Update RNA workflow and experiment configuration

seqnado/workflow/snakefile_rna

@@ -1,9 +1,16 @@
 import os
+import sys
 import shutil
+from datetime import datetime
 import glob
+from snakemake.utils import min_version
+from seqnado.utils import Design
 import seqnado.utils as utils
 import pandas as pd
 
+####################
+# Hardcoded config #
+####################
 ASSAY = "RNA"
 
 
@@ -13,31 +20,29 @@ configfile: "config_rna.yml"
 container: "library://asmith151/seqnado/seqnado_pipeline:latest"
 
 
+####################
+# Experiment config #
+####################
+
+# Load config
 utils.format_config_dict(config)
 
-# Get experiment design
+# Generate design
 if os.path.exists(config["design"]):
-    # Expect columns - sample fq1 fq2
-    FASTQ_SAMPLES = utils.GenericFastqSamples(
-        pd.read_csv(config["design"], sep="[\s+,\t]", engine="python")
-    )
-    assert FASTQ_SAMPLES.design.shape[0] > 0, "No samples found in design file"
-    for col in ["sample", "fq1", "fq2"]:
-        assert (
-            col in FASTQ_SAMPLES.design.columns
-        ), f"Design file must contain columns sample, fq1, fq2. Columns found: {FASTQ_SAMPLES.design.columns}"
+    df = pd.read_csv(config["design"], sep="[\s+,\t]", engine="python")
+    DESIGN = Design.from_dataframe(df)
 else:
-    # Use pattern matching to get samples
-    fq_files = list(utils.get_fastq_files("."))
-    if fq_files:
-        FASTQ_SAMPLES = utils.GenericFastqSamples.from_files(fq_files)
-    else:
-        raise ValueError("No FASTQ files found in the working directory")
+    DESIGN = Design.from_directory(".")
+
+# Attempt to symlink the fastq files
+assert (
+    len(DESIGN.fastq_paths) > 0
+), "No fastq files found in the working directory or no design file provided."
+utils.symlink_fastq_files(DESIGN, output_dir="seqnado_output/fastqs")
 
 
-DESIGN = FASTQ_SAMPLES.design
-SAMPLE_NAMES = FASTQ_SAMPLES.sample_names_all
-RUN_DESEQ2 = DESIGN.columns.str.contains("deseq2").any()
+SAMPLE_NAMES = DESIGN.sample_names
+RUN_DESEQ2 = DESIGN.to_dataframe().columns.str.contains("deseq2").any()
 
 
 include: "rules/qc.smk"