give up on snakemake lint for now

ktmeaton · Sep 23, 2020 · 3745cc8 · 3745cc8
1 parent d3a7bcf
commit 3745cc8
Show file tree

Hide file tree

Showing 6 changed files with 25 additions and 75 deletions.
diff --git a/.github/workflows/lint.yaml b/.github/workflows/lint.yaml
@@ -104,16 +104,10 @@ jobs:
           python-version: '3.7'
       - name: install linters
         run: pip install black flake8 flake8-bugbear
-      # Lint snakemake main
-      - name: lint snakefile
-        run: |
-          black $(find . -name "Snakefile")
-          flake8 $(find . -name "Snakefile")
-      # Lint snakemake modules
-      - name: lint snakefile submodules
-        run: |
-          black $(find . -name "*.smk")
-          flake8 $(find . -name "*.smk")
+      # Lint snakemake files
+      #- name: lint snakefile
+      #  run: |
+      #    snakemake --lint
       - name: lint other python
         run: |
           black $(find . -name "*.py")

diff --git a/workflow/Snakefile b/workflow/Snakefile
@@ -14,6 +14,9 @@ import os # Path manipulation
 
 from snakemake.remote.FTP import RemoteProvider as FTPRemoteProvider
 FTP = FTPRemoteProvider()
+# Enforce minimum version
+from snakemake.utils import min_version
+min_version("5.25.0")
 
 # -----------------------------------------------------------------------------#
 #                                 Setup                                        #
@@ -25,23 +28,22 @@ scripts_dir = os.path.join(project_dir, "workflow", "scripts")
 envs_dir = os.path.join(project_dir, "workflow", "envs")
 logs_dir = os.path.join(project_dir, "workflow", "logs")
 report_dir = os.path.join(project_dir, "workflow", "report")
+rules_dir = os.path.join(project_dir, "workflow", "rules")
 
 
 # Include the config file
 configfile: os.path.join(project_dir, "config", "snakemake.yaml")
 
-db_path = os.path.join(results_dir, "sqlite_db", config["sqlite_db"])
-
 # Sub snakefiles
-include: "rules/sqlite_import.smk"
-include: "rules/download.smk"
-include: "rules/alignment.smk"
-include: "rules/phylogeny.smk"
-include: "rules/functions.smk"
-include: "rules/targets.smk"
+include: rules_dir + "/sqlite_import.smk"
+include: rules_dir + "/download.smk"
+include: rules_dir + "/alignment.smk"
+include: rules_dir + "/phylogeny.smk"
+include: rules_dir + "/functions.smk"
+include: rules_dir + "/targets.smk"
 
 # Report file
-report: "report/workflow.rst"
+report: report_dir + "/workflow.rst"
 
 # -----------------------------------------------------------------------------#
 #                                Main Target                                   #
@@ -52,20 +54,7 @@ rule all:
     The default pipeline target.
     """
     input:
-        #---Database Import---#
-        #results_dir + "/sqlite_import/download_reference.txt",
-        #results_dir + "/sqlite_import/download_assembly.txt",
-        #results_dir + "/sqlite_import/eager_sra.tsv",
-        #---Data Download---#
-        #download_fna_output,
-        #download_ref_output,
-        #download_sra_output,
-        #---Alignment---#
-        eager_sra_output2,
-        #snippy_pairwise_fna_output,
-        #results_dir + "/snippy_multi/snippy-core.txt"
-        # IQTREE
-        iqtree_output
+        results_dir + "/iqtree/iqtree.core-filter" + str(config['snippy_missing_data']) + ".treefile"
 
 # -----------------------------------------------------------------------------#
 #                             Help and Usage                                   #
@@ -80,7 +69,6 @@ rule help:
       print("-" * 80)
       print("rule: ", rule.name )
       print(rule.docstring )
-      # Rule Inputs
       if rule._input:
           print("\tinput:")
           for in_file in rule.input:
@@ -105,4 +93,3 @@ rule help:
           print("\t\tconda: ", rule.conda_env)
       if rule._log:
           print("\t\tlog: ", rule._log)
-      #print(rule.conda_env)
diff --git a/workflow/rules/download.smk b/workflow/rules/download.smk
@@ -9,9 +9,9 @@ rule download_fna:
   """
     message: "Downloading and decompressing fasta file {wildcards.sample}."
     input:
-        results_dir + "/sqlite_import/{download_dir}.txt"
+        '{{results_dir}}/sqlite_import/{download_dir}.txt'
     output:
-        results_dir + "/{download_dir}/{sample}.fna"
+        '{{results_dir}}/{download_dir}/{sample}.fna'
     run:
         for file in input:
             with open(file) as temp_file:

diff --git a/workflow/rules/functions.smk b/workflow/rules/functions.smk
@@ -89,34 +89,3 @@ def parse_eager_tsv(eager_tsv, column):
     '''Extract a column from the eager TSV file, excluding the header.'''
     with open(eager_tsv) as temp_file:
         return [line.strip().split("\t")[column] for line in temp_file][1:]
-
-
-# Custom targets for aggregation rules
-
-# Data Download
-download_sra_output = expand(results_dir + "/download_sra/{biosample}/{sra_acc}_1.fastq.gz",
-                            zip,
-                            biosample=identify_sra_sample()["biosample"],
-                            sra_acc=identify_sra_sample()["sra_acc"])
-
-download_fna_output = expand(results_dir +"/download_assembly/{sample}.fna",
-                                sample=identify_assembly_sample(),
-                                )
-download_ref_output = expand(results_dir +"/download_reference/{sample}.fna",
-                                sample=identify_reference_sample(),
-                                )
-# Alignment
-eager_sra_output1 = expand(results_dir + "/eager_sra/final_bams/{biosample}.bam",
-                            biosample=identify_sra_sample()["biosample"])
-
-eager_sra_output2 = expand(results_dir + "/eager_sra/damageprofiler/{sra_acc}_rmdup_{biosample}/DamagePlot.pdf",
-                            zip,
-                            sra_acc=identify_sra_sample()["sra_acc"],
-                            biosample=identify_sra_sample()["biosample"])
-
-snippy_pairwise_fna_output = expand(results_dir + "/snippy_pairwise/{sample}/{sample}_snippy.aligned.fa",
-                                    sample=identify_assembly_sample())
-
-# Phylogeny
-
-iqtree_output = expand(results_dir + "/iqtree/iqtree.core-filter{missing_data}.treefile", missing_data = config["snippy_missing_data"])
diff --git a/workflow/rules/sqlite_import.smk b/workflow/rules/sqlite_import.smk
@@ -12,7 +12,7 @@ rule sqlite_import_reference:
     params:
         sql_command = config["sqlite_select_command_ref"],
     input:
-        db = results_dir + "/sqlite_db/" + config["sqlite_db"]
+        db = results_dir + "/sqlite_db/{config[sqlite_db]}"
     output:
         ref_txt = results_dir + "/sqlite_import/download_reference.txt"
     run:
@@ -25,10 +25,10 @@ rule sqlite_import_assembly:
     Import Assembly genome url from database.
     """
     input:
-        db = results_dir + "/sqlite_db/" + config["sqlite_db"]
+        db = results_dir + "/sqlite_db/{config[sqlite_db]}"
     output:
         asm_txt = results_dir + "/sqlite_import/download_assembly.txt",
-        asm_snippy_dir = results_dir + "/snippy_multi/snippy_pairwise_assembly.txt"
+        asm_snippy_dir = results_dir + "/snippy_multi/snippy_pairwise_assembly.txt",
     run:
         # Write the assembly FTP url
         with open(output.asm_txt, "w") as temp_file:
@@ -49,9 +49,9 @@ rule sqlite_import_sra:
         organism = config["organism"],
         max_sra = config["max_datasets_sra"]
     input:
-        db = results_dir + "/sqlite_db/" + config["sqlite_db"]
+        db = results_dir + "/sqlite_db/{config[sqlite_db]}",
     output:
-        eager_tsv = results_dir + "/sqlite_import/eager_sra.tsv",
+        eager_tsv = results_dir + "/sqlite_import/eager_sra.tsv".format(results_dir=results_dir),
     shell:
         "{scripts_dir}/sqlite_EAGER_tsv.py \
             --database {input.db} \

diff --git a/workflow/rules/targets.smk b/workflow/rules/targets.smk
@@ -24,12 +24,12 @@ rule test_download_sra:
 
 rule test_download_fna:
     input:
-        expand(results_dir +"/download_assembly/{sample}.fna",
+        expand(results_dir + "/download_assembly/{sample}.fna",
         sample=identify_assembly_sample(),
         )
 rule test_download_ref:
     input:
-        expand(results_dir +"/download_reference/{sample}.fna",
+        expand(results_dir + "/download_reference/{sample}.fna",
         sample=identify_reference_sample(),
         )
 # Alignment