levseq 1.3.2__tar.gz → 1.3.3__tar.gz

{levseq-1.3.2/levseq.egg-info → levseq-1.3.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: levseq
-Version: 1.3.2
+Version: 1.3.3
 Home-page: https://github.com/fhalab/levseq/
 Author: Yueming Long, Ariane Mora, Francesca-Zhoufan Li, Emre Gursoy
 Author-email: ylong@caltech.edu
@@ -87,6 +87,10 @@ conda create --name levseq python=3.12 -y
 conda activate levseq
 ```
 
+```
+pip install levseq
+```
+
 #### Dependencies 
 
 1. Samtools: https://www.htslib.org/download/ 

{levseq-1.3.2 → levseq-1.3.3}/README.md

@@ -40,6 +40,10 @@ conda create --name levseq python=3.12 -y
 conda activate levseq
 ```
 
+```
+pip install levseq
+```
+
 #### Dependencies 
 
 1. Samtools: https://www.htslib.org/download/ 
@@ -138,4 +142,4 @@ If you have found LevSeq useful, please cite our [paper](https://pubs.acs.org/do
 
 #### Contact
 
-Leave a feature request in the issues or reach us via [email](mailto:levseqdb@gmail.com). 
+Leave a feature request in the issues or reach us via [email](mailto:levseqdb@gmail.com). 

{levseq-1.3.2 → levseq-1.3.3}/levseq/__init__.py

@@ -18,7 +18,7 @@
 __title__ = 'levseq'
 __description__ = 'LevSeq nanopore sequencing'
 __url__ = 'https://github.com/fhalab/levseq/'
-__version__ = '1.3.2'
+__version__ = '1.3.3'
 __author__ = 'Yueming Long, Ariane Mora, Francesca-Zhoufan Li, Emre Gursoy'
 __author_email__ = 'ylong@caltech.edu'
 __license__ = 'GPL3'
@@ -31,4 +31,4 @@ from levseq.cmd import *
 from levseq.utils import *
 from levseq.simulation import *
 from levseq.user import *
-
+from levseq.filter_orientation import *

levseq-1.3.3/levseq/filter_orientation.py

@@ -0,0 +1,115 @@
+from Bio import SeqIO
+from Bio.Seq import Seq
+import os
+from pathlib import Path
+import logging
+from Bio.Align import PairwiseAligner
+import shutil
+from concurrent.futures import ThreadPoolExecutor, as_completed
+from tqdm import tqdm
+
+def calculate_alignment_score(seq1, seq2):
+    """Calculate alignment score between two sequences using PairwiseAligner."""
+    aligner = PairwiseAligner()
+    aligner.mode = 'global'
+    alignment = aligner.align(seq1, seq2)[0]
+    return alignment.score / max(len(seq1), len(seq2))
+
+def filter_single_file(args):
+    """
+    Filter a single fastq file. Used for parallel processing.
+    
+    Args:
+        args: tuple containing (input_file, parent_seq, parent_rev_comp)
+    Returns:
+        tuple: (file_path, total_reads, kept_reads, filtered_records)
+    """
+    input_file, parent_seq, parent_rev_comp = args
+    kept_reads = []
+    total_reads = 0
+    kept_count = 0
+    
+    is_forward = "forward" in str(input_file).lower()
+    
+    for record in SeqIO.parse(input_file, "fastq"):
+        total_reads += 1
+        seq = str(record.seq)
+        
+        forward_score = calculate_alignment_score(seq, str(parent_seq))
+        reverse_score = calculate_alignment_score(seq, str(parent_rev_comp))
+        
+        # If it's in forward file (plate barcode was rev comp)
+        # Then read should align to reverse complement parent sequence
+        if is_forward and reverse_score > forward_score:
+            kept_reads.append(record)
+            kept_count += 1
+        # If it's in reverse file (plate barcode was forward)
+        # Then read was already reverse complemented by demultiplexer
+        # So it should align to forward parent sequence
+        elif not is_forward and forward_score > reverse_score:
+            kept_reads.append(record)
+            kept_count += 1
+            
+    return str(input_file), total_reads, kept_count, kept_reads
+
+def filter_demultiplexed_folder(experiment_folder, parent_sequence, num_threads=8):
+    """
+    Filter demultiplexed files using multiple threads.
+    
+    Args:
+        experiment_folder (str): Path to experiment folder containing RBC/FBC structure
+        parent_sequence (str): Parent sequence for alignment checking
+        num_threads (int): Number of threads to use
+    """
+    exp_path = Path(experiment_folder)
+    filtered_counts = {}
+    
+    # Prepare parent sequences once
+    parent_seq = Seq(parent_sequence)
+    parent_rev_comp = parent_seq.reverse_complement()
+    
+    # Collect all fastq files
+    fastq_files = []
+    for rbc_dir in exp_path.glob("RB*"):
+        if not rbc_dir.is_dir():
+            continue
+        for fbc_dir in rbc_dir.glob("NB*"):
+            if not fbc_dir.is_dir():
+                continue
+            fastq_files.extend(list(fbc_dir.glob("*.fastq")))
+    
+    if not fastq_files:
+        logging.warning(f"No fastq files found in {experiment_folder}")
+        return filtered_counts
+    
+    # Prepare arguments for parallel processing
+    file_args = [(f, parent_seq, parent_rev_comp) for f in fastq_files]
+    
+    # Process files in parallel with progress bar
+    with ThreadPoolExecutor(max_workers=num_threads) as executor:
+        futures = [executor.submit(filter_single_file, args) for args in file_args]
+        
+        with tqdm(total=len(fastq_files), desc="Filtering files") as pbar:
+            for future in as_completed(futures):
+                try:
+                    file_path, total, kept, filtered_records = future.result()
+                    
+                    # Write filtered reads
+                    temp_file = Path(file_path).parent / f"temp_{Path(file_path).name}"
+                    SeqIO.write(filtered_records, temp_file, "fastq")
+                    shutil.move(str(temp_file), file_path)
+                    
+                    filtered_counts[file_path] = {
+                        'total': total,
+                        'kept': kept,
+                        'filtered': total - kept
+                    }
+                    
+                    logging.info(f"Processed {file_path}: {kept}/{total} reads kept")
+                    pbar.update(1)
+                    
+                except Exception as e:
+                    logging.error(f"Error processing file {file_path}: {str(e)}")
+                    pbar.update(1)
+    
+    return filtered_counts

{levseq-1.3.2 → levseq-1.3.3}/levseq/run_levseq.py

@@ -17,7 +17,7 @@
 
 # Import MinION objects
 from levseq import *
-
+from levseq.filter_orientation import filter_demultiplexed_folder
 # Import external packages
 import logging
 from pathlib import Path
@@ -472,8 +472,23 @@ def process_ref_csv(cl_args, tqdm_fn=tqdm.tqdm):
             file_to_fastq = cat_fastq_files(cl_args.get("path"), output_dir)
             try:
                 demux_fastq(output_dir, name_folder, barcode_path)
+
+                # Add filtering step here with multithreading
+                filtered_counts = filter_demultiplexed_folder(
+                        name_folder, 
+                        refseq,
+                        num_threads=10
+                )
+                logging.info(f"Orientation filtering completed for {name}")
+                total_reads = sum(counts['total'] for counts in filtered_counts.values())
+                kept_reads = sum(counts['kept'] for counts in filtered_counts.values())
+                logging.info(f"Total filtering results: {kept_reads}/{total_reads} reads kept ({kept_reads/total_reads*100:.2f}%)")
+                for file, counts in filtered_counts.items():
+                    logging.info(f"{file}: {counts['kept']}/{counts['total']} reads kept")
+
+
             except Exception as e:
-                logging.error("An error occurred during demultiplexing for sample {}. Skipping this sample.".format(name), exc_info=True)
+                logging.error("An error occurred during demultiplexing/filtering for sample {}. Skipping this sample.".format(name), exc_info=True)
                 continue
         
         if not cl_args["skip_variantcalling"]:

{levseq-1.3.2 → levseq-1.3.3/levseq.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: levseq
-Version: 1.3.2
+Version: 1.3.3
 Home-page: https://github.com/fhalab/levseq/
 Author: Yueming Long, Ariane Mora, Francesca-Zhoufan Li, Emre Gursoy
 Author-email: ylong@caltech.edu
@@ -87,6 +87,10 @@ conda create --name levseq python=3.12 -y
 conda activate levseq
 ```
 
+```
+pip install levseq
+```
+
 #### Dependencies 
 
 1. Samtools: https://www.htslib.org/download/ 

{levseq-1.3.2 → levseq-1.3.3}/levseq.egg-info/SOURCES.txt

@@ -7,6 +7,7 @@ levseq/__init__.py
 levseq/basecaller.py
 levseq/cmd.py
 levseq/coordinates.py
+levseq/filter_orientation.py
 levseq/globals.py
 levseq/interface.py
 levseq/parser.py