Merge pull request #5249 from tbrown91/ERGA-post-assembly-QC

Update Erga post assembly qc tools, workflow and text

CONTRIBUTORS.yaml

@@ -2474,3 +2474,10 @@ ThibaudGlinez:
     affiliations:
       - pndb
       - elixir-europe
+
+
+tbrown91:
+    name: Tom Brown
+    email: [email protected]
+    orcid: 0000-0001-8293-4816
+    joined: 2024-08

topics/assembly/tutorials/ERGA-post-assembly-QC/tutorial.bib

@@ -432,3 +432,33 @@ @online{Clavijo
   title = {k-mer counting, part I: Introduction},
   url = {https://bioinfologics.github.io/post/2018/09/17/k-mer-counting-part-i-introduction/},
 }
+
+@article{Mazzoni2023,
+  title = {Biodiversity: an atlas of European reference genomes},
+  volume = {619},
+  ISSN = {1476-4687},
+  url = {http://dx.doi.org/10.1038/d41586-023-02229-w},
+  DOI = {10.1038/d41586-023-02229-w},
+  number = {7969},
+  journal = {Nature},
+  publisher = {Springer Science and Business Media LLC},
+  author = {Mazzoni,  Camila J. and Ciofi,  Claudio and Waterhouse,  Robert M.},
+  year = {2023},
+  month = jul,
+  pages = {252–252}
+}
+@article{Li2018,
+  title = {Minimap2: pairwise alignment for nucleotide sequences},
+  volume = {34},
+  ISSN = {1367-4811},
+  url = {http://dx.doi.org/10.1093/bioinformatics/bty191},
+  DOI = {10.1093/bioinformatics/bty191},
+  number = {18},
+  journal = {Bioinformatics},
+  publisher = {Oxford University Press (OUP)},
+  author = {Li,  Heng},
+  editor = {Birol,  Inanc},
+  year = {2018},
+  month = may,
+  pages = {3094–3100}
+}

topics/assembly/tutorials/ERGA-post-assembly-QC/workflows/main_workflow-tests.yml

@@ -0,0 +1,162 @@
+- doc: Test outline for Post-assembly-workflow
+  job:
+    Metadata file:
+      class: File
+      path: test-data/Metadata file.yaml
+      filetype: yaml
+    NCBI taxdump directory:
+      class: File
+      path: https://zenodo.org/record/7781236/files/new_taxdump.tar.gz
+      filetype: gz
+    Primary genome assembly file (fasta):
+      class: File
+      path: https://zenodo.org/record/7831298/files/assembly_sponge.fasta.gz
+      filetype: fasta.gz
+    DIAMOND database:
+      class: File
+      path: https://zenodo.org/record/7788734/files/Diamond_makedb.dmnd
+      filetype: dmnd
+    Long-read FASTQ files:
+      class: Collection
+      collection_type: list
+      elements:
+      - class: File
+        identifier: dataset_01
+        path: https://zenodo.org/record/7786773/files/hifi.fastq.gz
+    Hi-C reverse:
+      class: Collection
+      collection_type: list
+      elements:
+      - class: File
+        identifier: '0'
+        path: https://zenodo.org/record/7786773/files/hiC_2.fastq.gz
+    Hi-C forward:
+      class: Collection
+      collection_type: list
+      elements:
+      - class: File
+        identifier: '0'
+        path: https://zenodo.org/record/7786773/files/hiC_1.fastq.gz
+    NCBI taxonomic ID: '121349'
+    Ploidy for model to use: '2'
+  outputs:
+    log_plot (Step 36):
+      path: https://zenodo.org/records/13639718/files/transformed_log_plot%20(Step%2036).png
+    transformed_linear_plot (Step 36):
+      path: https://zenodo.org/records/13639718/files/transformed_linear_plot%20(Step%2036).png
+    transformed_log_plot (Step 36):
+      path: https://zenodo.org/records/13639718/files/transformed_log_plot%20(Step%2036).png
+    linear_plot (Step 36):
+      path: https://zenodo.org/records/13639718/files/linear_plot%20(Step%2036).png
+    stats (Step 13):
+      path: 'test-data/stats_Step_13_.tabular'
+      asserts:
+        has_n_lines:
+          85
+        has_text:
+          "117390217"
+    smudgeplot (Step 21):
+      path: https://zenodo.org/records/13639718/files/smudgeplot%20(Step%2021).png
+    smudgeplot_log (Step 21):
+      path: https://zenodo.org/records/13639718/files/smudgeplot_log%20(Step%2021).png
+    outfile (Step 23):
+      path: https://zenodo.org/records/13639718/files/outfile%20(Step%2023).jpg
+    'Busco on input dataset(s) full table':
+      path: 'test-data/Busco_on_input_dataset_s_full_table.tabular'
+      asserts:
+        has_text:
+          "ENA_OX359190_OX359190.1_chromosome_2"
+        has_n_lines:
+          261
+    'Busco on input dataset(s) short summary':
+      path: 'test-data/Busco_on_input_dataset_s_short_summary.txt'
+      asserts:
+        has_n_lines:
+          31
+        has_text:
+          "eukaryota_odb10"
+    output (Step 28):
+      path: 'test-data/output_Step_28_.tabular'
+      asserts:
+        has_n_lines:
+          263902
+        has_text:
+          "This file contains statistics for all reads"
+    'Merqury on input dataset(s) stats':
+      element_tests:
+        output_merqury.completeness:
+          path: 'test-data/Merqury_on_input_dataset_s_stats_output_merqury.completeness.tabular'
+          asserts:
+            has_n_lines:
+              1
+            has_n_columns:
+              5
+            has_text:
+              "79096815"
+    'Merqury on input dataset(s) plots':
+      element_tests:
+        output_merqury.assembly.spectra-cn.fl:
+          path: 'test-data/Merqury on input datasets(s) https://zenodo.org/records/13639718/files/Merqury%20on%20input%20dataset(s)%20plots_output_merqury.assembly.spectra-cn.fl.png'
+        output_merqury.assembly.spectra-cn.ln:
+          path: 'test-data/Merqury on input dataset(s) https://zenodo.org/records/13639718/files/Merqury%20on%20input%20dataset(s)%20plots_output_merqury.assembly.spectra-cn.ln.png'
+        output_merqury.assembly.spectra-cn.st:
+          path: 'test-data/Merqury on input dataset(s) https://zenodo.org/records/13639718/files/Merqury%20on%20input%20dataset(s)%20plots_output_merqury.assembly.spectra-cn.st.png'
+        output_merqury.spectra-asm.fl:
+          path: 'test-data/Merqury on input dataset(s) https://zenodo.org/records/13639718/files/Merqury%20on%20input%20dataset(s)%20plots_output_merqury.spectra-asm.fl.png'
+        output_merqury.spectra-asm.ln:
+          path: 'test-data/Merqury on input dataset(s) https://zenodo.org/records/13639718/files/Merqury%20on%20input%20dataset(s)%20plots_output_merqury.spectra-asm.ln.png'
+        output_merqury.spectra-asm.st:
+          path: 'test-data/Merqury on input dataset(s) https://zenodo.org/records/13639718/files/Merqury%20on%20input%20dataset(s)%20plots_output_merqury.spectra-asm.st.png'
+    'Merqury on input dataset(s) QV stats':
+      element_tests:
+        output_merqury.assembly:
+          path: 'test-data/Merqury_on_input_dataset_s_QV_stats_output_merqury.assembly.tabular'
+          asserts:
+            has_n_lines:
+              15
+            has_n_columns:
+              5
+            has_text:
+              "ENA_OX359189_OX359189.1_chromosome_1"
+        output_merqury:
+          path: 'test-data/Merqury_on_input_dataset_s_QV_stats_output_merqury.tabular'
+          asserts:
+            has_n_lines:
+              1
+            has_n_columns:
+              5
+            has_text:
+              "117383757"
+    pretext_snap_out (Step 42):
+      element_tests:
+        pretext_snapshotENA_OX359189_OX359189.1_chromosome_1:
+          path: https://zenodo.org/records/13639718/files/pretext_snap_out%20(Step%2042)_pretext_snapshotENA_OX359189_OX359189.1_chromosome_1.png
+        pretext_snapshotENA_OX359190_OX359190.1_chromosome_2:
+          path: https://zenodo.org/records/13639718/files/pretext_snap_out%20(Step%2042)_pretext_snapshotENA_OX359190_OX359190.1_chromosome_2.png
+        pretext_snapshotENA_OX359191_OX359191.1_chromosome_3:
+          path: https://zenodo.org/records/13639718/files/pretext_snap_out%20(Step%2042)_pretext_snapshotENA_OX359191_OX359191.1_chromosome_3.png
+        pretext_snapshotENA_OX359192_OX359192.1_chromosome_4:
+          path: https://zenodo.org/records/13639718/files/pretext_snap_out%20(Step%2042)_pretext_snapshotENA_OX359192_OX359192.1_chromosome_4.png
+        pretext_snapshotENA_OX359193_OX359193.1_chromosome_5:
+          path: https://zenodo.org/records/13639718/files/pretext_snap_out%20(Step%2042)_pretext_snapshotENA_OX359193_OX359193.1_chromosome_5.png
+        pretext_snapshotENA_OX359194_OX359194.1_chromosome_6:
+          path: https://zenodo.org/records/13639718/files/pretext_snap_out%20(Step%2042)_pretext_snapshotENA_OX359194_OX359194.1_chromosome_6.png
+        pretext_snapshotENA_OX359195_OX359195.1_chromosome_7:
+          path: https://zenodo.org/records/13639718/files/pretext_snap_out%20(Step%2042)_pretext_snapshotENA_OX359195_OX359195.1_chromosome_7.png
+        pretext_snapshotENA_OX359196_OX359196.1_chromosome_8:
+          path: https://zenodo.org/records/13639718/files/pretext_snap_out%20(Step%2042)_pretext_snapshotENA_OX359196_OX359196.1_chromosome_8.png
+        pretext_snapshotENA_OX359197_OX359197.1_chromosome_9:
+          path: https://zenodo.org/records/13639718/files/pretext_snap_out%20(Step%2042)_pretext_snapshotENA_OX359197_OX359197.1_chromosome_9.png
+        pretext_snapshotENA_OX359198_OX359198.1_chromosome_10:
+          path: https://zenodo.org/records/13639718/files/pretext_snap_out%20(Step%2042)_pretext_snapshotENA_OX359198_OX359198.1_chromosome_10.png
+        pretext_snapshotENA_OX359199_OX359199.1_chromosome_11:
+          path: https://zenodo.org/records/13639718/files/pretext_snap_out%20(Step%2042)_pretext_snapshotENA_OX359199_OX359199.1_chromosome_11.png
+        pretext_snapshotENA_OX359200_OX359200.1_chromosome_12:
+          path: https://zenodo.org/records/13639718/files/pretext_snap_out%20(Step%2042)_pretext_snapshotENA_OX359200_OX359200.1_chromosome_12.png
+        pretext_snapshotENA_OX359201_OX359201.1_chromosome_13:
+          path: https://zenodo.org/records/13639718/files/pretext_snap_out%20(Step%2042)_pretext_snapshotENA_OX359201_OX359201.1_chromosome_13.png
+        pretext_snapshotENA_OX359202_OX359202.1_chromosome_14:
+          path: https://zenodo.org/records/13639718/files/pretext_snap_out%20(Step%2042)_pretext_snapshotENA_OX359202_OX359202.1_chromosome_14.png
+        pretext_snapshotFullMap:
+          path: https://zenodo.org/records/13639718/files/pretext_snap_out%20(Step%2042)_pretext_snapshotFullMap.png
+