public void find_coverage(SAMResource sres) {
int start_base = sres.region.range.start;
int end_base = sres.region.range.end;
int coverage_len = (end_base - start_base) + 1;
int i, end, ref_i, read_i, len;
int[] coverage = new int[coverage_len];
Arrays.fill(coverage, 0);
WorkingFile wf = null;
if (outfile != null) {
try {
wf = new WorkingFile(outfile);
ps = wf.getPrintStream();
} catch (Exception e) {
System.err.println("I/O error: " + e); // debug
e.printStackTrace();
System.exit(1);
}
}
try {
//
// gather coverage info:
//
CloseableIterator<SAMRecord> iterator = sres.get_iterator();
int read_count = 0;
int ref_min = -1;
int ref_max = -1;
while (iterator.hasNext()) {
SAMRecord sr = iterator.next();
read_count++;
// System.err.println(sr.getReadName() + ": " + sr.getAlignmentStart() + "-" +
// sr.getAlignmentEnd()); // debug
if (sr.getReadUnmappedFlag()) continue;
if (sr.getDuplicateReadFlag()) {
if (verbose_mode)
System.err.println(
sr.getReadName()
+ "."
+ (sr.getReadNegativeStrandFlag() ? "R" : "F")
+ " ignoring, duplicate");
continue;
}
byte[] read = sr.getReadBases();
byte[] quals = sr.getBaseQualities();
for (AlignmentBlock ab : sr.getAlignmentBlocks()) {
len = ab.getLength();
read_i = ab.getReadStart() - 1;
ref_i = ab.getReferenceStart() - start_base;
if (ref_min == -1 || ref_i < ref_min) ref_min = ref_i;
for (i = read_i, end = read_i + len; i < end; i++, ref_i++) {
if (ref_i >= 0 && ref_i < coverage_len) {
if (quals[i] >= MIN_QUALITY) {
if (verbose_mode)
System.err.println(
sr.getReadName()
+ "."
+ (sr.getReadNegativeStrandFlag() ? "R" : "F")
+ " hit at "
+ (ref_i + start_base)
+ " as="
+ sr.getAlignmentStart()
+ " ae="
+ sr.getAlignmentEnd());
coverage[ref_i]++;
} else if (verbose_mode) {
System.err.println(
sr.getReadName()
+ "."
+ (sr.getReadNegativeStrandFlag() ? "R" : "F")
+ " qual_reject at "
+ (ref_i + start_base)
+ " as="
+ sr.getAlignmentStart()
+ " ae="
+ sr.getAlignmentEnd());
}
}
}
if (ref_max == -1 || ref_i > ref_max) ref_max = ref_i;
}
}
sres.close();
System.err.println(
"records:"
+ read_count
+ " ref_min:"
+ (ref_min + start_base)
+ " ref_max:"
+ (ref_max + start_base)); // debug
//
// report coverage info:
//
for (i = 0; i < coverage.length; i++) {
if (name != null) ps.print(name + ",");
ps.println((i + start_base) + "," + coverage[i]); // debug
}
if (wf != null) wf.finish();
} catch (Exception e) {
System.err.println("ERROR: " + e); // debug
e.printStackTrace();
}
}
public void run() {
String line;
String id = null;
config.refgenes = new ArrayList<RefGene>();
config.dbsnp = new ArrayList<dbSNP>();
try {
// System.err.println("quality read start"); // debug
boolean need_ruler_rebuild = false;
boolean need_title = false;
SAMRegion sr = null;
while (true) {
line = br.readLine();
if (line == null) break;
// EOF
String[] stuff = line.split("\t");
if (stuff[0].equals("sample2id")) {
Sample sample = Sample.get_sample(stuff[1]);
for (int i = 2; i < stuff.length; i++) {
config.read2sample.put(new String(stuff[i]), sample);
}
} else if (stuff[0].equals("consensus_label")) {
config.CONSENSUS_TAG = new String(stuff[1]);
} else if (stuff[0].equals("ruler_start")) {
config.ruler_start = Integer.parseInt(stuff[1]);
need_ruler_rebuild = true;
} else if (stuff[0].equals("title")) {
config.title = stuff[1];
need_title = true;
} else if (stuff[0].equals("refGene")) {
config.refgenes.add(new RefGene(stuff));
} else if (stuff[0].equals("dbsnp")) {
config.dbsnp.add(new dbSNP(stuff));
} else if (stuff[0].toUpperCase().indexOf("SAM_") == 0) {
// FUGLY
SAMResourceTags v = SAMResourceTags.valueOf(stuff[0].toUpperCase());
if (v.equals(SAMResourceTags.SAM_URL)) config.sams.add(new SAMResource());
config.sams.get(config.sams.size() - 1).import_data(v, stuff[1]);
} else if (stuff[0].equals("reference_sequence")) {
StringBuffer target_sequence = new StringBuffer();
while (true) {
line = br.readLine();
if (line.equals(">")) {
// config.target_sequence = target_sequence.toString().toCharArray();
config.target_sequence = target_sequence.toString().getBytes();
break;
} else {
target_sequence.append(line);
}
}
} else if (stuff[0].equals("target_region")) {
sr = new SAMRegion();
sr.tname = new String(stuff[1]);
sr.range = new Range(Integer.parseInt(stuff[2]), Integer.parseInt(stuff[3]));
// System.err.println("range " + sr.tname + " " + sr.range.start + " " + sr.range.end);
// // debug
} else {
System.err.println("error, don't recognize tag " + stuff[0]); // debug
}
}
if (config.ruler_start > 0) {
for (dbSNP snp : config.dbsnp) {
snp.consensus_adjust(config.ruler_start);
}
for (RefGene rg : config.refgenes) {
rg.consensus_adjust(config.ruler_start);
}
}
if (config.dbsnp != null) {
for (dbSNP snp : config.dbsnp) {
// System.err.println("adding snp at " + snp.start + " = " + (snp.start +
// config.ruler_start)); // debug
}
config.snp_config.snp_query = new dbSNPSet(config.dbsnp);
}
for (SAMResource sre : config.sams) {
sre.set_region(sr);
}
if (av != null) {
while (av.get_acepanel().is_built() == false) {
// spin until dependency built
try {
System.err.println("MarkupReader spin..."); // debug
Thread.sleep(50);
} catch (Exception e) {
}
}
PadMap pm = av.get_acepanel().get_assembly().get_padmap();
for (RefGene rg : config.refgenes) {
rg.consensus_setup(pm);
}
Runnable later;
if (need_title) {
// System.err.println("title="+config.title); // debug
later =
new Runnable() {
public void run() {
av.setTitle(config.title);
av.repaint();
}
};
javax.swing.SwingUtilities.invokeLater(later);
}
if (need_ruler_rebuild) {
//
// ruler labeling has changed.
//
later =
new Runnable() {
public void run() {
// av.get_acepanel().get_canvas().build_ruler();
if (config.start_unpadded_offset != 0) {
AcePanel ap = av.get_acepanel();
PadMap pm = ap.get_assembly().get_padmap();
int upo = (config.start_unpadded_offset - config.ruler_start) + 1;
// +1: convert to 1-based offset
int po = pm.get_unpadded_to_padded(upo);
System.err.println("upo=" + upo + " po=" + po); // debug
SNPList sl = new SNPList();
sl.addElement(new SNP(po, 0.0));
ap.ace.set_snps(sl);
ap.get_canvas().center_on(po);
ap.get_canvas().repaint();
}
}
};
javax.swing.SwingUtilities.invokeLater(later);
}
if (config.enable_exon_navigation) {
if (false) {
System.err.println("DEBUG: exon nav disabled");
} else {
av.get_acepanel().init_exon_navigation();
}
}
av.get_acepanel().get_assembly().build_summary_info();
// group samples by tumor/normal, if applicable
// av.repaint();
later =
new Runnable() {
public void run() {
av.repaint();
}
};
javax.swing.SwingUtilities.invokeLater(later);
}
// System.err.println("quality read end"); // debug
} catch (Exception e) {
e.printStackTrace(); // debug
}
}
public static void main(String[] argv) {
SAMFileReader.setDefaultValidationStringency(SAMFileReader.ValidationStringency.SILENT);
// STFU
SAMResource sr = null;
SAMRegion region = new SAMRegion();
region.range = new Range();
region.range.start = -1;
region.range.end = -1;
String outfile = null;
String target_file = null;
SAMCoverage sc = new SAMCoverage();
for (int i = 0; i < argv.length; i++) {
if (argv[i].equals("-bam")) {
sr = new SAMResource();
// sr.import_data(SAMResourceTags.SAM_URL, argv[++i]);
sr.set_file(argv[++i]);
sr.detect_sample_id();
} else if (argv[i].equals("-targets")) {
target_file = argv[++i];
} else if (argv[i].equals("-tname")) {
region.tname = argv[++i];
} else if (argv[i].equals("-verbose")) {
sc.set_verbose(true);
} else if (argv[i].equals("-tstart")) {
region.range.start = Integer.parseInt(argv[++i]);
} else if (argv[i].equals("-tend")) {
region.range.end = Integer.parseInt(argv[++i]);
} else if (argv[i].equals("-of")) {
outfile = argv[++i];
} else if (argv[i].equals("-min-quality")) {
sc.set_min_quality(Integer.parseInt(argv[++i]));
} else {
System.err.println("error: unknown switch " + argv[i]); // debug
System.exit(1);
}
}
String error = null;
if (sr == null) {
error = "specify -bam [file]";
} else if (target_file == null) {
if (region.tname == null) {
error = "specify -tname";
} else if (region.range.start == -1) {
error = "specify -tstart";
} else if (region.range.end == -1) {
error = "specify -tend";
}
}
sr.set_region(region);
if (error != null) {
System.err.println("ERROR: " + error); // debug
} else if (target_file != null) {
try {
File f = new File(target_file);
BufferedReader br = new BufferedReader(new FileReader(f));
String line = br.readLine();
String[] headers = line.split("\t");
if (headers[0].equals("Name")
&& headers[1].equals("Chromosome")
&& headers[2].equals("Start")
&& headers[3].equals("End")) {
WorkingFile wf = null;
if (outfile != null) {
wf = new WorkingFile(outfile);
sc.setPrintStream(wf.getPrintStream());
}
while (true) {
line = br.readLine();
if (line == null) {
// EOF
break;
} else {
String[] row = line.split("\t");
region.tname = row[1];
region.range.start = Integer.parseInt(row[2]);
region.range.end = Integer.parseInt(row[3]);
// sc.set_name(new String(row[0]));
sc.set_name(new String(row[0]) + "," + new String(row[1]));
sc.find_coverage(sr);
}
}
if (outfile != null) wf.finish();
} else {
throw new IOException("file format error");
}
} catch (Exception e) {
System.err.println("ERROR: " + e); // debug
e.printStackTrace();
System.exit(1);
}
} else {
sc.set_outfile(outfile);
sc.find_coverage(sr);
}
}