init commit

Author: Pombert-JF

2025_E_intestinalis_isolates/ReadME

@@ -0,0 +1 @@
+Scripts used for E. intestinalis genome assemblies.

2025_E_intestinalis_isolates/assign_chromosome_number.py

@@ -0,0 +1,144 @@
+#!/usr/bin/env python3
+
+name = "assign_chromosome_number.py"
+version = "0.2.0"
+updated = "2025-08-12"
+
+from sys import argv
+from argparse import ArgumentParser
+from os import makedirs
+from os.path import isdir,basename
+from textwrap import wrap
+
+############################################################
+## Readme
+############################################################
+
+usage = f"""
+NAME        {name}
+VERSION     {version}
+UPDATED     {updated}
+SYNOPSIS    Utilizes chromosome map generated by orient_fastas_to_reference.py to homogenize naming between the reference
+            and the new assembly.
+
+USAGE       {name} \\
+              -m all.map \\
+              -f 50507.oriented.fasta \\
+              -o 50507
+
+OPTIONS
+-m (--map)      Chromosome map file
+-f (--fasta)    Assembly FASTA file
+-o (--outdir)   Output directory [Default = CHROMOSOME_ASSIGNMENT]
+"""
+
+if len(argv) < 2:
+    print(usage)
+    exit()
+
+############################################################
+## Command lines arguments
+############################################################
+
+GetOptions = ArgumentParser()
+
+GetOptions.add_argument("-m","--map",required=True)
+GetOptions.add_argument("-f","--fasta",required=True)
+GetOptions.add_argument("-o","--outdir",default="CHROMOSOME_ASSIGNMENT")
+
+args = GetOptions.parse_args()
+
+map_file = args.map
+fasta_file = args.fasta
+outdir = args.outdir
+
+if not isdir(outdir):
+    makedirs(outdir,mode=0o755)
+
+filename = basename(fasta_file).split(".")[0]
+
+############################################################
+## Read fasta file
+############################################################
+
+FASTA = open(fasta_file,'r')
+
+locus = ""
+contigs = {}
+
+for line in FASTA:
+
+    line = line.strip()
+
+    if line == "":
+        continue
+
+    ## Read fasta header
+    if line[0] == ">":
+
+        locus = line[1:]
+        contigs[locus] = ""
+        continue
+
+    contigs[locus] += line
+
+FASTA.close()
+
+############################################################
+## Read chromosome mapping file
+############################################################
+
+MAP = open(map_file,'r')
+
+mappings = {}
+mapped_to = ""
+
+for line in MAP:
+
+    line = line.strip()
+    
+    if line == "":
+        continue
+
+    if line[0:2] == ">>":
+    
+        mapped_to = line[2:].split("\t")[0]
+        mappings[mapped_to] = []
+        continue
+    
+    if line[0] == ">":
+
+        mapped,type = line[1:].split("\t")[0:2]
+
+        if type != "Primary":
+            continue
+
+        mappings[mapped_to].append(mapped)
+
+        continue
+
+MAP.close()
+
+ASSIGNED_FASTA = open(f"{outdir}/{filename}.assigned.fasta",'w')
+ASSIGNMENTS = open(f"{outdir}/{filename}.chromosome_assignments",'w')
+
+############################################################
+## Assign chromosome to arbitrary contigs
+############################################################
+
+## Iterate over chromsome:contig mappings
+for chromosome in sorted(mappings.keys()):
+
+    ## Iterate over all contigs that mapped to a chromosome
+    for index,contig in enumerate(mappings[chromosome]):
+
+        ASSIGNED_FASTA.write(f">{chromosome}s{index+1}\n")
+        
+        ## Wrap contig sequence at 60 character length
+        sequence = "\n".join(wrap(contigs[contig],60))
+
+        ASSIGNED_FASTA.write(f"{sequence}\n")
+        ASSIGNMENTS.write(f"{contig} => {chromosome}s{index+1}\n")
+
+ASSIGNED_FASTA.close()
+ASSIGNMENTS.close()