efischer/BiGpairSEQ
1
0
Fork 0
Code Issues Pull Requests Projects Releases 13 Wiki Activity

Hand-merge of some things from Dev_Vertex branch that didn't make it in for some reason

Browse Source
This commit is contained in:
eugenefischer
2022-09-25 19:07:25 -05:00
parent 16daf02dd6
commit d1a56c3578
5 changed files with 57 additions and 40 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
readme.md
View File

@@ -347,9 +347,9 @@ roughly as though it had a constant well population equal to the plate's average
* ~~Apache Commons CSV library writes entries a row at a time~~
* _Got this working, but at the cost of a profoundly strange bug in graph occupancy filtering. Have reverted the repo until I can figure out what caused that. Given how easily Thingiverse transposes CSV matrices in R, might not even be worth fixing.
* ~~Enable GraphML output in addition to serialized object binaries, for data portability~~ DONE
* ~~Custom vertex type with attribute for sequence occupancy?~~ ABANDONED
* ~~Custom vertex type with attribute for sequence occupancy?~~ DONE
* Advantage: would eliminate the need to use maps to associate vertices with sequences, which would make the code easier to understand.
* Have a branch where this is implemented, but there's a bug that broke matching. Don't currently have time to fix.
* ~~Have a branch where this is implemented, but there's a bug that broke matching. Don't currently have time to fix.~~
* ~~Re-implement command line arguments, to enable scripting and statistical simulation studies~~ DONE
* ~~Implement custom Vertex class to simplify code and make it easier to implement different MWM algorithms~~ DONE
* This also seems to be faster when using the same algorithm than the version with lots of maps, which is a nice bonus!

2
src/main/java/BiGpairSEQ.java
View File

@@ -16,7 +16,7 @@ public class BiGpairSEQ {
private static HeapType priorityQueueHeapType = HeapType.FIBONACCI;
private static boolean outputBinary = true;
private static boolean outputGraphML = false;
private static final String version = "version 2.0";
private static final String version = "version 3.0";
public static void main(String[] args) {
if (args.length == 0) {

79
src/main/java/GraphMLFileWriter.java
View File

@@ -3,8 +3,9 @@ import org.jgrapht.graph.SimpleWeightedGraph;
import org.jgrapht.nio.Attribute;
import org.jgrapht.nio.AttributeType;
import org.jgrapht.nio.DefaultAttribute;
import org.jgrapht.nio.dot.DOTExporter;
import org.jgrapht.nio.graphml.GraphMLExporter;
import org.jgrapht.nio.graphml.GraphMLExporter.AttributeCategory;
import org.w3c.dom.Attr;
import java.io.BufferedWriter;
import java.io.IOException;
@@ -12,14 +13,14 @@ import java.nio.file.Files;
import java.nio.file.Path;
import java.nio.file.StandardOpenOption;
import java.util.HashMap;
import java.util.LinkedHashMap;
import java.util.Map;
public class GraphMLFileWriter {
String filename;
SimpleWeightedGraph graph;
GraphWithMapData data;
Map<String, Attribute> graphAttributes;
public GraphMLFileWriter(String filename, GraphWithMapData data) {
if(!filename.matches(".*\\.graphml")){
@@ -27,52 +28,61 @@ public class GraphMLFileWriter {
}
this.filename = filename;
this.data = data;
this.graph = data.getGraph();
graphAttributes = createGraphAttributes();
}
// public void writeGraphToFile() {
// try(BufferedWriter writer = Files.newBufferedWriter(Path.of(filename), StandardOpenOption.CREATE_NEW);
// ){
// GraphMLExporter<SimpleWeightedGraph, BufferedWriter> exporter = new GraphMLExporter<>();
// exporter.exportGraph(graph, writer);
// } catch(IOException ex){
// System.out.println("Could not make new file named "+filename);
// System.err.println(ex);
// }
// }
public GraphMLFileWriter(String filename, SimpleWeightedGraph<Vertex, DefaultWeightedEdge> graph) {
if(!filename.matches(".*\\.graphml")){
filename = filename + ".graphml";
}
this.filename = filename;
this.graph = graph;
}
private Map<String, Attribute> createGraphAttributes(){
Map<String, Attribute> ga = new HashMap<>();
//Sample plate filename
ga.put("sample plate filename", DefaultAttribute.createAttribute(data.getSourceFilename()));
// Number of wells
ga.put("well count", DefaultAttribute.createAttribute(data.getNumWells().toString()));
//Well populations
Integer[] wellPopulations = data.getWellPopulations();
StringBuilder populationsStringBuilder = new StringBuilder();
populationsStringBuilder.append(wellPopulations[0].toString());
for(int i = 1; i < wellPopulations.length; i++){
populationsStringBuilder.append(", ");
populationsStringBuilder.append(wellPopulations[i].toString());
}
String wellPopulationsString = populationsStringBuilder.toString();
ga.put("well populations", DefaultAttribute.createAttribute(wellPopulationsString));
return ga;
}
public void writeGraphToFile() {
SimpleWeightedGraph graph = data.getGraph();
Map<Integer, Integer> vertexToAlphaMap = data.getPlateVtoAMap();
Map<Integer, Integer> vertexToBetaMap = data.getPlateVtoBMap();
Map<Integer, Integer> alphaOccs = data.getAlphaWellCounts();
Map<Integer, Integer> betaOccs = data.getBetaWellCounts();
try(BufferedWriter writer = Files.newBufferedWriter(Path.of(filename), StandardOpenOption.CREATE_NEW);
){
//create exporter. Let the vertex labels be the unique ids for the vertices
GraphMLExporter<Integer, SimpleWeightedGraph<Vertex, DefaultWeightedEdge>> exporter = new GraphMLExporter<>(v -> v.toString());
GraphMLExporter<Vertex, SimpleWeightedGraph<Vertex, DefaultWeightedEdge>> exporter = new GraphMLExporter<>(v -> v.getVertexLabel().toString());
//set to export weights
exporter.setExportEdgeWeights(true);
//Set graph attributes
exporter.setGraphAttributeProvider( () -> graphAttributes);
//set type, sequence, and occupancy attributes for each vertex
exporter.setVertexAttributeProvider( v -> {
Map<String, Attribute> attributes = new HashMap<>();
if(vertexToAlphaMap.containsKey(v)) {
attributes.put("type", DefaultAttribute.createAttribute("CDR3 Alpha"));
attributes.put("sequence", DefaultAttribute.createAttribute(vertexToAlphaMap.get(v)));
attributes.put("occupancy", DefaultAttribute.createAttribute(
alphaOccs.get(vertexToAlphaMap.get(v))));
}
else if(vertexToBetaMap.containsKey(v)) {
attributes.put("type", DefaultAttribute.createAttribute("CDR3 Beta"));
attributes.put("sequence", DefaultAttribute.createAttribute(vertexToBetaMap.get(v)));
attributes.put("occupancy", DefaultAttribute.createAttribute(
betaOccs.get(vertexToBetaMap.get(v))));
}
attributes.put("type", DefaultAttribute.createAttribute(v.getType().name()));
attributes.put("sequence", DefaultAttribute.createAttribute(v.getSequence()));
attributes.put("occupancy", DefaultAttribute.createAttribute(v.getOccupancy()));
return attributes;
});
//register the attributes
exporter.registerAttribute("type", GraphMLExporter.AttributeCategory.NODE, AttributeType.STRING);
exporter.registerAttribute("sequence", GraphMLExporter.AttributeCategory.NODE, AttributeType.STRING);
exporter.registerAttribute("occupancy", GraphMLExporter.AttributeCategory.NODE, AttributeType.STRING);
for(String s : graphAttributes.keySet()) {
exporter.registerAttribute(s, AttributeCategory.GRAPH, AttributeType.STRING);
}
exporter.registerAttribute("type", AttributeCategory.NODE, AttributeType.STRING);
exporter.registerAttribute("sequence", AttributeCategory.NODE, AttributeType.STRING);
exporter.registerAttribute("occupancy", AttributeCategory.NODE, AttributeType.STRING);
//export the graph
exporter.exportGraph(graph, writer);
} catch(IOException ex){
@@ -81,4 +91,3 @@ public class GraphMLFileWriter {
}
}
}

4
src/main/java/InteractiveInterface.java
View File

@@ -258,7 +258,7 @@ public class InteractiveInterface {
cellFile = sc.next();
System.out.print("\nPlease enter name of an existing sample plate file: ");
plateFile = sc.next();
System.out.println("\nThe graph and occupancy data will be written to a serialized binary file.");
System.out.println("\nThe graph and occupancy data will be written to a file.");
System.out.print("Please enter a name for the output file: ");
filename = sc.next();
} catch (InputMismatchException ex) {
@@ -504,7 +504,7 @@ public class InteractiveInterface {
System.out.println("2) Turn " + getOnOff(!BiGpairSEQ.cachePlate()) + " plate file caching");
System.out.println("3) Turn " + getOnOff(!BiGpairSEQ.cacheGraph()) + " graph/data file caching");
System.out.println("4) Turn " + getOnOff(!BiGpairSEQ.outputBinary()) + " serialized binary graph output");
System.out.println("5) Turn " + getOnOff(!BiGpairSEQ.outputGraphML()) + " GraphML graph output");
System.out.println("5) Turn " + getOnOff(!BiGpairSEQ.outputGraphML()) + " GraphML graph output (for data portability to other programs)");
System.out.println("6) Maximum weight matching algorithm options");
System.out.println("0) Return to main menu");
try {

8
src/main/java/SequenceType.java Normal file
View File

@@ -0,0 +1,8 @@
//enum for tagging types of sequences
//Listed in order that they appear in a cell array, so ordinal() method will return correct index
public enum SequenceType {
CDR3_ALPHA,
CDR3_BETA,
CDR1_ALPHA,
CDR1_BETA
}