From 3da6e95f920a0a00930e18d3929ec59f7bc3fee8 Mon Sep 17 00:00:00 2001
From: kohleman <kohleman>
Date: Tue, 11 Aug 2015 14:02:08 +0000
Subject: [PATCH] adopted for HiSeq3000 runs
SVN: 34436
---
.../read-demultiplex-stats-nextseq.py | 191 +++---
.../read_demultiplex_stats.java | 603 +++++++++---------
2 files changed, 407 insertions(+), 387 deletions(-)
diff --git a/deep_sequencing_unit/sourceTest/core-plugins/illumina-qgf/1/dss/drop-boxes/read-demultiplex-stats-nextseq/read-demultiplex-stats-nextseq.py b/deep_sequencing_unit/sourceTest/core-plugins/illumina-qgf/1/dss/drop-boxes/read-demultiplex-stats-nextseq/read-demultiplex-stats-nextseq.py
index b66873933cb..787e008d89c 100755
--- a/deep_sequencing_unit/sourceTest/core-plugins/illumina-qgf/1/dss/drop-boxes/read-demultiplex-stats-nextseq/read-demultiplex-stats-nextseq.py
+++ b/deep_sequencing_unit/sourceTest/core-plugins/illumina-qgf/1/dss/drop-boxes/read-demultiplex-stats-nextseq/read-demultiplex-stats-nextseq.py
@@ -239,23 +239,99 @@ def process(transaction):
##########################################################
def updateLane(transaction, codeSampleFlowCell, totalLaneStatistics):
-
- flowcell, lanes, numberOfLanes = sampleSearch(transaction, codeSampleFlowCell)
- lane = lanes[0]
- mutable_lane = transaction.getSampleForUpdate(lane.getSampleIdentifier())
- print("Setting Complete Lanes Statistics For: " + lane.getSampleIdentifier())
-
- mutable_lane.setPropertyValue("YIELD_MBASES", str(int(totalLaneStatistics.Sum_PfYield)))
- mutable_lane.setPropertyValue('RAW_YIELD_MBASES', str(int(totalLaneStatistics.Sum_RawYield)))
- mutable_lane.setPropertyValue('PERCENTAGE_PASSED_FILTERING',str(int(totalLaneStatistics.Percentage_PfClusterCount_RawClusterCount)))
- mutable_lane.setPropertyValue('PF_READS_SUM',str(int(totalLaneStatistics.Sum_PfClusterCount)))
- mutable_lane.setPropertyValue('RAW_READS_SUM',str(int(totalLaneStatistics.Sum_RawClusterCount)))
- mutable_lane.setPropertyValue('PFYIELDQ30PERCENTAGE', str(int(totalLaneStatistics.Percentage_PfYieldQ30_PfYield)))
- mutable_lane.setPropertyValue('PFMEANQUALITYSCORE', str(totalLaneStatistics.Fraction_PfQualityScoreSum_PfYield))
- mutable_lane.setPropertyValue('CLUSTERS_PF_WITHOUT_NOINDEX', str(int(totalLaneStatistics.Clusters_PfWithoutNoindex)))
+
+ print("Setting Complete Lanes Statistics For: " + lane.getSampleIdentifier())
+ mutable_lane = transaction.getSampleForUpdate(lane.getSampleIdentifier())
+ mutable_lane.setPropertyValue("YIELD_MBASES", str(int(totalLaneStatistics.get(lane_in_int).Sum_PfYield)))
+ mutable_lane.setPropertyValue('RAW_YIELD_MBASES', str(int(totalLaneStatistics.get(lane_in_int).Sum_RawYield)))
+ mutable_lane.setPropertyValue('PERCENTAGE_PASSED_FILTERING',str(int(totalLaneStatistics.get(lane_in_int).Percentage_PfClusterCount_RawClusterCount)))
+ mutable_lane.setPropertyValue('PF_READS_SUM',str(int(totalLaneStatistics.get(lane_in_int).Sum_PfClusterCount)))
+ mutable_lane.setPropertyValue('RAW_READS_SUM',str(int(totalLaneStatistics.get(lane_in_int).Sum_RawClusterCount)))
+ mutable_lane.setPropertyValue('PFYIELDQ30PERCENTAGE', str(int(totalLaneStatistics.get(lane_in_int).Percentage_PfYieldQ30_PfYield)))
+ mutable_lane.setPropertyValue('PFMEANQUALITYSCORE', str(totalLaneStatistics.get(lane_in_int).Fraction_PfQualityScoreSum_PfYield))
+ mutable_lane.setPropertyValue('CLUSTERS_PF_WITHOUT_NOINDEX', str(int(totalLaneStatistics.get(lane_in_int).Clusters_PfWithoutNoindex)))
##########################################################
+ def update_datatsets(transaction, samplestatisticslist, codeSampleFlowLane, codeSampleFlowCell):
+ # Prepare links between XML and openBIS w.r.t to indexes in DataSet (openBIS):
+ print(codeSampleFlowLane)
+ index1list, index2list = getIndexesOfDataSetsOfSample(codeSampleFlowLane)
+ print(index1list)
+
+ propertiesCode, propertiesCodeValue = getInfoSampleProperties(codeSampleFlowCell)
+ index1length = int(propertiesCodeValue[CODE_INDEX1LENGTH])
+ index2length = int(propertiesCodeValue[CODE_INDEX2LENGTH])
+
+ nprocessedDataSets = 0
+ for s in samplestatisticslist:
+ print "\nContent in XML file:\n", s
+
+ # Prepare link between XML and openBIS w.r.t to indexes in Barcode (XML):
+ indexes = s.Barcode.split(BARCODE_SPLIT_CHAR)
+ if len(indexes) == 1: # only first part in Barcode
+ index1search = indexes[0].upper()
+ index2search = INDEX_EMPTY
+ elif len(indexes) == 2: # both parts in Barcode
+ index1search = indexes[0].upper()
+ index2search = indexes[1].upper()
+ else:
+ index1search = INDEX_EMPTY
+ index2search = INDEX_EMPTY
+
+ # Set link between XML and openBIS w.r.t to indexes in DataSet (openBIS):
+ if index1search == INDEX_EMPTY or index1search == INDEX_UNKNOWN:
+ index1 = INDEX_NO
+ else: # Hint: just two cases were known about index1length, that is 8 or 6
+ if index1length > 7:
+ index1 = [ index1 for index1 in index1list if index1search == index1 ]
+ else: # for smaller indexlength, the index is by 1 shorter in XML-file than in openBIS
+ index1 = [ index1 for index1 in index1list if index1search == index1[:index1length] ]
+ try:
+ index1 = index1[0]
+ except:
+ print '\nOCCURRED EXCEPTION: First index \"' + index1search + '\" of Barcode in XML file has no corresponding DataSet in openBIS!'
+ index1 = 'MISSING'
+ if index2search == INDEX_EMPTY or index2search == INDEX_UNKNOWN:
+ index2 = INDEX_NO
+ else: # Hint: just one case was known about index2length, that is 8
+ if index2length > 7: # second and larger index must be reversed and complemented in contrast to first or smaller index
+ index2 = [ index2 for index2 in index2list if reversecomplement(index2search) == index2 ]
+ else: # second and smaller index is unknown how to handle
+ index2 = [ index2 for index2 in index2list if reversecomplement(index2search) == index2 ]
+ try:
+ index2 = index2[0]
+ except:
+ print '\nOCCURRED EXCEPTION: Second index \"' + index2search + '\" of Barcode in XML file has no corresponding DataSet in openBIS!'
+ index2 = 'MISSING'
+
+ # Get DataSet of openBIS corresponding to Project/Sample/Barcode of XML file:
+ correspondingDataSet = searchDataSetsOfSample(codeSampleFlowLane, index1, index2)
+ try:
+ assert correspondingDataSet.size() == 1
+ except AssertionError:
+ print ('\nOCCURRED EXCEPTION: ' + str(correspondingDataSet.size()) + ' DataSets found which Sample match the criteria index1 \"' + str(index1) + '\" and index2 \"' + str(index2) + '\" and code \"' + codeSampleFlowLane + '\" and type \"' + TYPE_DATASET + '\".')
+ continue
+
+ # Modify Properties of corresponding DataSet:
+ # (method setPropertyValue requires Strings as Input, but Number format must fit to Properties already defined in openBIS)
+ ds = transaction.getDataSetForUpdate(correspondingDataSet[0].getDataSetCode())
+ ds.setPropertyValue('YIELD_MBASES', str(int(s.Mega_PfYield)))
+ ds.setPropertyValue('RAW_YIELD_MBASES', str(int(s.Mega_RawYield)))
+ ds.setPropertyValue('PERCENTAGE_PASSED_FILTERING',str(s.Percentage_PfClusterCount_RawClusterCount))
+ ds.setPropertyValue('PF_READS_SUM',str(int(s.Sum_PfClusterCount))) # convert first to Integer, then to String
+ ds.setPropertyValue('RAW_READS_SUM',str(int(s.Sum_RawClusterCount))) # convert first to Integer, then to String
+ ds.setPropertyValue('PERCENTAGE_RAW_CLUSTERS_PER_LANE', str(s.Percentage_RawClusterCount_AllRawClusterCounts))
+ ds.setPropertyValue('PFYIELDQ30PERCENTAGE', str(s.Percentage_PfYieldQ30_PfYield))
+ ds.setPropertyValue('PFMEANQUALITYSCORE', str(s.Fraction_PfQualityScoreSum_PfYield))
+ print "Properties in DataSet \"" + correspondingDataSet[0].getDataSetCode() + "\" are modified."
+ nprocessedDataSets += 1
+
+ return nprocessedDataSets
+
+
+ ##########################################################
+
print('\nPROCESS RUNNING '+time.ctime())
incomingPath = transaction.getIncoming().getPath()
FileGenerator= locate(XML_FILENAME, incomingPath)
@@ -264,89 +340,24 @@ def process(transaction):
# Import data of XML file (independent of openBIS data):
JavaClassToProcessXML = read_demultiplex_stats() # this function is implemented as Class in Java:
- samplestatisticslist = JavaClassToProcessXML.importXMLdata_and_calculateStatistics(xmlfile)
+ samplestatisticslist = JavaClassToProcessXML.importXmlAndCalculateStatistics(xmlfile)
totalLaneStatistics = JavaClassToProcessXML.calculateTotalLaneStatistics(samplestatisticslist)
if len(samplestatisticslist) == 0:
print "\nNo Projects/Samples/Barcodes are contained in XML-file " + xmlfile + "!"
return
- # Prepare links between XML and openBIS w.r.t. Samples:
- codeSampleFlowCell = samplestatisticslist[0].Flowcell # expect just one equal FlowCell of all imported datasets
- codeSampleFlowLane = samplestatisticslist[0].Flowcell + ":1" # expect just one equal FlowLane of all imported datasets
+ print(samplestatisticslist[0].Flowcell)
+ codeSampleFlowCell = samplestatisticslist[0].Flowcell # expect just one equal FlowCell
+ flowcell, lanes, numberOfLanes = sampleSearch(transaction, codeSampleFlowCell)
- updateLane(transaction, codeSampleFlowCell, totalLaneStatistics)
-
- # Prepare links between XML and openBIS w.r.t to indexes in DataSet (openBIS):
- index1list, index2list = getIndexesOfDataSetsOfSample(codeSampleFlowLane)
- propertiesCode, propertiesCodeValue = getInfoSampleProperties(codeSampleFlowCell)
- index1length = int(propertiesCodeValue[CODE_INDEX1LENGTH])
- index2length = int(propertiesCodeValue[CODE_INDEX2LENGTH])
-
- nprocessedDataSets = 0
- for s in samplestatisticslist:
- print "\nContent in XML file:\n", s
- print "Connection to openBIS:"
-
- # Prepare link between XML and openBIS w.r.t to indexes in Barcode (XML):
- indexes = s.Barcode.split(BARCODE_SPLIT_CHAR)
- if len(indexes) == 1: # only first part in Barcode
- index1search = indexes[0].upper()
- index2search = INDEX_EMPTY
- elif len(indexes) == 2: # both parts in Barcode
- index1search = indexes[0].upper()
- index2search = indexes[1].upper()
- else:
- index1search = INDEX_EMPTY
- index2search = INDEX_EMPTY
-
- # Set link between XML and openBIS w.r.t to indexes in DataSet (openBIS):
- if index1search == INDEX_EMPTY or index1search == INDEX_UNKNOWN:
- index1 = INDEX_NO
- else: # Hint: just two cases were known about index1length, that is 8 or 6
- if index1length > 7:
- index1 = [ index1 for index1 in index1list if index1search == index1 ]
- else: # for smaller indexlength, the index is by 1 shorter in XML-file than in openBIS
- index1 = [ index1 for index1 in index1list if index1search == index1[:index1length] ]
- try:
- index1 = index1[0]
- except:
- print '\nOCCURRED EXCEPTION: First index \"' + index1search + '\" of Barcode in XML file has no corresponding DataSet in openBIS!'
- index1 = 'MISSING'
- if index2search == INDEX_EMPTY or index2search == INDEX_UNKNOWN:
- index2 = INDEX_NO
- else: # Hint: just one case was known about index2length, that is 8
- if index2length > 7: # second and larger index must be reversed and complemented in contrast to first or smaller index
- index2 = [ index2 for index2 in index2list if reversecomplement(index2search) == index2 ]
- else: # second and smaller index is unknown how to handle
- index2 = [ index2 for index2 in index2list if reversecomplement(index2search) == index2 ]
- try:
- index2 = index2[0]
- except:
- print '\nOCCURRED EXCEPTION: Second index \"' + index2search + '\" of Barcode in XML file has no corresponding DataSet in openBIS!'
- index2 = 'MISSING'
-
- # Get DataSet of openBIS corresponding to Project/Sample/Barcode of XML file:
- correspondingDataSet = searchDataSetsOfSample(codeSampleFlowLane, index1, index2)
- try:
- assert correspondingDataSet.size() == 1
- except AssertionError:
- print ('\nOCCURRED EXCEPTION: ' + str(correspondingDataSet.size()) + ' DataSets found which Sample match the criteria index1 \"' + str(index1) + '\" and index2 \"' + str(index2) + '\" and code \"' + codeSampleFlowLane + '\" and type \"' + TYPE_DATASET + '\".')
- continue
-
- # Modify Properties of corresponding DataSet:
- # (method setPropertyValue requires Strings as Input, but Number format must fit to Properties already defined in openBIS)
- ds = transaction.getDataSetForUpdate(correspondingDataSet[0].getDataSetCode())
- ds.setPropertyValue('YIELD_MBASES', str(int(s.Mega_PfYield)))
- ds.setPropertyValue('RAW_YIELD_MBASES', str(int(s.Mega_RawYield)))
- ds.setPropertyValue('PERCENTAGE_PASSED_FILTERING',str(s.Percentage_PfClusterCount_RawClusterCount))
- ds.setPropertyValue('PF_READS_SUM',str(int(s.Sum_PfClusterCount))) # convert first to Integer, then to String
- ds.setPropertyValue('RAW_READS_SUM',str(int(s.Sum_RawClusterCount))) # convert first to Integer, then to String
- ds.setPropertyValue('PERCENTAGE_RAW_CLUSTERS_PER_LANE', str(s.Percentage_RawClusterCount_AllRawClusterCounts))
- ds.setPropertyValue('PFYIELDQ30PERCENTAGE', str(s.Percentage_PfYieldQ30_PfYield))
- ds.setPropertyValue('PFMEANQUALITYSCORE', str(s.Fraction_PfQualityScoreSum_PfYield))
- print "Properties in DataSet \"" + correspondingDataSet[0].getDataSetCode() + "\" are modified."
- nprocessedDataSets += 1
+ for lane in lanes:
+ lane_in_int = int(lane.getCode().split(":")[-1])
+ if (lane_in_int in totalLaneStatistics.keySet()):
+ updateLane(transaction, codeSampleFlowCell, totalLaneStatistics)
+
+ codeSampleFlowLane = ":".join([codeSampleFlowCell, str(lane_in_int)])
+ nprocessedDataSets = update_datatsets(transaction, samplestatisticslist, codeSampleFlowLane, codeSampleFlowCell)
print "\n", nprocessedDataSets, " openBIS-DataSets were processed."
print len(samplestatisticslist), " XML-Projects/-Samples/-Barcodes were processed."
diff --git a/deep_sequencing_unit/sourceTest/core-plugins/illumina-qgf/1/dss/drop-boxes/read-demultiplex-stats-nextseq/read_demultiplex_stats.java b/deep_sequencing_unit/sourceTest/core-plugins/illumina-qgf/1/dss/drop-boxes/read-demultiplex-stats-nextseq/read_demultiplex_stats.java
index e10a38ce32f..385601962cd 100644
--- a/deep_sequencing_unit/sourceTest/core-plugins/illumina-qgf/1/dss/drop-boxes/read-demultiplex-stats-nextseq/read_demultiplex_stats.java
+++ b/deep_sequencing_unit/sourceTest/core-plugins/illumina-qgf/1/dss/drop-boxes/read-demultiplex-stats-nextseq/read_demultiplex_stats.java
@@ -25,29 +25,46 @@ limitations under the License.
- read_demultiplex_stats$Statistics.class
*/
-import java.io.FileInputStream;
-import java.io.FileNotFoundException;
-import java.io.InputStream;
-import java.util.ArrayList;
-import java.util.List;
import javax.xml.stream.XMLInputFactory;
import javax.xml.stream.XMLStreamConstants;
import javax.xml.stream.XMLStreamException;
import javax.xml.stream.XMLStreamReader;
+import java.io.FileInputStream;
+import java.io.FileNotFoundException;
+import java.io.InputStream;
+import java.util.ArrayList;
+import java.util.HashMap;
+import java.util.List;
+import java.util.Map;
//##########################################################
public final class read_demultiplex_stats
{
- public List<Statistics> importXMLdata_and_calculateStatistics(String XMLfile)
- {
+ public static ArrayList<Statistics> importXmlAndCalculateStatistics(String XMLFile) throws Exception {
+
+ ArrayList<Statistics> stats = executeImportXmlAndCalculateStatistics(XMLFile);
+ HashMap<Integer, ArrayList<Statistics>> groupedList = groupByLane(stats);
- ArrayList<Statistics> samplestatisticslist = new ArrayList<Statistics>();
+ for (Statistics s : stats)
+ s.adaptStatisticsWithRespectToAllSamples(stats, groupedList);
+ return stats;
+ }
+
+ /**
+ *
+ * Streams through a given XML file, parses the data and writes it into a Statistics object
+ *
+ * @param XMLfile: ConversionStats.xml
+ * @return a ArrayList of <Statistics>
+ */
+ private static ArrayList<Statistics> executeImportXmlAndCalculateStatistics(String XMLfile) throws Exception {
+ ArrayList<Statistics> sampleStatisticsList = new ArrayList<>();
/*Parse corresponding XML file, put all values into a memory structure, calculate statistics overall samples.
- Output: samplestatisticslist (list of Sample-Statistics-Objects)
+ Output: sampleStatisticsList (list of Sample-Statistics-Objects)
Input: XMLfile having structure of file ConversionStats.xml (Example of 1.10.2014):
<?xml version="1.0" encoding="utf-8"?> => Assumptions about XML structure:
<Stats> => Element is singlechild
@@ -86,70 +103,77 @@ public final class read_demultiplex_stats
</Tile>
<Tile number="11102">
[...]
- */
- try
- {
+ </Project>
+ <Lane number="2">
+ <TopUnknownBarcodes>
+ <Barcode count="150988002" sequence="NNNNNNN"/>
+ <Barcode count="167095" sequence="CCCCCCC"/>
+ <Barcode count="57859" sequence="CCCGTCC"/>
+ <Barcode count="49993" sequence="CCGATGT"/>
+ <Barcode count="42981" sequence="GTCCCGC"/>
+ <Barcode count="40446" sequence="TAAAATT"/>
+ <Barcode count="39962" sequence="CCAGATC"/>
+ <Barcode count="34688" sequence="GATGTAT"/>
+ <Barcode count="32013" sequence="AAAAAGT"/>
+ <Barcode count="30501" sequence="AGATCAT"/>
+ </TopUnknownBarcodes>
+ </Lane>
+ [...]
+ */
- // temporary variables (frequently changing during XML-read-in):
- String errormessage = "";
- int event = 0;
- int skip = 0;
- String curflowcellname = "";
- String curprojectname = "";
- String cursamplename = "";
- String curbarcodename = "";
- double curlanenumber = Double.NaN; // obvious double, but could be turned into int
- double curtilenumber = Double.NaN; // obvious double, but could be turned into int
- Sample cursample = null;
- Statistics curstatistics = null;
- SampleItem currawitem = null;
- SampleItem curpfitem = null;
-
- InputStream xmlfile = new FileInputStream(XMLfile);
- XMLInputFactory xmlfactory = XMLInputFactory.newInstance();
- XMLStreamReader xmlparser = xmlfactory.createXMLStreamReader(xmlfile);
+// Map<Integer, Map<String, Integer>> barcodesPerLane = null;
+
+ try {
+ String errorMessage;
+ int event;
+ int skip;
+ String flowcellName = "";
+ String projectName = "";
+ String sampleName = "";
+ String barcodeName = "";
+ int laneNumber = 0;
+ int tileNumber;
+ Sample currentSample = null;
+ Statistics statistics;
+ SampleItem rawItem;
+ SampleItem pfItem;
+ Map<String, Integer> barcodesMap = new HashMap<>();
+ Map<Integer, Map<String, Integer>> barcodesPerLane = new HashMap<>();
+
+ InputStream xmlFile = new FileInputStream(XMLfile);
+ XMLInputFactory xmlFactory = XMLInputFactory.newInstance();
+ XMLStreamReader xmlParser = xmlFactory.createXMLStreamReader(xmlFile);
// Start-Tag "Stats":
- event = xmlparser.nextTag(); // Assumption: just white space or comments are aside explicit start-tag
- if (event != XMLStreamConstants.START_ELEMENT || !xmlparser.getLocalName().equals("Stats"))
- {
- errormessage =
- "STRANGE ERROR IN METHOD importXMLdata_and_calculateStatistics WHEN READING IN XMLFILE. => CHECK CODE AND XMLFILE-STRUCTURE! Got " + event;
- throw new Exception(errormessage);
+ event = xmlParser.nextTag(); // Assumption: just white space or comments are aside explicit start-tag
+ if (event != XMLStreamConstants.START_ELEMENT || !xmlParser.getLocalName().equals("Stats")) {
+ errorMessage =
+ "STRANGE ERROR IN METHOD importXmlAndCalculateStatistics WHEN READING IN XMLFILE. => CHECK CODE AND XMLFILE-STRUCTURE! Got " + event;
+ throw new Exception(errorMessage);
}
- //System.out.println("\nStart-Element with tag " + xmlparser.getLocalName() + " with " + xmlparser.getAttributeCount() + " attributes with first attribute: " + xmlparser.getAttributeLocalName(0) +" = " + xmlparser.getAttributeValue(0));
// Loop over potential Tags "Flowcell":
- event = xmlparser.nextTag(); // Assumption: just white spaces or comments are aside start- or end-tag
+ event = xmlParser.nextTag(); // Assumption: just white spaces or comments are aside start- or end-tag
// List<Statistics> samplestatistics = new ArrayList<Statistics>();
boolean doimport = true;
- while (doimport)
- {
+ while (doimport) {
// concerning tag Flowcell:
- if (event == XMLStreamConstants.START_ELEMENT && xmlparser.getLocalName().equals("Flowcell"))
- {
- //System.out.println("\nStart-Element with tag " + xmlparser.getLocalName() + " with " + xmlparser.getAttributeCount() + " attributes with first attribute: " + xmlparser.getAttributeLocalName(0) +" = " + xmlparser.getAttributeValue(0));
- curflowcellname = xmlparser.getAttributeValue(0); // Assumption: Flowcell-attribute flowcell-id is just string
- event = xmlparser.nextTag();
- } else if (event == XMLStreamConstants.END_ELEMENT && xmlparser.getLocalName().equals("Flowcell"))
- {
- curflowcellname = "";
- event = xmlparser.nextTag();
+ if (event == XMLStreamConstants.START_ELEMENT && xmlParser.getLocalName().equals("Flowcell")) {
+ flowcellName = xmlParser.getAttributeValue(0);
+ event = xmlParser.nextTag();
+ } else if (event == XMLStreamConstants.END_ELEMENT && xmlParser.getLocalName().equals("Flowcell")) {
+ flowcellName = "";
+ event = xmlParser.nextTag();
// concerning tag Project:
- } else if (event == XMLStreamConstants.START_ELEMENT && xmlparser.getLocalName().equals("Project"))
- {
- //System.out.println("\nStart-Element with tag " + xmlparser.getLocalName() + " with " + xmlparser.getAttributeCount() + " attributes with first attribute: " + xmlparser.getAttributeLocalName(0) +" = " + xmlparser.getAttributeValue(0));
- if (xmlparser.getAttributeValue(0).equals("all"))
- {
- // skip the current XML element and all of its following subelements:
+ } else if (event == XMLStreamConstants.START_ELEMENT && xmlParser.getLocalName().equals("Project")) {
+ if (xmlParser.getAttributeValue(0).equals("all")) {
+ //skip the current XML element and all of its following subelements:
skip = 1;
- while (skip > 0)
- {
- event = xmlparser.next();
- switch (event)
- {
+ while (skip > 0) {
+ event = xmlParser.next();
+ switch (event) {
case XMLStreamConstants.END_ELEMENT:
skip -= 1;
break;
@@ -161,217 +185,239 @@ public final class read_demultiplex_stats
break;
}
}
- } else
- {
- curprojectname = xmlparser.getAttributeValue(0); // Assumption: Project-attribute name is just string
+ } else {
+ projectName = xmlParser.getAttributeValue(0);
+
}
- event = xmlparser.nextTag();
- } else if (event == XMLStreamConstants.END_ELEMENT && xmlparser.getLocalName().equals("Project"))
- {
- curprojectname = "";
- event = xmlparser.nextTag();
+ event = xmlParser.nextTag();
+ } else if (event == XMLStreamConstants.END_ELEMENT && xmlParser.getLocalName().equals("Project")) {
+ projectName = "";
+ event = xmlParser.nextTag();
// concerning tag Sample:
- } else if (event == XMLStreamConstants.START_ELEMENT && xmlparser.getLocalName().equals("Sample"))
- {
- //System.out.println("\nStart-Element with tag " + xmlparser.getLocalName() + " with " + xmlparser.getAttributeCount() + " attributes with first attribute: " + xmlparser.getAttributeLocalName(0) +" = " + xmlparser.getAttributeValue(0));
- if (xmlparser.getAttributeValue(0).equals("all"))
- {
+ } else if (event == XMLStreamConstants.START_ELEMENT && xmlParser.getLocalName().equals("Sample")) {
+ if (xmlParser.getAttributeValue(0).equals("all")) {
// skip the current XML element and all of its following subelements:
skip = 1;
- while (skip > 0)
- {
- event = xmlparser.next();
- switch (event)
- {
+ while (skip > 0) {
+ event = xmlParser.next();
+ switch (event) {
case XMLStreamConstants.END_ELEMENT:
skip -= 1;
- break; // break-command after each case is necessary in switch-statement
+ break;
case XMLStreamConstants.START_ELEMENT:
skip += 1;
- break; // break-command after each case is necessary in switch-statement
+ break;
default:
skip += 0; // text elements, spaces, ...
- break; // break-command after each case is necessary in switch-statement
+ break;
}
}
- } else
- {
- cursamplename = xmlparser.getAttributeValue(0); // Assumption: Sample-attribute name is just string
+ } else {
+ sampleName = xmlParser.getAttributeValue(0);
}
- event = xmlparser.nextTag();
- } else if (event == XMLStreamConstants.END_ELEMENT && xmlparser.getLocalName().equals("Sample"))
- {
- cursamplename = "";
- event = xmlparser.nextTag();
+ event = xmlParser.nextTag();
+ } else if (event == XMLStreamConstants.END_ELEMENT && xmlParser.getLocalName().equals("Sample")) {
+ sampleName = "";
+ event = xmlParser.nextTag();
// concerning tag Barcode (which is as well the start/end of Project-/Sample-Entry):
- } else if (event == XMLStreamConstants.START_ELEMENT && xmlparser.getLocalName().equals("Barcode"))
- {
- //System.out.println("\nStart-Element with tag " + xmlparser.getLocalName() + " with " + xmlparser.getAttributeCount() + " attributes with first attribute: " + xmlparser.getAttributeLocalName(0) +" = " + xmlparser.getAttributeValue(0));
- if (xmlparser.getAttributeValue(0).equals("all"))
- {
+ } else if (event == XMLStreamConstants.START_ELEMENT && xmlParser.getLocalName().equals("Barcode")) {
+ if (xmlParser.getAttributeValue(0).equals("all")) {
// skip the current XML element and all of its following subelements:
skip = 1;
- while (skip > 0)
- {
- event = xmlparser.next();
- switch (event)
- {
+ while (skip > 0) {
+ event = xmlParser.next();
+ switch (event) {
case XMLStreamConstants.END_ELEMENT:
skip -= 1;
- break; // break-command after each case is necessary in switch-statement
+ break;
case XMLStreamConstants.START_ELEMENT:
skip += 1;
- break; // break-command after each case is necessary in switch-statement
+ break;
default:
skip += 0; // text elements, spaces, ...
- break; // break-command after each case is necessary in switch-statement
+ break;
}
}
- } else
- {
- curbarcodename = xmlparser.getAttributeValue(0); // Assumption: Barcode-attribute name is just string
- cursample = new Sample();
- cursample.Flowcell = curflowcellname;
- cursample.Project = curprojectname;
- cursample.Sample = cursamplename;
- cursample.Barcode = curbarcodename;
+ } else {
+ barcodeName = xmlParser.getAttributeValue(0);
}
- event = xmlparser.nextTag();
- } else if (event == XMLStreamConstants.END_ELEMENT && xmlparser.getLocalName().equals("Barcode"))
- {
- // Statistics 1st step: calculate individual statistics per sample:
- curstatistics = new Statistics(cursample);
- samplestatisticslist.add(curstatistics);
- cursample = null;
- curstatistics = null;
- curbarcodename = "";
- event = xmlparser.nextTag();
+ event = xmlParser.nextTag();
+ } else if (event == XMLStreamConstants.END_ELEMENT && xmlParser.getLocalName().equals("Barcode")) {
+ barcodeName = "";
+ event = xmlParser.nextTag();
+
// concerning Lane:
- } else if (event == XMLStreamConstants.START_ELEMENT && xmlparser.getLocalName().equals("Lane"))
- {
- //System.out.println("\nStart-Element with tag " + xmlparser.getLocalName() + " with " + xmlparser.getAttributeCount() + " attributes with first attribute: " + xmlparser.getAttributeLocalName(0) +" = " + xmlparser.getAttributeValue(0));
- curlanenumber = Double.parseDouble(xmlparser.getAttributeValue(0)); // Assumption:Lane-attribute number is always numeric
- event = xmlparser.nextTag();
- } else if (event == XMLStreamConstants.END_ELEMENT && xmlparser.getLocalName().equals("Lane"))
- {
- curlanenumber = Double.NaN;
- event = xmlparser.nextTag();
+ } else if (event == XMLStreamConstants.START_ELEMENT && xmlParser.getLocalName().equals("Lane")) {
+// System.out.println("\nStart-Element with tag " + xmlparser.getLocalName() + " with " + xmlparser.getAttributeCount() + " attributes with first attribute: " + xmlparser.getAttributeLocalName(0) +" = " + xmlparser.getAttributeValue(0));
+ laneNumber = Integer.parseInt(xmlParser.getAttributeValue(0));
+
+ // Now we have everything we need, we put it into a Sample
+ currentSample = new Sample();
+
+ if (sampleName.startsWith("Undetermined")) {
+ currentSample.Sample = sampleName + "_" + flowcellName + "_" + laneNumber;
+ } else {
+ currentSample.Sample = sampleName;
+ }
+
+ currentSample.Flowcell = flowcellName;
+ currentSample.Lane = laneNumber;
+ currentSample.Project = projectName;
+ currentSample.Barcode = barcodeName;
+ event = xmlParser.nextTag();
+// System.out.println(currentSample.Sample);
+
+
+ } else if (event == XMLStreamConstants.END_ELEMENT && xmlParser.getLocalName().equals("Lane")) {
+ // Statistics 1st step: calculate individual statistics per sample:
+ statistics = new Statistics(currentSample);
+ if (!currentSample.Project.equals("")) {
+ sampleStatisticsList.add(statistics);
+ }
+ currentSample = null;
+ statistics = null;
+
+// laneNumber = Double.NaN;
+ event = xmlParser.nextTag();
// concerning Tile with all its sub-elements:
- } else if (event == XMLStreamConstants.START_ELEMENT && xmlparser.getLocalName().equals("Tile"))
- {
- //System.out.println("\nStart-Element with tag " + xmlparser.getLocalName() + " with " + xmlparser.getAttributeCount() + " attributes with first attribute: " + xmlparser.getAttributeLocalName(0) +" = " + xmlparser.getAttributeValue(0));
- curtilenumber = Double.parseDouble(xmlparser.getAttributeValue(0)); // Assumption: Tile-attribute number is always numeric
+ } else if (event == XMLStreamConstants.START_ELEMENT && xmlParser.getLocalName().equals("Tile")) {
+ tileNumber = Integer.parseInt(xmlParser.getAttributeValue(0));
// concerning Raw with Assumption: Raw-element is singlechild:
- xmlparser.nextTag();
- //System.out.println("\nStart-Element with tag " + xmlparser.getLocalName());
- currawitem = new SampleItem();
- currawitem.Type = "Raw";
- currawitem.Lane = curlanenumber;
- currawitem.Tile = curtilenumber;
- xmlparser.nextTag();
- currawitem.ClusterCount = Double.parseDouble(xmlparser.getElementText()); // Assumption: ClusterCount-element is numeric singlechild
- //System.out.println("\nValue: ClusterCount=" + currawitem.ClusterCount);
- xmlparser.nextTag();
- while (event == XMLStreamConstants.START_ELEMENT && xmlparser.getLocalName().equals("Read"))
- { // Assumption: at least or more than 1 Read-element
- //System.out.println("\nStart-Element with tag " + xmlparser.getLocalName() + " with " + xmlparser.getAttributeCount() + " attributes with first attribute: " + xmlparser.getAttributeLocalName(0) +" = " + xmlparser.getAttributeValue(0));
- xmlparser.nextTag();
- currawitem.YieldList.add(Double.parseDouble(xmlparser.getElementText())); // Assumption: Yield-element is numeric singlechild
- xmlparser.nextTag();
- currawitem.YieldQ30List.add(Double.parseDouble(xmlparser.getElementText())); // Assumption: YieldQ30List-element is numeric singlechild
- xmlparser.nextTag();
- currawitem.QualityScoreSumList.add(Double.parseDouble(xmlparser.getElementText())); // Assumption: QualityScoreSumList-element is numeric singlechild
- xmlparser.nextTag();
- xmlparser.nextTag();
- //System.out.println("Values in Read: Yield=" + currawitem.YieldList.get(currawitem.YieldList.size()-1) + ", YieldQ30=" + currawitem.YieldQ30List.get(currawitem.YieldQ30List.size()-1) + ", QualityScoreSum=" + currawitem.QualityScoreSumList.get(currawitem.QualityScoreSumList.size()-1));
+ xmlParser.nextTag();
+ rawItem = new SampleItem();
+ rawItem.Type = "Raw";
+ rawItem.Lane = laneNumber;
+ rawItem.Tile = tileNumber;
+ xmlParser.nextTag();
+ rawItem.ClusterCount = Integer.parseInt(xmlParser.getElementText()); // Assumption: ClusterCount-element is numeric singlechild
+ //System.out.println("\nValue: ClusterCount=" + rawItem.ClusterCount);
+ xmlParser.nextTag();
+ while (event == XMLStreamConstants.START_ELEMENT && xmlParser.getLocalName().equals("Read")) {
+ //System.out.println("\nStart-Element with tag " + xmlparser.getLocalName() + " with " + xmlparser.getAttributeCount() + " attributes with first attribute: " + xmlparser.getAttributeLocalName(0) +" = " + xmlparser.getAttributeValue(0));
+ xmlParser.nextTag();
+ rawItem.YieldList.add(Double.parseDouble(xmlParser.getElementText()));
+ xmlParser.nextTag();
+ rawItem.YieldQ30List.add(Double.parseDouble(xmlParser.getElementText()));
+ xmlParser.nextTag();
+ rawItem.QualityScoreSumList.add(Double.parseDouble(xmlParser.getElementText()));
+ xmlParser.nextTag();
+ xmlParser.nextTag();
+ //System.out.println("Values in Read: Yield=" + rawItem.YieldList.get(rawItem.YieldList.size()-1) + ", YieldQ30=" + rawItem.YieldQ30List.get(rawItem.YieldQ30List.size()-1) + ", QualityScoreSum=" + rawItem.QualityScoreSumList.get(rawItem.QualityScoreSumList.size()-1));
}
- //System.out.println("\nRaw-SampleItem " + currawitem);
- cursample.RawList.add(currawitem);
- currawitem = null;
+ //System.out.println("\nRaw-SampleItem " + rawItem);
+ currentSample.RawList.add(rawItem);
+
+
+ rawItem = null;
// concerning Pf with Assumption that entire Pf-element is structured same as Raw:
- xmlparser.nextTag();
+ xmlParser.nextTag();
//System.out.println("\nStart-Element with tag " + xmlparser.getLocalName());
- curpfitem = new SampleItem();
- curpfitem.Type = "Pf";
- curpfitem.Lane = curlanenumber;
- curpfitem.Tile = curtilenumber;
- xmlparser.nextTag();
- curpfitem.ClusterCount = Double.parseDouble(xmlparser.getElementText());
- //System.out.println("\nValue: ClusterCount=" + curpfitem.ClusterCount);
- xmlparser.nextTag();
- while (event == XMLStreamConstants.START_ELEMENT && xmlparser.getLocalName().equals("Read"))
- {
+ pfItem = new SampleItem();
+ pfItem.Type = "Pf";
+ pfItem.Lane = laneNumber;
+ pfItem.Tile = tileNumber;
+ xmlParser.nextTag();
+ pfItem.ClusterCount = Integer.parseInt(xmlParser.getElementText());
+ //System.out.println("\nValue: ClusterCount=" + pfItem.ClusterCount);
+ xmlParser.nextTag();
+ while (event == XMLStreamConstants.START_ELEMENT && xmlParser.getLocalName().equals("Read")) {
//System.out.println("\nStart-Element with tag " + xmlparser.getLocalName() + " with " + xmlparser.getAttributeCount() + " attributes with first attribute: " + xmlparser.getAttributeLocalName(0) +" = " + xmlparser.getAttributeValue(0));
- xmlparser.nextTag();
- curpfitem.YieldList.add(Double.parseDouble(xmlparser.getElementText()));
- xmlparser.nextTag();
- curpfitem.YieldQ30List.add(Double.parseDouble(xmlparser.getElementText()));
- xmlparser.nextTag();
- curpfitem.QualityScoreSumList.add(Double.parseDouble(xmlparser.getElementText()));
- xmlparser.nextTag();
- xmlparser.nextTag();
- //System.out.println("Values in Read: Yield=" + curpfitem.YieldList.get(curpfitem.YieldList.size()-1) + ", YieldQ30=" + curpfitem.YieldQ30List.get(curpfitem.YieldQ30List.size()-1) + ", QualityScoreSum=" + curpfitem.QualityScoreSumList.get(curpfitem.QualityScoreSumList.size()-1));
+ xmlParser.nextTag();
+ pfItem.YieldList.add(Double.parseDouble(xmlParser.getElementText()));
+ xmlParser.nextTag();
+ pfItem.YieldQ30List.add(Double.parseDouble(xmlParser.getElementText()));
+ xmlParser.nextTag();
+ pfItem.QualityScoreSumList.add(Double.parseDouble(xmlParser.getElementText()));
+ xmlParser.nextTag();
+ xmlParser.nextTag();
+ //System.out.println("Values in Read: Yield=" + pfItem.YieldList.get(pfItem.YieldList.size()-1) + ", YieldQ30=" + pfItem.YieldQ30List.get(pfItem.YieldQ30List.size()-1) + ", QualityScoreSum=" + pfItem.QualityScoreSumList.get(pfItem.QualityScoreSumList.size()-1));
}
- //System.out.println("\nPf-SampleItem " + curpfitem);
- cursample.PfList.add(curpfitem);
- curpfitem = null;
+ //System.out.println("\nPf-SampleItem " + pfItem);
+ currentSample.PfList.add(pfItem);
+ pfItem = null;
// attain end of current Tile and afterwards continue in next Tile/Lane/Barcode/Sample/Project:
- event = xmlparser.nextTag();
- } else if (event == XMLStreamConstants.END_ELEMENT && xmlparser.getLocalName().equals("Tile"))
- {
- curtilenumber = Double.NaN;
- event = xmlparser.nextTag();
+ event = xmlParser.nextTag();
+ } else if (event == XMLStreamConstants.END_ELEMENT && xmlParser.getLocalName().equals("Tile")) {
+ tileNumber = 0;
+ event = xmlParser.nextTag();
+
+
+ } else if (event == XMLStreamConstants.START_ELEMENT && xmlParser.getLocalName().equals("TopUnknownBarcodes")) {
+
+ event = xmlParser.nextTag();
+ while (event == XMLStreamConstants.START_ELEMENT && xmlParser.getLocalName().equals("Barcode")) {
+ Integer numberOfBarcodes = Integer.valueOf((xmlParser.getAttributeValue(0)));
+ String barcode = xmlParser.getAttributeValue(1);
+ barcodesMap.put(barcode, numberOfBarcodes);
+ xmlParser.nextTag();
+ event = xmlParser.nextTag();
+ }
+
+ } else if (event == XMLStreamConstants.END_ELEMENT && xmlParser.getLocalName().equals("TopUnknownBarcodes")) {
+
+ barcodesPerLane.put(laneNumber, barcodesMap);
+ event = xmlParser.nextTag();
// concerning finish of reading in XML or hit upon error due XML content:
- } else if (event == XMLStreamConstants.END_ELEMENT && xmlparser.getLocalName().equals("Stats"))
- {
+ } else if (event == XMLStreamConstants.END_ELEMENT && xmlParser.getLocalName().equals("Stats")) {
// this final part of while loop is just for analyzing potential errors, but
// could be removed and changed in: while xmlparser.getLocalName() != 'Stats'
doimport = false;
- } else
- {
+ } else {
doimport = false;
System.out.println("Warning: Different XML structure than expectet. Got event: " + event);
}
}
- xmlparser.close();
+ xmlParser.close();
- } catch (FileNotFoundException | XMLStreamException e)
- {
+ } catch (FileNotFoundException | XMLStreamException | IllegalArgumentException e) {
System.out.println("OCCURRED EXCEPTION " + e.toString());
e.printStackTrace();
- } catch (IllegalArgumentException e)
- {
- System.out.println("OCCURRED EXCEPTION " + e.toString());
- e.printStackTrace();
- } catch (Exception e)
- { // catch any other exception
- System.out.println("OCCURRED EXCEPTION " + e.toString());
- e.printStackTrace();
- } finally
- { // anyway adapt statistics and return output (It would be empty list due to constructor of this object)
- // Statistics 2nd step: adapt single sample's statistics including entire list of samples
- for (Statistics s : samplestatisticslist)
- s.adaptStatisticsWithRespectToAllSamples(samplestatisticslist);
}
- return samplestatisticslist;
-
+ return sampleStatisticsList;
}
- public LaneStatistics calculateTotalLaneStatistics(ArrayList<Statistics> samplestatisticslist)
+ public static HashMap<Integer, LaneStatistics> calculateTotalLaneStatistics(ArrayList<Statistics> samplestatisticslist)
{
- LaneStatistics laneStats = new LaneStatistics(samplestatisticslist);
- laneStats.calculateOverallStats();
- return laneStats;
+ HashMap<Integer, LaneStatistics> listOfLaneStatistics= new HashMap<Integer, LaneStatistics>();
+
+ HashMap<Integer, ArrayList<Statistics>> groupedList = groupByLane(samplestatisticslist);
+
+ for (Integer key : groupedList.keySet()) {
+
+ LaneStatistics laneStats = new LaneStatistics(groupedList.get(key));
+ laneStats.calculateOverallStats(key);
+ listOfLaneStatistics.put(key, laneStats);
+ }
+ return listOfLaneStatistics;
}
+
+ private static HashMap<Integer, ArrayList<Statistics>> groupByLane(ArrayList<Statistics> samplestatisticslist) {
+ // Group ArrayList by Lane
+ HashMap<Integer, ArrayList<Statistics>> groupedList = new HashMap <Integer, ArrayList<Statistics>>();
+ for (Statistics s : samplestatisticslist) {
+
+ if (groupedList.containsKey(s.Lane)) {
+ groupedList.get(s.Lane).add(s);
+ }
+ else {
+ ArrayList <Statistics> newEntry = new ArrayList<Statistics>();
+ newEntry.add(s);
+ groupedList.put(s.Lane, newEntry);
+ }
+ }
+ return groupedList;
+ }
+
+
// ##########################################################
- public class SampleItem
+ private static class SampleItem
{
/*
* Object of an item in sample including - the corresponding type Raw or Pf - the index of corresponding Lane, Tile - measured value of
@@ -380,20 +426,19 @@ public final class read_demultiplex_stats
public String Type = "";
- // Define unknown numerical value. Type double could be exchanged with int, but double is necessary to initialize NaN-value.
- public double Lane = Double.NaN;
+ public Integer Lane = 0;
- public double Tile = Double.NaN;
+ public Integer Tile = 0;
- public double ClusterCount = Double.NaN;
+ public Integer ClusterCount = 0;
// Define unknown ArrayList of numerical values with changeable List size. Type Double(object) instead of double(primitive) is necessary in
// Lists.
- public List<Double> YieldList = new ArrayList<Double>();
+ public List<Double> YieldList = new ArrayList<>();
- public List<Double> YieldQ30List = new ArrayList<Double>();
+ public List<Double> YieldQ30List = new ArrayList<>();
- public List<Double> QualityScoreSumList = new ArrayList<Double>();
+ public List<Double> QualityScoreSumList = new ArrayList<>();
public String toString()
{
@@ -406,13 +451,15 @@ public final class read_demultiplex_stats
// ##########################################################
- public class Sample
+ public static class Sample
{
/*
* Object of an entire sample including - the name of Flowcell, Project, Sample, Barcode - the list of Raw and Pf SampleItem-Objects
*/
public String Flowcell = "";
+
+ public Integer Lane = 0;
public String Project = "";
@@ -421,13 +468,13 @@ public final class read_demultiplex_stats
public String Barcode = "";
// Define unknown ArrayList of SampleItems:
- public List<SampleItem> RawList = new ArrayList<SampleItem>();
+ public List<SampleItem> RawList = new ArrayList<>();
- public List<SampleItem> PfList = new ArrayList<SampleItem>();
+ public List<SampleItem> PfList = new ArrayList<>();
public String toString()
{
- return "Flowcell: " + this.Flowcell + ", Project: " + this.Project + ", Sample: " + this.Sample + ", Barcode: " + this.Barcode
+ return "Flowcell: " + this.Flowcell + ", Lane: " + this.Lane + ", Project: " + this.Project + ", Sample: " + this.Sample + ", Barcode: " + this.Barcode
+ ", RawList: " + this.RawList + ", PfList: " + this.PfList;
}
@@ -435,15 +482,15 @@ public final class read_demultiplex_stats
// ##########################################################
- public class Statistics extends Sample
+ public static class Statistics extends Sample
{
/*
* Object of Statistics within one single sample inherited from Sample-Object
*/
- public double Sum_RawClusterCount = Double.NaN; // obvious double, but could be turned into int
+ public Integer Sum_RawClusterCount = 0;
- public double Sum_PfClusterCount = Double.NaN; // obvious double, but could be turned into int
+ public Integer Sum_PfClusterCount = 0;
public double Sum_RawYield = Double.NaN;
@@ -479,6 +526,7 @@ public final class read_demultiplex_stats
super();
Flowcell = sample.Flowcell;
+ Lane = sample.Lane;
Project = sample.Project;
Sample = sample.Sample;
Barcode = sample.Barcode;
@@ -539,17 +587,17 @@ public final class read_demultiplex_stats
public String toString()
{
- return "Flowcell: " + this.Flowcell + ", Project: " + this.Project + ", Sample: " + this.Sample + ", Barcode: " + this.Barcode
+ return "Flowcell: " + this.Flowcell + ", Lane: "+ this.Lane + ", Project: " + this.Project + ", Sample: " + this.Sample + ", Barcode: " + this.Barcode
+ ", Raw Clusters: " + (long) this.Sum_RawClusterCount + ", Mbases Raw Yield: " + this.Mega_RawYield
+ ", % Raw Clusters overall: " + this.Percentage_RawClusterCount_AllRawClusterCounts
+ ", Pf Clusters: " + (long) this.Sum_PfClusterCount + ", Mbases Pf Yield: " + this.Mega_PfYield
+ ", % PfYield/RawYield: " + this.Percentage_PfYield_RawYield
+ ", % PfYieldQ30/PfYield: " + this.Percentage_PfYieldQ30_PfYield
+ ", Mean Pf Quality Score: " + this.Fraction_PfQualityScoreSum_PfYield
- + ", % Passes Filtering: " + this.Percentage_PfClusterCount_RawClusterCount;
+ + ", % Passes Filtering: " + this.Percentage_PfClusterCount_RawClusterCount + "\n";
}
- public void adaptStatisticsWithRespectToAllSamples(List<Statistics> statisticslist)
+ public void adaptStatisticsWithRespectToAllSamples(ArrayList<Statistics> statisticslist, HashMap<Integer, ArrayList<Statistics>> groupedList)
{
/*
* This Statistics-Object (corresponding to one sample) is adapted by employing a list of Statistics-Objects corresponding to all samples
@@ -559,34 +607,25 @@ public final class read_demultiplex_stats
{ // here it additionally should be checked, if calling object is included ...
Percentage_RawClusterCount_AllRawClusterCounts = Double.NaN;
String errormessage =
- "INPUT ARGUMENT statisticslist MUST BE LIST OF Statistics OBJECTS INCLUDING THE CALLING OBJECT IN METHOD adaptStatisticsWithRespectToAllSamples!";
- // System.out.println(errormessage);
+ "INPUT ARGUMENT statisticslist MUST BE LIST OF Statistics OBJECTS INCLUDING THE CALLING OBJECT" +
+ " IN METHOD adaptStatisticsWithRespectToAllSamples!";
throw new IllegalArgumentException(errormessage); // Exception reasonable since otherwise wrong results.
} else
{
- double sum_allrawclustercounts = 0;
- for (Statistics s : statisticslist)
- sum_allrawclustercounts += s.Sum_RawClusterCount;
- Percentage_RawClusterCount_AllRawClusterCounts = calculate_Percentage(Sum_RawClusterCount, sum_allrawclustercounts);
+ for (Integer key : groupedList.keySet()) {
+ double sumAllRawClusterCounts = 0;
+ ArrayList<Statistics> groupList = groupedList.get(key);
+ for (Statistics element : groupList) {
+ sumAllRawClusterCounts += element.Sum_RawClusterCount;
+ }
+ for (Statistics element : groupList) {
+ element.Percentage_RawClusterCount_AllRawClusterCounts =
+ calculate_Percentage(element.Sum_RawClusterCount, sumAllRawClusterCounts);
+ }
+ }
}
}
- public double calculate_MegaUnit(double x)
- {
- double z;
- if (x == Double.POSITIVE_INFINITY || x == Double.NEGATIVE_INFINITY || Double.isNaN(x))
- {
- z = Double.NaN;
- String errormessage =
- "INPUT ARGUMENT WAS UNREASONABLE IN METHOD calculate_MegaUnit! x = " + x + " (Values were in Sample " + Sample + ")";
- // System.out.println(errormessage);
- // throw new IllegalArgumentException(errormessage);
- } else
- {
- z = x / 1000000;
- }
- return z;
- }
public double calculate_Percentage(double x, double y)
{
@@ -594,11 +633,6 @@ public final class read_demultiplex_stats
if (z == Double.POSITIVE_INFINITY || z == Double.NEGATIVE_INFINITY || Double.isNaN(z))
{
z = Double.NaN;
- String errormessage =
- "INPUT ARGUMENT WAS UNREASONABLE IN METHOD calculate_Percentage! x = " + x + ", y = " + y + " (Values were in Sample "
- + Sample + ")";
- // System.out.println(errormessage);
- // throw new IllegalArgumentException(errormessage);
} else
{
z = 100 * z;
@@ -612,47 +646,23 @@ public final class read_demultiplex_stats
if (z == Double.POSITIVE_INFINITY || z == Double.NEGATIVE_INFINITY || Double.isNaN(z))
{
z = Double.NaN;
- String errormessage =
- "INPUT ARGUMENT WAS UNREASONABLE IN METHOD calculate_Fraction! x = " + x + ", y = " + y + " (Values were in Sample "
- + Sample + ")";
- // System.out.println(errormessage);
- // throw new IllegalArgumentException(errormessage);
- }
- return z;
- }
-
- public double roundspecific(double x, int places)
- {
- double z;
- if (places < 0 || places > 13 || x == Double.POSITIVE_INFINITY || x == Double.NEGATIVE_INFINITY || Double.isNaN(x))
- {
- z = Double.NaN;
- String errormessage =
- "INPUT ARGUMENT WAS UNREASONABLE IN METHOD roundspecific! x = " + x + ", places = " + places + " (Values were in Sample "
- + Sample + ")";
- // System.out.println(errormessage);
- // throw new IllegalArgumentException(errormessage);
- } else
- {
- double factor = Math.pow(10, places);
- z = Math.round(x * factor);
- z = z / factor;
}
return z;
}
-
}
- public class LaneStatistics
+ public static class LaneStatistics
{
/*
* Total Lane Statistics
*/
public ArrayList<Statistics> statisticsList;
+ public Integer Lane = 0;
+
public double Sum_RawClusterCount = 0.0;
- public double Sum_PfClusterCount = 0.0;
+ public Integer Sum_PfClusterCount = 0;
public double Sum_RawYield = 0.0;
@@ -683,18 +693,12 @@ public final class read_demultiplex_stats
this.statisticsList = statisticsList;
}
- public void calculateOverallStats()
+ public void calculateOverallStats(Integer key)
{
-
int sampleNumber = statisticsList.size();
-
- for (Statistics s : statisticsList)
- {
- if (!s.Barcode.equals("unknown"))
- {
- System.out.println("BARCODE " + s.Barcode);
+ for (Statistics s : statisticsList) {
+ if (!s.Barcode.equals("") || s.Barcode.equals("unknown")) {
this.Clusters_PfWithoutNoindex += s.Sum_PfClusterCount;
- System.out.println(s.Sum_PfClusterCount);
}
this.Sum_RawClusterCount += s.Sum_RawClusterCount;
@@ -706,10 +710,14 @@ public final class read_demultiplex_stats
this.Sum_RawQualityScoreSum += s.Sum_RawQualityScoreSum;
this.Sum_PfQualityScoreSum += s.Sum_PfQualityScoreSum;
this.Percentage_PfYield_RawYield += s.Percentage_PfYield_RawYield;
- this.Percentage_PfYieldQ30_PfYield += s.Percentage_PfYieldQ30_PfYield;
+ if (!Double.isNaN(s.Percentage_PfYieldQ30_PfYield)) {
+ this.Percentage_PfYieldQ30_PfYield += s.Percentage_PfYieldQ30_PfYield;
+ }
this.Percentage_PfClusterCount_RawClusterCount += s.Percentage_PfClusterCount_RawClusterCount;
this.Fraction_PfQualityScoreSum_PfYield += s.Fraction_PfQualityScoreSum_PfYield;
}
+
+ this.Lane = key;
this.Sum_RawQualityScoreSum = this.Sum_RawQualityScoreSum / sampleNumber;
this.Sum_PfQualityScoreSum = this.Sum_PfQualityScoreSum / sampleNumber;
this.Percentage_PfYield_RawYield = this.Percentage_PfYield_RawYield / sampleNumber;
@@ -720,8 +728,9 @@ public final class read_demultiplex_stats
public String toString()
{
- return "Sum_RawClusterCount " + this.Sum_RawClusterCount + " Sum_PfClusterCount" + this.Sum_PfClusterCount +
- " Percentage_PfYieldQ30_PfYield " + this.Percentage_PfYieldQ30_PfYield;
+ return "Lane " + this.Lane + " Sum_RawClusterCount " + this.Sum_RawClusterCount + " Sum_PfClusterCount " + this.Sum_PfClusterCount +
+ " Percentage_PfYieldQ30_PfYield " + this.Percentage_PfYieldQ30_PfYield +
+ " Percentage_PfClusterCount_RawClusterCount " + this.Percentage_PfClusterCount_RawClusterCount;
}
}
}
\ No newline at end of file
--
GitLab