mgnify-pipelines-toolkit 0.2.0__py3-none-any.whl → 0.2.2__py3-none-any.whl

mgnify_pipelines_toolkit/analysis/amplicon/amplicon_utils.py

@@ -18,7 +18,7 @@ from collections import defaultdict, Counter
 import logging
 import gzip
 import os
-import subprocess
+import pyfastx
 
 from mgnify_pipelines_toolkit.constants.regex_ambiguous_bases import (
     _AMBIGUOUS_BASES_DICT,
@@ -29,7 +29,6 @@ logging.basicConfig(level=logging.DEBUG)
 
 
 def split_dir_into_sample_paths(dir):
-
     file_list = os.listdir(dir)
     file_list = [
         file
@@ -43,42 +42,33 @@ def split_dir_into_sample_paths(dir):
     return sample_list
 
 
-def get_read_count(read_path, type="fastq"):
-
-    cmd = []
-    stdout = ""
-
-    if type == "fastq":
-        cmd = ["zcat", read_path]
-        zcat_proc = subprocess.Popen(
-            cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE
-        )
-
-        cmd = ["wc", "-l"]
-        wc_proc = subprocess.Popen(
-            cmd, stdin=zcat_proc.stdout, stdout=subprocess.PIPE, stderr=subprocess.PIPE
-        )
-        stdout, stderr = wc_proc.communicate()
-
-    elif type == "fasta":
-        cmd = ["grep", "-c", "^>", read_path]
-        grep_proc = subprocess.Popen(
-            cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE
-        )
-        stdout, stderr = grep_proc.communicate()
-
-    read_count = stdout.strip() if stdout is not None else ""
-
-    if not read_count.isdigit():
-        logging.error(
-            f"Read count is not a digit, something is wrong. stdout: '{stdout}', stderr: '{stderr}'"
+def get_read_count(read_path: str, file_type: str = "fastq") -> int:
+    """
+    Get the read count of a FASTQ or FASTA file.
+
+    :param read_path: The path to the FASTQ or FASTA file.
+    :type read_path: str
+    :param fasta_type: The type of the file, either "fastq" or "fasta". Defaults to "fastq".
+    :type fasta_type: str
+    :return: The number of reads in the file.
+    :rtype: int
+    :raises ValueError: If the file type is not supported or the read count is not a positive integer.
+    """
+    read_count = 0
+
+    if file_type == "fasta":
+        fasta = pyfastx.Fasta(read_path, build_index=False)
+        read_count = sum(1 for _ in fasta)
+    elif file_type == "fastq":
+        fastq = pyfastx.Fastq(read_path, build_index=False)
+        read_count = sum(1 for _ in fastq)
+    else:
+        raise ValueError(
+            f"Invalid file_type {file_type}, it needs to be either 'fasta' or 'fastq'"
         )
-        exit(1)
 
-    read_count = int(read_count)
-
-    if type == "fastq":
-        read_count /= 4
+    if read_count <= 0:
+        raise ValueError(f"Read count is not a positive integer: {read_count}")
 
     return read_count
 
@@ -128,7 +118,10 @@ def build_cons_seq(
         counter += 1
 
         try:
-            max_prop = max_count / read_count
+            if max_line_count is None:
+                max_prop = max_count / read_count
+            else:
+                max_prop = max_count / max_line_count
 
             cons_bases = []
             curr_prop = 0.0

mgnify_pipelines_toolkit/analysis/amplicon/are_there_primers.py

@@ -27,7 +27,6 @@ from mgnify_pipelines_toolkit.analysis.amplicon.amplicon_utils import (
 
 
 def parse_args(argv=None):
-
     parser = argparse.ArgumentParser()
 
     parser.add_argument(
@@ -63,7 +62,9 @@ def are_there_primers_in_this_sample(path, rev=False):
         False if a primer was not identified
     """
 
-    read_count = get_read_count(path, "fastq")  # Get read count for fastq file
+    read_count = get_read_count(
+        path, file_type="fastq"
+    )  # Get read count for fastq file
     mcp_len = 100  # Script will look at first 100 base mcps (for rev=True, it will look at first 100 from 3' to 5')
 
     mcp_count_dict = fetch_mcp(
@@ -133,7 +134,6 @@ def save_out(results, sample_id, output):
 
 
 def main(argv=None):
-
     path, sample, output = parse_args(argv)
 
     fwd_primer_flag = are_there_primers_in_this_sample(

mgnify_pipelines_toolkit/analysis/amplicon/assess_mcp_proportions.py

@@ -87,7 +87,9 @@ def find_mcp_props_for_sample(path, rev=False):
             start + mcp_len - 1
         )  # compute the final index for the mcp (inclusive). Indices are of base 1 not 0.
 
-        read_count = get_read_count(path, type="fastq")  # get read count for fastq file
+        read_count = get_read_count(
+            path, file_type="fastq"
+        )  # get read count for fastq file
 
         max_line_count = None
         if read_count > MCP_MAX_LINE_COUNT:

mgnify_pipelines_toolkit/analysis/amplicon/standard_primer_matching.py

@@ -143,7 +143,7 @@ def get_primer_props(std_primer_dict_regex, input_path):
 
     threshold = 0.60  # Arbitrary threshold for collecting a matched primer
     read_count = get_read_count(
-        input_path, "fastq"
+        input_path, file_type="fastq"
     )  # Get read count of fastq file to calculate proportion with
     res_dict = defaultdict(defaultdict)
 

mgnify_pipelines_toolkit/analysis/assembly/add_rhea_chebi_annotation.py

@@ -62,45 +62,13 @@ def process_lines(lines, output_handler, rhea2reaction_dict, protein_hashes):
                 protein_rheas.add(rhea)
 
 
-def main(input: str, output: Path, proteins: Path, rhea2chebi: Path):
-    logging.info(
-        f"Step 1/3: Parse protein fasta and calculating SHA256 hash from {proteins.resolve()}"
-    )
-    protein_hashes = {}
-    with open(proteins, "r") as fasta_file:
-        for record in SeqIO.parse(fasta_file, "fasta"):
-            protein_hash = hashlib.sha256(str(record.seq).encode("utf-8")).hexdigest()
-            protein_hashes[record.id] = protein_hash
-
-    logging.info(f"Step 2/3: Load reactions from provided file {rhea2chebi.resolve()}")
-    df = pd.read_csv(rhea2chebi, delimiter="\t")
-    rhea2reaction_dict = dict(zip(df["ENTRY"], zip(df["EQUATION"], df["DEFINITION"])))
-
-    logging.info(
-        f"Step 3/3: Read DIAMOND results from {'STDIN' if input == '-' else Path(input).resolve()} and write output"
-    )
-    with open(output, "w") as output_handler:
-        if input == "-":
-            process_lines(sys.stdin, output_handler, rhea2reaction_dict, protein_hashes)
-        else:
-            with open(args.input, "r") as input_file:
-                process_lines(
-                    input_file, output_handler, rhea2reaction_dict, protein_hashes
-                )
-
-    logging.info("Processed successfully. Exiting.")
-
-
-if __name__ == "__main__":
+def main():
     parser = argparse.ArgumentParser(
-        """
-                                    Use diamond output file to create a table with Rhea and CHEBI
-                                    reaction annotation for every protein.
-                                    """
+        "Use diamond output file to create a table with Rhea and CHEBI reaction annotation for every protein."
     )
     parser.add_argument(
-        "-i",
-        "--input",
+        "-d",
+        "--diamond_hits",
         required=True,
         type=str,
         help="DIAMOND results file, use '-' for stdin",
@@ -121,10 +89,45 @@ if __name__ == "__main__":
     )
     parser.add_argument(
         "--rhea2chebi",
-        default=None,
+        required=True,
         type=Path,
         help="File that maps rhea_ids to CHEBI",
     )
 
     args = parser.parse_args()
-    main(args.input, args.output, args.proteins, args.rhea2chebi)
+
+    diamond_hits = args.diamond_hits
+    output = args.output
+    proteins = args.proteins
+    rhea2chebi = args.rhea2chebi
+
+    logging.info(
+        f"Step 1/3: Parse protein fasta and calculating SHA256 hash from {proteins.resolve()}"
+    )
+    protein_hashes = {}
+    with open(proteins, "r") as fasta_file:
+        for record in SeqIO.parse(fasta_file, "fasta"):
+            protein_hash = hashlib.sha256(str(record.seq).encode("utf-8")).hexdigest()
+            protein_hashes[record.id] = protein_hash
+
+    logging.info(f"Step 2/3: Load reactions from provided file {rhea2chebi.resolve()}")
+    df = pd.read_csv(rhea2chebi, delimiter="\t")
+    rhea2reaction_dict = dict(zip(df["ENTRY"], zip(df["EQUATION"], df["DEFINITION"])))
+
+    logging.info(
+        f"Step 3/3: Read DIAMOND results from {'STDIN' if diamond_hits == '-' else Path(diamond_hits).resolve()} and write output"
+    )
+    with open(output, "w") as output_handler:
+        if diamond_hits == "-":
+            process_lines(sys.stdin, output_handler, rhea2reaction_dict, protein_hashes)
+        else:
+            with open(diamond_hits, "r") as input_file:
+                process_lines(
+                    input_file, output_handler, rhea2reaction_dict, protein_hashes
+                )
+
+    logging.info("Processed successfully. Exiting.")
+
+
+if __name__ == "__main__":
+    main()