tagging release 4.1 as stable for promethion flowcell and releaseing …

…alfredstats

.Rproj.user/F43DE67C/pcs/windowlayoutstate.pper

@@ -1,14 +1,14 @@
 {
     "left": {
-        "splitterpos": 307,
+        "splitterpos": 345,
         "topwindowstate": "HIDE",
-        "panelheight": 741,
-        "windowheight": 779
+        "panelheight": 835,
+        "windowheight": 873
     },
     "right": {
-        "splitterpos": 461,
+        "splitterpos": 519,
         "topwindowstate": "NORMAL",
-        "panelheight": 741,
-        "windowheight": 779
+        "panelheight": 835,
+        "windowheight": 873
     }
 }

.Rproj.user/F43DE67C/pcs/workbench-pane.pper

@@ -1,5 +1,5 @@
 {
     "TabSet1": 3,
-    "TabSet2": 2,
+    "TabSet2": 0,
     "TabZoom": {}
 }

.Rproj.user/F43DE67C/persistent-state

@@ -1,8 +1,8 @@
 build-last-errors="[]"
 build-last-errors-base-dir="~/NanoR/"
-build-last-outputs="[{\"type\":0,\"output\":\"==> devtools::document(roclets = c('rd', 'collate', 'namespace'))\\n\\n\"},{\"type\":2,\"output\":\"ℹ Updating NanoR documentation\\n\"},{\"type\":2,\"output\":\"ℹ Loading NanoR\\n\"},{\"type\":2,\"output\":\"Warning: package ‘plotly’ was built under R version 4.1.1\\nWarning: package ‘ggplot2’ was built under R version 4.1.1\\n\"},{\"type\":2,\"output\":\"Warning: package ‘scales’ was built under R version 4.1.1\\nWarning: package ‘data.table’ was built under R version 4.1.1\\nWarning: package ‘dplyr’ was built under R version 4.1.1\\nWarning: package ‘tidyr’ was built under R version 4.1.1\\n\"},{\"type\":2,\"output\":\"Warning: Skipping 'NAMESPACE'\\n✖ It already exists and was not generated by roxygen2.\\n\"},{\"type\":1,\"output\":\"Documentation completed\\n\\n\"},{\"type\":0,\"output\":\"==> R CMD INSTALL --preclean --no-multiarch --with-keep.source NanoR\\n\\n\"},{\"type\":1,\"output\":\"* installing to library ‘/Users/davide.bolognini/Library/R/arm64/4.1/library’\\n\"},{\"type\":1,\"output\":\"* installing *source* package ‘NanoR’ ...\\n\"},{\"type\":1,\"output\":\"** using staged installation\\n\"},{\"type\":1,\"output\":\"\"},{\"type\":1,\"output\":\"** R\\n\"},{\"type\":1,\"output\":\"\"},{\"type\":1,\"output\":\"** data\\n\"},{\"type\":1,\"output\":\"\"},{\"type\":1,\"output\":\"*** moving datasets to lazyload DB\\n\"},{\"type\":1,\"output\":\"\"},{\"type\":1,\"output\":\"** inst\\n\"},{\"type\":1,\"output\":\"** byte-compile and prepare package for lazy loading\\n\"},{\"type\":1,\"output\":\"\"},{\"type\":1,\"output\":\"Warning messages:\\n\"},{\"type\":1,\"output\":\"1: package ‘plotly’ was built under R version 4.1.1 \\n\"},{\"type\":1,\"output\":\"2: package ‘ggplot2’ was built under R version 4.1.1 \\n\"},{\"type\":1,\"output\":\"3: package ‘scales’ was built under R version 4.1.1 \\n\"},{\"type\":1,\"output\":\"4: package ‘data.table’ was built under R version 4.1.1 \\n\"},{\"type\":1,\"output\":\"5: package ‘dplyr’ was built under R version 4.1.1 \\n\"},{\"type\":1,\"output\":\"6: package ‘tidyr’ was built under R version 4.1.1 \\n\"},{\"type\":1,\"output\":\"\"},{\"type\":1,\"output\":\"** help\\n\"},{\"type\":1,\"output\":\"\"},{\"type\":1,\"output\":\"*** installing help indices\\n\"},{\"type\":1,\"output\":\"** building package indices\\n\"},{\"type\":1,\"output\":\"\"},{\"type\":1,\"output\":\"** testing if installed package can be loaded from temporary location\\n\"},{\"type\":1,\"output\":\"\"},{\"type\":2,\"output\":\"Warning: package ‘plotly’ was built under R version 4.1.1\\n\"},{\"type\":2,\"output\":\"Warning: package ‘ggplot2’ was built under R version 4.1.1\\n\"},{\"type\":2,\"output\":\"Warning: package ‘scales’ was built under R version 4.1.1\\n\"},{\"type\":2,\"output\":\"Warning: package ‘data.table’ was built under R version 4.1.1\\n\"},{\"type\":2,\"output\":\"Warning: package ‘dplyr’ was built under R version 4.1.1\\n\"},{\"type\":2,\"output\":\"Warning: package ‘tidyr’ was built under R version 4.1.1\\n\"},{\"type\":1,\"output\":\"\"},{\"type\":1,\"output\":\"** testing if installed package can be loaded from final location\\n\"},{\"type\":1,\"output\":\"\"},{\"type\":2,\"output\":\"Warning: package ‘plotly’ was built under R version 4.1.1\\n\"},{\"type\":2,\"output\":\"Warning: package ‘ggplot2’ was built under R version 4.1.1\\n\"},{\"type\":2,\"output\":\"Warning: package ‘scales’ was built under R version 4.1.1\\n\"},{\"type\":2,\"output\":\"Warning: package ‘data.table’ was built under R version 4.1.1\\n\"},{\"type\":2,\"output\":\"Warning: package ‘dplyr’ was built under R version 4.1.1\\n\"},{\"type\":2,\"output\":\"Warning: package ‘tidyr’ was built under R version 4.1.1\\n\"},{\"type\":1,\"output\":\"\"},{\"type\":1,\"output\":\"** testing if installed package keeps a record of temporary installation path\\n\"},{\"type\":1,\"output\":\"\"},{\"type\":1,\"output\":\"* DONE (NanoR)\\n\"},{\"type\":1,\"output\":\"\"}]"
+build-last-outputs="[{\"type\":0,\"output\":\"==> devtools::document(roclets = c('rd', 'collate', 'namespace'))\\n\\n\"},{\"type\":2,\"output\":\"ℹ Updating NanoR documentation\\n\"},{\"type\":2,\"output\":\"ℹ Loading NanoR\\n\"},{\"type\":2,\"output\":\"Warning: package ‘plotly’ was built under R version 4.1.1\\n\"},{\"type\":2,\"output\":\"Warning: package ‘ggplot2’ was built under R version 4.1.1\\nWarning: package ‘scales’ was built under R version 4.1.1\\nWarning: package ‘data.table’ was built under R version 4.1.1\\n\"},{\"type\":2,\"output\":\"Warning: package ‘dplyr’ was built under R version 4.1.1\\nWarning: package ‘tidyr’ was built under R version 4.1.1\\n\"},{\"type\":1,\"output\":\"Writing '\\u001B]8;;ide:run:pkgload::dev_help('alfredstats')\\u0007alfredstats.Rd\\u001B]8;;\\u0007'\\n\"},{\"type\":2,\"output\":\"Warning: Skipping 'NAMESPACE'\\n✖ It already exists and was not generated by roxygen2.\\n\"},{\"type\":1,\"output\":\"Documentation completed\\n\\n\"},{\"type\":0,\"output\":\"==> R CMD INSTALL --preclean --no-multiarch --with-keep.source NanoR\\n\\n\"},{\"type\":1,\"output\":\"* installing to library ‘/Users/davide.bolognini/Library/R/arm64/4.1/library’\\n\"},{\"type\":1,\"output\":\"\"},{\"type\":1,\"output\":\"* installing *source* package ‘NanoR’ ...\\n\"},{\"type\":1,\"output\":\"** using staged installation\\n\"},{\"type\":1,\"output\":\"\"},{\"type\":1,\"output\":\"** R\\n\"},{\"type\":1,\"output\":\"** data\\n\"},{\"type\":1,\"output\":\"\"},{\"type\":1,\"output\":\"*** moving datasets to lazyload DB\\n\"},{\"type\":1,\"output\":\"\"},{\"type\":1,\"output\":\"** inst\\n\"},{\"type\":1,\"output\":\"** byte-compile and prepare package for lazy loading\\n\"},{\"type\":1,\"output\":\"\"},{\"type\":1,\"output\":\"Warning messages:\\n\"},{\"type\":1,\"output\":\"1: package ‘plotly’ was built under R version 4.1.1 \\n\"},{\"type\":1,\"output\":\"2: package ‘ggplot2’ was built under R version 4.1.1 \\n\"},{\"type\":1,\"output\":\"3: package ‘scales’ was built under R version 4.1.1 \\n\"},{\"type\":1,\"output\":\"4: package ‘data.table’ was built under R version 4.1.1 \\n\"},{\"type\":1,\"output\":\"5: package ‘dplyr’ was built under R version 4.1.1 \\n\"},{\"type\":1,\"output\":\"6: package ‘tidyr’ was built under R version 4.1.1 \\n\"},{\"type\":1,\"output\":\"\"},{\"type\":1,\"output\":\"** help\\n\"},{\"type\":1,\"output\":\"\"},{\"type\":1,\"output\":\"*** installing help indices\\n\"},{\"type\":1,\"output\":\"** building package indices\\n\"},{\"type\":1,\"output\":\"\"},{\"type\":1,\"output\":\"** testing if installed package can be loaded from temporary location\\n\"},{\"type\":1,\"output\":\"\"},{\"type\":2,\"output\":\"Warning: package ‘plotly’ was built under R version 4.1.1\\n\"},{\"type\":2,\"output\":\"Warning: package ‘ggplot2’ was built under R version 4.1.1\\n\"},{\"type\":2,\"output\":\"Warning: package ‘scales’ was built under R version 4.1.1\\n\"},{\"type\":2,\"output\":\"Warning: package ‘data.table’ was built under R version 4.1.1\\n\"},{\"type\":2,\"output\":\"Warning: package ‘dplyr’ was built under R version 4.1.1\\n\"},{\"type\":2,\"output\":\"Warning: package ‘tidyr’ was built under R version 4.1.1\\n\"},{\"type\":1,\"output\":\"\"},{\"type\":1,\"output\":\"** testing if installed package can be loaded from final location\\n\"},{\"type\":1,\"output\":\"\"},{\"type\":2,\"output\":\"Warning: package ‘plotly’ was built under R version 4.1.1\\n\"},{\"type\":2,\"output\":\"Warning: package ‘ggplot2’ was built under R version 4.1.1\\n\"},{\"type\":2,\"output\":\"Warning: package ‘scales’ was built under R version 4.1.1\\n\"},{\"type\":2,\"output\":\"Warning: package ‘data.table’ was built under R version 4.1.1\\n\"},{\"type\":2,\"output\":\"Warning: package ‘dplyr’ was built under R version 4.1.1\\n\"},{\"type\":2,\"output\":\"Warning: package ‘tidyr’ was built under R version 4.1.1\\n\"},{\"type\":1,\"output\":\"\"},{\"type\":1,\"output\":\"** testing if installed package keeps a record of temporary installation path\\n\"},{\"type\":1,\"output\":\"* DONE (NanoR)\\n\"},{\"type\":1,\"output\":\"\"}]"
 compile_pdf_state="{\"tab_visible\":false,\"running\":false,\"target_file\":\"\",\"output\":\"\",\"errors\":[]}"
 files.monitored-path=""
 find-in-files-state="{\"handle\":\"\",\"input\":\"\",\"path\":\"\",\"regex\":false,\"ignoreCase\":false,\"results\":{\"file\":[],\"line\":[],\"lineValue\":[],\"matchOn\":[],\"matchOff\":[],\"replaceMatchOn\":[],\"replaceMatchOff\":[]},\"running\":false,\"replace\":false,\"preview\":false,\"gitFlag\":false,\"replacePattern\":\"\"}"
-imageDirtyState="1"
-saveActionState="-1"
+imageDirtyState="0"
+saveActionState="0"

DESCRIPTION

@@ -1,7 +1,7 @@
 Package: NanoR
 Type: Package
 Title: Analyze MinION and GridION sequencing data
-Version: 4.0
+Version: 4.1
 Author: Davide Bolognini, PhD [aut, cre]
 Maintainer: Davide Bolognini <davidebolognini7@gmail.com>
 Depends:

R/alfredstats.R

@@ -0,0 +1,114 @@
+#' @title alfredstats
+#' @description generate an interactive HTML report with statistics from alfred qc (zgrep "^ME <qc.tsv.gz> | cut -f 2- | datamash transpose)
+#' @param qcdata path to alfred qc.tsv.gz 
+#' @param out path to HTML report
+#' @return HTML file
+#' @examples
+#' #do not run
+#' qcdata<-file.path("/path/to/qc.tsv.gz")
+#' outhtml<-file.path("/path/to/qc.html")
+#' NanoR::alfredstats(qcdata=qcdata, out=outhtml)
+
+alfredstats<-function(qcdata,out) {
+
+	qcdata<-normalizePath(file.path(qcdata))
+	out<-file.path(out)
+
+	message("[",Sys.time(),"]"," reading qc data")
+
+	#read, re-organize
+	df<-fread(qcdata)
+
+	#error-rate
+	keep<-c("#MatchedBases", "MatchRate",
+			"#MismatchedBases", "MismatchRate",
+			"#DeletionsCigarD", "DeletionRate",
+			"#InsertionsCigarI", "InsertionRate",
+			"ErrorRate")
+
+	error_df<- df[which(df$Sample %in% keep),]
+	error_df[match(keep, error_df$Sample),]
+
+	error_df<-transpose(error_df)
+	names(error_df) <- as.character(unlist(error_df[1,]))
+	error_df<-error_df[-1,]
+	TotalErrors<-as.integer(error_df[["#MismatchedBases"]]) + as.integer(error_df[["#DeletionsCigarD"]]) + as.integer(error_df[["#InsertionsCigarI"]])
+	error_df<-cbind(error_df,TotalErrors)
+	colnames(error_df)<-c(colnames(error_df)[c(1:length(colnames(error_df))-1)], c("#TotalErrors"))
+	cols<-colnames(error_df)
+	error_df<-transpose(error_df)
+	error_df$V2<-error_df$V1
+	error_df$V1<-cols
+
+	#counts
+	error_counts_df<-error_df[grepl("#", error_df$V1),]
+	error_counts_df$V1<-factor(error_counts_df$V1, levels=as.character(error_counts_df$V1))
+	#rates
+	error_rates_df<-error_df[!grepl("#", error_df$V1),]
+	error_rates_df$V1<-factor(error_rates_df$V1, levels=as.character(error_rates_df$V1))
+
+
+	#aligned reads
+
+	keep<-c("#Unmapped", "UnmappedFraction",
+			"#Mapped", "MappedFraction",
+			"#MappedForward", "MappedForwardFraction",
+			"#MappedReverse", "MappedReverseFraction",
+			"#SecondaryAlignments", "SecondaryAlignmentFraction",
+			"#SupplementaryAlignments", "SupplementaryAlignmentFraction",
+			"#SplicedAlignments", "SplicedAlignmentFraction"            
+			)
+
+	alignment_df<-df[which(df$Sample %in% keep),]
+	colnames(alignment_df)<-c("V1", "V2")
+
+	#counts
+	alignment_counts_df<-alignment_df[grepl("#", alignment_df$V1),]
+	alignment_counts_df$V1<-factor(alignment_counts_df$V1, levels=as.character(alignment_counts_df$V1))
+	#rates
+	alignment_rates_df<-alignment_df[!grepl("#", alignment_df$V1),]
+	alignment_rates_df$V1<-factor(alignment_rates_df$V1, levels=as.character(alignment_rates_df$V1))
+
+	f <- list(
+		size = 10,
+		color = "#7f7f7f"
+	)
+
+
+	chart_type <- list(
+		type = "dropdown",
+		xanchor = 'center',
+		yanchor = "bottom",
+		buttons = list(
+		list(label = "counts",
+			method = "restyle",
+			args = list("visible", list(TRUE,FALSE))),
+		list(label = "rates",
+			method = "restyle",
+			args = list("visible", list(FALSE,TRUE)))
+		)
+	)
+
+	message("[",Sys.time(),"]"," plotting")
+
+	p1<-plot_ly() %>% add_trace(x=error_counts_df$V1,y=as.numeric(error_counts_df$V2),type="bar", color = I("darkblue"), name = "#bp", visible=TRUE) %>%
+					add_trace(x=error_rates_df$V1,y=as.numeric(error_rates_df$V2),type="bar", color = I("darkred"), name = ":bp", visible=FALSE) %>%
+					layout(showlegend=FALSE,updatemenus = list(chart_type))
+
+	p2<-plot_ly() %>% add_trace(x=alignment_counts_df$V1,y=as.numeric(alignment_counts_df$V2),type="bar", color = I("darkblue"), name = "#reads", visible=TRUE) %>%
+					add_trace(x=alignment_rates_df$V1,y=as.numeric(alignment_rates_df$V2),type="bar", color = I("darkred"), name = ":reads", visible=FALSE) %>%
+					layout(showlegend=FALSE,updatemenus = list(chart_type), title="Alfred statistics")
+
+
+	fig<- subplot(p1,p2,nrows = 2,titleX=TRUE, titleY=TRUE,margin=.05)
+
+	message("[",Sys.time(),"]"," storing plot to file")
+
+	htmlwidgets::saveWidget(fig, out)
+
+	rm(list=ls())
+	invisible(gc())
+
+	message("[",Sys.time(),"]"," done")
+
+}

data/sample_alfred_qc.tsv

@@ -0,0 +1,58 @@
+Sample	Sample
+Library	DefaultLib
+#QCFail	0
+QCFailFraction	0
+#DuplicateMarked	0
+DuplicateFraction	0
+#Unmapped	1145
+UnmappedFraction	0.00420869
+#Mapped	270911
+MappedFraction	0.995791
+#MappedRead1	270911
+#MappedRead2	0
+RatioMapped2vsMapped1	0
+#MappedForward	136796
+MappedForwardFraction	0.504948
+#MappedReverse	134115
+MappedReverseFraction	0.495052
+#SecondaryAlignments	26
+SecondaryAlignmentFraction	9.59725e-05
+#SupplementaryAlignments	27071
+SupplementaryAlignmentFraction	0.0999258
+#SplicedAlignments	0
+SplicedAlignmentFraction	0
+#Pairs	0
+#MappedPairs	0
+MappedPairsFraction	0
+#MappedSameChr	0
+MappedSameChrFraction	0
+#MappedProperPair	0
+MappedProperFraction	0
+#ReferenceBp	48502
+#ReferenceNs	0
+#AlignedBases	3461850049
+#MatchedBases	3386511047
+MatchRate	0.978237
+#MismatchedBases	36853506
+MismatchRate	0.0106456
+#DeletionsCigarD	23582373
+DeletionRate	0.00681207
+HomopolymerContextDel	0.27756
+#InsertionsCigarI	14903123
+InsertionRate	0.00430496
+HomopolymerContextIns	0.348669
+#SoftClipped	266961
+SoftClipRate	0.98542
+#HardClipped	0
+HardClipRate	0
+ErrorRate	0.0217626
+MedianReadLength	8020
+DefaultLibraryLayout	0
+MedianInsertSize	0
+MedianCoverage	65344
+SDCoverage	7560.2
+CoveredBp	48502
+FractionCovered	1
+BpCov1ToCovNRatio	0
+BpCov1ToCov2Ratio	-nan
+MedianMAPQ	60