From 873be340e8adce476caac8f83c5f16eac7b77ff1 Mon Sep 17 00:00:00 2001
From: "fritz.sedlazeck" <fritz.sedlazeck@gmail.com>
Date: Fri, 16 Mar 2018 10:46:17 -0500
Subject: [PATCH] Changed VCF header of merge

---
 src/SURVIVOR.cpp                  |  14 +++-
 src/convert/Update_bam_pacbio.cpp | 106 ++++++++++++++++++++++++++++++
 src/convert/Update_bam_pacbio.h   |  20 ++++++
 src/merge_vcf/combine_svs.cpp     |  10 ++-
 4 files changed, 146 insertions(+), 4 deletions(-)
 create mode 100644 src/convert/Update_bam_pacbio.cpp
 create mode 100644 src/convert/Update_bam_pacbio.h

diff --git a/src/SURVIVOR.cpp b/src/SURVIVOR.cpp
index e8a8c67..97f8312 100644
--- a/src/SURVIVOR.cpp
+++ b/src/SURVIVOR.cpp
@@ -42,6 +42,7 @@
 #include "analysis_sv/MUMmer_overlap.h"
 #include "analysis_sv/Select_samples.h"
 #include "convert/Convert_hapcut2.h"
+#include "convert/Update_bam_pacbio.h"
 
 Parameter* Parameter::m_pInstance = NULL;
 
@@ -223,6 +224,17 @@ void official_interface(int argc, char *argv[]) {
 			}
 			exit(0);
 		}
+		/*else if (strcmp(argv[1], "updateBamfile") == 0) {
+			if (argc == 5) {
+				process_sam_forpacbio(std::string(argv[2]), std::string(argv[3]), std::string(argv[4]));
+			} else {
+				std::cerr << "original SNP file" << std::endl;
+				std::cerr << "Hapcut2 final file" << std::endl;
+				std::cerr << "Output: vcf file" << std::endl;
+			}
+			exit(0);
+
+		}*/
 
 	}
 	std::cerr << "Program: SURVIVOR (Tools for Structural Variations in the VCF format)" << std::endl;
@@ -252,7 +264,7 @@ void official_interface(int argc, char *argv[]) {
 	std::cerr << "\tbedtovcf\tConverts a bed file to a VCF file " << std::endl;
 	std::cerr << "\tsmaptovcf\tConverts the smap file to a VCF file (beta version)" << std::endl;
 	std::cerr << "\tbedpetovcf\tConverts a bedpe file ot a VCF file (beta version)" << std::endl;
-	std::cerr << "\thapcuttovcf\tConverts the Hapcut2 final file to a VCF file using the original SNP file provided to Hapcut2" <<std::endl;
+	std::cerr << "\thapcuttovcf\tConverts the Hapcut2 final file to a VCF file using the original SNP file provided to Hapcut2" << std::endl;
 
 	exit(0);
 }
diff --git a/src/convert/Update_bam_pacbio.cpp b/src/convert/Update_bam_pacbio.cpp
new file mode 100644
index 0000000..c2deedf
--- /dev/null
+++ b/src/convert/Update_bam_pacbio.cpp
@@ -0,0 +1,106 @@
+/*
+ * Update_bam_pacbio.cpp
+ *
+ *  Created on: Mar 15, 2018
+ *      Author: sedlazec
+ */
+
+#include "Update_bam_pacbio.h"
+
+
+std::vector<std::string> parse_header(std::string unmapped_sam){
+	std::vector<std::string> header;
+
+
+	return header;
+}
+
+
+
+void merge_header(std::string unmapped_sam,std::string mapped_sam,FILE *& file2) {
+	std::vector<std::string> header_un=parse_header(unmapped_sam);
+
+
+}
+
+void update_entries(std::map<std::string, std::string> & entries, std::string unmapped_sam) {
+	std::cout<<"check unmapped"<<std::endl;
+	std::string buffer;
+	std::ifstream myfile;
+	myfile.open(unmapped_sam.c_str(), std::ifstream::in);
+	if (!myfile.good()) {
+		std::cout << "Sam Parser: could not open file: " << unmapped_sam.c_str() << std::endl;
+		exit(0);
+	}
+	getline(myfile, buffer);
+	while (!myfile.eof()) {
+		if (buffer[0] != '@') {
+			size_t found = buffer.find_first_of('\t');
+			std::string id = buffer.substr(0, found);
+			if (entries.find(id) != entries.end()) { //found!
+				int count = 0;
+				for (size_t i = 0; i < buffer.size(); i++) {
+					if (count > 9) {
+						entries[id] += buffer[i];
+					}
+					if (buffer[i] == '\t') {
+						count++;
+					}
+				}
+			}
+		}
+		getline(myfile, buffer);
+	}
+
+}
+
+void process_sam_forpacbio(std::string unmapped_sam, std::string mapped_sam, std::string output_sam) {
+
+
+	std::string buffer;
+	std::ifstream myfile;
+	myfile.open(mapped_sam.c_str(), std::ifstream::in);
+	if (!myfile.good()) {
+		std::cout << "Sam Parser: could not open file: " << mapped_sam.c_str() << std::endl;
+		exit(0);
+	}
+
+	FILE *file2;
+	file2 = fopen(output_sam.c_str(), "w");
+
+	merge_header(unmapped_sam,mapped_sam,file2);
+
+	std::map<std::string, std::string> entries;
+	getline(myfile, buffer);
+	while (!myfile.eof()) { //avoid header.
+		if (buffer[0] != '@') {
+			//parse part of the mapped entries into a map (e.g. step size =100000)
+			size_t found = buffer.find_first_of('\t');
+			std::string id = buffer.substr(0, found);
+			entries[id] = buffer;
+			if (entries.size() > 1000) {
+				std::cout<<"check entries"<<std::endl;
+				//check orig file and update them
+				update_entries(entries, unmapped_sam);
+				for (std::map<std::string, std::string>::iterator i = entries.begin(); i != entries.end(); i++) {
+					fprintf(file2, "%s", (*i).second.c_str());
+					fprintf(file2, "%c", '\n');
+				}
+				entries.clear();
+			}
+		}
+
+		getline(myfile, buffer);
+	}
+	myfile.close();
+	//check orig file and update them
+	update_entries(entries, unmapped_sam);
+	for (std::map<std::string, std::string>::iterator i = entries.begin(); i != entries.end(); i++) {
+		fprintf(file2, "%s", (*i).second.c_str());
+		fprintf(file2, "%c", '\n');
+	}
+	fclose(file2);
+
+
+}
+
diff --git a/src/convert/Update_bam_pacbio.h b/src/convert/Update_bam_pacbio.h
new file mode 100644
index 0000000..a59474f
--- /dev/null
+++ b/src/convert/Update_bam_pacbio.h
@@ -0,0 +1,20 @@
+/*
+ * Update_bam_pacbio.h
+ *
+ *  Created on: Mar 15, 2018
+ *      Author: sedlazec
+ */
+
+#ifndef CONVERT_UPDATE_BAM_PACBIO_H_
+#define CONVERT_UPDATE_BAM_PACBIO_H_
+
+#include "../vcfs/Merge_VCF.h"
+#include "../structs.h"
+#include "../simulator/Eval_vcf.h"
+#include <math.h>
+#include <iosfwd>
+
+void process_sam_forpacbio(std::string unmapped_sam, std::string mapped_sam, std::string output_sam);
+
+
+#endif /* CONVERT_UPDATE_BAM_PACBIO_H_ */
diff --git a/src/merge_vcf/combine_svs.cpp b/src/merge_vcf/combine_svs.cpp
index 53c1f5b..0889060 100644
--- a/src/merge_vcf/combine_svs.cpp
+++ b/src/merge_vcf/combine_svs.cpp
@@ -74,8 +74,12 @@ void print_header(FILE *& file, std::vector<std::string> names,std::map<std::str
 	fprintf(file, "%s", "##INFO=<ID=RE,Number=1,Type=Integer,Description=\"read support\">\n");
 	fprintf(file, "%s", "##INFO=<ID=IMPRECISE,Number=0,Type=Flag,Description=\"Imprecise structural variation\">\n");
 	fprintf(file, "%s", "##INFO=<ID=PRECISE,Number=0,Type=Flag,Description=\"Precise structural variation\">\n");
-	fprintf(file, "%s", "##INFO=<ID=SVLEN,Number=1,Type=Integer,Description=\"Length of the SV\">\n");
-	fprintf(file, "%s", "##INFO=<ID=SVMETHOD,Number=1,Type=String,Description=\"Type of approach used to detect SV\">\n");
+	fprintf(file, "%s", "##INFO=<ID=AVGLEN,Number=1,Type=Integer,Description=\"Length of the SV\">\n");
+	fprintf(file, "%s", "##INFO=<ID=SVMETHOD,Number=1,Type=String,Description=\"Vector of samples supporting the SV.\">\n");
+	fprintf(file, "%s", "##INFO=<ID=SVTYPE,Number=1,Type=String,Description=\"Type of the SV.\">\n");
+	fprintf(file, "%s", "##INFO=<ID=SUPP_VEC,Number=1,Type=Integer,Description=\"Number of samples supporting the variant.\">\n");
+	fprintf(file, "%s", "##INFO=<ID=SUPP,Number=1,Type=String,Description=\"Previous support vector\">\n");
+	fprintf(file, "%s", "##INFO=<ID=STRANDS,Number=1,Type=String,Description=\"Indicating the direction of the reads with respect to the type and breakpoint.\">\n");
 	fprintf(file, "%s", "##FORMAT=<ID=GT,Number=1,Type=String,Description=\"Genotype\">\n");
 	fprintf(file, "%s", "##FORMAT=<ID=LN,Number=1,Type=Integer,Description=\"predicted length\">\n");
 	fprintf(file, "%s", "##FORMAT=<ID=DR,Number=1,Type=Integer,Description=\"# supporting reference,variant reads in that order\">\n");
@@ -228,7 +232,7 @@ void print_entry_overlap(FILE *& file, SVS_Node * entry, int id) {
 			}
 			pos++;
 		} else {
-			convert << "./.:0:0,0:--:NaN:NaN";
+			convert << "./.:NaN:0:0,0:--:NaN:NaN";
 		}
 
 	}