Merge pull request #24 from metagenlab/summary

Add option to only download summary tables
metagenlab · Oct 23, 2024 · 97c66ef · 97c66ef
2 parents 7c6c236 + fefa389
commit 97c66ef
Show file tree

Hide file tree

Showing 4 changed files with 31 additions and 27 deletions.
diff --git a/assembly_finder/__main__.py b/assembly_finder/__main__.py
@@ -71,7 +71,11 @@ def common_options(func):
             help="Custom config file [default: (outputDir)/config.yaml]",
         ),
         click.option(
-            "--threads", help="Number of threads to use", default=1, show_default=True
+            "--threads",
+            "-t",
+            help="Number of threads to use",
+            default=1,
+            show_default=True,
         ),
         click.option(
             "--profile",
@@ -130,9 +134,10 @@ def common_options(func):
             "options": [
                 "--input",
                 "--output",
-                "--taxonkit",
                 "--threads",
+                "--taxonkit",
                 "--taxon",
+                "--summary",
                 "--rank",
                 "--nrank",
                 "--print-versions",
@@ -204,6 +209,13 @@ def common_options(func):
     type=str,
     default=None,
 )
+@click.option(
+    "--summary/--all",
+    type=bool,
+    help="Download only summary tables or all files",
+    default=False,
+    show_default=True,
+)
 @click.option("--api-key", type=str, help="NCBI api-key", default=None)
 @click.option(
     "--compressed",
@@ -216,7 +228,7 @@ def common_options(func):
     "--include",
     type=str,
     help="Comma seperated files to download : genome,rna,protein,cds,gff3,gtf,gbff,seq-report",
-    default="genome,seq-report",
+    default="genome",
     show_default=True,
 )
 @click.option(
@@ -228,7 +240,7 @@ def common_options(func):
 )
 @click.option(
     "--taxon/--accession",
-    help="Are queries taxa names or accession",
+    help="Type of queries",
     type=bool,
     default=True,
     show_default=True,

diff --git a/assembly_finder/workflow/Snakefile b/assembly_finder/workflow/Snakefile
@@ -46,12 +46,9 @@ API_KEY = config.args.api_key
 LIMIT = config.args.limit
 COMPRESSED = config.args.compressed
 SOURCE = config.args.source
+SUMMARY = config.args.summary
 INCLUDE = config.args.include
 INCLUDE_LIST = INCLUDE.split(",")
-if "genome" not in INCLUDE_LIST or "seq-report" not in INCLUDE_LIST:
-    INCLUDE_LIST = ["genome", "seq-report"] + INCLUDE_LIST
-    INCLUDE = ",".join(INCLUDE_LIST)
-
 TAXON = config.args.taxon
 REFERENCE = config.args.reference
 ASM_LVL = config.args.assembly_level
@@ -71,10 +68,15 @@ include: os.path.join("rules", "download.smk")
 
 targets = [
     os.path.join(dir.out.base, "assembly_summary.tsv"),
-    os.path.join(dir.out.base, "sequence_report.tsv"),
     os.path.join(dir.out.base, "taxonomy.tsv"),
     os.path.join(dir.out.base, "cleanup.flag"),
 ]
+if SUMMARY:
+    targets = [
+        os.path.join(dir.out.base, "taxonomy.tsv"),
+        os.path.join(dir.out.base, "assembly_summary.tsv"),
+        os.path.join(dir.out.base, "accessions.txt"),
+    ]
 
 if PRINT_VERSIONS:
 

diff --git a/assembly_finder/workflow/envs/datasets.yml b/assembly_finder/workflow/envs/datasets.yml
@@ -3,4 +3,4 @@ channels:
   - conda-forge
   - defaults
 dependencies:
-  - ncbi-datasets-cli =16.31.0
+  - ncbi-datasets-cli =16.32.0
diff --git a/assembly_finder/workflow/rules/download.smk b/assembly_finder/workflow/rules/download.smk
@@ -166,12 +166,18 @@ rule format_taxonkit_lineage:
         """
 
 
+if SUMMARY:
+    asm_table = os.path.join(dir.out.base, "assembly_summary.tsv")
+else:
+    asm_table = temp(os.path.join(dir.out.base, "assembly_summary.txt"))
+
+
 rule filter_genome_summaries:
     input:
         summary=os.path.join(dir.out.base, "genome_summaries.json"),
         lineage=os.path.join(dir.out.base, "lineage.tsv"),
     output:
-        gen=temp(os.path.join(dir.out.base, "assembly_summary.txt")),
+        gen=asm_table,
         tax=os.path.join(dir.out.base, "taxonomy.tsv"),
         acc=temp(os.path.join(dir.out.base, "accessions.txt")),
     params:
@@ -260,21 +266,6 @@ rule copy_files:
         """
 
 
-rule cat_sequence_reports:
-    input:
-        os.path.join(dir.out.download),
-    output:
-        os.path.join(dir.out.base, "sequence_report.tsv"),
-    params:
-        jsonl=os.path.join(dir.out.base, "download", "*", "sequence_report.jsonl"),
-    conda:
-        os.path.join(dir.env, "datasets.yml")
-    shell:
-        """
-        cat {params.jsonl} | dataformat tsv genome-seq > {output}
-        """
-
-
 rule add_genome_paths:
     input:
         dir=os.path.join(dir.out.download),
@@ -293,7 +284,6 @@ rule cleanup_files:
     input:
         os.path.join(dir.out.base, "archive"),
         os.path.join(dir.out.base, "assembly_summary.tsv"),
-        os.path.join(dir.out.base, "sequence_report.tsv"),
         os.path.join(dir.out.base, "taxonomy.tsv"),
     output:
         temp(os.path.join(dir.out.base, "cleanup.flag")),