Merge pull request #9 from GenomiqueENS/gh-page

Gh page

bin/AsaruSim.py

@@ -0,0 +1,36 @@
+import argparse
+from badread_caller import badread_caller, setup_badread_command
+from template_maker import template_maker, setup_template_parameters
+from PCR_amplificator import PCR_amplificator, setup_PCR_parameters
+
+def setup_parent_parser():
+    parent_parser = argparse.ArgumentParser(add_help=False)
+    parent_parser.add_argument('--debug', action='store_true', help='Enable debug mode')
+    return parent_parser
+
+
+def main():
+    parent_parser = setup_parent_parser()
+    main_parser = argparse.ArgumentParser()
+
+    subparsers = main_parser.add_subparsers(title="command", dest="command", required=True)
+
+    subparsers.add_parser('call_badread', parents=[setup_badread_command(parent_parser)], 
+                                           add_help=False)
+    subparsers.add_parser('template_maker', parents=[setup_template_parameters(parent_parser)], 
+                                             add_help=False)
+    subparsers.add_parser('PCR', parents=[setup_PCR_parameters(parent_parser)], 
+                                             add_help=False)
+
+    args = main_parser.parse_args()
+
+    if args.command == 'call_badread':
+        badread_caller(args)
+    if args.command == 'template_maker':
+        template_maker(args)
+    if args.command == 'PCR':
+        PCR_amplificator(args)
+
+
+if __name__ == "__main__":
+    main()

bin/PCR.py → bin/PCR_amplificator.py

@@ -4,23 +4,33 @@
 import random
 import os, sys, math
 from toolkit import multiprocessing_submit
+from toolkit import read_template
 
 YELLOW = "\033[93m"
 GRAY = "\033[90m"
 RESET = "\033[0m"
 
 logging.basicConfig(level=logging.INFO, format=GRAY+ '%(message)s' +RESET)
-parser = argparse.ArgumentParser(description="Script for generating template sequences for scRNAseq simulation.")
-
-parser.add_argument('-f','--template', type=str, required=True, help="Path to the template FASTA file.")
-parser.add_argument('-o','--out', type=str, default="out.fa", help="Path to the output FASTA file.")
-parser.add_argument('-c','--cycles', type=int, default=5, help="number of cycles.")
-parser.add_argument('-d','--dup', type=float, default=0.7, help="duplication rate.")
-parser.add_argument('-e','--error', type=float, default=0.00003, help="error rate.")
-parser.add_argument('-t','--thread', type=int, default=4, help="number of threads to use.")
-parser.add_argument('-b','--batch_size', type=int, default=500, help="batch size.")
-parser.add_argument('-n','--totalNamber', type=int, default=None, help="total number of sequence to select from the finel pool.")
-parser.add_argument('-s','--seed', type=int, default=2024, help="seed value.")
+
+
+def setup_PCR_parameters(parent_parser):
+    description="Nanopore template maker."
+    if parent_parser:
+        parser = argparse.ArgumentParser(parents=[parent_parser], 
+                                        description=description)
+    else :
+        parser = argparse.ArgumentParser(description=description)
+
+    parser.add_argument('-f','--template', type=str, required=True, help="Path to the template FASTA file.")
+    parser.add_argument('-o','--out', type=str, default="out.fa", help="Path to the output FASTA file.")
+    parser.add_argument('-c','--cycles', type=int, default=5, help="number of cycles.")
+    parser.add_argument('-d','--dup', type=float, default=0.7, help="duplication rate.")
+    parser.add_argument('-e','--error', type=float, default=0.00003, help="error rate.")
+    parser.add_argument('-t','--thread', type=int, default=4, help="number of threads to use.")
+    parser.add_argument('-b','--batch_size', type=int, default=500, help="batch size.")
+    parser.add_argument('-n','--totalNamber', type=int, default=None, help="total number of sequence to select from the finel pool.")
+    parser.add_argument('-s','--seed', type=int, default=2024, help="seed value.")
+    return parser
 
 class Molecule ():
     def __init__(self, name, length, seq, root, inherited_mut):
@@ -113,39 +123,8 @@ def PCR(template, cycles, dup_rate, error_rate, totalNumber, outfile):
     sequencing(pool_list, outfile, totalNumber)
 
 
-def read_template(fasta, thread, batch_size):
-    """
-    Function to read and extract sequences from a FASTQ file. It supports both plain text and gzipped files.
-    Inputs:
-    fastq: String, path to the FASTQ file.
-    Returns: List of sequences encoded in ASCII.
-    """
-    if thread==1:
-        with open(fasta, 'rt') as f:
-            while True:
-                header = f.readline()
-                if not header: break
-                name = header[1:].strip()
-                seq = f.readline().strip()
-                yield name, seq
-    else:
-        batch = []
-        with open(fasta, 'r') as f:
-                while True:
-                    header = f.readline()
-                    if not header: break
-                    name = header[1:].strip()
-                    seq = f.readline().strip()
-                    batch.append([name, seq])
-                    if len(batch) == batch_size:
-                        yield batch
-                        batch = []
-                if len(batch) > 0:
-                    yield batch
-
-
-def main():
-    args = parser.parse_args()
+def PCR_amplificator(args):
+
     logging.info("_____________________________")
     logging.info("Template file name : %s" , args.template)
     logging.info("PCR cycles         : %s" , args.cycles)
@@ -206,4 +185,6 @@ def main():
     logging.info("DONE!_______________________________")
 
 if __name__ == "__main__":
-    main()  
+    args = setup_PCR_parameters(None).parse_args()
+    if args:
+        PCR_amplificator(args)

bin/QC.py

@@ -1,12 +1,11 @@
 import pandas as pd
 import argparse
 
-from libs import qc_generator
-from libs.figs import over_time_graph
-from libs.figs import ATGC_graph
-from libs.figs import GC_content_plot
-from libs.report import make_report
-from libs.reporte_maker import reporter
+from QC_tools import qc_generator
+from QC_tools.figs import over_time_graph
+from QC_tools.figs import ATGC_graph
+from QC_tools.figs import GC_content_plot
+from QC_tools.reporte_maker import reporter
 import plotly.graph_objects as go
 
 parser = argparse.ArgumentParser(description='Process some integers.')
@@ -65,8 +64,8 @@ def create_table(stats_data, table_width=500, table_height=400, margin=10):
     data=[go.Table(
         header=dict(
             values=['', '<b>Value</b>'],
-            fill_color='#EBEBEB',  # Couleur de fond de l'en-tête
-            font=dict(color='black', size=12)  # Couleur et taille du texte de l'en-tête
+            fill_color='#EBEBEB',
+            font=dict(color='black', size=12)
         ),
         cells=dict(
             values=[
@@ -78,8 +77,8 @@ def create_table(stats_data, table_width=500, table_height=400, margin=10):
                     int(int(stats_data['Simulated UMI counts']) / int(stats_data['Simulated Cell BC']))
                 ]
             ],
-            fill_color='#f4f4f4',  # Couleur de fond des cellules
-            font=dict(color='black', size=11)  # Couleur et taille du texte des cellules
+            fill_color='#f4f4f4',
+            font=dict(color='black', size=11)
         )
     )]
 
@@ -131,7 +130,6 @@ def main():
     pie_fig = pie_unknown(df_stats)
     stats_table = create_table(df_stats)
 
-    #make_report(Q_over_time, atgc, gc, args.project, args.positions)
     reporter(stats_table, 
              pie_fig, 
              Q_over_time, 

bin/libs/figs.py → bin/QC_tools/figs.py

@@ -52,7 +52,7 @@ def make_plots(df_stats, positions, q1, q_scores, q3):
                      percentage_T=df_stats["%T"],
                      result_directory='your/directory/path',
                      graph_name='Base % over sequence',
-                     yaxis_title='Q Score',
+                     yaxis_title='Base (%)',
                      log=False,
                      sigma=1,
                      yaxis_starts_zero=False,

bin/libs/qc_generator.py → bin/QC_tools/qc_generator.py

@@ -5,7 +5,7 @@
 from tqdm import tqdm
 from concurrent.futures import ProcessPoolExecutor, as_completed
 
-from fqread.fastq_reader import SequenceStats
+from QC_tools.fqread.fastq_reader import SequenceStats
 
 
 def process_fastq_file(filename, pos, reverse):
@@ -16,14 +16,14 @@ def process_fastq_file(filename, pos, reverse):
     with open_fn(filename[0], 'rb') as f:
         while sequence_count < 100000:
             header = f.readline()
-            if not header: break  # EOF
+            if not header: break
             if reverse:
                 seq = f.readline().strip()[::-1][:pos]
-                f.readline()  # Plus line
+                f.readline() 
                 quality = f.readline().strip()[::-1]
             else:
                 seq = f.readline().strip()[:pos]
-                f.readline()  # Plus line
+                f.readline()
                 quality = f.readline().strip()
 
             stats.add_sequence(seq, quality)

bin/libs/reporte_maker.py → bin/QC_tools/reporte_maker.py

@@ -4,7 +4,7 @@
 from dominate.tags import *
 from dominate.util import raw
 from datetime import date, datetime
-from libs.css_style import body_style, head_style, div_summary_style
+from QC_tools.css_style import body_style, head_style, div_summary_style
 
 import plotly.express as px
 df2 = px.data.iris()