-
Notifications
You must be signed in to change notification settings - Fork 1
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
Showing
2 changed files
with
21 additions
and
49 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -1,85 +1,56 @@ | ||
| # ABOUT: This a config for submitting samples, paired-end reads, an assembly, bins and MAGs | ||
| # ABOUT: Coverage is derived from 2 bam files. | ||
| # ABOUT: This is a config for submitting 2 set of paired end reads, an assembly and bins | ||
| # ABOUT: Coverage is known. | ||
| # ABOUT: Taxonomy is derived from `gtdb_to_ncbi_majority_vote.py` output and a MANUAL_TAXONOMY_FILE | ||
| # USAGE: navigate to the <examples> directory | ||
| # USAGE: submg submit --config 01_samples_reads_assembly_bins_mags.yaml --staging_dir <path/to/staging/dir> --logging_dir <path/to/logging/dir> --submit_samples --submit_reads --submit_assembly --submit_bins --submit_mags | ||
| # USAGE: submg submit --config 05_reads_assembly_bins.yaml --staging_dir <path/to/staging/dir> --logging_dir <path/to/logging/dir> --submit_reads --submit_assembly --submit_bins | ||
|
|
||
|
|
||
| STUDY: "PRJEB71644" # The accession of your study (which has to already exist in ENA) >>EXAMPLE: "PRJEB71644" | ||
| METAGENOME_SCIENTIFIC_NAME: "biogas fermenter metagenome" # Taxonomic identifier of the metagenome. Check the ENA metagenome taxonomy tree to find a taxonomy ID and species name fitting your sample >>EXAMPLE: "biogas fermenter metagenome" | ||
| METAGENOME_TAXID: "718289" # Taxonomic identifier of the assembly. Must match SPECIES_SCIENTIFIC_NAME >>EXAMPLE: "718289" | ||
| SEQUENCING_PLATFORMS: ["ILLUMINA"] # One of https://ena-docs.readthedocs.io/en/latest/submit/reads/webin-cli.html#platform >>EXAMPLE: ["ILLUMINA","OXFORD_NANOPORE"] | ||
| PROJECT_NAME: "7yyIc_AgRFex 2 Survey" # Name of the project within which the sequencing was organized >>EXAMPLE: "AgRFex 2 Biogas Survey" | ||
| NEW_SAMPLES: # These samples will be created in ENA according to the data entered below. Your assembly MUST BE BASED ON ALL OF THESE. | ||
| - TITLE: "7yyIc_hydrolysis digester sample" # A unique title for your sample >>EXAMPLE: "Bioreactor_2_sample" | ||
| collection date: "2022-07-12" # Any ISO compliant time. Can be truncated from the righ (e.g. '2023-12-27T16:07' or '2023-12') >>EXAMPLE: "2023-03" | ||
| geographic location (country and/or sea): "Germany" # See ENA checklists (e.g. https://www.ebi.ac.uk/ena/browser/view/ERC000011) for valid values >>EXAMPLE: "Germany" | ||
| ADDITIONAL_SAMPLESHEET_FIELDS: # Please add more fields from the ENA samplesheet that most closely matches your experiment | ||
| geographic location (latitude): 52.51 # Use WGS84. For more information consult appropriate an ENA samplesheet template (e.g. https://www.ebi.ac.uk/ena/browser/view/ERC000050) >>EXAMPLE: "41.85" | ||
| geographic location (longitude): 8.77 # Use WGS84. For more information consult appropriate an ENA samplesheet template (e.g. https://www.ebi.ac.uk/ena/browser/view/ERC000050) >>EXAMPLE: "-87.65" | ||
| broad-scale environmental context: "tropical biome" # For more information consult appropriate an ENA samplesheet template (e.g. https://www.ebi.ac.uk/ena/browser/view/ERC000050) >>EXAMPLE: "tropical biome" | ||
| local environmental context: "tropical marine upwelling biome" # For more information consult an appropriate ENA samplesheet template (e.g. https://www.ebi.ac.uk/ena/browser/view/ERC000050) >>EXAMPLE: "tropical marine upwelling biome" | ||
| environmental medium: "grass silage|animal waste material|anoxic water" # Pipe separated! For more information consult an ENA samplesheet template (e.g. https://www.ebi.ac.uk/ena/browser/view/ERC000050) and https://github.com/EnvironmentOntology/envo/wiki/Using-ENVO-with-MIxS >>EXAMPLE: "grass silage|animal waste material|anoxic water" | ||
| - TITLE: "7yyIc_main digester sample" # A unique title for your sample >>EXAMPLE: "Bioreactor_2_sample" | ||
| collection date: "2022-07-12" # Any ISO compliant time. Can be truncated from the righ (e.g. '2023-12-27T16:07' or '2023-12') >>EXAMPLE: "2023-03" | ||
| geographic location (country and/or sea): "Germany" # See ENA checklists (e.g. https://www.ebi.ac.uk/ena/browser/view/ERC000011) for valid values >>EXAMPLE: "Germany" | ||
| ADDITIONAL_SAMPLESHEET_FIELDS: # Please add more fields from the ENA samplesheet that most closely matches your experiment | ||
| geographic location (latitude): 52.51 # Use WGS84. For more information consult appropriate an ENA samplesheet template (e.g. https://www.ebi.ac.uk/ena/browser/view/ERC000050) >>EXAMPLE: "41.85" | ||
| geographic location (longitude): 8.77 # Use WGS84. For more information consult appropriate an ENA samplesheet template (e.g. https://www.ebi.ac.uk/ena/browser/view/ERC000050) >>EXAMPLE: "-87.65" | ||
| broad-scale environmental context: "tropical biome" # For more information consult appropriate an ENA samplesheet template (e.g. https://www.ebi.ac.uk/ena/browser/view/ERC000050) >>EXAMPLE: "tropical biome" | ||
| local environmental context: "tropical marine upwelling biome" # For more information consult an appropriate ENA samplesheet template (e.g. https://www.ebi.ac.uk/ena/browser/view/ERC000050) >>EXAMPLE: "tropical marine upwelling biome" | ||
| environmental medium: "grass silage|animal waste material|anoxic water" # Pipe separated! For more information consult an ENA samplesheet template (e.g. https://www.ebi.ac.uk/ena/browser/view/ERC000050) and https://github.com/EnvironmentOntology/envo/wiki/Using-ENVO-with-MIxS >>EXAMPLE: "grass silage|animal waste material|anoxic water" | ||
| SAMPLE_ACCESSIONS: ['SAMEA113417017', 'SAMEA113417018'] # These samples exist in ENA. Your assembly is based on them. >>EXAMPLE: ["ERS15898933","ERS15898932"] | ||
| PAIRED_END_READS: | ||
| - NAME: "7yyIc_dh_pe" # Choose a unique name >>EXAMPLE: "Bioreactor_2_replicate_1" | ||
| - NAME: "AKQ4G_ex05_rp1" # Choose a unique name >>EXAMPLE: "Bioreactor_2_replicate_1" | ||
| SEQUENCING_INSTRUMENT: "Illumina HiSeq 1500" # One of https://ena-docs.readthedocs.io/en/latest/submit/reads/webin-cli.html#instrument >>EXAMPLE: ["Illumina HiSeq 1500", "GridION"] | ||
| LIBRARY_SOURCE: "METAGENOMIC" # One of https://ena-docs.readthedocs.io/en/latest/submit/reads/webin-cli.html#permitted-values-for-library-source >>EXAMPLE: "GENOMIC" | ||
| LIBRARY_SELECTION: "RANDOM" # One of https://ena-docs.readthedocs.io/en/latest/submit/reads/webin-cli.html#permitted-values-for-library-source >>EXAMPLE: "RANDOM" | ||
| LIBRARY_STRATEGY: "WGS" # One of https://ena-docs.readthedocs.io/en/latest/submit/reads/webin-cli.html#permitted-values-for-library-strategy >>EXAMPLE: "WGS" | ||
| INSERT_SIZE: "300" # Insert size of the paired-end reads (https://www.ebi.ac.uk/fg/annotare/help/seq_lib_spec.html) >>EXAMPLE: "300" | ||
| FASTQ1_FILE: "data/reads/fwd1.fastq" # Path to the fastq file with forward reads >>EXAMPLE: "/mnt/data/reads_R1.fastq.gz" | ||
| FASTQ2_FILE: "data/reads/rev1.fastq" # Path to the fastq file with reverse reads >>EXAMPLE: "/mnt/data/reads_R2.fastq.gz" | ||
| RELATED_SAMPLE_TITLE: "7yyIc_hydrolysis digester sample" # The title of the sample that these reads originate from >>EXAMPLE: "Bioreactor_2_sample" | ||
| RELATED_SAMPLE_ACCESSION: 'SAMEA113417017' # The accession of the sample that these reads originate from >>EXAMPLE: "ERS15898933" | ||
| ADDITIONAL_MANIFEST_FIELDS: # You can add additional fields that will be written to the manifest | ||
| - NAME: "7yyIc_dm_pe" # Choose a unique name >>EXAMPLE: "Bioreactor_2_replicate_1" | ||
| - NAME: "AKQ4G_ex05_rp2" # Choose a unique name >>EXAMPLE: "Bioreactor_2_replicate_1" | ||
| SEQUENCING_INSTRUMENT: "Illumina HiSeq 1500" # One of https://ena-docs.readthedocs.io/en/latest/submit/reads/webin-cli.html#instrument >>EXAMPLE: ["Illumina HiSeq 1500", "GridION"] | ||
| LIBRARY_SOURCE: "GENOMIC" # One of https://ena-docs.readthedocs.io/en/latest/submit/reads/webin-cli.html#permitted-values-for-library-source >>EXAMPLE: "GENOMIC" | ||
| LIBRARY_SOURCE: "METAGENOMIC" # One of https://ena-docs.readthedocs.io/en/latest/submit/reads/webin-cli.html#permitted-values-for-library-source >>EXAMPLE: "GENOMIC" | ||
| LIBRARY_SELECTION: "RANDOM" # One of https://ena-docs.readthedocs.io/en/latest/submit/reads/webin-cli.html#permitted-values-for-library-source >>EXAMPLE: "RANDOM" | ||
| LIBRARY_STRATEGY: "WGS" # One of https://ena-docs.readthedocs.io/en/latest/submit/reads/webin-cli.html#permitted-values-for-library-strategy >>EXAMPLE: "WGS" | ||
| INSERT_SIZE: "300" # Insert size of the paired-end reads (https://www.ebi.ac.uk/fg/annotare/help/seq_lib_spec.html) >>EXAMPLE: "300" | ||
| FASTQ1_FILE: "data/reads/fwd2.fastq" # Path to the fastq file with forward reads >>EXAMPLE: "/mnt/data/reads_R1.fastq.gz" | ||
| FASTQ2_FILE: "data/reads/rev2.fastq" # Path to the fastq file with reverse reads >>EXAMPLE: "/mnt/data/reads_R2.fastq.gz" | ||
| RELATED_SAMPLE_TITLE: "7yyIc_main digester sample" # The title of the sample that these reads originate from >>EXAMPLE: "Bioreactor_2_sample" | ||
| RELATED_SAMPLE_ACCESSION: 'SAMEA113417018' # The accession of the sample that these reads originate from >>EXAMPLE: "ERS15898933" | ||
| ADDITIONAL_MANIFEST_FIELDS: # You can add additional fields that will be written to the manifest | ||
| ASSEMBLY: | ||
| ASSEMBLY_NAME: "7yyIc_e01_coasm" # Choose a name, even if your assembly has been uploaded already. Will only be used for naming assembly and bins/MAGs. >>EXAMPLE: "SGMA project mg" | ||
| ASSEMBLY_NAME: "AKQ4G_e05_coasm" # Choose a name, even if your assembly has been uploaded already. Will only be used for naming assembly and bins/MAGs. >>EXAMPLE: "SGMA project mg" | ||
| ASSEMBLY_SOFTWARE: "MEGAHIT" # Software used to generate the assembly >>EXAMPLE: "MEGAHIT" | ||
| ISOLATION_SOURCE: "biogas plant anaerobic digester" # Describe where your sample was taken from >>EXAMPLE: "biogas plant anaerobic digester" | ||
| FASTA_FILE: "data/assembly.fasta" # Path to the fasta file >>EXAMPLE: "/mnt/data/assembly.fasta.gz" | ||
| collection date: "2022-07-12" # Any ISO compliant time. Can be truncated from the righ (e.g. '2023-12-27T16:07' or '2023-12') >>EXAMPLE: "2023-03" | ||
| collection date: "2024-01-01" # Any ISO compliant time. Can be truncated from the righ (e.g. '2023-12-27T16:07' or '2023-12') >>EXAMPLE: "2023-03" | ||
| geographic location (country and/or sea): "Germany" # See ENA checklists (e.g. https://www.ebi.ac.uk/ena/browser/view/ERC000011) for valid values >>EXAMPLE: "Germany" | ||
| COVERAGE_VALUE: 128.27 # Read coverage of the assembly. | ||
| ADDITIONAL_SAMPLESHEET_FIELDS: # Please add more fields from the ENA samplesheet that most closely matches your experiment | ||
| geographic location (latitude): 52.51 # Use WGS84. For more information consult appropriate an ENA samplesheet template (e.g. https://www.ebi.ac.uk/ena/browser/view/ERC000050) >>EXAMPLE: "41.85" | ||
| geographic location (longitude): 8.77 # Use WGS84. For more information consult appropriate an ENA samplesheet template (e.g. https://www.ebi.ac.uk/ena/browser/view/ERC000050) >>EXAMPLE: "-87.65" | ||
| broad-scale environmental context: "tropical biome" # For more information consult appropriate an ENA samplesheet template (e.g. https://www.ebi.ac.uk/ena/browser/view/ERC000050) >>EXAMPLE: "tropical biome" | ||
| local environmental context: "tropical marine upwelling biome" # For more information consult an appropriate ENA samplesheet template (e.g. https://www.ebi.ac.uk/ena/browser/view/ERC000050) >>EXAMPLE: "tropical marine upwelling biome" | ||
| environmental medium: "grass silage|animal waste material|anoxic water" # Pipe separated! For more information consult an ENA samplesheet template (e.g. https://www.ebi.ac.uk/ena/browser/view/ERC000050) and https://github.com/EnvironmentOntology/envo/wiki/Using-ENVO-with-MIxS >>EXAMPLE: "grass silage|animal waste material|anoxic water" | ||
| ADDITIONAL_MANIFEST_FIELDS: # You can add additional fields that will be written to the manifest | ||
| BINS: | ||
| BINS_DIRECTORY: "data/3bins" # Directory containing the fasta files of all bins/MAGs >>EXAMPLE: "/mnt/data/bins" | ||
| COMPLETENESS_SOFTWARE: "CheckM" # Software used to calculate completeness >>EXAMPLE: "CheckM" | ||
| QUALITY_FILE: "data/checkm_quality_3bins.tsv" # tsv file containing quality values of each bin. Header must include 'Bin_id', 'Completeness', 'Contamination'. A CheckM output table will work here. >>EXAMPLE: "/mnt/data/checkm_quality.tsv" | ||
| NCBI_TAXONOMY_FILES: # A list of files with NCBI taxonomy information about the bins. Consult the README to see how they should be structured. >>EXAMPLE: ["/mnt/data/bacteria_tax.tsv","/mnt/data/archaea_tax.tsv"] | ||
| - "data/taxonomy/archaea_taxonomy.tsv" | ||
| - "data/taxonomy/bacteria_taxonomy.tsv" | ||
| - "data/taxonomy/bacteria_taxonomy.tsv" | ||
| MANUAL_TAXONOMY_FILE: "data/taxonomy/manual_taxonomy.tsv" # Scientific names and taxids for bins. See example file for the structure. Columns must be 'Bin_id', 'Tax_id' and 'Scientific_name'. Consult the README for more information. >>EXAMPLE: "/mnt/data/manual_tax.tsv" | ||
| BINNING_SOFTWARE: "metabat2" # The program that was used for binning. >>EXAMPLE: "metabat2" | ||
| ADDITIONAL_SAMPLESHEET_FIELDS: # Please add more fields from the ENA samplesheet that most closely matches your experiment | ||
| binning parameters: "default" # For more information consult an appropriate ENA samplesheet template (e.g. https://www.ebi.ac.uk/ena/browser/view/ERC000047) >>EXAMPLE: "default" | ||
| taxonomic identity marker: "multi marker approach" # For more information consult an appropriate ENA samplesheet template (e.g. https://www.ebi.ac.uk/ena/browser/view/ERC000047) >>EXAMPLE: "multi marker approach" | ||
| ADDITIONAL_MANIFEST_FIELDS: # You can add additional fields that will be written to the manifest | ||
| MAGS: | ||
| MAG_METADATA_FILE: "data/mag_metadata/mag_metadata.tsv" # A .tsv specifying 'Bin_id', 'Sample_id', 'Quality_category', 'Flatfile_path' and 'Unlocalised_path' for all MAGs. See README for more details. >>EXAMPLE: "/mnt/data/mag_data.tsv" | ||
| ADDITIONAL_SAMPLESHEET_FIELDS: # Please add more fields from the ENA samplesheet that most closely matches your experiment | ||
| ADDITIONAL_MANIFEST_FIELDS: # You can add additional fields that will be written to the manifest | ||
| BAM_FILES: # The reads from your experiment mapped back to the assembly | ||
| - "data/mapping/1.sorted.bam" | ||
| - "data/mapping/2.sorted.bam" | ||
| COVERAGE_FILE: "data/bin_coverage.tsv" # .tsv file containing the coverage values of each bin. Columns must be 'Bin_id' and 'Coverage'. | ||
|
|
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters