Repository 'protein_rna_correlation'
hg clone https://toolshed.g2.bx.psu.edu/repos/pravs/protein_rna_correlation

Changeset 5:6bf0203ee17e (2018-06-20)
Previous changeset 4:b014014e685a (2018-06-17) Next changeset 6:8e9428eca82c (2018-06-20)
Commit message:
planemo upload
modified:
protein_rna_correlation.r
protein_rna_correlation.xml
added:
test_data/PE_abundance_GE_abundance_pearson.html
tool_dependencies.xml
b
diff -r b014014e685a -r 6bf0203ee17e protein_rna_correlation.r
--- a/protein_rna_correlation.r Sun Jun 17 05:06:18 2018 -0400
+++ b/protein_rna_correlation.r Wed Jun 20 20:43:56 2018 -0400
[
b'@@ -80,8 +80,8 @@\n # ............................SCRIPT STARTS FROM HERE .............................\n #==================================================================================\n # Warning Off\n-oldw <- getOption("warn")\n-options(warn = -1)\n+# oldw <- getOption("warn")\n+# options(warn = -1)\n #=============================================================================================================\n # Functions\n #=============================================================================================================\n@@ -411,10 +411,10 @@\n \t\t\n \t\t\tcat(\n \t\t"<font color=\'blue\'><h3>Download mapped unmapped data</h3></font>",\n-\t\t"<ul><li>Protein mapped data: ", \'<a href="\',paste(outdir,"/",PE_outfile_mapped,sep="",collapse=""),\'" target="_blank"> Link</a>\',"</li>",\n-\t\t"<li>Protein unmapped data: ", \'<a href="\',paste(outdir,"/",PE_outfile_unmapped,sep="",collapse=""),\'" target="_blank"> Link</a>\',"</li>",\n-\t\t"<li>Transcript mapped data: ", \'<a href="\',paste(outdir,"/",GE_outfile_mapped,sep="",collapse=""),\'" target="_blank"> Link</a>\',"</li>",\n-\t\t"<li>Transcript unmapped data: ", \'<a href="\',paste(outdir,"/",GE_outfile_unmapped,sep="",collapse=""),\'" target="_blank"> Link</a>\',"</li>",\n+\t\t"<ul><li>Protein mapped data: ", \'<a href="\',paste(PE_outfile_mapped,sep="",collapse=""),\'" target="_blank"> Link</a>\',"</li>",\n+\t\t"<li>Protein unmapped data: ", \'<a href="\',paste(PE_outfile_unmapped,sep="",collapse=""),\'" target="_blank"> Link</a>\',"</li>",\n+\t\t"<li>Transcript mapped data: ", \'<a href="\',paste(GE_outfile_mapped,sep="",collapse=""),\'" target="_blank"> Link</a>\',"</li>",\n+\t\t"<li>Transcript unmapped data: ", \'<a href="\',paste(GE_outfile_unmapped,sep="",collapse=""),\'" target="_blank"> Link</a>\',"</li>",\n \t\tfile = htmloutfile, append = TRUE);\n \t}\n \t\n@@ -422,8 +422,8 @@\n \twrite.table(GE_df[rowpair[,2], c(GE_idcolno,GE_expcolno)], file=paste(outdir,"/",GE_expfile,sep="",collapse=""), row.names=F, quote=F, sep="\\t", eol="\\n")\n \t\n \t\tcat(\n-\t"<li>Protein abundance data: ", \'<a href="\',paste(outdir,"/",PE_expfile,sep="",collapse=""),\'" target="_blank"> Link</a>\',"</li>",\n-\t"<li>Transcript abundance data: ", \'<a href="\',paste(outdir,"/",GE_expfile,sep="",collapse=""),\'" target="_blank"> Link</a>\',"</li></ul>",\n+\t"<li>Protein abundance data: ", \'<a href="\',paste(PE_expfile,sep="",collapse=""),\'" target="_blank"> Link</a>\',"</li>",\n+\t"<li>Transcript abundance data: ", \'<a href="\',paste(GE_expfile,sep="",collapse=""),\'" target="_blank"> Link</a>\',"</li></ul>",\n \tfile = htmloutfile, append = TRUE);\n \t\n #==========================================================================================\n@@ -470,8 +470,8 @@\n \t\t\n \t\t# Write excluded transcriptomics and proteomics data link to html file\n \t\tcat(\n-\t\t"<ul><li>Protein excluded data with NA or Inf or -Inf: ", \'<a href="\',paste(outdir,"/",PE_outfile_excluded_naInf,sep="",collapse=""),\'" target="_blank"> Link</a>\',"</li>",\n-\t\t"<li>Transcript excluded data with NA or Inf or -Inf: ", \'<a href="\',paste(outdir,"/",GE_outfile_excluded_naInf,sep="",collapse=""),\'" target="_blank"> Link</a>\',"</li></ul>",\n+\t\t"<ul><li>Protein excluded data with NA or Inf or -Inf: ", \'<a href="\',paste(PE_outfile_excluded_naInf,sep="",collapse=""),\'" target="_blank"> Link</a>\',"</li>",\n+\t\t"<li>Transcript excluded data with NA or Inf or -Inf: ", \'<a href="\',paste(GE_outfile_excluded_naInf,sep="",collapse=""),\'" target="_blank"> Link</a>\',"</li></ul>",\n \t\tfile = htmloutfile, append = TRUE);\n \t\t\n \t\t# Keep the unexcluded entries only\n@@ -535,7 +535,7 @@\n # Distribution of proteome and transcriptome abundance (Box and Density plot)\n #=============================================================================================================\n \tcat("Generating Box and Density plot\\n",file=logfile, append=T);\n-\toutplot = paste("./",outdir,"/AbundancePlot.png",sep="",collapse="");\n+\toutplot = paste(outdir,"/AbundancePlot.png",sep="",collapse="");\n \tpng(outplot);\n \tpar(mfrow=c(2,2));\n \tboxplot(proteome_df[,2], ylab="Abund'..b' predict(regmodel_lqs, PE_GE_data);\n-\toutplot = paste("./",outdir,"/PE_GE_lqs.pdf",sep="",collapse="");\n+\toutplot = paste(outdir,"/PE_GE_lqs.pdf",sep="",collapse="");\n \tpdf(outplot);\n \tplot(PE_GE_data[,"GE_abundance"], PE_GE_data[,"PE_abundance"], xlab="GE_abundance", ylab="PE_abundance",main="Resistant regression (lqs / least trimmed squares method)");\n \tpoints(PE_GE_data[,"GE_abundance"], regmodel_lqs_predictedy, col="red");\n@@ -890,7 +892,7 @@\n \t# Robust regression (rlm /  Huber M-estimator method)\n \tregmodel_rlm = rlm(PE_abundance~GE_abundance, data=PE_GE_data);\n \tregmodel_rlm_predictedy = predict(regmodel_rlm, PE_GE_data);\n-\toutplot = paste("./",outdir,"/PE_GE_rlm.pdf",sep="",collapse="");\n+\toutplot = paste(outdir,"/PE_GE_rlm.pdf",sep="",collapse="");\n \tplot(PE_GE_data[,"GE_abundance"], PE_GE_data[,"PE_abundance"], xlab="GE_abundance", ylab="PE_abundance",main="Robust regression (rlm /  Huber M-estimator method)");\n \tpoints(PE_GE_data[,"GE_abundance"], regmodel_rlm_predictedy, col="red");\n \tpdf(outplot);\n@@ -915,7 +917,7 @@\n \tregmodel_poly5_predictedy = predict(regmodel_poly5, PE_GE_data);\n \tregmodel_poly6_predictedy = predict(regmodel_poly6, PE_GE_data);\n \t\n-\toutplot = paste("./",outdir,"/PE_GE_poly2.pdf",sep="",collapse="");\n+\toutplot = paste(outdir,"/PE_GE_poly2.pdf",sep="",collapse="");\n \tdev.set(devnum);\n \tplot(PE_GE_data[,"GE_abundance"], PE_GE_data[,"PE_abundance"], xlab="GE_abundance", ylab="PE_abundance",main="Polynomial regression with degree 2");\n \tpoints(PE_GE_data[,"GE_abundance"], regmodel_poly2_predictedy, col="red");\n@@ -923,7 +925,7 @@\n \tplot(regmodel_poly2);\n \tdev.off();\n \n-\toutplot = paste("./",outdir,"/PE_GE_poly3.pdf",sep="",collapse="");\n+\toutplot = paste(outdir,"/PE_GE_poly3.pdf",sep="",collapse="");\n \tdev.set(devnum);\n \tplot(PE_GE_data[,"GE_abundance"], PE_GE_data[,"PE_abundance"], xlab="GE_abundance", ylab="PE_abundance",main="Polynomial regression with degree 3");\n \tpoints(PE_GE_data[,"GE_abundance"], regmodel_poly3_predictedy, col="red");\n@@ -931,7 +933,7 @@\n \tplot(regmodel_poly3);\n \tdev.off();\n \n-\toutplot = paste("./",outdir,"/PE_GE_poly4.pdf",sep="",collapse="");\n+\toutplot = paste(outdir,"/PE_GE_poly4.pdf",sep="",collapse="");\n \tdev.set(devnum);\n \tplot(PE_GE_data[,"GE_abundance"], PE_GE_data[,"PE_abundance"], xlab="GE_abundance", ylab="PE_abundance",main="Polynomial regression with degree 4");\n \tpoints(PE_GE_data[,"GE_abundance"], regmodel_poly4_predictedy, col="red");\n@@ -939,7 +941,7 @@\n \tplot(regmodel_poly4);\n \tdev.off();\n \n-\toutplot = paste("./",outdir,"/PE_GE_poly5.pdf",sep="",collapse="");\n+\toutplot = paste(outdir,"/PE_GE_poly5.pdf",sep="",collapse="");\n \tdev.set(devnum);\n \tplot(PE_GE_data[,"GE_abundance"], PE_GE_data[,"PE_abundance"], xlab="GE_abundance", ylab="PE_abundance",main="Polynomial regression with degree 5");\n \tpoints(PE_GE_data[,"GE_abundance"], regmodel_poly5_predictedy, col="red");\n@@ -947,7 +949,7 @@\n \tplot(regmodel_poly5);\n \tdev.off();\n \t\n-\toutplot = paste("./",outdir,"/PE_GE_poly6.pdf",sep="",collapse="");\n+\toutplot = paste(outdir,"/PE_GE_poly6.pdf",sep="",collapse="");\n \tdev.set(devnum);\n \tplot(PE_GE_data[,"GE_abundance"], PE_GE_data[,"PE_abundance"], xlab="GE_abundance", ylab="PE_abundance",main="Polynomial regression with degree 6");\n \tpoints(PE_GE_data[,"GE_abundance"], regmodel_poly6_predictedy, col="red");\n@@ -960,7 +962,7 @@\n \tregmodel_gam_predictedy = predict(regmodel_gam, PE_GE_data);\n \t\n \tregmodel_gam_metrics = regr.eval(PE_GE_data$PE_abundance, regmodel_gam$fitted.values)\n-\toutplot = paste("./",outdir,"/PE_GE_gam.pdf",sep="",collapse="");\n+\toutplot = paste(outdir,"/PE_GE_gam.pdf",sep="",collapse="");\n \tdev.set(devnum);\n \tplot(PE_GE_data[,"GE_abundance"], PE_GE_data[,"PE_abundance"], xlab="GE_abundance", ylab="PE_abundance",main="Generalized additive models");\n \tpoints(PE_GE_data[,"GE_abundance"], regmodel_gam_predictedy, col="red");\n@@ -1019,7 +1021,7 @@\n \t\n \t\n \t# Warning On\n-\toptions(warn = oldw)\n+\t# options(warn = oldw)\n \t\n \t\n \t\n\\ No newline at end of file\n'
b
diff -r b014014e685a -r 6bf0203ee17e protein_rna_correlation.xml
--- a/protein_rna_correlation.xml Sun Jun 17 05:06:18 2018 -0400
+++ b/protein_rna_correlation.xml Wed Jun 20 20:43:56 2018 -0400
[
@@ -1,28 +1,20 @@
-<tool id="protein_rna_correlation" name="protein_rna_correlation" version="0.1.1">
-  <description>Correlation between protein and rna expression (Single Sample)</description>
+<tool id="protein_rna_correlation" name="protein_rna_correlation" version="0.0.2">
+  <description>Correlation between protein and transcript expression  </description>
   <requirements>
-    <requirement type="package" version="3.3.1">r-base</requirement>
-    <requirement type="package" version="1.18.0">bioconductor-rgalaxy</requirement>
-    <requirement type="package" version="1.21.0">bioconductor-biocinstaller</requirement>
-    <requirement type="package" version="1.9">rmarkdown</requirement>
-    <requirement type="package" version="1.9">MASS</requirement>
-    <requirement type="package" version="1.8-23">mgcv</requirement>
-    <requirement type="package" version="0.4.1">DMwR</requirement>
-    <requirement type="package" version="1.11.4">data.table</requirement>
-    <requirement type="package" version="3.0.1">gplots</requirement>
-    <requirement type="package" version="0.20-35">lattice</requirement>
-    <requirement type="package" version="3.5.0">grid</requirement>
-    <requirement type="package" version="3.1-137">nlme</requirement>
+    <requirement type="package" version="3.2.1">R</requirement>
+    <requirement type="package" version="0.0.1">r-protrnacorr</requirement>
+    <requirement type="package" version="1.5.0">x11</requirement>
+    
   </requirements>
   <command detect_errors="exit_code" interpreter="Rscript"><![CDATA[protein_rna_correlation.r $pe_exp $ge_exp $pe_idcol $ge_idcol $pe_expcol $ge_expcol $pe_idtype $ge_idtype $organism_map $writeMapUnmap $doScale $html_file $html_file.files_path]]></command>
   <inputs>
     <param name="pe_exp" type="data" format="tabular">
       <label>Input Protein Expression File</label>
     </param>
-    <param name="pe_idcol" type="integer">
+    <param name="pe_idcol" type="integer" value="1">
       <label>Column: Protein/Gene ID</label>
     </param>
-    <param name="pe_expcol" type="integer">
+    <param name="pe_expcol" type="integer" value="1">
       <label>Column: Protein Expression Values</label>
     </param>
     
@@ -30,41 +22,41 @@
       <label>Input RNA Expression File</label>
     </param>
     
-    <param name="ge_idcol" type="integer">
+    <param name="ge_idcol" type="integer" value="1">
       <label>Column: RNA/Gene ID</label>
     </param>
-    <param name="ge_expcol" type="integer">
+    <param name="ge_expcol" type="integer" value="1">
       <label>Column: RNA Expression Values</label>
     </param>
     
-    <param name="pe_idtype" type="select">
-        <option value='ensembl' selected>Ensembl</option>
-        <option value='uniprot'>Uniprot</option>
-        <option value='hgnc'>HGNC</option>
+    <param name="pe_idtype" type="select" label="Protein ID type">
+        <option value="Ensembl_with_version" selected="True">Ensembl</option>
+        <option value="uniprot">Uniprot</option>
+        <option value="hgnc">HGNC</option>
     </param>
     
-    <param name="ge_idtype" type="select">
-        <option value='ensembl' selected>Ensembl</option>
-        <option value='uniprot'>Uniprot</option>
-        <option value='hgnc'>HGNC</option>
+    <param name="ge_idtype" type="select" label="Transcript ID type">
+        <option value="Ensembl_with_version" selected="True">Ensembl</option>
+        <option value="uniprot">Uniprot</option>
+        <option value="hgnc">HGNC</option>
     </param>
     
     <param name="organism_map" type="data" format="tabular">
         <label>Biomart ID Mapping file (.map)</label>
     </param>
     
-    <param name="writeMapUnmap" type="boolean">
+    <param name="writeMapUnmap" type="boolean" checked="true" truevalue="1" falsevalue="0">
       <label>Create the list of Mapped and Unmapped Identifiers in HTML</label>
     </param>
     
-    <param name="doScale" type="boolean">
+    <param name="doScale" type="boolean" checked="true" truevalue="1" falsevalue="0">
       <label>Scale the abundance values</label>
     </param>
     
   </inputs>
   
   <outputs>
-    <data format="html" name="html_file" label="protein_rna_corr_${tool_name}.html"/>
+    <data format="html" name="html_file" label="protein_rna_corr_${tool.name}.html"/>
   </outputs>
   
   <tests>
@@ -78,14 +70,23 @@
             <param name="pe_idtype" value="Ensembl_with_version"/>
             <param name="ge_idtype" value="Ensembl_with_version"/>
             <param name="organism_map" value="mmusculus_gene_ensembl__GRCm38.p6.map"/>
-            <param name="writeMapUnmap" value="1"/>
-            <param name="doScale" value="1"/>
-            <output name="html_file" file="PE_abundance_GE_abundance_pearson.html"/>
+            <param name="writeMapUnmap" value="true"/>
+            <param name="doScale" value="true"/>
+            <output name="html_file" file="protein_rna_corr_protein_transcript_correlation.html"/>
         </test>
   </tests>
     
-  <help>
+  <help><![CDATA[
 Proteome Transcriptome Correlation
 Developer: Priyabrata Panigrahi
-  </help>
+  ]]></help>
+  <citations>
+      <citation type="bibtex">
+@misc{protein_rna_correlation,
+    author={Panigrahi, Priyabrata},
+    year={2018},
+    title={ProteinRNACorrelation}
+}
+      </citation>
+    </citations>
 </tool>
b
diff -r b014014e685a -r 6bf0203ee17e test_data/PE_abundance_GE_abundance_pearson.html
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test_data/PE_abundance_GE_abundance_pearson.html Wed Jun 20 20:43:56 2018 -0400
b
b'@@ -0,0 +1,56 @@\n+<html><body>\n+<h1>Association between proteomics and transcriptomics data</h1>\n+ <font color=\'blue\'><h3>Input data summary</h3></font> <ul> <li>Abbrebiations used: PE (Proteomics) and GE (Transcriptomics) </li> <li>Input PE data dimension (Row Column):  3597 58 </li> <li>Input GE data dimension (Row Column):  191650 14 </li> <li>Protein ID fetched from column:  7 </li> <li>Transcript ID fetched from column:  1 </li> <li>Protein ID type:  ensembl_peptide_id_version </li> <li>Transcript ID type:  ensembl_transcript_id_version </li> <li>Protein expression data fetched from column:  13 </li> <li>Transcript expression data fetched from column:  10 </li><li>Total Protein ID mapped:  3582 </li> <li>Total Protein ID unmapped:  15 </li> <li>Total Transcript ID mapped:  3582 </li> <li>Total Transcript ID unmapped:  188068 </li></ul><font color=\'blue\'><h3>Download mapped unmapped data</h3></font> <ul><li>Protein mapped data:  <a href=" output_fold/PE_mapped.tsv " target="_blank"> Link</a> </li> <li>Protein unmapped data:  <a href=" output_fold/PE_unmapped.tsv " target="_blank"> Link</a> </li> <li>Transcript mapped data:  <a href=" output_fold/GE_mapped.tsv " target="_blank"> Link</a> </li> <li>Transcript unmapped data:  <a href=" output_fold/GE_unmapped.tsv " target="_blank"> Link</a> </li><li>Protein abundance data:  <a href=" output_fold/PE_abundance.tsv " target="_blank"> Link</a> </li> <li>Transcript abundance data:  <a href=" output_fold/GE_abundance.tsv " target="_blank"> Link</a> </li></ul><ul> <li>Number of entries in Transcriptome data used for correlation:  3582 </li> <li>Number of entries in Proteome data used for correlation:  3582 </li></ul><font color=\'blue\'><h3>Filtering</h3></font> Checking for NA or Inf or -Inf in either Transcriptome or Proteome data, if found, remove those entry<br> <ul> <li>Number of NA found:  88 </li> <li>Number of Inf or -Inf found:  559 </li></ul><ul><li>Protein excluded data with NA or Inf or -Inf:  <a href=" output_fold/PE_excluded_NA_Inf.tsv " target="_blank"> Link</a> </li> <li>Transcript excluded data with NA or Inf or -Inf:  <a href=" output_fold/GE_excluded_NA_Inf.tsv " target="_blank"> Link</a> </li></ul><font color=\'blue\'><h3>Filtered data summary</h3></font> Excluding entires with abundance values: NA/Inf/-Inf<br> <ul> <li>Number of entries in Transcriptome data remained:  2949 </li> <li>Number of entries in Proteome data remained:  2949 </li></ul><font color=\'blue\'><h3>Proteome data summary</h3></font>\n+ <table class="embedded-table" border=1 cellspacing=0 cellpadding=5 style="table-layout:auto; "> <tr bgcolor="#c3f0d6"><th>Parameter</th><th>Value</th></tr><tr><td> </td><td> Min.   :-2.98277   </td></tr>\n+<tr><td> </td><td> 1st Qu.:-0.40393   </td></tr>\n+<tr><td> </td><td> Median :-0.07986   </td></tr>\n+<tr><td> </td><td> Mean   : 0.00000   </td></tr>\n+<tr><td> </td><td> 3rd Qu.: 0.26061   </td></tr>\n+<tr><td> </td><td> Max.   :15.13211   </td></tr>\n+</table>\n+<font color=\'blue\'><h3>Transcriptome data summary</h3></font>\n+ <table class="embedded-table" border=1 cellspacing=0 cellpadding=5 style="table-layout:auto; "> <tr bgcolor="#c3f0d6"><th>Parameter</th><th>Value</th></tr><tr><td> </td><td> Min.   :-8.33003   </td></tr>\n+<tr><td> </td><td> 1st Qu.:-0.06755   </td></tr>\n+<tr><td> </td><td> Median : 0.09635   </td></tr>\n+<tr><td> </td><td> Mean   : 0.00000   </td></tr>\n+<tr><td> </td><td> 3rd Qu.: 0.18103   </td></tr>\n+<tr><td> </td><td> Max.   : 8.50430   </td></tr>\n+</table>\n+<font color=\'blue\'><h3>Distribution of Proteome and Transcripome abundance (Box plot and Density plot)</h3></font>\n+ <img src="AbundancePlot.png"><font color=\'blue\'><h3>Scatter plot between Proteome and Transcriptome Abundance</h3></font>\n+ <img src="AbundancePlot_scatter.png"><font color=\'blue\'><h3>Correlation with all data</h3></font>\n+ <table class="embedded-table" border=1 cellspacing=0 cellpadding=5 style="table-layout:auto; "> <tr bgcolor="#c3f0d6"><th>Parameter</th><th>Method 1</th><th>'..b'3 </td> <td> 0.9756628 </td> <td> 0.001209039 </td></tr><tr> <td> ENSMUSP00000081956.8 </td> <td> 3.674308 </td> <td> ENSMUST00000005607 </td> <td> 1.306612 </td> <td> 0.006223403 </td></tr></table><font color=\'blue\'><h3>Scatter plot between Proteome and Transcriptome Abundance, after removal of outliers/influential observations</h3></font>\n+ <img src="AbundancePlot_scatter_without_outliers.png"><font color=\'blue\'><h3>Correlation with removal of outliers / influential observations</h3></font>\n+ <p>We removed the influential observations and reestimated the correlation values.</p><table class="embedded-table" border=1 cellspacing=0 cellpadding=5 style="table-layout:auto; "> <tr bgcolor="#c3f0d6"><th>Parameter</th><th>Method 1</th><th>Method 2</th><th>Method 3</th></tr><tr><td>Correlation method used</td><td> Pearson\'s product-moment correlation </td><td> Spearman\'s rank correlation rho </td><td> Kendall\'s rank correlation tau </td></tr> <tr><td>Correlation</td><td> 0.01485058 </td><td> 0.0246989 </td><td> 0.01689519 </td></tr> <tr><td>Pvalue</td><td> 0.4273403 </td><td> 0.1867467 </td><td> 0.1918906 </td></tr></table>\n+<font color=\'blue\'><h3>Heatmap of PE and GE abundance values</h3></font>\n+<img src="PE_GE_heatmap.png"><font color=\'blue\'><h3>Kmean clustering</h3></font>\n+Number of Clusters: 5<br><a href=" output_fold/PE_GE_kmeans_clusterpoints.txt " target="_blank">Download cluster list</a><br><img src="PE_GE_kmeans.png"><font color=\'blue\'><h3>Other regression model fitting</h3></font>\n+<ul>\n+\t<li>MAE:mean absolute error</li>\n+\t<li>MSE: mean squared error</li>\n+\t<li>RMSE:root mean squared error ( sqrt(MSE) )</li>\n+\t<li>MAPE:mean absolute percentage error</li>\n+\t</ul>\n+\t<h4><a href="PE_GE_modelfit.pdf" target="_blank">Comparison of model fits</a></h4><table class="embedded-table" border=1 cellspacing=0 cellpadding=5 style="table-layout:auto; "> <tr bgcolor="#c3f0d6"><th>Model</th><th>MAE</th><th>MSE</th><th>RMSE</th><th>MAPE</th><th>Diagnostics Plot</th></tr><tr><td>Linear regression with all data</td><td> 0.5463329 </td><td> 0.9996481 </td><td> 0.999824 </td><td> 0.9996321 </td><td> <a href="PE_GE_lm.pdf" target="_blank">Link</a> </td></tr> <tr><td>Linear regression with removal of outliers</td><td> 0.5404805 </td><td> 1.006281 </td><td> 1.003136 </td><td> 1.455637 </td><td> <a href="PE_GE_lm_without_outliers.pdf" target="_blank">Link</a> </td></tr> <tr><td>Resistant regression (lqs / least trimmed squares method)</td><td> 0.5407598 </td><td> 1.007932 </td><td> 1.003958 </td><td> 1.537172 </td><td> <a href="PE_GE_lqs.pdf" target="_blank">Link</a> </td></tr> <tr><td>Robust regression (rlm /  Huber M-estimator method)</td><td> 0.5404879 </td><td> 1.005054 </td><td> 1.002524 </td><td> 1.411806 </td><td> <a href="PE_GE_rlm.pdf" target="_blank">Link</a> </td></tr> <tr><td>Polynomial regression with degree 2</td><td> 0.546322 </td><td> 0.9996472 </td><td> 0.9998236 </td><td> 0.9993865 </td><td> <a href="PE_GE_poly2.pdf" target="_blank">Link</a> </td></tr> <tr><td>Polynomial regression with degree 3</td><td> 0.5469588 </td><td> 0.9976384 </td><td> 0.9988185 </td><td> 1.043158 </td><td> <a href="PE_GE_poly3.pdf" target="_blank">Link</a> </td></tr> <tr><td>Polynomial regression with degree 4</td><td> 0.5467885 </td><td> 0.9975077 </td><td> 0.9987531 </td><td> 1.041541 </td><td> <a href="PE_GE_poly4.pdf" target="_blank">Link</a> </td></tr> <tr><td>Polynomial regression with degree 5</td><td> 0.5467813 </td><td> 0.9975076 </td><td> 0.998753 </td><td> 1.041209 </td><td> <a href="PE_GE_poly5.pdf" target="_blank">Link</a> </td></tr> <tr><td>Polynomial regression with degree 6</td><td> 0.5465911 </td><td> 0.996652 </td><td> 0.9983246 </td><td> 1.056632 </td><td> <a href="PE_GE_poly6.pdf" target="_blank">Link</a> </td></tr> <tr><td>Generalized additive models</td><td> 0.5463695 </td><td> 0.9976796 </td><td> 0.9988391 </td><td> 1.032766 </td><td> <a href="PE_GE_gam.pdf" target="_blank">Link</a> </td></tr> </table>\n\\ No newline at end of file\n'
b
diff -r b014014e685a -r 6bf0203ee17e tool_dependencies.xml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/tool_dependencies.xml Wed Jun 20 20:43:56 2018 -0400
b
@@ -0,0 +1,44 @@
+<?xml version="1.0"?>
+<tool_dependency>
+    <package name="R" version="3.2.1">
+        <repository changeset_revision="d9f7d84125b7" name="package_r_3_2_1" owner="iuc" prior_installation_required="True" toolshed="https://toolshed.g2.bx.psu.edu" />
+    </package>
+    
+    <package name="r-protrnacorr" version="0.0.1">
+        <install version="1.0">
+            <actions>
+                <action type="setup_r_environment">
+                    <repository changeset_revision="d9f7d84125b7" name="package_r_3_2_1" owner="iuc" toolshed="https://toolshed.g2.bx.psu.edu">
+                        <package name="R" version="3.2.1" />
+                    </repository>
+                    <package>https://cran.r-project.org/src/contrib/MASS_7.3-50.tar.gz</package>
+                    <package>https://cran.r-project.org/src/contrib/mgcv_1.8-24.tar.gz</package>
+                    <package>https://cran.r-project.org/src/contrib/zoo_1.8-2.tar.gz</package>
+                    <package>https://cran.r-project.org/src/contrib/xts_0.10-2.tar.gz</package>
+                    <package>https://cran.r-project.org/src/contrib/curl_3.2.tar.gz</package>
+                    <package>https://cran.r-project.org/src/contrib/TTR_0.23-3.tar.gz</package>
+                    <package>https://cran.r-project.org/src/contrib/quantmod_0.4-13.tar.gz</package>
+                    <package>https://cran.r-project.org/src/contrib/abind_1.4-5.tar.gz</package>
+                    <package>https://cran.r-project.org/src/contrib/gtools_3.5.0.tar.gz</package>
+                    <package>https://cran.r-project.org/src/contrib/gdata_2.18.0.tar.gz</package>
+                    <package>https://cran.r-project.org/src/contrib/bitops_1.0-6.tar.gz</package>
+                    <package>https://cran.r-project.org/src/contrib/caTools_1.17.1.tar.gz</package>
+                    <package>https://cran.r-project.org/src/contrib/gplots_3.0.1.tar.gz</package>
+                    <package>https://cran.r-project.org/src/contrib/ROCR_1.0-7.tar.gz</package>
+                    <package>https://cran.r-project.org/src/contrib/lattice_0.20-35.tar.gz</package>
+                    <package>https://cran.r-project.org/src/contrib/DMwR_0.4.1.tar.gz</package>
+                    <package>https://cran.r-project.org/src/contrib/data.table_1.11.4.tar.gz</package>
+                    <!--<package>https://cran.r-project.org/src/contrib/Archive/grid/grid_0.7-3.tar.gz</package>-->
+                    <package>https://cran.r-project.org/src/contrib/Archive/nlme/nlme_3.1-120.tar.gz</package>
+                    <!--<package>https://cran.r-project.org/src/contrib/nlme_3.1-137.tar.gz</package>-->
+                </action>
+            </actions>
+        </install>
+        <readme>
+        Contains a tool dependency definition that downloads and installs protein rna correlation tool package for R library.
+        </readme>
+    </package>
+    <package name="x11" version="1.5.0">
+        <repository changeset_revision="2ecb3f1f8fbb" name="package_libx11_1_5_0" owner="devteam" prior_installation_required="True" toolshed="https://toolshed.g2.bx.psu.edu" />
+    </package>
+</tool_dependency>