MetaPont 0.0.1__tar.gz → 0.0.2__tar.gz

{metapont-0.0.1/src/MetaPont.egg-info → metapont-0.0.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: MetaPont
-Version: 0.0.1
+Version: 0.0.2
 Summary: MetaPont - A tool to bridge the gap between the output of metagenomic tools and the analysis of the data
 Home-page: https://github.com/TheHuwsLab/MetaPont
 Author: Nicholas Dimonaco
@@ -47,6 +47,23 @@ pip install MetaPont
 ## Usage
 
 ### Command-line Arguments
+```Extract-By-Function -h ``` 
+```bash
+usage: Extract-By-Function [-h] -d DIRECTORY -f FUNCTION_ID [-o OUTPUT] [-m MIN_PROPORTION]
+
+MetaPont v0.0.2: Extract-By-Function - Identify taxa contributing to a specific function.
+
+options:
+  -h, --help            show this help message and exit
+  -d DIRECTORY, --directory DIRECTORY
+                        Directory containing TSV files to analyse.
+  -f FUNCTION_ID, --function_id FUNCTION_ID
+                        Specific function ID to search for (e.g., 'GO:0002').
+  -o OUTPUT, --output OUTPUT
+                        Output file to save results (default: output_taxa_details.tsv).
+  -m MIN_PROPORTION, --min_proportion MIN_PROPORTION
+                        Minimum proportion threshold for taxa to be included in the output (default: 0.05).
+```
 
 The `Extract-By-Function` tool provides several command-line options:
 
@@ -79,11 +96,13 @@ Example output:
 
 ```
 Function ID: GO:0002
-Sample	Taxa	Proportion
-sample1.tsv	Escherichia	0.542857
-sample1.tsv	Salmonella	0.457143
-sample2.tsv	Bacillus	0.650000
-sample2.tsv	Clostridium	0.350000
+Sample	Taxa	Reads Assigned (Function)	Proportion (Function)	Proportion (Total Reads)
+PN0536_0003_S83_Final_Contig.tsv	Gordonibacter	60788	0.075	0.002
+PN0536_0003_S83_Final_Contig.tsv	Streptomyces	115671	0.142	0.004
+PN0536_0003_S83_Final_Contig.tsv	unknown	80890	0.099	0.003
+PN0536_0003_S83_Final_Contig.tsv	Clostridium	51018	0.063	0.002
+PN0536_0003_S83_Final_Contig.tsv	Lactobacillus	149909	0.184	0.005
+PN0536_0003_S83_Final_Contig.tsv	Limosilactobacillus	79694	0.098	0.003
 ```
 
 ---

{metapont-0.0.1 → metapont-0.0.2}/README.md

@@ -32,6 +32,23 @@ pip install MetaPont
 ## Usage
 
 ### Command-line Arguments
+```Extract-By-Function -h ``` 
+```bash
+usage: Extract-By-Function [-h] -d DIRECTORY -f FUNCTION_ID [-o OUTPUT] [-m MIN_PROPORTION]
+
+MetaPont v0.0.2: Extract-By-Function - Identify taxa contributing to a specific function.
+
+options:
+  -h, --help            show this help message and exit
+  -d DIRECTORY, --directory DIRECTORY
+                        Directory containing TSV files to analyse.
+  -f FUNCTION_ID, --function_id FUNCTION_ID
+                        Specific function ID to search for (e.g., 'GO:0002').
+  -o OUTPUT, --output OUTPUT
+                        Output file to save results (default: output_taxa_details.tsv).
+  -m MIN_PROPORTION, --min_proportion MIN_PROPORTION
+                        Minimum proportion threshold for taxa to be included in the output (default: 0.05).
+```
 
 The `Extract-By-Function` tool provides several command-line options:
 
@@ -64,11 +81,13 @@ Example output:
 
 ```
 Function ID: GO:0002
-Sample	Taxa	Proportion
-sample1.tsv	Escherichia	0.542857
-sample1.tsv	Salmonella	0.457143
-sample2.tsv	Bacillus	0.650000
-sample2.tsv	Clostridium	0.350000
+Sample	Taxa	Reads Assigned (Function)	Proportion (Function)	Proportion (Total Reads)
+PN0536_0003_S83_Final_Contig.tsv	Gordonibacter	60788	0.075	0.002
+PN0536_0003_S83_Final_Contig.tsv	Streptomyces	115671	0.142	0.004
+PN0536_0003_S83_Final_Contig.tsv	unknown	80890	0.099	0.003
+PN0536_0003_S83_Final_Contig.tsv	Clostridium	51018	0.063	0.002
+PN0536_0003_S83_Final_Contig.tsv	Lactobacillus	149909	0.184	0.005
+PN0536_0003_S83_Final_Contig.tsv	Limosilactobacillus	79694	0.098	0.003
 ```
 
 ---

{metapont-0.0.1 → metapont-0.0.2}/setup.cfg

@@ -1,6 +1,6 @@
 [metadata]
 name = MetaPont
-version = v0.0.1
+version = v0.0.2
 author = Nicholas Dimonaco
 author_email = nicholas@dimonaco.co.uk
 description = MetaPont - A tool to bridge the gap between the output of metagenomic tools and the analysis of the data

metapont-0.0.2/src/MetaPont/Extract_By_Function.py

@@ -0,0 +1,108 @@
+import argparse
+import os
+import csv
+import sys
+from collections import defaultdict
+
+try:
+    from .constants import *
+except (ModuleNotFoundError, ImportError, NameError, TypeError) as error:
+    from constants import *
+
+# Needed to account for the large CSV/TSV files we are working with
+csv.field_size_limit(sys.maxsize)
+
+
+def process_tsv(file_path, function_id):
+    """
+    Processes a TSV file to calculate:
+    1. Total reads for each taxon (within the function).
+    2. Total reads for the specified function.
+    3. Total reads across all contigs in the file.
+    """
+    taxa_reads_function = defaultdict(int)  # Reads for each taxon within the function
+    total_reads_function = 0  # Total reads for the specified function
+    total_reads_all = 0  # Total reads across all contigs
+
+    with open(file_path, "r") as tsv_file:
+        reader = csv.reader(tsv_file, delimiter="\t")
+        next(reader)  # Skip the first row (sample name)
+        headers = next(reader)  # Read headers from the second row
+
+        # Locate the necessary columns
+        taxa_idx = headers.index("Lineage")
+        reads_idx = headers.index("Mapped_Reads")
+
+        # Process each row
+        for idx, row in enumerate(reader):
+            if len(row) < len(headers):
+                continue  # Skip malformed rows
+
+            lineage = row[taxa_idx]
+            reads = int(row[reads_idx])  # Get the number of reads for this row
+            total_reads_all += reads  # Increment total reads for all contigs
+
+            # Check if this row matches the specified function ID
+            for cell in row[6:]:
+                if cell and any(function_id in part for part in cell.replace(',', '|').split('|')):
+                    if "g__" in lineage:
+                        genus = lineage.split("g__")[1].split("|")[0]
+                        taxa_reads_function[genus] += reads
+                        total_reads_function += reads
+                    break  # Stop checking further functional columns for this row
+
+    return taxa_reads_function, total_reads_function, total_reads_all
+
+
+def main():
+    parser = argparse.ArgumentParser(description='MetaPont ' + MetaPont_Version + ': Extract-By-Function - Identify taxa contributing to a specific function.')
+    parser.add_argument(
+        "-d", "--directory", required=True,
+        help="Directory containing TSV files to analyse."
+    )
+    parser.add_argument(
+        "-f", "--function_id", required=True,
+        help="Specific function ID to search for (e.g., 'GO:0002')."
+    )
+    parser.add_argument(
+        "-o", "--output", default="output_taxa_details.tsv",
+        help="Output file to save results (default: output_taxa_details.tsv)."
+    )
+    parser.add_argument(
+        "-m", "--min_proportion", type=float, default=0.05,
+        help="Minimum proportion threshold for taxa to be included in the output (default: 0.05)."
+    )
+
+    options = parser.parse_args()
+    print("Running MetaPont: Extract-By-Function " + MetaPont_Version)
+
+    input_path = os.path.abspath(options.directory)
+    output_path = os.path.abspath(options.output)
+
+    all_results = {}
+
+    # Process each TSV file in the directory
+    for file_name in os.listdir(input_path):
+        if file_name.endswith("_Final_Contig.tsv"):
+            file_path = os.path.join(options.directory, file_name)
+            print(f"Processing file: {file_name}")
+            taxa_reads_function, total_reads_function, total_reads_all = process_tsv(file_path, options.function_id)
+            all_results[file_name] = (taxa_reads_function, total_reads_function, total_reads_all)
+
+    # Write results to output
+    with open(output_path, "w") as out:
+        out.write("Function ID: " + options.function_id + "\n")
+        out.write("Sample\tTaxa\tReads Assigned (Function)\tProportion (Function)\tProportion (Total Reads)\n")
+        for sample, (taxa_reads_function, total_reads_function, total_reads_all) in all_results.items():
+            for taxa, reads_function in taxa_reads_function.items():
+                proportion_function = reads_function / total_reads_function if total_reads_function > 0 else 0
+                proportion_total = reads_function / total_reads_all if total_reads_all > 0 else 0
+
+                if proportion_function >= options.min_proportion:  # Apply minimum proportion filter
+                    out.write(f"{sample}\t{taxa}\t{reads_function}\t{proportion_function:.3f}\t{proportion_total:.3f}\n")
+
+    print(f"Results saved to {options.output}")
+
+
+if __name__ == "__main__":
+    main()

metapont-0.0.2/src/MetaPont/constants.py

@@ -0,0 +1,2 @@
+MetaPont_Version = 'v0.0.2'
+

{metapont-0.0.1 → metapont-0.0.2/src/MetaPont.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: MetaPont
-Version: 0.0.1
+Version: 0.0.2
 Summary: MetaPont - A tool to bridge the gap between the output of metagenomic tools and the analysis of the data
 Home-page: https://github.com/TheHuwsLab/MetaPont
 Author: Nicholas Dimonaco
@@ -47,6 +47,23 @@ pip install MetaPont
 ## Usage
 
 ### Command-line Arguments
+```Extract-By-Function -h ``` 
+```bash
+usage: Extract-By-Function [-h] -d DIRECTORY -f FUNCTION_ID [-o OUTPUT] [-m MIN_PROPORTION]
+
+MetaPont v0.0.2: Extract-By-Function - Identify taxa contributing to a specific function.
+
+options:
+  -h, --help            show this help message and exit
+  -d DIRECTORY, --directory DIRECTORY
+                        Directory containing TSV files to analyse.
+  -f FUNCTION_ID, --function_id FUNCTION_ID
+                        Specific function ID to search for (e.g., 'GO:0002').
+  -o OUTPUT, --output OUTPUT
+                        Output file to save results (default: output_taxa_details.tsv).
+  -m MIN_PROPORTION, --min_proportion MIN_PROPORTION
+                        Minimum proportion threshold for taxa to be included in the output (default: 0.05).
+```
 
 The `Extract-By-Function` tool provides several command-line options:
 
@@ -79,11 +96,13 @@ Example output:
 
 ```
 Function ID: GO:0002
-Sample	Taxa	Proportion
-sample1.tsv	Escherichia	0.542857
-sample1.tsv	Salmonella	0.457143
-sample2.tsv	Bacillus	0.650000
-sample2.tsv	Clostridium	0.350000
+Sample	Taxa	Reads Assigned (Function)	Proportion (Function)	Proportion (Total Reads)
+PN0536_0003_S83_Final_Contig.tsv	Gordonibacter	60788	0.075	0.002
+PN0536_0003_S83_Final_Contig.tsv	Streptomyces	115671	0.142	0.004
+PN0536_0003_S83_Final_Contig.tsv	unknown	80890	0.099	0.003
+PN0536_0003_S83_Final_Contig.tsv	Clostridium	51018	0.063	0.002
+PN0536_0003_S83_Final_Contig.tsv	Lactobacillus	149909	0.184	0.005
+PN0536_0003_S83_Final_Contig.tsv	Limosilactobacillus	79694	0.098	0.003
 ```
 
 ---

{metapont-0.0.1 → metapont-0.0.2}/src/MetaPont.egg-info/SOURCES.txt

@@ -2,7 +2,7 @@ LICENSE
 README.md
 pyproject.toml
 setup.cfg
-src/MetaPont/Extraction_By_Function.py
+src/MetaPont/Extract_By_Function.py
 src/MetaPont/Function_By_Taxa.py
 src/MetaPont/__init__.py
 src/MetaPont/constants.py

metapont-0.0.1/src/MetaPont/Extraction_By_Function.py

@@ -1,95 +0,0 @@
-import argparse
-import os
-import csv
-import sys
-from collections import Counter
-
-from HuwsLab.MetaPont.src.MetaPont.constants import MetaPont_Version
-
-# Needed to account for the large CSV/TSV files we are working with
-csv.field_size_limit(sys.maxsize)
-
-
-def process_tsv(file_path, function_id):
-    """
-    Processes a TSV file to calculate taxa counts and total matches for a given function ID.
-    """
-    taxa_counts = Counter()
-    total_matches = 0
-
-    with open(file_path, "r") as tsv_file:
-        reader = csv.reader(tsv_file, delimiter="\t")
-        next(reader)  # Skip the first row (sample name)
-        headers = next(reader)  # Read headers from the second row
-
-        # Locate the Lineage column
-        taxa_idx = headers.index("Lineage")
-
-        # Process each row to find matches
-        for idx, row in enumerate(reader):
-            if len(row) < len(headers):
-                continue  # Skip malformed rows
-
-            lineage = row[taxa_idx]
-
-            # Search functional columns starting from column 6
-            for cell in row[6:]:
-                if cell and any(function_id in part for part in cell.replace(',', '|').split('|')):
-                    # Extract genus from the Lineage field
-                    if "g__" in lineage:
-                        genus = lineage.split("g__")[1].split("|")[0]
-                        taxa_counts[genus] += 1
-                        total_matches += 1
-                    break  # Stop checking further functional columns for this row
-
-    return taxa_counts, total_matches
-
-
-def main():
-
-    parser = argparse.ArgumentParser(description='MetaPont ' + MetaPont_Version + ': Extract-By-Function - Identify taxa contributing to a specific function.')
-    parser.add_argument(
-        "-d", "--directory", required=True,
-        help="Directory containing TSV files to analyse."
-    )
-    parser.add_argument(
-        "-f", "--function_id", required=True,
-        help="Specific function ID to search for (e.g., 'GO:0002')."
-    )
-    parser.add_argument(
-        "-o", "--output", default="output_taxa_proportions.tsv",
-        help="Output file to save results (default: output_taxa_proportions.tsv)."
-    )
-    parser.add_argument(
-        "-m", "--min_proportion", type=float, default=0.05,
-        help="Minimum proportion threshold for taxa to be included in the output (default: 0.05)."
-    )
-
-    options = parser.parse_args()
-    print("Running MetaPont: Extract-By-Function " + MetaPont_Version)
-
-    all_results = {}
-
-    # Process each TSV file in the directory
-    for file_name in os.listdir(options.directory):
-        if file_name.endswith("_Final_Contig.tsv"):
-            file_path = os.path.join(options.directory, file_name)
-            print(f"Processing file: {file_name}")
-            taxa_counts, total_matches = process_tsv(file_path, options.function_id)
-            all_results[file_name] = (taxa_counts, total_matches)
-
-    # Write results to output
-    with open(options.output, "w") as out:
-        out.write("Function ID: " + options.function_id + "\n")
-        out.write("Sample\tTaxa\tProportion\n")
-        for sample, (taxa_counts, total_matches) in all_results.items():
-            for taxa, count in taxa_counts.items():
-                proportion = count / total_matches if total_matches > 0 else 0
-                if proportion >= options.min_proportion:  # Apply minimum proportion filter
-                    out.write(f"{sample}\t{taxa}\t{proportion:.6f}\n")
-
-    print(f"Results saved to {options.output}")
-
-
-if __name__ == "__main__":
-    main()

metapont-0.0.1/src/MetaPont/constants.py

@@ -1,2 +0,0 @@
-MetaPont_Version = 'v0.0.1'
-