Virus genome extraction workflow

Script

String baseUrl = "http://xml.nig.ac.jp/rest/Invoke";
String service = "ARSA";
String method = "searchByXMLPath";
String count = "1";
String offset = "1";

String queryPath = "((/ENTRY/DDBJ/division=='PHG' OR /ENTRY/DDBJ/division=='VRL') AND "
			+ "(((/ENTRY/DDBJ/definition='segment' AND /ENTRY/DDBJ/definition='complete sequence') OR "
			+ "/ENTRY/DDBJ/definition='complete genome')) AND (/ENTRY/DDBJ/definition!='nearly complete' AND "
			+ "/ENTRY/DDBJ/definition!='TPA:'))";

String returnPath = "/ENTRY/DDBJ/primary-accession,/ENTRY/DDBJ/definition";
String encode = "UTF8";

String query = baseUrl + "?" + "queryPath=" + URLEncoder.encode(queryPath, encode)
		+ "&returnPath=" + URLEncoder.encode(returnPath, encode)
		+ "&service=" + URLEncoder.encode(service, encode)
		+ "&method=" + URLEncoder.encode(method, encode)
		+ "&count=" + URLEncoder.encode(count, encode)
		+ "&offset="+ URLEncoder.encode(offset, encode)

Script

URL inputURL = null;
if (base != void) {
  inputURL = new URL(new URL(base), url);
}
else {
  inputURL = new URL(url);
}
URLConnection con = inputURL.openConnection();
InputStream in = con.getInputStream();

InputStreamReader isr = new InputStreamReader(in);
Reader inReader = new BufferedReader(isr);

StringBuffer buf = new StringBuffer();
int ch;
while ((ch = inReader.read()) > -1) {
  buf.append((char)ch);
}
inReader.close();
contents = buf.toString();


//String NEWLINE = System.getProperty("line.separator");
//
//URL inputURL = null;
//if (base != void) {
//	inputURL = new URL(new URL(base), url);
//} else {
//	inputURL = new URL(url);
//}
//StringBuffer result = new StringBuffer();
//BufferedReader reader = new BufferedReader(new InputStreamReader(inputURL.openStream()));
//String line = null;
//while ((line = reader.readLine()) != null) {
//	result.append(line);
//	result.append(NEWLINE);
//}
//
//contents = result.toString();

Script

List split = new ArrayList();
if (!string.equals("")) {
	String regexString = ",";
	if (regex != void) {
		regexString = regex;
	}
	String[] result = string.split(regexString);
	for (int i = 0; i < result.length; i++) {
		split.add(result[i]);
	}
}

Value

Script

for (int i = 0; i < arsaResult.size(); i++) {
	if (arsaResult.get(i).indexOf("hitscount") >= 0) {
		arsaResultNum = arsaResult.get(i).replaceAll("hitscount       =", "").trim();
		break;
	}
}

Script

List offsets = new ArrayList();
int cnt = 1000;
for (int i = 0; i < Integer.parseInt(hitCount)/cnt + 1; i++) {
	offsets.add(Integer.toString(i*cnt+1));
}

Script

String baseUrl = "http://xml.nig.ac.jp/rest/Invoke";
String service = "ARSA";
String method = "searchByXMLPath";
String count = "1000";
String queryPath = "((/ENTRY/DDBJ/division=='PHG' OR /ENTRY/DDBJ/division=='VRL') AND "
			+ "(((/ENTRY/DDBJ/definition='segment' AND /ENTRY/DDBJ/definition='complete sequence') OR "
			+ "/ENTRY/DDBJ/definition='complete genome')) AND (/ENTRY/DDBJ/definition!='nearly complete' AND "
			+ "/ENTRY/DDBJ/definition!='TPA:'))";
String returnPath = "/ENTRY/DDBJ/primary-accession,/ENTRY/DDBJ/definition";
String encode= "UTF8";

String query = baseUrl + "?" + "queryPath=" + URLEncoder.encode(queryPath, encode)
		+ "&returnPath=" + URLEncoder.encode(returnPath, encode)
		+ "&service=" + URLEncoder.encode(service, encode)
		+ "&method=" + URLEncoder.encode(method, encode)
		+ "&count=" + URLEncoder.encode(count, encode);
List queries = new ArrayList();
for (int i = 0; i < offsets.size(); i++) {
	String offset = offsets.get(i);
	queries.add(query + "&offset=" + URLEncoder.encode(offset, encode));
}

Script

URL inputURL = null;
if (base != void) {
  inputURL = new URL(new URL(base), url);
}
else {
  inputURL = new URL(url);
}
URLConnection con = inputURL.openConnection();
InputStream in = con.getInputStream();

InputStreamReader isr = new InputStreamReader(in);
Reader inReader = new BufferedReader(isr);

StringBuffer buf = new StringBuffer();
int ch;
while ((ch = inReader.read()) > -1) {
  buf.append((char)ch);
}
inReader.close();
contents = buf.toString();


//String NEWLINE = System.getProperty("line.separator");
//
//URL inputURL = null;
//if (base != void) {
//	inputURL = new URL(new URL(base), url);
//} else {
//	inputURL = new URL(url);
//}
//StringBuffer result = new StringBuffer();
//BufferedReader reader = new BufferedReader(new InputStreamReader(inputURL.openStream()));
//String line = null;
//while ((line = reader.readLine()) != null) {
//	result.append(line);
//	result.append(NEWLINE);
//}
//
//contents = result.toString();

Script

StringBuffer sb = new StringBuffer();
sb.append(arsaResultNum + " entries found\n");
sb.append("accession number\tDefinition\tgenome/segment\n");
for (int i = 0; i < ARSA_results.size(); i++){
	String[] split = ARSA_results.get(i).split("\n");
	for (int j = 2; j < split.length; j++) {
		sb.append(split[j] + "\t");
		if (split[j].indexOf("complete genome") != -1) {
			sb.append("genome");
		}else if (split[j].indexOf("segment") != -1) {
			sb.append("segment");
		}
		sb.append("\n");
	}
}
retrieving_virus_entry = sb.toString();