Merge pull request #6 from ncbi/dev

Updates to --amrfinder output preparing for new AMRFinderPlus release

.github/workflows/conda.yml

@@ -0,0 +1,70 @@
+name: Bioconda 
+
+on:
+    workflow_dispatch:
+    schedule:
+        - cron: '30 10 * * *' # 
+    repository_dispatch:
+        types: [linux-bioconda-test, install-test]
+jobs:
+  x86_linux:
+    runs-on: ubuntu-latest
+    steps:
+    - name: When was this run
+      run: date
+    - name: configure conda
+      run: |
+          . $CONDA/bin/activate
+          conda config --add channels defaults
+          conda config --add channels bioconda
+          conda config --add channels conda-forge
+    - name: install StxTyper
+      run: |
+          . $CONDA/bin/activate
+          conda install --update-deps -c conda-forge -c bioconda --strict-channel-priority -y ncbi-stxtyper
+          stxtyper --version
+    - name: download tests
+      run: |
+          BASE_URL=https://raw.githubusercontent.com/${GITHUB_REPOSITORY}/master
+          curl --silent --location -O ${BASE_URL}/test_stxtyper.sh
+    - name: run tests
+      run: |
+          source /usr/share/miniconda/bin/activate
+          echo CONDA_PREFIX = $CONDA_PREFIX
+          bash ./test_stxtyper.sh path
+  x86_mac:
+    runs-on: macos-latest
+    steps:
+    - name: Install conda b/c built-in conda was borked
+      run: |
+          curl -O https://repo.anaconda.com/miniconda/Miniconda3-latest-MacOSX-x86_64.sh
+          bash ./Miniconda3-latest-MacOSX-x86_64.sh -b -p /Users/runner/miniconda3
+    - name: Configure conda
+      run: |
+          source /Users/runner/miniconda3/bin/activate
+          conda init
+          # THIS DOESN"T WORK! Just install miniconda myself
+          # . $CONDA/bin/activate
+          conda config --add channels defaults
+          conda config --add channels bioconda
+          conda config --add channels conda-forge
+          # permissions are messed up on the mac runner
+          # Is this faster than installing miniconda myself?
+          # sudo chown -R 501:20 $CONDA
+          conda update conda
+    - name: Install StxTyper
+      run: |
+          source /Users/runner/miniconda3/bin/activate
+          conda install --update-deps -c bioconda -c conda-forge -y ncbi-stxtyper
+    - name: Download tests
+      run: |
+          BASE_URL=https://raw.githubusercontent.com/${GITHUB_REPOSITORY}/master
+          curl --silent --location -O ${BASE_URL}/test_stxtyper.sh
+    - name: Run tests
+      run: |
+          source /Users/runner/miniconda3/bin/activate
+          echo CONDA_PREFIX = $CONDA_PREFIX
+          bash ./test_stxtyper.sh path
+
+
+

Makefile

@@ -90,17 +90,17 @@ all:	$(BINARIES)
 
 common.o:	common.hpp common.inc
 
-stxtyper.o:  common.hpp common.inc 
+stxtyper.o:  common.hpp common.inc amrfinder_columns.hpp tsv.hpp version.txt 
 stxtyperOBJS=stxtyper.o common.o tsv.o
 stxtyper:	$(stxtyperOBJS)
 	$(CXX) -o $@ $(stxtyperOBJS) -pthread $(DBDIR)
 
-fasta_check.o:	common.hpp common.inc 
+fasta_check.o:	common.hpp common.inc version.txt 
 fasta_checkOBJS=fasta_check.o common.o 
 fasta_check:	$(fasta_checkOBJS)
 	$(CXX) -o $@ $(fasta_checkOBJS)
 
-fasta_extract.o:	common.hpp common.inc 
+fasta_extract.o:	common.hpp common.inc version.txt 
 fasta_extractOBJS=fasta_extract.o common.o 
 fasta_extract:	$(fasta_extractOBJS)
 	$(CXX) -o $@ $(fasta_extractOBJS)

README.md

@@ -2,6 +2,8 @@
 
 StxTyper is used to determine stx type from nucleotide sequence. Stx (Shiga-toxin) genes are found in some strains of _Escherichia coli_ and code for powerful toxins that can cause severe illness. StxTyper is software to classify these genes from assembled sequence using a standard algorithm.
 
+## WARNING: This is currently beta software and changes and new releases may come quickly. Please report any issues or comments to [email protected] or open an issue on GitHub.
+
 # Installation
 
 ## Installing with Bioconda

amrfinder_columns.hpp

@@ -0,0 +1,30 @@
+// AMRFinderPlus column names
+// PD-5085
+
+constexpr const char* prot_colName = "Protein id";   // PD-2534  
+constexpr const char* contig_colName = "Contig id";
+// Target 
+constexpr const char* start_colName = "Start"; 
+constexpr const char* stop_colName = "Stop";
+constexpr const char* strand_colName = "Strand";
+//        
+constexpr const char* genesymbol_colName = "Element symbol";  // PD-4924 
+constexpr const char* elemName_colName = "Element name";  // PD-4910
+constexpr const char* scope_colName = "Scope";  // PD-2825 
+// PD-1856
+constexpr const char* type_colName = "Type";
+constexpr const char* subtype_colName = "Subtype";
+constexpr const char* class_colName = "Class";
+constexpr const char* subclass_colName = "Subclass";
+//        
+constexpr const char* method_colName = "Method";
+constexpr const char* targetLen_colName = "Element length";  // was: "Target length" ??
+constexpr const char* refLen_colName = "Reference sequence length";
+constexpr const char* refCov_colName = "% Coverage of reference";
+constexpr const char* refIdent_colName = "% Identity to reference";
+constexpr const char* alignLen_colName = "Alignment length";
+constexpr const char* closestRefAccession_colName = "Closest reference accession";
+constexpr const char* closestRefName_colName = "Closest reference name";
+constexpr const char* hmmAccession_colName = "HMM accession";
+constexpr const char* hmmDescr_colName = "HMM description";
+constexpr const char* hierarchyNode_colName = "Hierarchy node";

stxtyper.cpp

@@ -32,6 +32,7 @@
 * Dependencies: NCBI BLAST, gunzip (optional)
 *
 * Release changes:
+*  1.0.25 08/16/2024 PD-5085  AMRFinderPlus column names to match MicroBIGG-E
 *  1.0.24 08/05/2024 PD-5076  "na" -> "NA"
 *  1.0.23 07/29/2024 PD-5064  AMBIGUOUS operon type
 *  1.0.22 07/25/2024          First codon L|I|V -> M
@@ -94,6 +95,7 @@
 #include "common.hpp"
 #include "tsv.hpp"
 using namespace Common_sp;
+#include "amrfinder_columns.hpp"
 
 #include "common.inc"
 
@@ -950,31 +952,31 @@ struct ThisApplication : ShellApplication
       td << "name";
     if (amrfinder)
     {
-      td << /* 1*/ "Protein identifier"  
-         << /* 2*/ "Contig id"
-         << /* 3*/ "Start"
-         << /* 4*/ "Stop"
-         << /* 5*/ "Strand"
-         << /* 6*/ "Element symbol"  // PD-4924
-         << /* 7*/ "Element name"  // PD-4910
-         << /* 8*/ "Scope"
-         << /* 9*/ "Element type"
-         << /*10*/ "Element subtype"
-         << /*11*/ "Class"
-         << /*12*/ "Subclass"
-         << /*13*/ "Method"
-         << /*14*/ "Target length"
-         << /*15*/ "Reference sequence length"
-         << /*16*/ "% Coverage of reference sequence"
-         << /*17*/ "% Identity to reference sequence"
-         << /*18*/ "Alignment length"
-         << /*19*/ "Accession of closest sequence"
-         << /*20*/ "Name of closest sequence"
-         << /*21*/ "HMM id"
-         << /*22*/ "HMM description"
+      td << /* 1*/ prot_colName 
+         << /* 2*/ contig_colName
+         << /* 3*/ start_colName
+         << /* 4*/ stop_colName
+         << /* 5*/ strand_colName
+         << /* 6*/ genesymbol_colName
+         << /* 7*/ elemName_colName
+         << /* 8*/ scope_colName
+         << /* 9*/ type_colName
+         << /*10*/ subtype_colName
+         << /*11*/ class_colName
+         << /*12*/ subclass_colName
+         << /*13*/ method_colName
+         << /*14*/ targetLen_colName
+         << /*15*/ refLen_colName
+         << /*16*/ refCov_colName
+         << /*17*/ refIdent_colName
+         << /*18*/ alignLen_colName
+         << /*19*/ closestRefAccession_colName
+         << /*20*/ closestRefName_colName
+         << /*21*/ hmmAccession_colName
+         << /*22*/ hmmDescr_colName
          ;
       if (print_node)
-        td << "Hierarchy node";  
+        td << hierarchyNode_colName;  
     }
     else
       td << "target_contig"

test/amrfinder_integration.expected

@@ -1,4 +1,4 @@
-#Protein identifier	Contig id	Start	Stop	Strand	Element symbol	Element name	Scope	Element type	Element subtype	Class	Subclass	Method	Target length	Reference sequence length	% Coverage of reference sequence	% Identity to reference sequence	Alignment length	Accession of closest sequence	Name of closest sequence	HMM id	HMM description
+#Protein id	Contig id	Start	Stop	Strand	Element symbol	Element name	Scope	Type	Subtype	Class	Subclass	Method	Element length	Reference sequence length	% Coverage of reference	% Identity to reference	Alignment length	Closest reference accession	Closest reference name	HMM accession	HMM description
 NA	partial	27	1048	+	stx2_operon	Partial stx2 operon	plus	VIRULENCE	STX_TYPE	STX2	STX2	PARTIAL	1022			99.41	337	AAA16362.1, AAS07607.1	Shiga toxin stx2	NA	NA
 NA	partial_contig_end	3	661	-	stx2_operon	Partial stx2 operon	plus	VIRULENCE	STX_TYPE	STX2	STX2	PARTIAL_CONTIG_END	659			100.00	216	AAM70046.1, AAA16362.1	Shiga toxin stx2	NA	NA
 NA	stx1a	218	1444	+	stx1a_operon	stx1a operon	plus	VIRULENCE	STX_TYPE	STX1	STX1A	COMPLETE	1227			100.00	406	AAA98347.1, AAA71894.1	Shiga toxin stx1a	NA	NA

test/amrfinder_integration2.expected

@@ -1,4 +1,4 @@
-#Protein identifier	Contig id	Start	Stop	Strand	Element symbol	Element name	Scope	Element type	Element subtype	Class	Subclass	Method	Target length	Reference sequence length	% Coverage of reference sequence	% Identity to reference sequence	Alignment length	Accession of closest sequence	Name of closest sequence	HMM id	HMM description	Hierarchy node
+#Protein id	Contig id	Start	Stop	Strand	Element symbol	Element name	Scope	Type	Subtype	Class	Subclass	Method	Element length	Reference sequence length	% Coverage of reference	% Identity to reference	Alignment length	Closest reference accession	Closest reference name	HMM accession	HMM description	Hierarchy node
 NA	partial	27	1048	+	stx2_operon	Partial stx2 operon	plus	VIRULENCE	STX_TYPE	STX2	STX2	PARTIAL	1022			99.41	337	AAA16362.1, AAS07607.1	Shiga toxin stx2	NA	NA	stxA2c, stxB2a
 NA	partial_contig_end	3	661	-	stx2_operon	Partial stx2 operon	plus	VIRULENCE	STX_TYPE	STX2	STX2	PARTIAL_CONTIG_END	659			100.00	216	AAM70046.1, AAA16362.1	Shiga toxin stx2	NA	NA	stxB2a, stxA2c
 NA	stx1a	218	1444	+	stx1a_operon	stx1a operon	plus	VIRULENCE	STX_TYPE	STX1	STX1A	COMPLETE	1227			100.00	406	AAA98347.1, AAA71894.1	Shiga toxin stx1a	NA	NA	stxA1a, stxB1a

version.txt

@@ -1 +1 @@
-1.0.24
+1.0.25