Merge pull request #20 from CEGRcode/revisions

BioRxiv submission update (BWA to Bowtie2)

Author: owlang

.gitignore

@@ -5,6 +5,12 @@ EpitopeID/sacCer3_EpiID/FASTA_genome/genome.fa.ann
 EpitopeID/sacCer3_EpiID/FASTA_genome/genome.fa.bwt
 EpitopeID/sacCer3_EpiID/FASTA_genome/genome.fa.pac
 EpitopeID/sacCer3_EpiID/FASTA_genome/genome.fa.sa
+EpitopeID/sacCer3_EpiID/FASTA_genome/genome.fa.1.bt2
+EpitopeID/sacCer3_EpiID/FASTA_genome/genome.fa.2.bt2
+EpitopeID/sacCer3_EpiID/FASTA_genome/genome.fa.3.bt2
+EpitopeID/sacCer3_EpiID/FASTA_genome/genome.fa.4.bt2
+EpitopeID/sacCer3_EpiID/FASTA_genome/genome.fa.rev.1.bt2
+EpitopeID/sacCer3_EpiID/FASTA_genome/genome.fa.rev.2.bt2
 EpitopeID/ecoli_EpiID/FASTA_genome/genome.fa.amb
 EpitopeID/ecoli_EpiID/FASTA_genome/genome.fa.ann
 EpitopeID/ecoli_EpiID/FASTA_genome/genome.fa.bwt
@@ -16,3 +22,9 @@ EpitopeID/hg19_EpiID/FASTA_genome/genome.fa.ann
 EpitopeID/hg19_EpiID/FASTA_genome/genome.fa.bwt
 EpitopeID/hg19_EpiID/FASTA_genome/genome.fa.pac
 EpitopeID/hg19_EpiID/FASTA_genome/genome.fa.sa
+EpitopeID/hg19_EpiID/FASTA_genome/genome.fa.1.bt2
+EpitopeID/hg19_EpiID/FASTA_genome/genome.fa.2.bt2
+EpitopeID/hg19_EpiID/FASTA_genome/genome.fa.3.bt2
+EpitopeID/hg19_EpiID/FASTA_genome/genome.fa.4.bt2
+EpitopeID/hg19_EpiID/FASTA_genome/genome.fa.rev.1.bt2
+EpitopeID/hg19_EpiID/FASTA_genome/genome.fa.rev.2.bt2

DeletionID/delScripts/detect_deletion_BAM.py

@@ -28,15 +28,15 @@ def calculateDeletion(PASS):
 		if float(PASS[key]) == 0:
 			SCORES.append((key, 'No Data Detected'))
 		elif np.isnan(float(PASS[key])):
-                        SCORES.append((key, 'Region does not meet mappability threshold'))
+			SCORES.append((key, 'Region does not meet mappability threshold'))
 		else:
-                        SCORES.append((key, np.log(float(PASS[key]) / MEDIAN) / np.log(2)))
+			SCORES.append((key, np.log(float(PASS[key]) / MEDIAN) / np.log(2)))
 	return SCORES
 
 def iterateBAM(bam, bed, READLENGTH, MAP, MAPTHRESH):
 	# open BAM file
 	samfile = pysam.AlignmentFile(bam, "rb")
-       	# open BED file
+	# open BED file
 	file = open(bed, "r")
 
 	# Counter of total tags mapping across all intervals
@@ -65,16 +65,16 @@ def iterateBAM(bam, bed, READLENGTH, MAP, MAPTHRESH):
 					intervalCount[index] = intervalCount[index] + 1
 			totalSize = totalSize + intervalSize
 
-        	        # Calculate avg tags per bp across the entire region
+			# Calculate avg tags per bp across the entire region
 			intervalAvg = list(map(lambda x : float(x) / float(intervalSize), intervalCount))
-			
-	                # Normalize avg reads per interval by mappability
+
+			# Normalize avg reads per interval by mappability
 			for index in range(0, len(MAP[intervalID])):
-                	        if float(MAP[intervalID][index]) >= MAPTHRESH:
-                        	        mapAvg[index] = float(intervalAvg[index] * intervalCount[index]) / float(MAP[intervalID][index])
-	                        else:   
-        	                        mapAvg[index] = float('NaN')
-			
+				if float(MAP[intervalID][index]) >= MAPTHRESH:
+					mapAvg[index] = float(intervalAvg[index] * intervalCount[index]) / float(MAP[intervalID][index])
+				else:
+					mapAvg[index] = float('NaN')
+
 			PASS[intervalID] = (mapAvg, intervalCount)
 
 		except (IndexError, ValueError):
@@ -90,7 +90,7 @@ def iterateBAM(bam, bed, READLENGTH, MAP, MAPTHRESH):
 		if all(float(x) < MAPTHRESH for x in MAP[key]):
 			normalizedScore = float('NaN')
 		elif sum(PASS[key][1]) != 0:
-                	normalizedScore = np.nansum(PASS[key][0]) / sum(PASS[key][1])
+			normalizedScore = np.nansum(PASS[key][0]) / sum(PASS[key][1])
 		else:
 			normalizedScore = 0
 		SCORE[key] = normalizedScore
@@ -99,11 +99,11 @@ def iterateBAM(bam, bed, READLENGTH, MAP, MAPTHRESH):
 	if float(totalSize) <= 0:
 		print("ERROR!!!\tTotal size of all intervals surveyed is less than 1")
 		sys.exit(-1)
-	
+
 	# Close files
 	file.close()
 	samfile.close()
-	
+
 	return SCORE,FAIL
 
 def closestLength(READLENGTH, read):
@@ -120,7 +120,7 @@ def loadMap(MAP):
 	file = open(MAP, "r")
 	header = 0;
 	MAP = {}
-        # Iterate BED coord file, getting tag counts across interval
+	# Iterate BED coord file, getting tag counts across interval
 	for line in file:
 		mapline = line.rstrip().split("\t")
 		if header == 0:
@@ -140,8 +140,8 @@ def validateBAM(bam):
 		print("BAM index not detected.\nAttempting to index now...\n")
 		pysam.index(str(bam))
 		if not os.path.isfile(bam + ".bai"):
-        	        raise RuntimeError("BAM indexing failed, please check if BAM file is sorted")     
-                	return False
+			raise RuntimeError("BAM indexing failed, please check if BAM file is sorted")
+			return False
 		print("BAM index successfully generated.\n")
 		return True
 
@@ -150,9 +150,9 @@ def validateBAM(bam):
 	if len(sys.argv) < 2 or not sys.argv[1].startswith("-"): sys.exit(usage)
 	BAM = BED = MAP = OUT = ""
 
-        # Variable to set the mappability threshold so that we do not consider regions with mappability 
-        # below this number 0-1, Default to 0.25 meaning at least 25% of the region must be uniquely mappable
-        # by at least one actively used readlength
+	# Variable to set the mappability threshold so that we do not consider regions with mappability
+	# below this number 0-1, Default to 0.25 meaning at least 25% of the region must be uniquely mappable
+	# by at least one actively used readlength
 	MAPTHRESH = 0.25
 
 	OUTPUTTHRESH = -3
@@ -173,11 +173,11 @@ def validateBAM(bam):
 		print("No BAM file detected!!!")
 		sys.exit(usage)
 	elif BED == "":
-                print("No BED Coordinate file detected!!!")
-                sys.exit(usage)
+		print("No BED Coordinate file detected!!!")
+		sys.exit(usage)
 	elif MAP == "":
-                print("No Mappability file detected!!!")
-                sys.exit(usage)
+		print("No Mappability file detected!!!")
+		sys.exit(usage)
 	if OUT == "":
 		OUT = os.path.splitext(os.path.basename(BAM))[0] + "_" + os.path.splitext(os.path.basename(BED))[0] + ".tab"
 
@@ -189,11 +189,11 @@ def validateBAM(bam):
 	print("Output file: ",OUT)
 	print("Log2 output threshold: ",OUTPUTTHRESH)
 
-        # Validate BAM file
+	# Validate BAM file
 	if(not validateBAM(BAM)):
-                print("ERROR!!!\tNo BAM index detected.\n")
-                sys.exit(-1)
-	
+		print("ERROR!!!\tNo BAM index detected.\n")
+		sys.exit(-1)
+
 	# Load mappability file
 	READLENGTH, REGIONMAP = loadMap(MAP)
 	print("Mappability file loaded")
@@ -203,7 +203,7 @@ def validateBAM(bam):
 	print("Genomic coordinate coverage calculated")
 
 	# Calculate log2 tag enrichment over median of mappability-normalized tag avg per region
-	SCORE = calculateDeletion(PASS)	
+	SCORE = calculateDeletion(PASS)
 	print("Depletion calculated")
 
 	# Output final data
@@ -215,7 +215,7 @@ def validateBAM(bam):
 	for id,score in reversed(FINAL):
 		try:
 			if float(score) < OUTPUTTHRESH:
-                        	output.write(id + "\t" + str(score) + "\n")
+				output.write(id + "\t" + str(score) + "\n")
 			else:
 				break
 		except(ValueError):

DeletionID/identify-Deletion.sh

@@ -1,39 +1,39 @@
 #!/bin/bash
 
 # Required software:
-# python v2.15 with scipy
+# python3 with scipy
 
 usage()
 {
-    echo 'identify-Deletion.sh -i /path/to/BAM -o /path/to/output -d /path/to/genome/database'
-    echo 'eg: bash identify-Deletion.sh -i /input -o /output -d /sacCer3_Del'
-    exit
+	echo 'identify-Deletion.sh -i /path/to/BAM -o /path/to/output -d /path/to/genome/database'
+	echo 'eg: bash identify-Deletion.sh -i /input -o /output -d /sacCer3_Del'
+	exit
 }
 
 if [ "$#" -ne 6 ]; then
-    usage
+	usage
 fi
 
 while getopts ":i:o:d:" IN; do
-    case "${IN}" in
-        i)
-            INPUT=${OPTARG}
-            ;;
-        o)
-            OUTPUT=${OPTARG}
-            ;;
-	d)
-	    DATABASE=${OPTARG}
-	    ;;
-        *)
-            usage
-            ;;
-    esac
+	case "${IN}" in
+		i)
+			INPUT=${OPTARG}
+			;;
+		o)
+			OUTPUT=${OPTARG}
+			;;
+		d)
+			DATABASE=${OPTARG}
+			;;
+		*)
+			usage
+			;;
+	esac
 done
 shift $((OPTIND-1))
 
 if [ -z "${INPUT}" ] || [ -z "${OUTPUT}" ] || [ -z "$DATABASE" ]; then
-    usage
+	usage
 fi
 
 echo "Input folder = ${INPUT}"

EpitopeID/epiScripts/calculate_EpitopeSignificance.py

@@ -32,20 +32,20 @@
 		print("No Pvalue input!!!")
 		sys.exit(usage)
 	elif COUNT == "":
-                print("No Single-end epitope counts input!!!")
-                sys.exit(usage)
+		print("No Single-end epitope counts input!!!")
+		sys.exit(usage)
 	elif SIZE == "":
-                print("No Genome-size input!!!")
-                sys.exit(usage)
+		print("No Genome-size input!!!")
+		sys.exit(usage)
 	if OUT == "":
-                OUT = os.path.splitext(os.path.basename(BAM))[0] + ".tab"
+		OUT = os.path.splitext(os.path.basename(BAM))[0] + ".tab"
 
 	# Minimum fold enrichment over background
 	MINFOLD = 2;
 
 	# Open output file for writing
 	output = open(OUT, "w")
-       	# open PE_table
+	# open PE_table
 	file = open(TABLE, "r")
 
 	TABLE = []

EpitopeID/epiScripts/count_raw_epitope.pl

@@ -27,7 +27,7 @@
 
 open(OUT, ">$output") or die "Can't open $output for writing!\n";
 if($#SORT == -1) {
-        print OUT "EpitopeID\tEpitopeCount\nNo Tag ID'd\n";
+	print OUT "EpitopeID\tEpitopeCount\nNo Tag ID'd\n";
 } else {
 	print OUT "EpitopeID\tEpitopeCount\n";
 	for($x = 0; $x <= $#SORT; $x++) {

EpitopeID/epiScripts/sum_PE_epitope-alignment.pl

@@ -36,7 +36,7 @@
 	chomp($line);
 	next if((substr $line, 0, 1) eq "@");
 	@array = split(/\t/, $line);
-	
+
 	# Set predicted terminus of epitope
 	$LOC = "C-term";
 	if($array[5] eq "+" && $array[18] eq "-") { $LOC = "N-term"; }
@@ -56,12 +56,12 @@
 
 open(OUT, ">$output") or die "Can't open $output for writing!\n";
 if($#SORT == -1) {
-        print OUT "Epitope could not be detected genomically\n";
+	print OUT "Epitope could not be detected genomically\n";
 } else {
 	for($x = 0; $x <= $#SORT; $x++) {
 		@temparray = split(/\~/, $SORT[$x]{'id'});
 		for($y = 0; $y <= $#temparray; $y++) { print OUT "$temparray[$y]\t" }
-		print OUT "$SORT[$x]{'count'}\n";; 
+		print OUT "$SORT[$x]{'count'}\n";;
 	}
 }
 close OUT;