updated some paths

metagenlab · Aug 2, 2024 · 1e7f6be · 1e7f6be
1 parent 9e1031e
commit 1e7f6be
Show file tree

Hide file tree

Showing 3 changed files with 56 additions and 53 deletions.
diff --git a/zamp/rules/In_silico/amplicons_reference.rules b/zamp/rules/In_silico/amplicons_reference.rules
@@ -20,15 +20,14 @@ rule Import_ReferenceSequences:
 
 
 def get_DADA2_samples_path(sample):
-    RUN = all_samples.at[sample, config["run_column"]]
-    sample_layout = layout[sample]
+    run = SAMPLES.at[sample, "run"]
     path = (
         "DADA2/2_denoised/"
-        + RUN
+        + run
         + "/"
         + sample
         + "_"
-        + sample_layout
+        + PAIRING[sample]
         + "_infer_seq_tab.rds"
     )
     return path
@@ -37,7 +36,7 @@ def get_DADA2_samples_path(sample):
 ### Take the squences after denoising
 rule export_DADA2_QuerySequences:
     conda:
-        "../../envs/DADA2_in_R.yml"
+        os.path.join(dir.envs, "DADA2_in_R.yml")
     container:
         singularity_envs["dada2"]
     input:
@@ -49,26 +48,26 @@ rule export_DADA2_QuerySequences:
         count_table="QualityControl/DADA2/{sample}/count_table.tsv",
         length_histo="QualityControl/DADA2/{sample}/merged_reads_length.png",
     params:
-        merged_min_length=config["merged_min_length"],
-        merged_max_length=config["merged_max_length"],
+        merged_min_length=MINLEN,
+        merged_max_length=MAXLEN,
     log:
-        logging_folder + "QualityControl/DADA2/{sample}/dna-sequences.log",
+        dir.logs + "/" + "QualityControl/DADA2/{sample}/dna-sequences.log",
     script:
         "scripts/extract_DADA2_sequences.R"
 
 
 ### Count the number of occurences of the representative sequences in the samples. I takes the sequences before clustering, i.e. their "raw sequence"
 rule vsearch_count_occurences_for_QC:
     conda:
-        "../../envs/amplicons_r_utils.yml"
+        os.path.join(dir.envs, "amplicons_r_utils.yml")
     container:
         singularity_envs["r_utils"]
     input:
         uc="vsearch/1c_derep/{sample}_derep.uc",
     output:
         count_table="QualityControl/vsearch/{sample}/count_table.tsv",
     log:
-        logging_folder + "QualityControl/vsearch/{sample}/count_table.log",
+        dir.logs + "/" + "QualityControl/vsearch/{sample}/count_table.log",
     script:
         "scripts/extract_vsearch_counts.R"
 
@@ -201,14 +200,14 @@ rule Export_quality_Control_raw:
          """
 
 
-def get_RUN(sample):
-    RUN = all_samples.at[sample, config["run_column"]]
-    return RUN
+def get_run(sample):
+    run = SAMPLES.at[sample, "run"]
+    return run
 
 
 rule mismatch_table_per_sample:
     conda:
-        "../../envs/amplicons_r_utils.yml"
+        os.path.join(dir.envs, "amplicons_r_utils.yml")
     container:
         singularity_envs["r_utils"]
     input:
@@ -218,18 +217,18 @@ rule mismatch_table_per_sample:
         merged_mismatch_table_path="QualityControl/{denoiser}/export_{sample}/with_counts.tsv",
         missmatch_plot_path="QualityControl/{denoiser}/export_{sample}/with_counts_plot.png",
     params:
-        RUN=lambda wildcards: get_RUN(wildcards.sample),
+        run=lambda wildcards: get_run(wildcards.sample),
     log:
-        logging_folder + "QualityControl/{denoiser}/export_{sample}/with_counts.log",
+        dir.logs + "/" + "QualityControl/{denoiser}/export_{sample}/with_counts.log",
     threads: 1
     script:
         "scripts/abundance_to_mismatches.R"
 
 
-def select_samples(RUN):
-    selected_samples = all_samples.index.values[
-        (all_samples[config["select_column"]] == config["select_value"])
-        & (all_samples[config["run_column"]] == RUN)
+def select_samples(run):
+    selected_samples = SAMPLES.index.values[
+        (SAMPLES[config["select_column"]] == config["select_value"])
+        & (SAMPLES["run"] == run)
     ]
     selected_paths = expand(
         "QualityControl/{{denoiser}}/export_{sample}/with_counts.tsv",
@@ -241,36 +240,36 @@ def select_samples(RUN):
 
 rule Compare_mismatch_per_run:
     conda:
-        "../../envs/amplicons_r_utils.yml"
+        os.path.join(dir.envs, "amplicons_r_utils.yml")
     container:
         singularity_envs["r_utils"]
     input:
-        mismatch_tables_path=lambda wildcards: select_samples(wildcards.RUN),
+        mismatch_tables_path=lambda wildcards: select_samples(wildcards.run),
     output:
-        missmatch_plot="QualityControl/{denoiser}/{RUN}_compare_quality.png",
-        merged_mismatch_table="QualityControl/{denoiser}/{RUN}_compare_quality_table.tsv",
+        missmatch_plot="QualityControl/{denoiser}/{run}_compare_quality.png",
+        merged_mismatch_table="QualityControl/{denoiser}/{run}_compare_quality_table.tsv",
     log:
-        logging_folder + "QualityControl/{denoiser}/{RUN}_compare_quality_table.log",
+        dir.logs + "/" + "QualityControl/{denoiser}/{run}_compare_quality_table.log",
     threads: 1
     script:
         "scripts/compare_mismatches.R"
 
 
 rule Compare_mismatch_all:
     conda:
-        "../../envs/amplicons_r_utils.yml"
+        os.path.join(dir.envs, "amplicons_r_utils.yml")
     container:
         singularity_envs["r_utils"]
     input:
         mismatch_tables_path=expand(
-            "QualityControl/{{denoiser}}/{RUN}_compare_quality_table.tsv",
-            RUN=set(all_samples[config["run_column"]]),
+            "QualityControl/{{denoiser}}/{run}_compare_quality_table.tsv",
+            run=set(SAMPLES["run"]),
         ),
     output:
         missmatch_plot="QualityControl/{denoiser}/compare_quality.pdf",
         merged_mismatch_table="QualityControl/{denoiser}/compare_quality_table.tsv",
     log:
-        logging_folder + "QualityControl/{denoiser}/compare_quality.log",
+        dir.logs + "/" + "QualityControl/{denoiser}/compare_quality.log",
     threads: 1
     script:
         "scripts/compare_all_mismatches.R"
diff --git a/zamp/rules/In_silico/insilico_validation.rules b/zamp/rules/In_silico/insilico_validation.rules
@@ -15,8 +15,8 @@ rule print_primers_to_files:
     output:
         "InSilico/PCR/Primers.fasta",
     params:
-        config["forward_primer"],
-        config["reverse_primer"],
+        FW_PRIMER,
+        RV_PRIMER,
     shell:
         """
         printf \
@@ -34,12 +34,13 @@ rule Extract_amplicon:
         "InSilico/PCR/{sample}/Primers.fasta.pair.{sample}.fna.amplicons.fasta",
         temp("InSilico/PCR/{sample}/Primers.fasta.pair.{sample}.fna.blastout"),
     params:
-        min_length=config["merged_min_length"],
-        max_length=config["merged_max_length"],
+        min_length=MINLEN,
+        max_length=MAXLEN,
         mismatch=config["mismatch"],
         threeprime=config["threeprime"],
     log:
-        logging_folder
+        dir.logs
+        + "/"
         + "InSilico/PCR/{sample}/Primers.fasta.pair.{sample}.fna.amplicons.log",
     threads: 1
     shell:
@@ -67,15 +68,16 @@ rule Extract_amplicon:
 ## Some sequences are extracted as reverse-complemented. Two be sure to have them in the right direction, we add reverse complemented version to each fasta. Then, the next step with cutadapt w
 rule reverse_complement:
     conda:
-        "../../envs/amplicons_r_utils.yml"
+        os.path.join(dir.envs, "amplicons_r_utils.yml")
     container:
         singularity_envs["r_utils"]
     input:
         simple_fasta="InSilico/PCR/{sample}/Primers.fasta.pair.{sample}.fna.amplicons.fasta",
     output:
         fasta_with_rev="InSilico/PCR/{sample}/Primers.fasta.pair.{sample}.fna.amplicons_complemented.fasta",
     log:
-        logging_folder
+        dir.logs
+        + "/"
         + "InSilico/PCR/{sample}/Primers.fasta.pair.{sample}.fna.amplicons_complemented.txt",
     threads: 1
     script:
@@ -84,21 +86,21 @@ rule reverse_complement:
 
 rule cutadapt_trim_in_silico:
     conda:
-        "../../envs/cutadapt.yml"
+        os.path.join(dir.envs, "cutadapt.yml")
     container:
         singularity_envs["cutadapt"]
     input:
         R1_raw_reads="InSilico/PCR/{sample}/Primers.fasta.pair.{sample}.fna.amplicons_complemented.fasta",
     output:
         R1_trimmed_reads=temp("InSilico/1a_trimmed_primers/{sample}_trimmed.fasta"),
     log:
-        logging_folder + "InSilico/1a_trimmed_primers/{sample}_trimmed.txt",
+        dir.logs + "/" + "InSilico/1a_trimmed_primers/{sample}_trimmed.txt",
     params:
-        forward_primer=config["forward_primer"],
-        reverse_primer=config["reverse_primer"],
+        forward_primer=FW_PRIMER,
+        reverse_primer=RV_PRIMER,
         excepted_errors=config["excepted_errors"],
-        min_length=config["merged_min_length"],
-        max_length=config["merged_max_length"],
+        min_length=MINLEN,
+        max_length=MAXLEN,
         coverage=config["amplicon_min_coverage"],
     threads: 1
     script:
@@ -133,15 +135,15 @@ rule Insilico_merge_all_in_one_fasta:
 ### Again, dereplicate all identical sequences after merging.
 rule InSilico_derepicate_all:
     conda:
-        "../../envs/vsearch.yml"
+        os.path.join(dir.envs, "vsearch.yml")
     container:
         singularity_envs["vsearch"]
     input:
         "InSilico/1c_derep/merged_all.fasta",
     output:
         "InSilico/2_denoised/dna-sequences.fasta",
     log:
-        logging_folder + "InSilico/1c_all_merged_sequences/dereplicate_all.txt",
+        dir.logs + "/" + "InSilico/1c_all_merged_sequences/dereplicate_all.txt",
     shell:
         """
         vsearch --derep_fulllength {input} \
@@ -157,7 +159,7 @@ rule InSilico_derepicate_all:
 
 rule InSilico_count_occurences:
     conda:
-        "../../envs/vsearch.yml"
+        os.path.join(dir.envs, "vsearch.yml")
     container:
         singularity_envs["vsearch"]
     input:
@@ -166,7 +168,7 @@ rule InSilico_count_occurences:
     output:
         "InSilico/2_denoised/countSeqs/{sample}_count_table.tsv",
     log:
-        logging_folder + "InSilico/2_denoised/countSeqs/{sample}_count_table.tsv",
+        dir.logs + "/" + "InSilico/2_denoised/countSeqs/{sample}_count_table.tsv",
     shell:
         """       
         if [ -s "{input[samples]}" ]
@@ -199,23 +201,23 @@ def list_samples_counts(wildcards):
 ### Format count table from InSilico
 rule create_InSilico_count_table:
     conda:
-        "../../envs/amplicons_r_utils.yml"
+        os.path.join(dir.envs, "amplicons_r_utils.yml")
     container:
         singularity_envs["r_utils"]
     input:
         count_table_samples=list_samples_counts,
     output:
         count_table="InSilico/2_denoised/count_table.tsv",
     log:
-        logging_folder + "InSilico/2_denoised/count_table.tsv",
+        dir.logs + "/" + "InSilico/2_denoised/count_table.tsv",
     script:
         "scripts/create_count_table_from_insilico.R"
 
 
 ### Create a table to compare tax assignment
 rule In_silico_tax_compare:
     conda:
-        "../../envs/amplicons_r_utils.yml"
+        os.path.join(dir.envs, "amplicons_r_utils.yml")
     container:
         singularity_envs["r_utils"]
     input:
@@ -226,9 +228,10 @@ rule In_silico_tax_compare:
         output_table="InSilico/3_classified/{classifier}_{tax_DB}/InSilico_compare_tax.tsv",
         output_table_long="InSilico/3_classified/{classifier}_{tax_DB}/InSilico_compare_tax_long.tsv",
     params:
-        viz_replace_empty_tax=config["viz_replace_empty_tax"],
+        viz_replace_empty_tax=REPL_EMPTY,
     log:
-        logging_folder
+        dir.logs
+        + "/"
         + "InSilico/3_classified/{classifier}_{tax_DB}/InSilico_compare_tax.log",
     script:
         "scripts/In_silico_tax_comparison.R"
diff --git a/zamp/rules/PICRUSt2/picrust.rules b/zamp/rules/PICRUSt2/picrust.rules
@@ -3,7 +3,7 @@
 
 rule picrust2_custom_tree:
     conda:
-        "../../envs/picrust2.yml"
+        os.path.join(dir.envs, "picrust2.yml")
     container:
         singularity_envs["picrust2"]
     input:
@@ -14,7 +14,8 @@ rule picrust2_custom_tree:
             "{denoiser}/6_picrust2/{classifier}_{tax_DB}/{filtering_or_not}/{raref_or_not}/picrust/"
         ),
     log:
-        logging_folder
+        dir.logs
+        + "/"
         + "{denoiser}/5_visualization/{classifier}_{tax_DB}/{filtering_or_not}/{raref_or_not}/picrust/picrust.txt",
     threads: 4
     shell: