RTCalc Retention Time Prediction and Outlier Removal

Script

BufferedReader getReader (String fileUrl, String encoding) throws IOException {
		InputStreamReader reader;
		try {
			if (encoding == null) {
				reader = new FileReader(fileUrl);
			} else {
				reader = new InputStreamReader(new FileInputStream(fileUrl),encoding); 
			}
		}
		catch (FileNotFoundException e) {
			// try a real URL instead
			URL url = new URL(fileUrl);
			if (encoding == null) {
				reader = new InputStreamReader (url.openStream());
			} else {
				reader = new InputStreamReader (url.openStream(), encoding);
			}
		}
		return new BufferedReader(reader);
	}



StringBuffer sb = new StringBuffer(4000);

if (encoding == void) {
	encoding = null;
}

BufferedReader in = getReader(fileurl, encoding);
String str;
String lineEnding = System.getProperty("line.separator");

while ((str = in.readLine()) != null) {
	sb.append(str);
	sb.append(lineEnding);
}
in.close();
filecontents = sb.toString();
  

Xpath Expression

/default:msms_pipeline_analysis/default:msms_run_summary/default:spectrum_query/default:search_result/default:search_hit/@peptide

Xpath Expression

/default:msms_pipeline_analysis/default:msms_run_summary/default:spectrum_query/@start_scan

Script

String temp_training = new String();
String temp_validation_flat = new String();

for (i=0; i

Script

file_split=unlist(strsplit(measured, split="\\n"))                          # split data into lines
peptides=lapply(strsplit(file_split,"\\t"), function(x) x[1])# create string vector using every second element
filtered_peptide_list<-"peptide\tprobability";

measured_RT=as.numeric(lapply(strsplit(file_split,"\\t"), function(x) x[2]))# create string vector using every second element

file_split=unlist(strsplit(predicted, split="\\n"))                          # split data into lines
predicted_RT=as.numeric(lapply(strsplit(file_split,"\\t"), function(x) x[2]))# create string vector using every second element

file_split=unlist(strsplit(probabilities, split="\\n"))                          # split data into lines
probabilities_P=as.numeric(lapply(strsplit(file_split,"\\t"), function(x) x[1])) # create string vector using every first element

rmsd2<-sqrt(sum(((measured_RT-predicted_RT)^2)/length(measured_RT)))

Z_score<-(measured_RT-predicted_RT)/rmsd2;

png("Z_scores_vs_probabilities.png", width=700, height=700); # make PNG plot

plot(log10(1-probabilities_P), Z_score, pch=20, xlab="log10(1-probability)", ylab="RTCalc Z-score");

for(i in 1:length(probabilities_P)) {
  if (abs(Z_score[i])>max_abs_Z_score) points(log10(1-probabilities_P[i]), Z_score[i], pch=4, col="red")
  if (abs(Z_score[i])<=max_abs_Z_score) {
	new_line<-paste(peptides[i], probabilities_P[i], sep = "\t"); 
  	filtered_peptide_list<-paste(filtered_peptide_list, new_line ,sep = "\n"); 
	}
}

temp<-dev.off();

R Server

Xpath Expression

/default:msms_pipeline_analysis/default:msms_run_summary/default:spectrum_query/default:search_result/default:search_hit/default:analysis_result/default:peptideprophet_result/@probability

Script

//can be removed, connecting the nodelist to a numerical vector input

String temp_probabilities = new String();

for (i=0; i