Genome info can be loaded from separate .yaml.

CLIP/iCLIP.snakefile

@@ -25,6 +25,7 @@ import os
 OPJ = os.path.join
 from glob import glob
 from subprocess import CalledProcessError
+from yaml import safe_load as yload
 
 from collections import defaultdict
 from itertools import product
@@ -53,7 +54,16 @@ from smwrappers import wrappers_dir
 shell.prefix(SHELL_FUNCTIONS)
 
 aligner = config["aligner"]
-genome_dict = config["genome_dict"]
+########################
+# Genome configuration #
+########################
+# config["genome_dict"] can be either the path to a genome configuration file
+# or a dict
+if isinstance(config["genome_dict"], str):
+    with open(config["genome_dict"]) as fh:
+        genome_dict = yload(fh)
+else:
+    genome_dict = config["genome_dict"]
 genome = genome_dict["name"]
 chrom_sizes = get_chrom_sizes(genome_dict["size"])
 chrom_sizes.update(valmap(int, genome_dict.get("extra_chromosomes", {})))

Degradome-seq/Degradome-seq.snakefile

@@ -26,6 +26,7 @@ import os
 OPJ = os.path.join
 from glob import glob
 from pickle import load
+from yaml import safe_load as yload
 import numpy as np
 import pandas as pd
 
@@ -87,7 +88,13 @@ alignment_settings = {
 ########################
 # Genome configuration #
 ########################
-genome_dict = config["genome_dict"]
+# config["genome_dict"] can be either the path to a genome configuration file
+# or a dict
+if isinstance(config["genome_dict"], str):
+    with open(config["genome_dict"]) as fh:
+        genome_dict = yload(fh)
+else:
+    genome_dict = config["genome_dict"]
 genome = genome_dict["name"]
 chrom_sizes = get_chrom_sizes(genome_dict["size"])
 chrom_sizes.update(valmap(int, genome_dict.get("extra_chromosomes", {})))

PRO-seq/PRO-seq.snakefile

@@ -32,6 +32,7 @@ import os
 OPJ = os.path.join
 from glob import glob
 from pickle import load
+from yaml import safe_load as yload
 from fileinput import input as finput
 
 import warnings
@@ -193,8 +194,16 @@ aligner = config["aligner"]
 ########################
 # Genome configuration #
 ########################
-genome_dict = config.get("genome_dict", None)
-if genome_dict is not None:
+# config["genome_dict"] can be either the path to a genome configuration file
+# or a dict
+if isinstance(config["genome_dict"], str):
+    with open(config["genome_dict"]) as fh:
+        genome_dict = yload(fh)
+else:
+    genome_dict = config["genome_dict"]
+# genome_dict = config.get("genome_dict", None)
+# if genome_dict is not None:
+if True:
     genome = genome_dict["name"]
     chrom_sizes = get_chrom_sizes(genome_dict["size"])
     chrom_sizes.update(valmap(int, genome_dict.get("extra_chromosomes", {})))

RNA_Seq_Cecere/RNA-seq.snakefile

@@ -49,6 +49,7 @@ import os
 OPJ = os.path.join
 from glob import glob
 from pickle import load
+from yaml import safe_load as yload
 from collections import defaultdict
 from itertools import combinations
 from functools import partial
@@ -253,7 +254,13 @@ aligner = config["aligner"]
 ########################
 # Genome configuration #
 ########################
-genome_dict = config["genome_dict"]
+# config["genome_dict"] can be either the path to a genome configuration file
+# or a dict
+if isinstance(config["genome_dict"], str):
+    with open(config["genome_dict"]) as fh:
+        genome_dict = yload(fh)
+else:
+    genome_dict = config["genome_dict"]
 genome = genome_dict["name"]
 chrom_sizes = get_chrom_sizes(genome_dict["size"])
 chrom_sizes.update(valmap(int, genome_dict.get("extra_chromosomes", {})))

Ribo-seq/Ribo-seq.snakefile

@@ -75,6 +75,7 @@ from glob import glob
 from gzip import open as gzopen
 from re import sub
 from pickle import load
+from yaml import safe_load as yload
 from fileinput import input as finput
 from shutil import copyfile
 from sys import stderr
@@ -317,7 +318,13 @@ aligner = config["aligner"]
 ########################
 # Genome configuration #
 ########################
-genome_dict = config["genome_dict"]
+# config["genome_dict"] can be either the path to a genome configuration file
+# or a dict
+if isinstance(config["genome_dict"], str):
+    with open(config["genome_dict"]) as fh:
+        genome_dict = yload(fh)
+else:
+    genome_dict = config["genome_dict"]
 genome = genome_dict["name"]
 genome_version = genome_dict.get("version", "WBcel235")
 chrom_sizes = get_chrom_sizes(genome_dict["size"])
@@ -1659,7 +1666,7 @@ bam2bigwig.sh: bedGraphToBigWig failed
                     (bedtools_v,) = re.match(r"bedtools\s+(.*)", getoutput("bedtools --version")).groups()
                     (bedops_v,) = re.match(r".*version:\s+(.*)\s+.*", getoutput("bedops --version | grep 'version'")).groups()
                     (bg2bw_v,) = re.match(r".*version:\s+([^)]+).*", getoutput("bedGraphToBigWig")).groups()
-                    methods.write(f"# {rule}\nThe resulting alignment was used to generate a bigwig file with a custom bash script using bedtools (version {bedtools_v}), bedops (version {bedops_v}) and bedGraphToBigWig (version {bg2bw_v})\n{norm_methods}.\n")
+                    methods.write(f"# {rule}\nThe resulting alignment was used to generate a bigwig file with a custom bash script using bedtools (version {bedtools_v}), bedops (version {bedops_v}) and bedGraphToBigWig (version {bg2bw_v}).\n{norm_methods}\n")
             except CalledProcessError as e:
                 if last_lines(log.err, 2) == no_reads:
                     warn(f"{output.bigwig_norm} will be empty.\n")

small_RNA-seq/small_RNA-seq.snakefile

@@ -104,6 +104,7 @@ OPJ = os.path.join
 from glob import glob
 from re import sub
 from pickle import load
+from yaml import safe_load as yload
 from fileinput import input as finput
 from sys import stderr
 from subprocess import Popen, PIPE, CalledProcessError
@@ -409,7 +410,13 @@ aligner = config["aligner"]
 ########################
 # Genome configuration #
 ########################
-genome_dict = config["genome_dict"]
+# config["genome_dict"] can be either the path to a genome configuration file
+# or a dict
+if isinstance(config["genome_dict"], str):
+    with open(config["genome_dict"]) as fh:
+        genome_dict = yload(fh)
+else:
+    genome_dict = config["genome_dict"]
 genome = genome_dict["name"]
 chrom_sizes = get_chrom_sizes(genome_dict["size"])
 chrom_sizes.update(valmap(int, genome_dict.get("extra_chromosomes", {})))