| Next changeset 1:746b5af0a9a2 (2015-04-20) |
|
Commit message:
Initial upload |
|
added:
heatmap_colormanipulation/.ruby-version heatmap_colormanipulation/heatmap_extra_v2beta_2.xml heatmap_colormanipulation/heatmap_extra_v2beta_VERSION.R heatmap_colormanipulation/test-data/heatmap_extracolors_in1.tab heatmap_colormanipulation/tool_dependencies.xml |
| b |
| diff -r 000000000000 -r 3797463c65f8 heatmap_colormanipulation/.ruby-version --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/heatmap_colormanipulation/.ruby-version Mon Apr 20 15:26:53 2015 -0400 |
| b |
| @@ -0,0 +1,1 @@ +2.0.0-dev |
| b |
| diff -r 000000000000 -r 3797463c65f8 heatmap_colormanipulation/heatmap_extra_v2beta_2.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/heatmap_colormanipulation/heatmap_extra_v2beta_2.xml Mon Apr 20 15:26:53 2015 -0400 |
| b |
| b'@@ -0,0 +1,267 @@\n+<tool id="heatmap_extra_v2_2" name="Heatmap with extra color options" version="1.0.1">\n+ <description>based on R\'s heatmap.2 function.</description>\n+ <command>R --quiet --slave --file=heatmap_extra_v2beta_VERSION.R --args $input $rowvar.rowcorr $rowvar.rowlink $colvar.colcorr $colvar.collink $var_cols $scale $na_remove $header $rowheader $grad_style $col_min $col_max $out_file1 $main@$xlab@$ylab@ ZZZZ_END $ColorManip_outer.ColorManip\n+\t#if $ColorManip_outer.ColorManip=="InnerClip" or $ColorManip_outer.ColorManip=="OuterClip":\n+\t\t$ColorManip_outer.clipValLow\n+\t\t$ColorManip_outer.clipValHigh\n+\t\t1>NUL 2>$err_out\n+\t#else:\n+\t\t$ColorManip_outer.clipVal 1>NUL 2>$err_out\n+\t#end if\n+ </command>\n+ <inputs>\n+ <param name="main" type="text" value="title" size="30" label="Plot Title" help="Must not be blank or contain some special characters (^,!,?, and * are ok. Parentheses, brackets, @, %, and \' are not) and be under 45 characters in length, or else the title will not fit on the plot. Christy will work allowing more characters here."/>\n+ <conditional name="rowvar">\n+ \t<param name="what" type="select" label="Select whether rows are genes or samples.">\n+\t\t<option value="genes">Genes</option>\n+\t\t<option value="samples">Samples</option>\n+ \t</param>\n+\t<when value="genes">\n+\t <param name="rowcorr" type="select" label="Distance metric for row clustering" help="Default is recommended method for gene clustering. If No clustering is selected, linkage type below will be ignored.">\n+ \t<option value="pearson" selected="true">Pearson (1-r)</option>\n+ \t<option value="spearman">Spearman rank (1-rho)</option>\n+ \t<option value="euclidean">Euclidean</option>\n+ \t<option value="none">No clustering</option>\n+ \t </param>\n+ \t <param name="rowlink" type="select" label="Type of linkage for row clustering" help="Default is recommendation to use for most cases. See below for more information on linkage types.">\n+ \t<option value="average" selected="true">Average</option>\n+ \t<option value="complete">Complete</option>\n+ \t<option value="single">Single</option>\n+ \t </param>\n+\t</when>\n+\t<when value="samples">\n+\t <param name="rowcorr" type="select" label="Distance metric for row clustering" help="Default is recommended method for sample clustering. If No clustering is selected, linkage type below will be ignored.">\n+\t\t<option value="spearman" selected="true">Spearman rank (1-rho)</option>\n+\t\t<option value="pearson">Pearson (1-r)</option>\n+\t\t<option value="euclidean">Euclidean</option>\n+ \t<option value="none">No clustering</option>\n+\t </param>\n+\t <param name="rowlink" type="select" label="Type of linkage for row clustering" help="Default is recommendation to use for most cases. See below for more information on linkage types.">\n+\t\t<option value="average" selected="true">Average</option>\n+\t\t<option value="complete">Complete</option>\n+\t\t<option value="single">Single</option>\n+\t </param>\n+\t</when>\n+ </conditional>\n+ <conditional name="colvar">\n+ <param name="colwhat" type="select" label="Select whether columns are genes or samples.">\n+ <option value="samples">Samples</option>\n+ <option value="genes">Genes</option>\n+ </param>\n+ <when value="genes">\n+ <param name="colcorr" type="select" label="Distance metric for column clustering" help="Default is recommended method for gene clustering.">\n+ <option value="pearson" selected="true">Pearson (1-r)</option>\n+ <option value="spearman">Spearman rank (1-rho)</option>\n+ <option value="euclidean">Euclidean</option>\n+ \t<option value="none">No clustering</option>\n+ </param>\n+ <param name="collink" type="select" label="Type of linkage for column clustering" help="Default is recommendation to use for most cases. See below for more information on linkage types.">\n+ <option v'..b' clip low color". The color transition will occur halfway between this minimum value and the maximum value in the dataset (automatically determined), and the color mapped to the highest data value (high color) will take on a gradient from the aforementioned halfway point (darkest hue) up to the maximum value in the dataset (lightest hue). Example dataset for which this is a good visualization choice (some outliers AT THE LOW END ONLY but most of the remaining data is close together)::\n+\n+\tGeneID\tlog2_FC(S2/S1)\tlog2_FC(S3/S1)\tlog2_FC(S4/S1)\tlog2_FC(S5/S1)\tlog2_FC(S6/S1))\n+\tASNS\t-1093.001\t1.824679717\t1.575430565\t0.970889\t2.104598893\n+\tBEST1\t3.341922966\t3.25087179\t3.961852285\t3.429484142\t3.717432789\n+\tBHLHE41\t-1.936238732\t2.145753785\t2.44525769\t-1000.123\t2.07475321\n+\tC8orf46\t4.334222947\t-4.30902017\t3.981405448\t3.161135243\t4.251538767\n+\tCCDC64\t2.516662746\t2.540500932\t3.842305595\t4.617812421\t2.365768433\n+\n+A good display value for the above dataset to visualize the differences in lower magnitude values without the -1000-range values dominating the color scheme is a "Min value to clip low color" of -5.\n+\n+\n+*Clip color at max value point only (best for outliers at the high end of the dataset)*: Color mapped to the highest data value (high color) will take on a gradient for which the darkest hue is mapped from the minimum data value (determined automatically) to the value halfway between the minimum and the chosen "Max value to clip high color". The high color will continue from the halfway point to the specified max value. All values above this will have the same color. Example dataset for which this is a good visualization choice (some outliers AT THE HIGH END ONLY but most of the remaining data is close together)::\n+\n+ GeneID log2_FC(S2/S1) log2_FC(S3/S1) log2_FC(S4/S1) log2_FC(S5/S1) log2_FC(S6/S1))\n+ ASNS 1093.001 1.824679717 1.575430565 0.970889 2.104598893\n+ BEST1 3.341922966 3.25087179 3.961852285 3.429484142 3.717432789\n+ BHLHE41 -1.936238732 2.145753785 2.44525769 1000.123 \t2.07475321\n+ C8orf46 4.334222947 -4.30902017 3.981405448 3.161135243 4.251538767\n+ CCDC64 2.516662746 2.540500932 3.842305595 4.617812421 2.365768433\n+\n+A good display value for the above dataset to visualize the differences in lower magnitude values without the +1000-range values dominating the color scheme is a "Max value to clip high color" of 5.\n+\n+\n+*Clip colors at max and min points (best for outliers at both ends of the dataset)*: This scheme is a combination of the previous two visualization schemes. It is best used when a dataset has outliers at both high and low ends of the value distribution, such as the following example::\n+\n+ GeneID log2_FC(S2/S1) log2_FC(S3/S1) log2_FC(S4/S1) log2_FC(S5/S1) log2_FC(S6/S1))\n+ ASNS 1093.001 1.824679717 1.575430565 0.970889 2.104598893\n+ BEST1 -2000.111 \t3.25087179 3.961852285 3.429484142 3.717432789\n+ BHLHE41 -1.936238732 2.145753785 2.44525769 1000.123 2.07475321\n+ C8orf46 4.334222947 -4.30902017 3.981405448 3.161135243 4.251538767\n+ CCDC64 2.516662746 2.540500932 -12345.6 \t4.617812421 2.365768433\n+\n+Good max and min clip values to display the above data are 5 and -5, respectively.\n+\n+\n+\n+**Linkage Types**\n+\n+*Average linkage:* the distance between clusters is defined as the average distance between all members of one cluster and all members of another cluster (default method, good to use for most cases).\n+\n+*Complete linkage:* the distance between clusters is defined as the maximum distance between members of one cluster and members of another cluster.\n+\n+*Single linkage:* the distance between clusters is defined as the minimum distance between the members of one culster and members of another cluster.\n+\n+\n+</help>\n+</tool>\n+\n' |
| b |
| diff -r 000000000000 -r 3797463c65f8 heatmap_colormanipulation/heatmap_extra_v2beta_VERSION.R --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/heatmap_colormanipulation/heatmap_extra_v2beta_VERSION.R Mon Apr 20 15:26:53 2015 -0400 |
| [ |
| @@ -0,0 +1,244 @@ +sink(file="/tmp/none") +sink("/dev/null") +options(warn=-1) +options(echo=F) + +args <- commandArgs(trailingOnly = T) +#title <- args[17] +Rowcorr <- args[2] +Rowlink <- args[3] +Colcorr <- args[4] +Collink <- args[5] +#Xlab <- args[18] +#Ylab <- args[19] +inputfile <- args[1] +Var_cols <- args[6] +Scale_var <- args[7] +Remove_na <- args[8] +header_yes <- args[9] +rowhead_yes <- args[10] +color_grad <- args[11] +color_min <- args[12] +#max_val_mincol <- args[13] +color_max <- args[13] +#min_val_maxcol <- args[15] +out_file <- args[14] +#logfile <- args[15] + +##Now for title, xlabel, and ylabel (spaces are hard to deal with here): +#title <- args[17] +#Xlab <- args[18] +#Ylab <- args[19] + +stoptime = 0 +argIndex = 16 +everything = args[argIndex] + +debugcounter = 0 + +suppressMessages(library(gplots)) +Rinfo = sessionInfo() +Rinfo_pkg = sessionInfo(package="gplots") +gplots_info = Rinfo_pkg$otherPkgs +#sink(logfile) +Rinfo +gplots_info +sink(file="/tmp/none") +sink("/dev/null") + +#cat(paste("arg value is ",args[argIndex],".\n"),file=logfile,append="TRUE") + +#while (stoptime < 1){ +while ((stoptime < 1)&&(debugcounter<50)){ + argIndex=argIndex+1 +# cat(paste("in while loop now, arg index is ",argIndex,".\n"),file=logfile,append="TRUE") +# cat(paste("arg value is ",args[argIndex],".\n"),file=logfile,append="TRUE") + everything = paste(everything,args[argIndex]) + if (args[argIndex]=="ZZZZ_END") { + stoptime = 1 + } + debugcounter=debugcounter+1 +} + +argIndex=argIndex+1 +#cat(paste("Out of while loop. arg index value is now ",argIndex,".\n"),file=logfile,append="TRUE") + +splitThese = strsplit(everything,"[@]") +title = splitThese[[1]][1] +Xlab = splitThese[[1]][2] +Ylab = splitThese[[1]][3] + +##Now grab the rest of the arguments passed in: +colorManip = args[argIndex] +argIndex = argIndex+1 + +#cat(paste("Color manip value is ",colorManip,".\n"),file=logfile,append="TRUE") + +if ((colorManip == "InnerClip") || (colorManip == "OuterClip")) { + LowClipVal = as.numeric(args[argIndex]) + HighClipVal = as.numeric(args[argIndex+1]) +# cat(paste("Two vals to clip: ",LowClipVal,HighClipVal,".\n"),file=logfile,append="TRUE") + +} else { + ClipVal = as.numeric(args[argIndex]) +# cat(paste("One val to clip: ",ClipVal,".\n"),file=logfile,append="TRUE") +} + +if (header_yes == "yes") { + inp = read.table(inputfile,stringsAsFactors=F, header=T, sep="\t") +} else { + inp = read.table(inputfile,stringsAsFactors=F, sep="\t") +} + + +these_cols = read.csv(text=Var_cols,header=F) + +if (ncol(these_cols)<2) { + x = data.frame(cbind(inp[, c(as.matrix(these_cols))],inp[, c(as.matrix(these_cols))])) + currentColNames=colnames(x) + labColVar = c(currentColNames[1],"") +} else { + x = inp[, c(as.matrix(these_cols))] + labColVar = colnames(x) +} + + +genemat = do.call(cbind,x) +x = apply(genemat,2,as.numeric) + +scale_value = Scale_var +na_rm_value = FALSE + +if (Remove_na == "yes") { + na_rm_value = TRUE +} + + +if (rowhead_yes == "yes") { + rownames(x)=inp[[1]] +} + +pdf(out_file) + + +if ((Rowcorr=="none") && (Colcorr!="none")) { + dendro_val = "column" +} else if ((Rowcorr!="none") && (Colcorr=="none")) { + dendro_val = "row" +} + +if ((Rowcorr=="none") && (Colcorr=="none")) { + dendro_val = "none" +} + +if ((Rowcorr!="none") && (Colcorr!="none")) { + dendro_val = "both" +} + +if (Rowcorr == "none") { + Rowv_val = FALSE +} else { + Rcor = cor(t(x),method=Rowcorr) + R_clust = hclust(as.dist(1-Rcor),method=Rowlink) + R_dendro = as.dendrogram(R_clust) + Rowv_val = R_dendro +} + +##Column clustering (if any) set up: +if (Colcorr == "none") { + Colv_val = FALSE +} else { + Ccor = cor(x,method=Colcorr) + C_clust = hclust(as.dist(1-Ccor),method=Collink) + C_dendro = as.dendrogram(C_clust) + Colv_val = C_dendro +} + +par(cex.main=0.8) ##font size for title +##Estimate good guesses for font sizes of rows and columns: +font_r1 = 0.2 + 1/log10(nrow(x)) ##default done in heatmap, based on number of rows +font_size_r = min(0.8,font_r1) + +font_c1 = 0.2 + 1/log10(ncol(x)) ##default done in heatmap, based on number of columns +font_size_c = min(0.8,font_c1) + +#min_value = min(x) ##x should be the original data matrix +#max_value = max(x) + +if (colorManip == "InnerClip") { + min_value = min(x) + max_value = max(x) + max_val_mincol = LowClipVal + min_val_maxcol = HighClipVal + +} else if (colorManip == "OuterClip") { + min_value = LowClipVal + max_value = HighClipVal + ##How do we set the other values if 0 isn't included in the range? Probably want central color to be center value: + if ((min_value<=0)&&(max_value>=0)) { + max_val_mincol = 0 ##will be reset later to account for slight tolerance (so black is included) + min_val_maxcol = 0 + } else { + ##0 is not in range, center around halfway point + max_val_mincol = (min_value+max_value)/2 + 0.00005 + min_val_maxcol = (min_value+max_value)/2 - 0.00005 + } +} else if (colorManip == "ClipMax") { + min_value = min(x) + max_value = ClipVal + if ((min_value<=0)&&(max_value>=0)) { + max_val_mincol = 0 ##will be reset later to account for slight tolerance (so black is included) + min_val_maxcol = 0 + } else { + ##0 is not in range, center around halfway point + max_val_mincol = (min_value+max_value)/2 + 0.00005 + min_val_maxcol = (min_value+max_value)/2 - 0.00005 + } +} else { + min_value = ClipVal + max_value = max(x) + if ((min_value<=0)&&(max_value>=0)) { + max_val_mincol = 0 ##will be reset later to account for slight tolerance (so black is included) + min_val_maxcol = 0 + } else { + ##0 is not in range, center around halfway point + max_val_mincol = (min_value+max_value)/2 + 0.00005 + min_val_maxcol = (min_value+max_value)/2 - 0.00005 + } +} + + +##is 0 included in the data range? if so we want it centered +if ((min_value <= 0) && (max_value >=0)) { + sym_breaks_value = "TRUE" + sym_key_value = "TRUE" +} else { + sym_breaks_value = "FALSE" + sym_key_value = "FALSE" +} + +if (color_grad == "double") { + my_palette = colorRampPalette(c(color_min,"black",color_max))(n=299) +} else { + my_palette = colorRampPalette(c(color_min,color_max))(n=299) +} + +##Need some tolerance otherwise black won't be included for 0 +if ((max_val_mincol==0) && (min_val_maxcol==0)) { + max_val_mincol = -0.00005 + min_val_maxcol = 0.00005 +} + +#cat(paste("max_val_mincol value is ",max_val_mincol,".\n"),file=logfile,append="TRUE") +#cat(paste("min_val_maxcol value is ",min_val_maxcol,".\n"),file=logfile,append="TRUE") + +colors = c(seq(min_value,max_val_mincol,length=100),seq(max_val_mincol,min_val_maxcol,length=100),seq(min_val_maxcol,max_value,length=100)) + +##Call heatmap.2. cexCol value is constant to account for long sample names +heatmap.2(x, margins=c(9,10), main=title, xlab=Xlab, ylab=Ylab, cexCol=font_size_c, cexRow=font_size_r, scale=scale_value, symbreaks=sym_breaks_value, symm=F, symkey=sym_key_value, na.rm=na_rm_value, trace="none", col=my_palette, breaks=colors, dendrogram=dendro_val, Rowv=Rowv_val, Colv=Colv_val, labCol=labColVar) + + +## Close the PDF file +devname = dev.off() + + |
| b |
| diff -r 000000000000 -r 3797463c65f8 heatmap_colormanipulation/test-data/heatmap_extracolors_in1.tab --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/heatmap_colormanipulation/test-data/heatmap_extracolors_in1.tab Mon Apr 20 15:26:53 2015 -0400 |
| b |
| @@ -0,0 +1,51 @@ + MES_R1 MES_R2 CP_R1 CP_R2 CM_R1 CM_R2 +9930023K05Rik 1.04 3.24 0.01 2.06 2.52 1.72 +A4galt 64.07 64.13 56.77 46.42 9.47 14.77 +Ace 5.21 7.56 8.11 10.28 58.68 77.41 +Actr3 94.84 76.57 85.83 74.3 16.12 99.82 +Actr3b 34.33 43.16 44.62 24.68 98.26 64.69 +Adam34 0.01 0 0 0 0 0 +Adnp 8.17 0.36 27.6 21.28 22.32 72.76 +Amac1 2.08 5.4 2.02 1.03 3.35 4.3 +Asb3 0.77 44.11 58.32 11.61 88.08 64.64 +Asf1a 57.33 26.32 32.35 27.59 88.08 57.44 +AU021092 0 0 3.04 6.17 1.67 7.73 +Bahcc1 50.46 67.97 80.31 78.86 30.8 84.1 +Bcl2a1d 0 0 1 0 1 0 +Ccdc40 95.58 34.39 14.58 49.98 62.8 58.42 +Chst9 0 0 1.01 1.03 0 0 +Cphx 1.04 0 3.04 0 0 0 +Cyp26a1 75.25 44.44 15.9 89.6 2.52 0.86 +Dcaf4 57.32 55.04 46.66 0.98 20.44 22.59 +Dnajc13 31.99 31.77 56.95 34.65 36.6 77.76 +Dusp2 80.1 83.17 99.08 26.02 41.19 52.09 +Elf4 45.78 40.01 1.98 69 55.22 52.68 +Fdxacb1 43.56 55.54 20.66 12.1 56.21 84.21 +Ganab 12.71 15.48 81.09 32.53 27.24 57.27 +Gm7616 1.17 1.15 0.71 2.13 4.51 2.78 +Grlf1 1.4 49.15 36.68 95.45 56.72 85.49 +Grwd1 77.35 3.83 32.4 1.09 25.6 44.04 +Il1rapl2 0 0.08 0 0 0 0 +Ippk 90.45 92.1 47.79 31.16 65.81 21.68 +Luc7l 89.97 20.02 76.71 68.3 89.65 73.67 +Med1 66.69 94.87 46.13 32.17 63.8 66.91 +Mlf2 30.27 79.06 20.31 86.77 25.24 10.88 +Mrgprb8 0 0 0.01 0 0 0 +Ncoa1 57.05 45.13 55.27 51.49 24.64 12.05 +Ndc80 5.52 24.72 39.69 94.19 69.5 47.13 +Nkpd1 16.64 28.09 55.78 51.42 88.74 75.61 +Nr2c2 78.94 1.63 90.58 11.88 36.04 85.89 +Pif1 81.99 92.94 51.59 70.76 6.01 54.13 +Raet1c 0.98 0 0 0 0.53 0 +Rnf7 55.49 30.38 16.26 10.74 90.98 40.75 +Rom1 32.12 52.3 4.44 24.44 44.04 40.53 +Rtf1 1.17 15.78 25.88 11.4 64.28 33.68 +Sec16b 4.16 1.08 2.02 5.15 18.42 12.88 +Slamf9 0 0 3.04 1.03 4.19 4.3 +Suv39h1 7.65 71.36 7.38 24.62 13.75 1.01 +Sys1 74.12 70.77 27.66 4.72 33.22 46.68 +Tmem159 90.51 81.01 96.32 100.79 80.15 88.17 +Tubb6 79.94 69.93 40.96 85.84 50.38 78.96 +Ube2i 0.74 26.57 71.35 75.41 92.69 107.4 +Wdr54 9.23 103.7 42.97 102.84 13.05 27.94 +Wipf2 25.14 28.88 57.58 32.75 56.6 24.07 |
| b |
| diff -r 000000000000 -r 3797463c65f8 heatmap_colormanipulation/tool_dependencies.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/heatmap_colormanipulation/tool_dependencies.xml Mon Apr 20 15:26:53 2015 -0400 |
| b |
| @@ -0,0 +1,18 @@ +<?xml version="1.0"?> +<tool_dependency> + <package name="R" version="3.0.3"> + <repository changeset_revision="f386d7431fe0" name="package_r_3_0_3" owner="iuc" toolshed="https://toolshed.g2.bx.psu.edu" /> + </package> + <package name="gtools" version="3.4.1"> + <install version="1.0"> + <actions> + <action type="setup_r_environment"> + <repository changeset_revision="f386d7431fe0" name="package_r_3_0_3" owner="iuc" toolshed="https://toolshed.g2.bx.psu.edu"> + <package name="R" version="3.0.3" /> + </repository> + <package>https://depot.galaxyproject.org/package/noarch/gtools_3.4.1.tar.gz</package> + </action> + </actions> + </install> + </package> +</tool_dependency> |