fix issues with qc and lims report

Dockerfile

@@ -3,7 +3,7 @@
 # Shelby Bennett, Erin Young, Curtis Kapsak, & Kutluhan Incekara
 
 ARG SAMTOOLS_VER="1.18"
-ARG TBP_PARSER_VER="1.4.1"
+ARG TBP_PARSER_VER="1.4.2"
 
 FROM ubuntu:jammy as builder
 
@@ -42,7 +42,7 @@ ARG TBP_PARSER_VER
 LABEL base.image="ubuntu:jammy"
 LABEL dockerfile.version="1"
 LABEL software="tbp-parser"
-LABEL software.version="1.4.1"
+LABEL software.version="1.4.2"
 LABEL description="tbp-parser and samtools"
 LABEL website="https://github.com/theiagen/tbp-parser"
 LABEL license="https://github.com/theiagen/tbp-parser/blob/main/LICENSE"

README.md

@@ -22,16 +22,16 @@ See also [this page](https://theiagen.notion.site/tbp-parser-b02bef0cbc814b12987
 We highly recommend using the following Docker image to run tbp-parser:
 
 ```markdown
-docker pull us-docker.pkg.dev/general-theiagen/theiagen/tbp-parser:1.4.1
+docker pull us-docker.pkg.dev/general-theiagen/theiagen/tbp-parser:1.4.2
 ```
 
 The entrypoint for this Docker image is the tbp-parser help message. To run this container interactively, use the following command:
 
 ```markdown
-docker run -it --entrypoint=/bin/bash us-docker.pkg.dev/general-theiagen/theiagen/tbp-parser:1.4.1
+docker run -it --entrypoint=/bin/bash us-docker.pkg.dev/general-theiagen/theiagen/tbp-parser:1.4.2
 # Once inside the container interactively, you can run the tbp-parser tool
 python3 /tbp-parser/tbp_parser/tbp_parser.py -v
-# v1.4.1
+# v1.4.2
 ```
 
 ### Locally with Python

tbp_parser/LIMS.py

@@ -155,7 +155,10 @@ def apply_lims_rules(self, gene_dictionary, DF_LIMS, max_mdl_resistance, antimic
               else:
                 self.logger.debug("LIMS:The other mutation ({}) has higher read support ({}) than the current mutation ({}; {})".format(aa_mutations_per_gene[matching_index], read_supports[matching_index], mutation, read_supports[current_index]))
                 removal_list.append(mutation)
-
+
+          if ("This mutation is outside the expected region" in warnings[current_index]):
+            removal_list.append(mutation)
+
         # remove all mutations that have lower read support
         if len(removal_list) > 0:
           for mutation in removal_list:
@@ -189,9 +192,9 @@ def apply_lims_rules(self, gene_dictionary, DF_LIMS, max_mdl_resistance, antimic
             aa_mutation = ""
 
           # do not add the mutation if the particular mutation has low quality or is blank
-          if ("Failed quality in the mutation position" in warnings[index]) or ("Insufficient Coverage" in mdl_interpretations[index]) or (mutation == "") or ("This mutation is outside the expected region" in warnings[index]):
+          if ("Failed quality in the mutation position" in warnings[index]) or ("Insufficient Coverage" in mdl_interpretations[index]) or (mutation == ""):
             self.logger.debug("LIMS:This mutation (\"{}\", origin gene: {}) is not being added to the LIMS report because it failed quality in the mutation position, was WT, or had insufficient locus coverage".format(mutation, gene))
-            if "del" in mutation and "Failed quality in the mutation position" in warnings[index]:
+            if "del" in mutation and "Failed quality in the mutation position" in warnings[index] and "Insufficient coverage in locus" in warnings[index]:
               DF_LIMS[gene_code] = "No sequence"
             else:
               DF_LIMS[gene_code] = "No mutations detected"
@@ -205,10 +208,16 @@ def apply_lims_rules(self, gene_dictionary, DF_LIMS, max_mdl_resistance, antimic
                 all_responsible_mdl_interpretations[gene][index] = "WT"
 
               if "del" in mutation and "Failed quality in the mutation position" in warnings[index]:
-                mdl_interpretations[index] = "Insufficient Coverage"
-                if gene in responsible_gene:
-                  all_responsible_mdl_interpretations[gene][index] = "Insufficient Coverage"
-
+                try:
+                  if int(globals.COVERAGE_DICTIONARY[gene]) < globals.COVERAGE_THRESHOLD:
+                    mdl_interpretations[index] = "Insufficient Coverage"
+                    if gene in responsible_gene:
+                      all_responsible_mdl_interpretations[gene][index] = "Insufficient Coverage"
+                  else:
+                    self.logger.debug("This gene ({}) has sufficient coverage a deletion being present".format(gene))
+                except:
+                  self.logger.debug("This gene ({})is not in the coverage dictionary".format(gene))
+
               self.logger.debug("LIMS:Since this MDL interpretation changed, we are now potentially recalculating max_mdl_resistance (currently {})".format(max_mdl_resistance[0]))
               if (max([globals.RESISTANCE_RANKING[interpretation] for gene_set in all_responsible_mdl_interpretations.values() for interpretation in gene_set]) != globals.RESISTANCE_RANKING[max_mdl_resistance[0]]) and gene in responsible_gene:
 

tbp_parser/Row.py

@@ -74,7 +74,7 @@ def __init__(self, logger, variant, who_confidence, drug, gene_name=None, depth=
         # if self.tbprofiler_gene_name in globals.TNGS_REGIONS.keys():
         #   self.logger.debug("ROW:[tNGS only] This mutation's genomic position is outside the expected region.")
         #   self.warning.append("This mutation is outside the expected region")
-        try:
+        if self.tbprofiler_gene_name in globals.COVERAGE_DICTIONARY:
           if (self.depth < globals.MIN_DEPTH) or (float(globals.COVERAGE_DICTIONARY[self.tbprofiler_gene_name]) < globals.COVERAGE_THRESHOLD):
             self.logger.debug("ROW:The depth of coverage for this variant is {} and the coverage for the gene is {}; applying a locus warning".format(self.depth, globals.COVERAGE_DICTIONARY[self.tbprofiler_gene_name]))
             if (float(globals.COVERAGE_DICTIONARY[self.tbprofiler_gene_name]) < globals.COVERAGE_THRESHOLD):
@@ -84,40 +84,7 @@ def __init__(self, logger, variant, who_confidence, drug, gene_name=None, depth=
                 self.logger.debug("ROW:This is a deletion, no warning added for the locus unless it fails positional qc (checked next)")
               else:
                 self.warning.append("Insufficient coverage in locus")
-
-          protein_position = globals.get_position(self.tbprofiler_variant_substitution_aa)
-
-          # check to see if we need to apply a mutation warning 
-          # (check rrs & rrl for low frequency and read support; 
-          #  also check ethA & rpoB for specific protein position frequency)
-          if ((self.depth < globals.MIN_DEPTH) 
-              or (self.tbprofiler_gene_name not in ["rrs", "rrl"] and 
-                  (float(self.frequency) < globals.MIN_FREQUENCY or self.read_support < globals.MIN_READ_SUPPORT)) 
-              or (self.tbprofiler_gene_name == "rrs" and 
-                  (float(self.frequency) < globals.RRS_FREQUENCY or self.read_support < globals.RRS_READ_SUPPORT)) 
-              or (self.tbprofiler_gene_name == "rrl" and 
-                  (float(self.frequency) < globals.RRL_FREQUENCY or self.read_support < globals.RRL_READ_SUPPORT)) 
-              or (self.tbprofiler_gene_name == "ethA" and 
-                  237 in protein_position and float(self.frequency) < globals.ETHA237_FREQUENCY) 
-              or (self.tbprofiler_gene_name == "rpoB" and 
-                  449 in protein_position and float(self.frequency) < globals.RPOB449_FREQUENCY)):
-            self.logger.debug("ROW:The depth of coverage for this variant is {}, the frequency is {}, and the read support is {}; applying an additional mutation position warning".format(self.depth, self.frequency, self.read_support))
-
-            if ((float(globals.COVERAGE_DICTIONARY[self.tbprofiler_gene_name]) < globals.COVERAGE_THRESHOLD) and 
-                ("del" in self.tbprofiler_variant_substitution_nt 
-                 or self.tbprofiler_gene_name in globals.GENES_WITH_DELETIONS)):
-              self.logger.debug("ROW:This deletion failed in the mutation position and there was insufficient coverage locus, adding insufficient coverage warning")
-              self.warning.append("Insufficient coverage in locus")
-
-            globals.MUTATION_FAIL_LIST.append(self.tbprofiler_variant_substitution_nt)
-            self.warning.append("Failed quality in the mutation position")
-
-          elif (float(globals.COVERAGE_DICTIONARY[self.tbprofiler_gene_name]) < globals.COVERAGE_THRESHOLD):
-            self.logger.debug("ROW:The depth of coverage for this variant is {}, the frequency is {}, and the read support is {}; no additional warning added for the mutation position".format(self.depth, self.frequency, self.read_support))
-
-          else: # all other variants, no warning added
-            self.warning = [""]
-        except:
+        else:
           self.logger.debug("ROW:This gene does not appear in the coverage dictionary. An additional warning will be given.")
           if self.tbprofiler_gene_name in globals.TNGS_REGIONS.keys():
             self.logger.debug("ROW:[tNGS only] This mutation's genomic position is outside the expected region")
@@ -127,6 +94,39 @@ def __init__(self, logger, variant, who_confidence, drug, gene_name=None, depth=
             self.mdl_interpretation = "NA"
           else:
             self.warning.append("This mutation is outside the expected region")
+
+        protein_position = globals.get_position(self.tbprofiler_variant_substitution_aa)
+
+        # check to see if we need to apply a mutation warning 
+        # (check rrs & rrl for low frequency and read support; 
+        #  also check ethA & rpoB for specific protein position frequency)
+        if ((self.depth < globals.MIN_DEPTH) 
+            or (self.tbprofiler_gene_name not in ["rrs", "rrl"] and 
+                (float(self.frequency) < globals.MIN_FREQUENCY or self.read_support < globals.MIN_READ_SUPPORT)) 
+            or (self.tbprofiler_gene_name == "rrs" and 
+                (float(self.frequency) < globals.RRS_FREQUENCY or self.read_support < globals.RRS_READ_SUPPORT)) 
+            or (self.tbprofiler_gene_name == "rrl" and 
+                (float(self.frequency) < globals.RRL_FREQUENCY or self.read_support < globals.RRL_READ_SUPPORT)) 
+            or (self.tbprofiler_gene_name == "ethA" and 
+                237 in protein_position and float(self.frequency) < globals.ETHA237_FREQUENCY) 
+            or (self.tbprofiler_gene_name == "rpoB" and 
+                449 in protein_position and float(self.frequency) < globals.RPOB449_FREQUENCY)):
+          self.logger.debug("ROW:The depth of coverage for this variant is {}, the frequency is {}, and the read support is {}; applying an additional mutation position warning".format(self.depth, self.frequency, self.read_support))
+
+          if self.tbprofiler_gene_name in globals.COVERAGE_DICTIONARY.keys():
+            if ((float(globals.COVERAGE_DICTIONARY[self.tbprofiler_gene_name]) < globals.COVERAGE_THRESHOLD) and 
+                ("del" in self.tbprofiler_variant_substitution_nt 
+                or self.tbprofiler_gene_name in globals.GENES_WITH_DELETIONS)):
+              self.logger.debug("ROW:This deletion failed in the mutation position and there was insufficient coverage locus, adding insufficient coverage warning")
+              self.warning.append("Insufficient coverage in locus")
+
+          globals.MUTATION_FAIL_LIST.append(self.tbprofiler_variant_substitution_nt)
+          self.warning.append("Failed quality in the mutation position")
+
+        else:
+          self.logger.debug("ROW:The depth of coverage for this variant is {}, the frequency is {}, and the read support is {}; no additional warning added for the mutation position".format(self.depth, self.frequency, self.read_support))
+          if len(self.warning) == 0:
+            self.warning = [""]        
 
         self.logger.debug("ROW:This variant has the following warnings: {}".format(self.warning))
 

tbp_parser/__init__.py

@@ -1 +1 @@
-__VERSION__ = "v1.4.1"
+__VERSION__ = "v1.4.2"