PyamilySeq 0.0.1__py3-none-any.whl → 0.2.0__py3-none-any.whl

PyamilySeq/combine_FASTA_with_genome_IDs.py

@@ -0,0 +1,49 @@
+
+import argparse
+import gzip
+import glob
+
+def combine_files(files, split, glob_location, combined_out):
+    count = 0
+
+    for file in glob.glob(glob_location + '/' + files):
+        count += 1
+        try:
+            with gzip.open(file, 'rb') as genome:
+
+                for line in genome:
+                    if line.startswith(b'#'):
+                        continue
+                    elif line.startswith(b'>'):
+                        genome_name = bytes(file.split(split)[0].split('/')[-1], 'utf-8')
+                        line = line.split(b' ')[0]
+                        line = line.replace(b'>', b'>' + genome_name + b'|')
+                        combined_out.write(line.decode('utf-8')+'\n')
+                    else:
+                        combined_out.write(line.decode('utf-8'))
+        except gzip.BadGzipFile:
+            with open(file, 'r') as genome:
+
+                for line in genome:
+                    if line.startswith('#'):
+                        continue
+                    elif line.startswith('>'):
+                        genome_name = file.split(split)[0].split('/')[-1]
+                        line = line.replace('>', '>' + genome_name + '|')
+                        combined_out.write(line)
+                    else:
+                        combined_out.write(line)
+
+def main():
+    parser = argparse.ArgumentParser(description="Combine gzipped fasta files.")
+    parser.add_argument("files", help="File pattern to match within the specified directory.")
+    parser.add_argument("split", help="String used to split the file path and extract the genome name.")
+    parser.add_argument("glob_location", help="Directory location where the files are located.")
+    parser.add_argument("combined_out", help="Output file where the combined data will be written.")
+    args = parser.parse_args()
+
+    with open(args.combined_out, 'w') as combined_out:
+        combine_files(args.files, args.split, args.glob_location, combined_out)
+
+if __name__ == "__main__":
+    main()

{PyamilySeq-0.0.1.dist-info → PyamilySeq-0.2.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: PyamilySeq
-Version: 0.0.1
+Version: 0.2.0
 Summary: PyamilySeq - A a tool to look for sequence-based gene families identified by clustering methods such as CD-HIT, DIAMOND, BLAST or MMseqs2.
 Home-page: https://github.com/NickJD/PyamilySeq
 Author: Nicholas Dimonaco
@@ -12,7 +12,6 @@ Classifier: Operating System :: OS Independent
 Requires-Python: >=3.6
 Description-Content-Type: text/markdown
 License-File: LICENSE
-Requires-Dist: numpy
 
 # PyamilySeq
 PyamilySeq (Family Seek) is a Python tool for clustering gene sequences into families based on sequence similarity identified by tools such as CD-HIT, DIAMOND or MMseqs2.
@@ -32,7 +31,37 @@ PyamilySeq requires Python 3.6 or higher. Install dependencies using pip:
 pip install PyamilySeq
 ```
 
-## Usage
+## Usage - Menu
+```
+PyamilySeq_Species.py -h
+usage: PyamilySeq_Species.py [-h] -c CLUSTERS -f {CD-HIT,CSV,TSV} [-w WRITE_FAMILIES] [-fasta FASTA] [-rc RECLUSTERED] [-st SEQUENCE_TAG]
+                             [-groups CORE_GROUPS] [-gpa GENE_PRESENCE_ABSENCE_OUT] [-verbose {True,False}] [-v]
+
+PyamilySeq v0.2.0: PyamilySeq Run Parameters.
+
+Required Arguments:
+  -c CLUSTERS           Clustering output file from CD-HIT, TSV or CSV Edge List
+  -f {CD-HIT,CSV,TSV}   Which format to use (CD-HIT or Comma/Tab Separated Edge-List (such as MMseqs2 tsv output))
+
+Output Parameters:
+  -w WRITE_FAMILIES     Default - No output: Output sequences of identified families (provide levels at which to output "-w 99 95" - Must provide
+                        FASTA file with -fasta
+  -fasta FASTA          FASTA file to use in conjunction with "-w"
+
+Optional Arguments:
+  -rc RECLUSTERED       Clustering output file from secondary round of clustering
+  -st SEQUENCE_TAG      Default - "StORF": Unique identifier to be used to distinguish the second of two rounds of clustered sequences
+  -groups CORE_GROUPS   Default - ('99,95,90,80,15'): Gene family groups to use
+  -gpa GENE_PRESENCE_ABSENCE_OUT
+                        Default - False: If selected, a Roary formatted gene_presence_absence.csv will be created - Required for Coinfinder and other
+                        downstream tools
+
+Misc:
+  -verbose {True,False}
+                        Default - False: Print out runtime messages
+  -v                    Default - False: Print out version number and exit
+
+```
 
 ### Clustering Analysis
 
@@ -59,6 +88,7 @@ Replace `reclustered_file` with the path to the file containing additional seque
 PyamilySeq generates various outputs, including:
 
 - **Gene Presence-Absence File**: This CSV file details the presence and absence of genes across genomes.
+- **FASTA Files for Each Gene Family**:  
 
 ## Gene Family Groups
 

PyamilySeq-0.2.0.dist-info/RECORD

@@ -0,0 +1,11 @@
+PyamilySeq/CD-Hit_StORF-Reporter_Cross-Genera_Builder.py,sha256=UzQ5iOKCNfurxmj1pnkowF11YfWBO5vnBCKxQK6goB8,26538
+PyamilySeq/Constants.py,sha256=3Nr6JfUVt2eZT4M7fV-sz_bPXIvPgxIBT5nR76kCPIo,30
+PyamilySeq/PyamilySeq_Species.py,sha256=SCWeK7bEfnKLrfzliiOx7Jtmie8vvAXGtQE_PpJD5hY,31040
+PyamilySeq/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+PyamilySeq/combine_FASTA_with_genome_IDs.py,sha256=aMUVSk6jKnKX0g04RMM360QueZS83lRLqLLysBtQbLo,2009
+PyamilySeq-0.2.0.dist-info/LICENSE,sha256=OXLcl0T2SZ8Pmy2_dmlvKuetivmyPd5m1q-Gyd-zaYY,35149
+PyamilySeq-0.2.0.dist-info/METADATA,sha256=FUiZzxQzqnOwokb7MflZCMUzK9JgFVUVzEvLBPAlpgk,4144
+PyamilySeq-0.2.0.dist-info/WHEEL,sha256=Z4pYXqR_rTB7OWNDYFOm1qRk0RX6GFP2o8LgvP453Hk,91
+PyamilySeq-0.2.0.dist-info/entry_points.txt,sha256=zGtA2Ycf0LG3PR7zuuT0wjaAKLFxtyGgBc0O_W7E250,66
+PyamilySeq-0.2.0.dist-info/top_level.txt,sha256=J6JhugUQTq4rq96yibAlQu3o4KCM9WuYfqr3w1r119M,11
+PyamilySeq-0.2.0.dist-info/RECORD,,

PyamilySeq-0.2.0.dist-info/top_level.txt

@@ -0,0 +1 @@
+PyamilySeq

PyamilySeq-0.0.1.dist-info/RECORD

@@ -1,6 +0,0 @@
-PyamilySeq-0.0.1.dist-info/LICENSE,sha256=OXLcl0T2SZ8Pmy2_dmlvKuetivmyPd5m1q-Gyd-zaYY,35149
-PyamilySeq-0.0.1.dist-info/METADATA,sha256=gYAN6guZiV3POfjJJTn20Usj3PJZ-UTsdV5gruMo86g,2571
-PyamilySeq-0.0.1.dist-info/WHEEL,sha256=Z4pYXqR_rTB7OWNDYFOm1qRk0RX6GFP2o8LgvP453Hk,91
-PyamilySeq-0.0.1.dist-info/entry_points.txt,sha256=zGtA2Ycf0LG3PR7zuuT0wjaAKLFxtyGgBc0O_W7E250,66
-PyamilySeq-0.0.1.dist-info/top_level.txt,sha256=AbpHGcgLb-kRsJGnwFEktk7uzpZOCcBY74-YBdrKVGs,1
-PyamilySeq-0.0.1.dist-info/RECORD,,

PyamilySeq-0.0.1.dist-info/top_level.txt

@@ -1 +0,0 @@
-