA</option>
<option value="reads_encoding_23s_rrna">Reads enconding 23S rRNA</option>
</param>
</xml>
<xml name="file_type_taxonomic_analysis_its">
</xml>
<xml name="citations">
<citations>
<citation type="bibtex">
Expand Down
50 changes: 50 additions & 0 deletions tools/mg_toolkit/test-data/functional_analysis/MGYS00006583_metadata.tsv
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1,50 @@
analysis_id name group_type description download_url pipeline_version experiment_type
MGYA00722210 ERZ21819995_Archaea_SRP.RF01857.fasta.gz non-coding RNAs Predicted Archaea SRP RNA https://www.ebi.ac.uk/metagenomics/api/v1/analyses/MGYA00722210/file/ERZ21819995_Archaea_SRP.RF01857.fasta.gz 5.0 assembly
MGYA00722210 ERZ21819995_FASTA.fasta.gz Sequence data Processed contigs https://www.ebi.ac.uk/metagenomics/api/v1/analyses/MGYA00722210/file/ERZ21819995_FASTA.fasta.gz 5.0 assembly
MGYA00722210 ERZ21819995_FASTA_GO.csv Functional analysis Complete GO annotation https://www.ebi.ac.uk/metagenomics/api/v1/analyses/MGYA00722210/file/ERZ21819995_FASTA_GO.csv 5.0 assembly
MGYA00722210 ERZ21819995_FASTA_GO_slim.csv Functional analysis GO slim annotation https://www.ebi.ac.uk/metagenomics/api/v1/analyses/MGYA00722210/file/ERZ21819995_FASTA_GO_slim.csv 5.0 assembly
MGYA00722210 ERZ21819995_FASTA_InterPro.csv Functional analysis InterPro summary https://www.ebi.ac.uk/metagenomics/api/v1/analyses/MGYA00722210/file/ERZ21819995_FASTA_InterPro.csv 5.0 assembly
MGYA00722210 ERZ21819995_FASTA_InterPro.tsv.gz Functional analysis InterPro matches https://www.ebi.ac.uk/metagenomics/api/v1/analyses/MGYA00722210/file/ERZ21819995_FASTA_InterPro.tsv.gz 5.0 assembly
MGYA00722210 ERZ21819995_FASTA_LSU.fasta.gz Taxonomic analysis LSU rRNA Contigs encoding LSU rRNA https://www.ebi.ac.uk/metagenomics/api/v1/analyses/MGYA00722210/file/ERZ21819995_FASTA_LSU.fasta.gz 5.0 assembly
MGYA00722210 ERZ21819995_FASTA_LSU_MAPSeq.mseq.gz Taxonomic analysis LSU rRNA MAPseq LSU assignments https://www.ebi.ac.uk/metagenomics/api/v1/analyses/MGYA00722210/file/ERZ21819995_FASTA_LSU_MAPSeq.mseq.gz 5.0 assembly
MGYA00722210 ERZ21819995_FASTA_LSU_OTU.tsv Taxonomic analysis LSU rRNA OTUs, counts and taxonomic assignments for LSU rRNA https://www.ebi.ac.uk/metagenomics/api/v1/analyses/MGYA00722210/file/ERZ21819995_FASTA_LSU_OTU.tsv 5.0 assembly
MGYA00722210 ERZ21819995_FASTA_LSU_OTU_TABLE_HDF5.biom Taxonomic analysis LSU rRNA OTUs, counts and taxonomic assignments for LSU rRNA https://www.ebi.ac.uk/metagenomics/api/v1/analyses/MGYA00722210/file/ERZ21819995_FASTA_LSU_OTU_TABLE_HDF5.biom 5.0 assembly
MGYA00722210 ERZ21819995_FASTA_LSU_OTU_TABLE_JSON.biom Taxonomic analysis LSU rRNA OTUs, counts and taxonomic assignments for LSU rRNA https://www.ebi.ac.uk/metagenomics/api/v1/analyses/MGYA00722210/file/ERZ21819995_FASTA_LSU_OTU_TABLE_JSON.biom 5.0 assembly
MGYA00722210 ERZ21819995_FASTA_SSU.fasta.gz Taxonomic analysis SSU rRNA Contigs encoding SSU rRNA https://www.ebi.ac.uk/metagenomics/api/v1/analyses/MGYA00722210/file/ERZ21819995_FASTA_SSU.fasta.gz 5.0 assembly
MGYA00722210 ERZ21819995_FASTA_SSU_MAPSeq.mseq.gz Taxonomic analysis SSU rRNA MAPseq SSU assignments https://www.ebi.ac.uk/metagenomics/api/v1/analyses/MGYA00722210/file/ERZ21819995_FASTA_SSU_MAPSeq.mseq.gz 5.0 assembly
MGYA00722210 ERZ21819995_FASTA_SSU_OTU.tsv Taxonomic analysis SSU rRNA OTUs, counts and taxonomic assignments for SSU rRNA https://www.ebi.ac.uk/metagenomics/api/v1/analyses/MGYA00722210/file/ERZ21819995_FASTA_SSU_OTU.tsv 5.0 assembly
MGYA00722210 ERZ21819995_FASTA_SSU_OTU_TABLE_HDF5.biom Taxonomic analysis SSU rRNA OTUs, counts and taxonomic assignments for SSU rRNA https://www.ebi.ac.uk/metagenomics/api/v1/analyses/MGYA00722210/file/ERZ21819995_FASTA_SSU_OTU_TABLE_HDF5.biom 5.0 assembly
MGYA00722210 ERZ21819995_FASTA_SSU_OTU_TABLE_JSON.biom Taxonomic analysis SSU rRNA OTUs, counts and taxonomic assignments for SSU rRNA https://www.ebi.ac.uk/metagenomics/api/v1/analyses/MGYA00722210/file/ERZ21819995_FASTA_SSU_OTU_TABLE_JSON.biom 5.0 assembly
MGYA00722210 ERZ21819995_FASTA_annotations.gff.bgz Functional analysis Combined (eggNOG, InterPro, antiSMASH) annotation https://www.ebi.ac.uk/metagenomics/api/v1/analyses/MGYA00722210/file/ERZ21819995_FASTA_annotations.gff.bgz 5.0 assembly
MGYA00722210 ERZ21819995_FASTA_diamond.tsv.gz Functional analysis Diamond annotation https://www.ebi.ac.uk/metagenomics/api/v1/analyses/MGYA00722210/file/ERZ21819995_FASTA_diamond.tsv.gz 5.0 assembly
MGYA00722210 ERZ21819995_FASTA_emapper.annotations.tsv.gz Functional analysis eggNOG annotation https://www.ebi.ac.uk/metagenomics/api/v1/analyses/MGYA00722210/file/ERZ21819995_FASTA_emapper.annotations.tsv.gz 5.0 assembly
MGYA00722210 ERZ21819995_FASTA_emapper.seed_orthologs.tsv.gz Functional analysis eggNOG seed orthologs https://www.ebi.ac.uk/metagenomics/api/v1/analyses/MGYA00722210/file/ERZ21819995_FASTA_emapper.seed_orthologs.tsv.gz 5.0 assembly
MGYA00722210 ERZ21819995_FASTA_ko.tsv Functional analysis KEGG orthologues annotation https://www.ebi.ac.uk/metagenomics/api/v1/analyses/MGYA00722210/file/ERZ21819995_FASTA_ko.tsv 5.0 assembly
MGYA00722210 ERZ21819995_FASTA_pfam.tsv Functional analysis Pfam annotation https://www.ebi.ac.uk/metagenomics/api/v1/analyses/MGYA00722210/file/ERZ21819995_FASTA_pfam.tsv 5.0 assembly
MGYA00722210 ERZ21819995_FASTA_predicted_cds.faa.gz Sequence data Predicted CDS (aa) https://www.ebi.ac.uk/metagenomics/api/v1/analyses/MGYA00722210/file/ERZ21819995_FASTA_predicted_cds.faa.gz 5.0 assembly
MGYA00722210 ERZ21819995_FASTA_predicted_orf.ffn.gz Sequence data Predicted ORF (nt) https://www.ebi.ac.uk/metagenomics/api/v1/analyses/MGYA00722210/file/ERZ21819995_FASTA_predicted_orf.ffn.gz 5.0 assembly
MGYA00722210 ERZ21819995_alpha_tmRNA.RF01849.fasta.gz non-coding RNAs Predicted alpha tmRNA https://www.ebi.ac.uk/metagenomics/api/v1/analyses/MGYA00722210/file/ERZ21819995_alpha_tmRNA.RF01849.fasta.gz 5.0 assembly
MGYA00722210 ERZ21819995_Bacteria_large_SRP.RF01854.fasta.gz non-coding RNAs Predicted Bacteria large SRP RNA https://www.ebi.ac.uk/metagenomics/api/v1/analyses/MGYA00722210/file/ERZ21819995_Bacteria_large_SRP.RF01854.fasta.gz 5.0 assembly
MGYA00722210 ERZ21819995_Bacteria_small_SRP.RF00169.fasta.gz non-coding RNAs Predicted Bacteria small SRP RNA https://www.ebi.ac.uk/metagenomics/api/v1/analyses/MGYA00722210/file/ERZ21819995_Bacteria_small_SRP.RF00169.fasta.gz 5.0 assembly
MGYA00722210 ERZ21819995_FASTA_antismash.embl.gz Pathways and Systems antiSMASH annotation https://www.ebi.ac.uk/metagenomics/api/v1/analyses/MGYA00722210/file/ERZ21819995_FASTA_antismash.embl.gz 5.0 assembly
MGYA00722210 ERZ21819995_FASTA_antismash.gbk.gz Pathways and Systems antiSMASH annotation https://www.ebi.ac.uk/metagenomics/api/v1/analyses/MGYA00722210/file/ERZ21819995_FASTA_antismash.gbk.gz 5.0 assembly
MGYA00722210 ERZ21819995_FASTA_antismash.gff.bgz Pathways and Systems antiSMASH annotation https://www.ebi.ac.uk/metagenomics/api/v1/analyses/MGYA00722210/file/ERZ21819995_FASTA_antismash.gff.bgz 5.0 assembly
MGYA00722210 ERZ21819995_FASTA_antismash_summary.csv Pathways and Systems antiSMASH summary https://www.ebi.ac.uk/metagenomics/api/v1/analyses/MGYA00722210/file/ERZ21819995_FASTA_antismash_summary.csv 5.0 assembly
MGYA00722210 ERZ21819995_FASTA_gp.csv Pathways and Systems Genome Properties annotation https://www.ebi.ac.uk/metagenomics/api/v1/analyses/MGYA00722210/file/ERZ21819995_FASTA_gp.csv 5.0 assembly
MGYA00722210 ERZ21819995_FASTA_kegg_pathways.csv Pathways and Systems KEGG pathway annotation https://www.ebi.ac.uk/metagenomics/api/v1/analyses/MGYA00722210/file/ERZ21819995_FASTA_kegg_pathways.csv 5.0 assembly
MGYA00722210 ERZ21819995_FASTA_kegg_pathways_contigs.tsv Pathways and Systems KEGG pathway annotation (contig) https://www.ebi.ac.uk/metagenomics/api/v1/analyses/MGYA00722210/file/ERZ21819995_FASTA_kegg_pathways_contigs.tsv 5.0 assembly
MGYA00722210 ERZ21819995_Fungi_SRP.RF01502.fasta.gz non-coding RNAs Predicted Fungi SRP RNA https://www.ebi.ac.uk/metagenomics/api/v1/analyses/MGYA00722210/file/ERZ21819995_Fungi_SRP.RF01502.fasta.gz 5.0 assembly
MGYA00722210 ERZ21819995_Metazoa_SRP.RF00017.fasta.gz non-coding RNAs Predicted Metazoa SRP RNA https://www.ebi.ac.uk/metagenomics/api/v1/analyses/MGYA00722210/file/ERZ21819995_Metazoa_SRP.RF00017.fasta.gz 5.0 assembly
MGYA00722210 ERZ21819995_Plant_SRP.RF01855.fasta.gz non-coding RNAs Predicted Plant SRP RNA https://www.ebi.ac.uk/metagenomics/api/v1/analyses/MGYA00722210/file/ERZ21819995_Plant_SRP.RF01855.fasta.gz 5.0 assembly
MGYA00722210 ERZ21819995_Protozoa_SRP.RF01856.fasta.gz non-coding RNAs Predicted Protozoa SRP RNA https://www.ebi.ac.uk/metagenomics/api/v1/analyses/MGYA00722210/file/ERZ21819995_Protozoa_SRP.RF01856.fasta.gz 5.0 assembly
MGYA00722210 ERZ21819995_RNaseP_arch.RF00373.fasta.gz non-coding RNAs Predicted Archaeal RNase P RNA https://www.ebi.ac.uk/metagenomics/api/v1/analyses/MGYA00722210/file/ERZ21819995_RNaseP_arch.RF00373.fasta.gz 5.0 assembly
MGYA00722210 ERZ21819995_RNaseP_bact_a.RF00010.fasta.gz non-coding RNAs Predicted Bacterial RNase P class A RNA https://www.ebi.ac.uk/metagenomics/api/v1/analyses/MGYA00722210/file/ERZ21819995_RNaseP_bact_a.RF00010.fasta.gz 5.0 assembly
MGYA00722210 ERZ21819995_RNaseP_bact_b.RF00011.fasta.gz non-coding RNAs Predicted Bacterial RNase P class B RNA https://www.ebi.ac.uk/metagenomics/api/v1/analyses/MGYA00722210/file/ERZ21819995_RNaseP_bact_b.RF00011.fasta.gz 5.0 assembly
MGYA00722210 ERZ21819995_RNase_MRP.RF00030.fasta.gz non-coding RNAs Predicted RNase MRP RNA https://www.ebi.ac.uk/metagenomics/api/v1/analyses/MGYA00722210/file/ERZ21819995_RNase_MRP.RF00030.fasta.gz 5.0 assembly
MGYA00722210 ERZ21819995_RNase_P.RF01577.fasta.gz non-coding RNAs Predicted Plasmodium RNase P https://www.ebi.ac.uk/metagenomics/api/v1/analyses/MGYA00722210/file/ERZ21819995_RNase_P.RF01577.fasta.gz 5.0 assembly
MGYA00722210 ERZ21819995_beta_tmRNA.RF01850.fasta.gz non-coding RNAs Predicted beta tmRNA https://www.ebi.ac.uk/metagenomics/api/v1/analyses/MGYA00722210/file/ERZ21819995_beta_tmRNA.RF01850.fasta.gz 5.0 assembly
MGYA00722210 ERZ21819995_cyano_tmRNA.RF01851.fasta.gz non-coding RNAs Predicted cyano tmRNA https://www.ebi.ac.uk/metagenomics/api/v1/analyses/MGYA00722210/file/ERZ21819995_cyano_tmRNA.RF01851.fasta.gz 5.0 assembly
MGYA00722210 ERZ21819995_mt-tmRNA.RF02544.fasta.gz non-coding RNAs Predicted mt-tmRNA https://www.ebi.ac.uk/metagenomics/api/v1/analyses/MGYA00722210/file/ERZ21819995_mt-tmRNA.RF02544.fasta.gz 5.0 assembly
MGYA00722210 ERZ21819995_tRNA-Sec.RF01852.fasta.gz non-coding RNAs Predicted tRNA-Sec https://www.ebi.ac.uk/metagenomics/api/v1/analyses/MGYA00722210/file/ERZ21819995_tRNA-Sec.RF01852.fasta.gz 5.0 assembly
MGYA00722210 ERZ21819995_tRNA.RF00005.fasta.gz non-coding RNAs Predicted tRNA https://www.ebi.ac.uk/metagenomics/api/v1/analyses/MGYA00722210/file/ERZ21819995_tRNA.RF00005.fasta.gz 5.0 assembly
MGYA00722210 ERZ21819995_tmRNA.RF00023.fasta.gz non-coding RNAs Predicted tmRNA https://www.ebi.ac.uk/metagenomics/api/v1/analyses/MGYA00722210/file/ERZ21819995_tmRNA.RF00023.fasta.gz 5.0 assembly
Loading

0 comments on commit df500c2

Please sign in to comment.