fix: Handle missing bam columns in units.tsv

.test/config/units.tsv

@@ -1,4 +1,4 @@
-sample	unit	fragment_len_mean	fragment_len_sd	fq1	fq2	bam_single	bam_paired
+sample	unit	fragment_len_mean	fragment_len_sd	fq1	fq2
 A	1			ngs-test-data/reads/a.chr21.1.fq	ngs-test-data/reads/a.chr21.2.fq
 B	1			ngs-test-data/reads/b.chr21.1.fq	ngs-test-data/reads/b.chr21.2.fq
 B	2	300	14	ngs-test-data/reads/b.chr21.1.fq	

workflow/rules/bam.smk

@@ -4,6 +4,7 @@ rule bam_paired_to_fastq:
             query="sample == '{sample}' & unit == '{unit}'",
             within=units,
             cols="bam_paired",
+            default=None,
         ),
     output:
         "results/fastq/{sample}-{unit}.1.fq.gz",
@@ -23,6 +24,7 @@ rule bam_single_to_fastq:
             query="sample == '{sample}' & unit == '{unit}'",
             within=units,
             cols="bam_single",
+            default=None,
         ),
     output:
         "results/fastq/{sample}-{unit}.fq.gz",

workflow/rules/common.smk

@@ -88,16 +88,23 @@ def get_model(wildcards):
 
 def is_single_end(sample, unit):
     """Determine whether unit is single-end."""
-    bam_paired_not_present = pd.isnull(units.loc[(sample, unit), "bam_paired"])
+    if "bam_paired" in units.columns:
+        bam_paired_not_present = pd.isnull(units.loc[(sample, unit), "bam_paired"])
+    else:
+        bam_paired_not_present = True
     fq2_not_present = pd.isnull(units.loc[(sample, unit), "fq2"])
     return fq2_not_present and bam_paired_not_present
 
 
 def get_fastqs(wildcards):
     """Get raw FASTQ files from unit sheet."""
-    if not pd.isnull(units.loc[(wildcards.sample, wildcards.unit), "bam_single"]):
+    if "bam_single" in units.columns and not pd.isnull(
+        units.loc[(wildcards.sample, wildcards.unit), "bam_single"]
+    ):
         return f"results/fastq/{wildcards.sample}-{wildcards.unit}.fq.gz"
-    elif not pd.isnull(units.loc[(wildcards.sample, wildcards.unit), "bam_paired"]):
+    elif "bam_paired" in units.columns and not pd.isnull(
+        units.loc[(wildcards.sample, wildcards.unit), "bam_paired"]
+    ):
         fqfrombam1 = f"results/fastq/{wildcards.sample}-{wildcards.unit}.1.fq.gz"
         fqfrombam2 = f"results/fastq/{wildcards.sample}-{wildcards.unit}.2.fq.gz"
         return [fqfrombam1, fqfrombam2]