Merge pull request #360 from Nesvilab/v4.2.2

V4.2.2

.github/workflows/go.yml

@@ -7,10 +7,10 @@ jobs:
     runs-on: ubuntu-latest
     steps:
 
-    - name: Set up Go 1.15
+    - name: Set up Go 1.18
       uses: actions/setup-go@v1
       with:
-        go-version: 1.15
+        go-version: 1.18
       id: go
 
     - name: Check out code into the Go module directory
@@ -34,9 +34,6 @@ jobs:
         unzip -o lib/ext/ptmprophet/win/bindata.go.zip -d lib/ext/ptmprophet/win/
         unzip -o lib/ext/proteinprophet/unix/bindata.go.zip -d lib/ext/proteinprophet/unix/
         unzip -o lib/ext/proteinprophet/win/bindata.go.zip -d lib/ext/proteinprophet/win/
-        unzip -o lib/ext/rawfilereader/deb64/bindata.go.zip -d lib/ext/rawfilereader/deb64/
-        unzip -o lib/ext/rawfilereader/reh64/bindata.go.zip -d lib/ext/rawfilereader/reh64/
-        unzip -o lib/ext/rawfilereader/win/bindata.go.zip -d lib/ext/rawfilereader/win/
         unzip -o lib/pip/bindata.go.zip -d lib/pip/
         unzip -o lib/dat/bindata.go.zip -d lib/dat/
         unzip -o lib/obo/unimod/bindata.go.zip -d lib/obo/unimod/

.gitignore

@@ -3,7 +3,6 @@
 *.a
 *.so
 
-Makefile
 philosopher
 
 # Folders

Changelog

@@ -1,13 +1,8 @@
 ### Added
-- Added support for TMT 18
-- Added option for contaminant tags in the database.
-
-### Changed
-- Added the parsing rules from the Prophets to the protein description.
-- Removed RawReader because of licensing issues.
-- Improved processing speed and resource usage.
-- Reduced binariy size.
+- Decoys tag now appear inthe Gene and ProteinID
+- Support for TAIR database
+- Support for neXtProt database
+- Support for MSBooster scores which now appear in the PSM table
 
 ### Fixed
-- Several bugs and code fizes added.
-- Fixed issue with TMT 6 plex quantification.
+- Minor bugs andd issues were fixed

Makefile

@@ -0,0 +1,71 @@
+SOURCEDIR=.
+SOURCES := $(shell find $(SOURCEDIR) -name '*.go')
+
+BINARY = philosopher
+
+VERSION = $(shell date +%Y%m%d)
+BUILD = $(shell  date +%Y%m%d%H%M)
+
+TAG = v4.2.2
+
+LDFLAGS = -ldflags "-w -s -extldflags -static -X main.version=${TAG} -X main.build=${BUILD}"
+
+.DEFAULT_GOAL: $(BINARY)
+
+$(BINARY): $(SOURCES)
+	go build ${LDFLAGS} -o ${BINARY} main.go
+
+.PHONY: deploy
+deploy:
+	unzip -o lib/dat/bindata.go.zip -d lib/dat/
+
+	unzip -o lib/ext/cdhit/unix/bindata.go.zip -d lib/ext/cdhit/unix/
+	unzip -o lib/ext/cdhit/win/bindata.go.zip -d lib/ext/cdhit/win/
+
+	unzip -o lib/ext/comet/unix/bindata.go.zip -d lib/ext/comet/unix/
+	unzip -o lib/ext/comet/win/bindata.go.zip -d lib/ext/comet/win/rm -rf /usr/local/go && tar -C /usr/local -xzf go1.18.2.linux-amd64.tar.gz
+	unzip -o lib/ext/rawfilereader/reh64/bindata.go.zip -d lib/ext/rawfilereader/reh64/
+	unzip -o lib/ext/rawfilereader/win/bindata.go.zip -d lib/ext/rawfilereader/win/
+
+	unzip -o lib/pip/bindata.go.zip -d  lib/pip/
+
+	unzip -o lib/dat/bindata.go.zip -d  lib/dat/
+
+	unzip -o lib/obo/unimod/bindata.go.zip -d  lib/obo/unimod/
+
+.PHONY: test
+test:
+	go test ./... -v
+
+.PHONY: rc
+rc:
+	env CGO_ENABLED=0 gox -os="linux" ${LDFLAGS} -arch=amd64 -output philosopher-${TAG}-RC
+	env CGO_ENABLED=0 gox -os="windows" ${LDFLAGS} -arch=amd64 -output philosopher-${TAG}-RC
+	mv philosopher-${TAG}-RC ~/bin/
+	mv philosopher-${TAG}-RC.exe ~/bin/
+
+.PHONY: linux
+linux:
+	env CGO_ENABLED=0 gox -os="linux" ${LDFLAGS} -arch=amd64 -output philosopher
+
+.PHONY: windows
+windows:
+	env CGO_ENABLED=0 gox -os="windows" ${LDFLAGS} -arch=amd64 -output philosopher
+
+.PHONY: all
+all:
+	env CGO_ENABLED=0 gox -os="linux" ${LDFLAGS} -arch=amd64 -output philosopher
+	env CGO_ENABLED=0 gox -os="windows" ${LDFLAGS} -arch=amd64 -output philosopher
+
+.PHONY: draft
+draft:
+	goreleaser --skip-publish --snapshot --release-notes=Changelog --rm-dist
+
+.PHONY: push
+push:
+	git tag -a ${TAG} -m "Philosopher ${TAG}"
+	git push origin master -f --tags
+
+.PHONY: release
+release:
+	goreleaser --release-notes=Changelog --rm-dist

cmd/freequant.go

@@ -38,6 +38,10 @@ var freequant = &cobra.Command{
 			msg.InputNotFound(errors.New("unknown file format"), "fatal")
 		}
 
+		if m.Quantify.Raw {
+			msg.Custom(errors.New("support for Thermo raw files was temporarily removed, please convert your files to mzML"), "fatal")
+		}
+
 		//forcing the larger time window to be the same as the smaller one
 		//m.Quantify.RTWin = 3
 		m.Quantify.RTWin = m.Quantify.PTWin
@@ -64,7 +68,7 @@ func init() {
 		freequant.Flags().StringVarP(&m.Quantify.Dir, "dir", "", "", "folder path containing the raw files")
 		freequant.Flags().Float64VarP(&m.Quantify.Tol, "tol", "", 10, "m/z tolerance in ppm")
 		freequant.Flags().Float64VarP(&m.Quantify.PTWin, "ptw", "", 0.4, "specify the time windows for the peak (minute)")
-		//freequant.Flags().BoolVarP(&m.Quantify.Raw, "raw", "", false, "read raw files instead of converted XML")
+		freequant.Flags().BoolVarP(&m.Quantify.Raw, "raw", "", false, "read raw files instead of converted XML")
 		freequant.Flags().BoolVarP(&m.Quantify.Faims, "faims", "", false, "Use FAIMS information for the quantification")
 	}
 

cmd/labelquant.go

@@ -43,6 +43,10 @@ var labelquantCmd = &cobra.Command{
 			msg.InputNotFound(errors.New("unknown file format"), "fatal")
 		}
 
+		if m.Quantify.Raw {
+			msg.Custom(errors.New("support for Thermo raw files was temporarily removed, please convert your files to mzML"), "fatal")
+		}
+
 		m.Quantify = qua.RunIsobaricLabelQuantification(m.Quantify, m.Filter.Mapmods)
 
 		// store parameters on meta data
@@ -72,7 +76,7 @@ func init() {
 		labelquantCmd.Flags().Float64VarP(&m.Quantify.RemoveLow, "removelow", "", 0.0, "ignore the lower % of PSMs based on their summed abundances. 0 means no removal, entry value must be a decimal")
 		labelquantCmd.Flags().BoolVarP(&m.Quantify.Unique, "uniqueonly", "", false, "report quantification based only on unique peptides")
 		labelquantCmd.Flags().BoolVarP(&m.Quantify.BestPSM, "bestpsm", "", false, "select the best PSMs for protein quantification")
-		//labelquantCmd.Flags().BoolVarP(&m.Quantify.Raw, "raw", "", false, "read raw files instead of converted XML")
+		labelquantCmd.Flags().BoolVarP(&m.Quantify.Raw, "raw", "", false, "read raw files instead of converted XML")
 
 	}
 

lib/aba/pro.go

@@ -402,7 +402,7 @@ func saveProteinAbacusResult(session string, evidences rep.CombinedProteinEviden
 	}
 	defer file.Close()
 
-	header := "Protein\tProtein ID\tEntry Name\tGene\tProtein Length\tCoverage\tOrganism\tProtein Existence\tDescription\tProtein Probability\tTop Peptide Probability\tCombined Total Peptides\tCombined Spectral Count\tCombined Unique Spectral Count\tCombined Total Spectral Count"
+	header := "Protein\tProtein ID\tEntry Name\tGene\tProtein Length\tOrganism\tProtein Existence\tDescription\tProtein Probability\tTop Peptide Probability\tCombined Total Peptides\tCombined Spectral Count\tCombined Unique Spectral Count\tCombined Total Spectral Count"
 
 	// Add Unique+Razor SPC
 	for _, i := range namesList {
@@ -492,8 +492,6 @@ func saveProteinAbacusResult(session string, evidences rep.CombinedProteinEviden
 
 			line += fmt.Sprintf("%d\t", i.Length)
 
-			line += fmt.Sprintf("%.2f\t", i.Coverage)
-
 			line += fmt.Sprintf("%s\t", i.Organism)
 
 			line += fmt.Sprintf("%s\t", i.ProteinExistence)
@@ -512,10 +510,6 @@ func saveProteinAbacusResult(session string, evidences rep.CombinedProteinEviden
 
 			line += fmt.Sprintf("%d\t", summTotalSpC[i.ProteinID])
 
-			//line += fmt.Sprintf("%d\t", len(razorPeptides[i.ProteinID]))
-
-			//line += fmt.Sprintf("%d\t", len(uniquePeptides[i.ProteinID]))
-
 			// Add Unique+Razor SPC
 			for _, j := range namesList {
 				line += fmt.Sprintf("%d\t", i.UrazorSpc[j])

lib/dat/dat.go

@@ -152,6 +152,16 @@ func (d *Base) ProcessDB(file, decoyTag string) {
 			db := ProcessUniRef(k, v, decoyTag)
 			d.Records = append(d.Records, db)
 
+		} else if class == "tair" {
+
+			db := ProcessTair(k, v, decoyTag)
+			d.Records = append(d.Records, db)
+
+		} else if class == "nextprot" {
+
+			db := ProcessNextProt(k, v, decoyTag)
+			d.Records = append(d.Records, db)
+
 		} else {
 			msg.ParsingFASTA(errors.New(""), "fatal")
 		}

lib/dat/dat_test.go

@@ -73,8 +73,8 @@ func TestBase_ProcessDB(t *testing.T) {
 			}
 			d.ProcessDB(tt.args.file, tt.args.decoyTag)
 
-			if len(d.Records) != 20361 {
-				t.Errorf("Number of FASTA entries is incorrect, got %d, want %d", len(d.Records), 20360)
+			if len(d.Records) != 20371 {
+				t.Errorf("Number of FASTA entries is incorrect, got %d, want %d", len(d.Records), 20371)
 			}
 		})
 	}