Merge pull request #13 from Kalan-Lab/update

Update to v1.1.4

Author: raufs

bin/lsaBGC-Sociate

@@ -332,7 +332,10 @@ def lsaBGC_Sociate():
                 if i == 0: continue
                 tot_tests += 1
 
-    mt_cor_alpha = 0.05/tot_tests
+    tot_tests = 0
+    mt_cor_alpha = 0.05
+    if tot_tests >= 1:
+        mt_cor_alpha = 0.05/tot_tests
 
     hits = []
     sociated_ogs = set([])

pyproject.toml

@@ -1,7 +1,7 @@
 [project]
 name = "lsaBGC-Pan"
 authors = [{name="Rauf Salamzade", email="salamzader@gmail.com"}]
-version = "1.1.3"
+version = "1.1.4"
 readme = "README.md"
 description = "lsaBGC-Pan: a workflow/suite for pan-BGC-ome analyses."
 

src/lsaBGC/classes/BGC.py

@@ -325,4 +325,4 @@ def parseGenbanks(self, comprehensive_parsing=True, flank_size=2000):
 		elif self.prediction_method.upper() == 'GECCO':
 			self.parseGECCO(comprehensive_parsing=comprehensive_parsing, flank_size=flank_size)
 		else:
-			raise RuntimeError("Unable to parse file because BGC prediction method is not an accepted option!")
+			raise RuntimeError("Unable to parse file because BGC prediction method is not an accepted option!")

src/lsaBGC/classes/Pan.py

@@ -367,7 +367,7 @@ def runMCLAndReportGCFs(self, mip, jcp, sccp, ccp, outdir, run_parameter_tests=F
 		try:
 			subprocess.call(' '.join(mcl_cmd), shell=True, stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL,
 							executable='/bin/bash')
-			assert (os.path.isfile(relations_mcl_file) and os.path.getsize(relations_mcl_file) > 50)
+			assert (os.path.isfile(relations_mcl_file)) # and os.path.getsize(relations_mcl_file) > 50)
 			self.logObject.info('Successfully ran: %s' % ' '.join(mcl_cmd))
 		except Exception as e:
 			if self.logObject:
@@ -381,7 +381,7 @@ def runMCLAndReportGCFs(self, mip, jcp, sccp, ccp, outdir, run_parameter_tests=F
 		try:
 			subprocess.call(' '.join(mcxdump_cmd), shell=True, stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL,
 							executable='/bin/bash')
-			assert (os.path.isfile(mcxdump_out_file) and os.path.getsize(mcxdump_out_file) > 50)
+			assert (os.path.isfile(mcxdump_out_file)) # and os.path.getsize(mcxdump_out_file) > 50)
 			if self.logObject:
 				self.logObject.info('Successfully ran: %s' % ' '.join(mcl_cmd))
 		except Exception as e:

src/lsaBGC/util.py

@@ -15,11 +15,15 @@
 import gzip
 import warnings
 warnings.simplefilter('ignore')
-import pkg_resources  # part of setuptools
+import importlib.metadata
 import pandas as pd 
 
-version = pkg_resources.require("lsaBGC-Pan")[0].version
-
+try:
+	package_name = "lsaBGC-Pan"
+	package_version = str(importlib.metadata.version(package_name))
+except importlib.metadata.PackageNotFoundError:
+	package_version = "NA"
+	
 valid_alleles = set(['A', 'C', 'G', 'T'])
 
 def reformatOrthologInfo(ortholog_matrix_file, zol_results_dir, logObject):
@@ -322,7 +326,7 @@ def runZol(detailed_BGC_listing_with_Pop_and_GCF_map_file, ortholog_listing_file
 
 		zp = zol_parameters
 		if zol_high_quality_preset:
-			zp = '-qa -b -s'
+			zp = '-qa -s -b'
 
 		for gcf in gcf_sample_bgcs:
 			gcf_bgcs_to_input = []
@@ -1726,7 +1730,7 @@ def parseVersion():
 	"""
 	Returns suite version. 
 	"""
-	return(str(version))
+	return(package_version)
 
 def castToNumeric(x):
 	"""
@@ -1853,12 +1857,11 @@ def createFinalSpreadsheets(detailed_BGC_listing_with_Pop_and_GCF_map_file, zol_
 							'Proportion of sites which are highly ambiguous in trimmed codon alignment', 'Median GC', 'Median GC Skew',
 							'BGC score (GECCO weights)', 'Viral score (V-Score)']
 
-		# TODO consider bringing back the following - will affect column referencing for coloring below:
-		#if zol_high_qual_flag:
-		#	zol_sheet_header += ['GARD Partitions Based on Recombination Breakpoints',
-		#	           'Number of Sites Identified as Under Positive or Negative Selection by FUBAR',
-		#		       'Average delta(Beta, Alpha) by FUBAR across sites',
-		#		       'Proportion of Sites Under Selection which are Positive'] 
+		if zol_high_qual_flag:
+			zol_sheet_header += ['GARD Partitions Based on Recombination Breakpoints',
+			           'Number of Sites Identified as Under Positive or Negative Selection by FUBAR',
+				       'Average delta(Beta, Alpha) by FUBAR across sites',
+				       'Proportion of Sites Under Selection which are Positive', 'P-value for gene-wide episodic selection by BUSTED'] 
 
 		zol_sheet_header += ['KO Annotation (E-value)', 'PGAP Annotation (E-value)', 'PaperBLAST Annotation (E-value)', 'CARD Annotation (E-value)',
 							'IS Finder (E-value)', 'MIBiG Annotation (E-value)', 'VOG Annotation (E-value)', 'VFDB Annotation (E-value)', 
@@ -1896,7 +1899,7 @@ def createFinalSpreadsheets(detailed_BGC_listing_with_Pop_and_GCF_map_file, zol_
 					ls = line.split('\t')
 					row = [gcf, ls[0], ls[1], ls[2], comp_cons[gcf][ls[0]]] + ls[3:18] + ls[19:]
 					if zol_high_qual_flag:
-						row = [gcf, ls[0], ls[1], ls[2], comp_cons[gcf][ls[0]]] + ls[3:22] + ls[23:]
+						row = [gcf, ls[0], ls[1], ls[2], comp_cons[gcf][ls[0]]] + ls[3:23] + ls[24:]
 					zctf_handle.write('\t'.join(row) + '\n')
 					num_rows += 1
 		zctf_handle.close()