vsnp3 version 3.32

Author: stuber

README.md

@@ -71,7 +71,7 @@ Benefits of defining SNPs:
 ## 📦 Installation
 
 ```bash
-conda create -c conda-forge -c bioconda -n vsnp3 vsnp3=3.31
+conda create -c conda-forge -c bioconda -n vsnp3 vsnp3=3.32
 conda activate vsnp3
 ```
 

bin/vsnp3_alignment_vcf.py

@@ -1,6 +1,6 @@
 #!/usr/bin/env python3
 
-__version__ = "3.31"
+__version__ = "3.32"
 
 import os
 import subprocess

bin/vsnp3_annotation.py

@@ -1,6 +1,6 @@
 #!/usr/bin/env python3
 
-__version__ = "3.31"
+__version__ = "3.32"
 
 import os
 import sys
@@ -189,15 +189,19 @@ def stats(self, FASTA=None):
         self.total_contig_lengths = total_contig_lengths
         self.mean_coverage = mean_coverage
 
-        print(f'\t     Contig count: {bcolors.YELLOW}{self.contig_count:,}{bcolors.ENDC}, \n \
-            Contig length counts <|301-999bp|>: {bcolors.RED}{self.small_contigs_count:,}{bcolors.ENDC}|{bcolors.BLUE}{self.mid_size:,}{bcolors.ENDC}|{bcolors.GREEN}{self.greater_one_kb_count:,}{bcolors.ENDC}, \n \
-            Longest contig: {bcolors.GREEN}{self.longest_contig:,}{bcolors.ENDC}, \n \
-            Total length: {bcolors.WHITE}{self.total_contig_lengths:,}{bcolors.ENDC}, \n \
-            N50: {bcolors.PURPLE}{self.n50:,}{bcolors.ENDC}, \n \
-            {self.coverage_title}: {bcolors.YELLOW}{self.mean_coverage:,.1f}X{bcolors.ENDC}\n')
+        # Fixed multi-line f-string using parentheses for string concatenation
+        print(f'\t     Contig count: {bcolors.YELLOW}{self.contig_count:,}{bcolors.ENDC}, \n'
+              f'            Contig length counts <|301-999bp|>: {bcolors.RED}{self.small_contigs_count:,}{bcolors.ENDC}|{bcolors.BLUE}{self.mid_size:,}{bcolors.ENDC}|{bcolors.GREEN}{self.greater_one_kb_count:,}{bcolors.ENDC}, \n'
+              f'            Longest contig: {bcolors.GREEN}{self.longest_contig:,}{bcolors.ENDC}, \n'
+              f'            Total length: {bcolors.WHITE}{self.total_contig_lengths:,}{bcolors.ENDC}, \n'
+              f'            N50: {bcolors.PURPLE}{self.n50:,}{bcolors.ENDC}, \n'
+              f'            {self.coverage_title}: {bcolors.YELLOW}{self.mean_coverage:,.1f}X{bcolors.ENDC}\n')
 
     def latex(self, tex, groups=None):
         blast_banner = Banner("Assembly")
+        # Define LaTeX newline constant to avoid raw string in f-string
+        latex_newline = r"\\"
+        
         print(r'\begin{table}[ht!]', file=tex)
         print(r'\begin{adjustbox}{width=1\textwidth}', file=tex)
         print(r'\begin{center}', file=tex)
@@ -206,9 +210,11 @@ def latex(self, tex, groups=None):
         print(r'\end{adjustbox}', file=tex)
         print(r'\begin{adjustbox}{width=1\textwidth}', file=tex)
         print(r'\begin{tabular}{ l | l | l | l | l | l }', file=tex)
-        print(f'Contig count & Contig length counts $<$ | 301-999bp | $>$ & Longest contig & Total length & N50 & {self.coverage_title} {r"\\"}', file=tex)
+        # Fixed raw string in f-string by defining constant
+        print(f'Contig count & Contig length counts $<$ | 301-999bp | $>$ & Longest contig & Total length & N50 & {self.coverage_title} {latex_newline}', file=tex)
         print(r'\hline', file=tex)
-        print(f'{self.contig_count:,} & {self.small_contigs_count:,} | {self.mid_size:,} | {self.greater_one_kb_count:,} & {self.longest_contig:,} & {self.total_contig_lengths:,} & {self.n50:,} & {self.mean_coverage:,.1f}X {r"\\"}', file=tex)
+        # Fixed raw string in f-string by using constant
+        print(f'{self.contig_count:,} & {self.small_contigs_count:,} | {self.mid_size:,} | {self.greater_one_kb_count:,} & {self.longest_contig:,} & {self.total_contig_lengths:,} & {self.n50:,} & {self.mean_coverage:,.1f}X {latex_newline}', file=tex)
         print(r'\hline', file=tex)
         print(r'\end{adjustbox}', file=tex)
         print(r'\vspace{0.1 mm}', file=tex)

bin/vsnp3_assembly.py

@@ -1,6 +1,6 @@
 #!/usr/bin/env python3
 
-__version__ = "3.31"
+__version__ = "3.32"
 
 import os
 import subprocess
@@ -41,7 +41,7 @@ def run(self,):
         sourmash search *_R1*.fastq.gz.sig ../sourmash/ref_db.sbt.zip -o sourmash_findings.csv
         '''
         all_ref_options = []
-        ref_options_file = os.path.abspath(f'{self.script_path}/../dependencies/reference_options_paths.txt')
+        ref_options_file = os.path.abspath(os.path.join(self.script_path, '..', 'dependencies', 'reference_options_paths.txt'))
         self.ref_options_file = ref_options_file
 
         # Check if reference options file exists
@@ -56,13 +56,13 @@ def run(self,):
             return
 
         # Read reference paths
-        with open(f'{ref_options_file}', 'r') as dep_paths:
+        with open(ref_options_file, 'r') as dep_paths:
             dependency_paths = [line.strip() for line in dep_paths]
 
         # Collect all reference options from the specified paths
         for path in dependency_paths:
             if os.path.exists(path):
-                ref_options = glob.glob(f'{path}/*')
+                ref_options = glob.glob(os.path.join(path, '*'))
                 all_ref_options = all_ref_options + ref_options
             else:
                 print(f"Warning: Reference path does not exist: {path}")
@@ -73,7 +73,7 @@ def run(self,):
         # Get FASTA files from each reference directory
         self.fasta_list = []
         for each_path in all_ref_options:
-            self.fasta_list.extend(glob.glob(f'{each_path}/*.fasta'))
+            self.fasta_list.extend(glob.glob(os.path.join(each_path, '*.fasta')))
 
         # Create dictionary mapping FASTA headers to file paths
         header_dict = {}
@@ -97,7 +97,7 @@ def run(self,):
             return
 
         # Check if sourmash database exists
-        sourmash_db = f'{self.script_path}/../dependencies/ref_db.sbt.zip'
+        sourmash_db = os.path.join(self.script_path, '..', 'dependencies', 'ref_db.sbt.zip')
         if not os.path.exists(sourmash_db):
             print(f"Error: Sourmash database not found: {sourmash_db}")
             self.top_header_found = "Sourmash Database Not Found"
@@ -108,6 +108,9 @@ def run(self,):
             self.sourmash_df = pd.DataFrame()
             return
 
+        # Create signature file path
+        fastq_sig_file = f'{self.FASTQ_R1}.sig'
+            
         # Run sourmash sketch
         try:
             sketch_result = subprocess.run(
@@ -128,16 +131,19 @@ def run(self,):
             self.sourmash_df = pd.DataFrame()
             return
 
+        # Create search CSV file path
+        search_csv_file = f'{self.sample_name}_search.csv'
+            
         # Run sourmash search
         try:
             search_result = subprocess.run(
                 [
                     "sourmash", 
                     "search", 
-                    f'{self.FASTQ_R1}.sig', 
+                    fastq_sig_file, 
                     sourmash_db,
                     "-o", 
-                    f'{self.sample_name}_search.csv', 
+                    search_csv_file, 
                     '--threshold=0.001'
                 ],
                 capture_output=True,
@@ -154,22 +160,22 @@ def run(self,):
             self.reference_set = None
             self.top_fasta_header = "Sourmash Search Failed"
             self.sourmash_df = pd.DataFrame()
-            if os.path.exists(f'{self.FASTQ_R1}.sig'):
-                os.remove(f'{self.FASTQ_R1}.sig')
+            if os.path.exists(fastq_sig_file):
+                os.remove(fastq_sig_file)
             return
 
         # Read search results
         try:
-            if os.path.exists(f'{self.sample_name}_search.csv') and os.path.getsize(f'{self.sample_name}_search.csv') > 0:
-                self.sourmash_df = pd.read_csv(f'{self.sample_name}_search.csv')
+            if os.path.exists(search_csv_file) and os.path.getsize(search_csv_file) > 0:
+                self.sourmash_df = pd.read_csv(search_csv_file)
             else:
                 print("Warning: Sourmash search produced no results or empty file")
                 self.sourmash_df = pd.DataFrame()
         except Exception as e:
             print(f"Error reading sourmash search results: {str(e)}")
             self.sourmash_df = pd.DataFrame()
 
-        #Force a top hit to a specific reference, ie TB lineages to
+        # Force a top hit to a specific reference, ie TB lineages to
         try: 
             self.top_header_found = self.sourmash_df['name'][0].split()[0] # top hit
         except (IndexError, KeyError):
@@ -212,15 +218,15 @@ def run(self,):
                 self.top_fasta_header = 'Error reading reference file'
 
         # Create sourmash directory and move results
-        dir = 'sourmash'
-        if not os.path.exists(dir):
-            os.makedirs(dir)
+        sourmash_dir = 'sourmash'
+        if not os.path.exists(sourmash_dir):
+            os.makedirs(sourmash_dir)
 
-        if os.path.exists(f'{self.sample_name}_search.csv'):
-            shutil.move(f'{self.sample_name}_search.csv', dir)
+        if os.path.exists(search_csv_file):
+            shutil.move(search_csv_file, sourmash_dir)
 
-        if os.path.exists(f'{self.FASTQ_R1}.sig'):
-            os.remove(f'{self.FASTQ_R1}.sig')
+        if os.path.exists(fastq_sig_file):
+            os.remove(fastq_sig_file)
 
         print("#############\n")
 
@@ -246,7 +252,7 @@ def latex(self, tex):
                     count+=1
                     if count <= 10:
                         percentage = f'{row[1]:.1%}'
-                        name = row[4].replace("_", r"\_") if isinstance(row[2], str) else "Invalid Name"
+                        name = row[4].replace("_", r"\_") if isinstance(row[4], str) else "Invalid Name"
                         print(percentage.replace("%", r"\%") + ' & ' + name + r' \\', file=tex)
                         print(r'\hline', file=tex)
             except Exception as e: