5 Commits

3 changed files with 146 additions and 55 deletions

View File

@@ -58,13 +58,14 @@ main menu looks like this:
```
--------BiGPairSEQ SIMULATOR--------
ALPHA/BETA T CELL RECEPTOR MATCHING
USING WEIGHTED BIPARTITE GRAPHS
USING WEIGHTED BIPARTITE GRAPHS
------------------------------------
Please select an option:
1) Generate a population of distinct cells
2) Generate a sample plate of T cells
3) Generate CDR3 alpha/beta occupancy data and overlap graph
4) Simulate bipartite graph CDR3 alpha/beta matching (BiGpairSEQ)
8) Options
9) About/Acknowledgments
0) Exit
```
@@ -77,18 +78,20 @@ To run the simulation, the program reads and writes 4 kinds of files:
* Graph/Data files in binary object serialization format
* Matching Results files in CSV format
These files are often generated in sequence. To save file I/O time, the most recent instance of each of these four
files either generated or read from disk is cached in program memory. This is especially important for Graph/Data files,
These files are often generated in sequence. When entering filenames, it is not necessary to include the file extension
(.csv or .ser). When reading or writing files, the program will automatically add the correct extension to any filename without one.
To save file I/O time, the most recent instance of each of these four
files either generated or read from disk can be cached in program memory. This is especially important for Graph/Data files,
which can be several gigabytes in size. Since some simulations may require running multiple,
differntly-configured BiGpairSEQ matchings on the same graph, keeping the most recent graph cached drastically reduces
execution time.
differently-configured BiGpairSEQ matchings on the same graph, keeping the most recent graph cached can reduce execution time
Subsequent uses of the same data file won't need to be read in again until another file of that type is used or generated.
The program checks whether it needs to update its cached data by comparing filenames as entered by the user. On
encountering a new filename, the program flushes its cache and reads in the new file.
Subsequent uses of the same data file won't need to be read in again until another file of that type is used or generated,
or caching is turned off for that file type. The program checks whether it needs to update its cached data by comparing
filenames as entered by the user. On encountering a new filename, the program flushes its cache and reads in the new file.
When entering filenames, it is not necessary to include the file extension (.csv or .ser). When reading or
writing files, the program will automatically add the correct extension to any filename without one.
The program's caching behavior can be controlled in the Options menu. By default, caching for cell sample and
sample plate files is OFF, and caching for graph/data files is ON.
#### Cell Sample Files
Cell Sample files consist of any number of distinct "T cells." Every cell contains

View File

@@ -10,6 +10,9 @@ public class BiGpairSEQ {
private static String plateFilename = null;
private static GraphWithMapData graphInMemory = null;
private static String graphFilename = null;
private static boolean cacheCells = false;
private static boolean cachePlate = false;
private static boolean cacheGraph = true;
public static void main(String[] args) {
if (args.length == 0) {
@@ -30,66 +33,122 @@ public class BiGpairSEQ {
return cellSampleInMemory;
}
public static void setCellSampleInMemory(CellSample cellSampleInMemory) {
BiGpairSEQ.cellSampleInMemory = cellSampleInMemory;
public static void setCellSampleInMemory(CellSample cellSample, String filename) {
if(cellSampleInMemory != null) {
clearCellSampleInMemory();
}
cellSampleInMemory = cellSample;
cellFilename = filename;
System.out.println("Cell sample file " + filename + " cached.");
}
public static void clearCellSampleInMemory() {
cellSampleInMemory = null;
cellFilename = null;
System.gc();
System.out.println("Cell sample file cache cleared.");
}
public static String getCellFilename() {
return cellFilename;
}
public static void setCellFilename(String cellFilename) {
BiGpairSEQ.cellFilename = cellFilename;
}
public static Plate getPlateInMemory() {
return plateInMemory;
}
public static void setPlateInMemory(Plate plateInMemory) {
BiGpairSEQ.plateInMemory = plateInMemory;
public static void setPlateInMemory(Plate plate, String filename) {
if(plateInMemory != null) {
clearPlateInMemory();
}
plateInMemory = plate;
plateFilename = filename;
System.out.println("Sample plate file " + filename + " cached.");
}
public static void clearPlateInMemory() {
plateInMemory = null;
plateFilename = null;
System.gc();
System.out.println("Sample plate file cache cleared.");
}
public static String getPlateFilename() {
return plateFilename;
}
public static void setPlateFilename(String plateFilename) {
BiGpairSEQ.plateFilename = plateFilename;
public static GraphWithMapData getGraphInMemory() {return graphInMemory;
}
public static GraphWithMapData getGraphInMemory() {
return graphInMemory;
}
public static void setGraphInMemory(GraphWithMapData g) {
public static void setGraphInMemory(GraphWithMapData g, String filename) {
if (graphInMemory != null) {
clearGraphInMemory();
}
graphInMemory = g;
graphFilename = filename;
System.out.println("Graph and data file " + filename + " cached.");
}
public static void clearGraphInMemory() {
graphInMemory = null;
graphFilename = null;
System.gc();
System.out.println("Graph and data file cache cleared.");
}
public static String getGraphFilename() {
return graphFilename;
}
public static void setGraphFilename(String filename) {
graphFilename = filename;
public static boolean cacheCells() {
return cacheCells;
}
public static void setCacheCells(boolean cacheCells) {
//if not caching, clear the memory
if(!cacheCells){
BiGpairSEQ.clearCellSampleInMemory();
System.out.println("Cell sample file caching: OFF.");
}
else {
System.out.println("Cell sample file caching: ON.");
}
BiGpairSEQ.cacheCells = cacheCells;
}
public static boolean cachePlate() {
return cachePlate;
}
public static void setCachePlate(boolean cachePlate) {
//if not caching, clear the memory
if(!cachePlate) {
BiGpairSEQ.clearPlateInMemory();
System.out.println("Sample plate file caching: OFF.");
}
else {
System.out.println("Sample plate file caching: ON.");
}
BiGpairSEQ.cachePlate = cachePlate;
}
public static boolean cacheGraph() {
return cacheGraph;
}
public static void setCacheGraph(boolean cacheGraph) {
//if not caching, clear the memory
if(!cacheGraph) {
BiGpairSEQ.clearGraphInMemory();
System.out.println("Graph/data file caching: OFF.");
}
else {
System.out.println("Graph/data file caching: ON.");
}
BiGpairSEQ.cacheGraph = cacheGraph;
}
}

View File

@@ -27,6 +27,7 @@ public class InteractiveInterface {
//Need to re-do the CDR3/CDR1 matching to correspond to new pattern
//System.out.println("5) Generate CDR3/CDR1 occupancy graph");
//System.out.println("6) Simulate CDR3/CDR1 T cell matching");
System.out.println("8) Options");
System.out.println("9) About/Acknowledgments");
System.out.println("0) Exit");
try {
@@ -37,6 +38,7 @@ public class InteractiveInterface {
case 3 -> makeCDR3Graph();
case 4 -> matchCDR3s();
//case 6 -> matchCellsCDR1();
case 8 -> options();
case 9 -> acknowledge();
case 0 -> quit = true;
default -> throw new InputMismatchException("Invalid input.");
@@ -78,11 +80,9 @@ public class InteractiveInterface {
CellFileWriter writer = new CellFileWriter(filename, sample);
writer.writeCellsToFile();
System.out.println("Cell sample written to: " + filename);
if(BiGpairSEQ.getCellSampleInMemory() != null) {
BiGpairSEQ.clearCellSampleInMemory();
if(BiGpairSEQ.cacheCells()) {
BiGpairSEQ.setCellSampleInMemory(sample, filename);
}
BiGpairSEQ.setCellSampleInMemory(sample);
BiGpairSEQ.setCellFilename(filename);
}
//Output a CSV of sample plate
@@ -219,9 +219,9 @@ public class InteractiveInterface {
System.out.println("Reading Cell Sample file: " + cellFile);
CellFileReader cellReader = new CellFileReader(cellFile);
cells = cellReader.getCellSample();
BiGpairSEQ.clearCellSampleInMemory();
BiGpairSEQ.setCellSampleInMemory(cells);
BiGpairSEQ.setCellFilename(cellFile);
if(BiGpairSEQ.cacheCells()) {
BiGpairSEQ.setCellSampleInMemory(cells, cellFile);
}
}
assert filename != null;
Plate samplePlate;
@@ -242,8 +242,9 @@ public class InteractiveInterface {
System.out.println("Writing Sample Plate to file");
writer.writePlateFile();
System.out.println("Sample Plate written to file: " + filename);
BiGpairSEQ.setPlateInMemory(samplePlate);
BiGpairSEQ.setPlateFilename(filename);
if(BiGpairSEQ.cachePlate()) {
BiGpairSEQ.setPlateInMemory(samplePlate, filename);
}
}
//Output serialized binary of GraphAndMapData object
@@ -271,16 +272,16 @@ public class InteractiveInterface {
assert cellFile != null;
CellSample cellSample;
//check if cells are already in memory
if(cellFile.equals(BiGpairSEQ.getCellFilename())) {
if(cellFile.equals(BiGpairSEQ.getCellFilename()) && BiGpairSEQ.getCellSampleInMemory() != null) {
cellSample = BiGpairSEQ.getCellSampleInMemory();
}
else {
BiGpairSEQ.clearCellSampleInMemory();
System.out.println("Reading Cell Sample file: " + cellFile);
CellFileReader cellReader = new CellFileReader(cellFile);
cellSample = cellReader.getCellSample();
BiGpairSEQ.setCellSampleInMemory(cellSample);
BiGpairSEQ.setCellFilename(cellFile);
if(BiGpairSEQ.cacheCells()) {
BiGpairSEQ.setCellSampleInMemory(cellSample, cellFile);
}
}
assert plateFile != null;
@@ -290,12 +291,12 @@ public class InteractiveInterface {
plate = BiGpairSEQ.getPlateInMemory();
}
else {
BiGpairSEQ.clearPlateInMemory();
System.out.println("Reading Sample Plate file: " + plateFile);
PlateFileReader plateReader = new PlateFileReader(plateFile);
plate = new Plate(plateReader.getFilename(), plateReader.getWells());
BiGpairSEQ.setPlateInMemory(plate);
BiGpairSEQ.setPlateFilename(plateFile);
if(BiGpairSEQ.cachePlate()) {
BiGpairSEQ.setPlateInMemory(plate, plateFile);
}
}
if (cellSample.getCells().size() == 0){
System.out.println("No cell sample found.");
@@ -312,9 +313,10 @@ public class InteractiveInterface {
GraphDataObjectWriter dataWriter = new GraphDataObjectWriter(filename, data);
dataWriter.writeDataToFile();
System.out.println("Graph and Data file written to: " + filename);
BiGpairSEQ.setGraphInMemory(data);
BiGpairSEQ.setGraphFilename(filename);
System.out.println("Graph and Data file " + filename + " cached.");
if(BiGpairSEQ.cacheGraph()) {
BiGpairSEQ.setGraphInMemory(data, filename);
}
}
}
@@ -366,17 +368,15 @@ public class InteractiveInterface {
assert graphFilename != null;
//check if this is the same graph we already have in memory.
GraphWithMapData data;
if(!(graphFilename.equals(BiGpairSEQ.getGraphFilename())) || BiGpairSEQ.getGraphInMemory() == null) {
BiGpairSEQ.clearGraphInMemory();
//read object data from file
GraphDataObjectReader dataReader = new GraphDataObjectReader(graphFilename);
data = dataReader.getData();
//set new graph in memory and new filename
BiGpairSEQ.setGraphInMemory(data);
BiGpairSEQ.setGraphFilename(graphFilename);
if(graphFilename.equals(BiGpairSEQ.getGraphFilename())) {
data = BiGpairSEQ.getGraphInMemory();
}
else {
data = BiGpairSEQ.getGraphInMemory();
GraphDataObjectReader dataReader = new GraphDataObjectReader(graphFilename);
data = dataReader.getData();
if(BiGpairSEQ.cacheGraph()) {
BiGpairSEQ.setGraphInMemory(data, graphFilename);
}
}
//simulate matching
MatchingResult results = Simulator.matchCDR3s(data, graphFilename, lowThreshold, highThreshold, maxOccupancyDiff,
@@ -493,6 +493,35 @@ public class InteractiveInterface {
// }
// }
private static void options(){
boolean backToMain = false;
while(!backToMain) {
System.out.println("\n--------------OPTIONS---------------");
System.out.println("1) Turn " + getOnOff(!BiGpairSEQ.cacheCells()) + " cell sample file caching");
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("0) Return to main menu");
try {
input = sc.nextInt();
switch (input) {
case 1 -> BiGpairSEQ.setCacheCells(!BiGpairSEQ.cacheCells());
case 2 -> BiGpairSEQ.setCachePlate(!BiGpairSEQ.cachePlate());
case 3 -> BiGpairSEQ.setCacheGraph(!BiGpairSEQ.cacheGraph());
case 0 -> backToMain = true;
default -> throw new InputMismatchException("Invalid input.");
}
} catch (InputMismatchException ex) {
System.out.println(ex);
sc.next();
}
}
}
private static String getOnOff(boolean b) {
if (b) { return "on";}
else { return "off"; }
}
private static void acknowledge(){
System.out.println("This program simulates BiGpairSEQ, a graph theory based adaptation");
System.out.println("of the pairSEQ algorithm for pairing T cell receptor sequences.");