Merge branch 'develop' into feat-handle-failed-peak-calls

README.md

@@ -4,4 +4,4 @@
 
 Pipeline based on snakemake to process ChIP-seq, ATAC-seq, RNA-seq and short read WGS data for SNP calling.
 
-See the [SeqNado documentation](alsmith151.github.io/SeqNado/) for more information.
+See the SeqNado documentation https://alsmith151.github.io/SeqNado/ for more information. 

docs/faq.md

@@ -5,3 +5,17 @@
 ### Workflow defines configfile config_chip.yml but it is not present or accessible.
 
 This error occurs when the pipeline is run without a config file present in the working directory. Follow the [Pipeline Setup](pipeline.md#create-a-design-file) instructions to create a config file.
+
+
+## Singularity configuration
+
+### Workflow Error
+
+Failed to pull singularity image from library://asmith151/seqnado/seqnado_pipeline:latest:  
+FATAL: Unable to get library client configuration:  
+remote has no library client (see https://apptainer.org/docs/user/latest/endpoint.html#no-default-remote)
+
+Fix:
+
+apptainer remote add --no-login SylabsCloud cloud.sylabs.io  
+apptainer remote use SylabsCloud  

docs/pipeline.md

@@ -10,6 +10,11 @@ The following command will generate the working directory and configuration file
 
 ```bash
 seqnado-config chip
+
+# options 
+-r, --rerun # Re-run the config
+-g, --genome [dm6|hg19|hg38|hg38_dm6|hg38_mm39|hg38_spikein|mm10|mm39|other] # Genome to use if genome preset is configured
+
 ```
 
 You should get somthing like this:

seqnado/cli.py

@@ -9,6 +9,7 @@
 
 @click.command(context_settings=dict(ignore_unknown_options=True))
 @click.argument("method", type=click.Choice(["atac", "chip", "rna", "snp"]))
+@click.option("-r", "--rerun", is_flag=True, help="Re-run the config")
 @click.option(
     "-g",
     "--genome",
@@ -28,13 +29,13 @@
         ]
     ),
 )
-def cli_config(method, help=False, genome="other"):
+def cli_config(method, help=False, genome="other", rerun=False):
     """
     Runs the config for the data processing pipeline.
     """
     import seqnado.config as config
 
-    config.create_config(method, genome)
+    config.create_config(method, genome, rerun)
 
 
 @click.command()

seqnado/config.py

@@ -178,7 +178,7 @@ def setup_configuration(assay, genome, template_data):
     colormap: RdYlBu_r
 """
 
-def create_config(assay, genome):
+def create_config(assay, genome, rerun):
     env = Environment(loader=FileSystemLoader(template_dir), auto_reload=False)
 
     template = env.get_template("config.yaml.jinja")        
@@ -189,15 +189,20 @@ def create_config(assay, genome):
 
     # Setup configuration
     setup_configuration(assay, genome, template_data)
-
-    # Create directory and render template
-    dir_name = f"{template_data['project_date']}_{template_data['assay']}_{template_data['project_name']}"
-    os.makedirs(dir_name, exist_ok=True)
-    fastq_dir = os.path.join(dir_name, "fastq")
-    os.makedirs(fastq_dir, exist_ok=True)
 
-    with open(os.path.join(dir_name, f"config_{assay}.yml"), 'w') as file:
-        file.write(template.render(template_data))
+    # Create directory and render template
+    if rerun:
+        dir_name = os.getcwd()
+        with open(os.path.join(dir_name, f"config_{assay}.yml"), 'w') as file:
+            file.write(template.render(template_data))
+    else:
+        dir_name = f"{template_data['project_date']}_{template_data['assay']}_{template_data['project_name']}"
+        os.makedirs(dir_name, exist_ok=True)
+        fastq_dir = os.path.join(dir_name, "fastq")
+        os.makedirs(fastq_dir, exist_ok=True)
+
+        with open(os.path.join(dir_name, f"config_{assay}.yml"), 'w') as file:
+            file.write(template.render(template_data))
 
     # add deseq2 qmd file if rna
     if assay == "rna":

seqnado/utils.py

@@ -624,6 +624,7 @@ def to_dataframe(self, simplify: bool = True):
 
     @classmethod
     def from_dataframe(cls, df: pd.DataFrame, simplified: bool = True, **kwargs):
+
         experiments = {}
         for experiment_name, row in df.iterrows():
             if simplified: