diff --git a/partitioning/partitioning.cpp b/partitioning/partitioning.cpp
index b6a18c536b2338715adce9da4e864274860683d1..d84efe651c32da1dc29059120f8c3ec2a013f044 100755
--- a/partitioning/partitioning.cpp
+++ b/partitioning/partitioning.cpp
@@ -2,6 +2,7 @@
#include <fstream>
#include <string>
#include <vector>
+#include <list>
#include <bitset>
#include <unordered_map>
#include <cmath>
@@ -110,19 +111,24 @@ std::vector<std::vector<int>> get_minimizers(const std::string& filename) {
}
}
+ // Remove empty lists from the minimizer list
+ minimizer_list.erase(std::remove_if(minimizer_list.begin(), minimizer_list.end(),
+ [](const std::vector<int>& v) { return v.empty(); }),
+ minimizer_list.end());
+
// End the timer and print the elapsed time
auto end = std::chrono::high_resolution_clock::now();
std::chrono::duration<double> elapsed = end - start;
- std::cout << elapsed.count() << " for minimizer list" << std::endl;
+ std::cout << elapsed.count() << "s for minimizer list" << std::endl;
return minimizer_list;
}
-void minlist_to_graph(int reads_number, const std::vector<std::vector<int>>& minimizer_list, const std::string& graph_file_path) {
-
- // Create a vector of vectors to store the graph
+void minlist_to_graph(const std::vector<std::vector<int>>& minimizer_list, int reads_number, const std::string& graph_file_path) {
+ // Create a vector of lists to store the graph
std::vector<std::vector<int>> graph_lines(reads_number);
+ //std::vector<std::list<int>> graph_lines(reads_number);
// Start the timer
auto start = std::chrono::high_resolution_clock::now();
@@ -141,6 +147,11 @@ void minlist_to_graph(int reads_number, const std::vector<std::vector<int>>& min
}
}
+ // End the timer and print the elapsed time
+ auto end = std::chrono::high_resolution_clock::now();
+ std::chrono::duration<double> elapsed = end - start;
+ std::cout << elapsed.count() << " create graph" << std::endl;
+
// Calculate the number of edges in the graph
int edge_number = 0;
for (const auto& neighbours_list_by_id : graph_lines) {
@@ -153,31 +164,107 @@ void minlist_to_graph(int reads_number, const std::vector<std::vector<int>>& min
// Write the number of vertices and edges to the output file
output_graph_file << reads_number << " " << edge_number << std::endl;
-
+
// Write the graph to the output file
for (const auto& neighbours_list_by_id : graph_lines) {
- for (int i = 0; i < neighbours_list_by_id.size(); i++) {
- output_graph_file << neighbours_list_by_id[i];
- if (i != neighbours_list_by_id.size() - 1) {
- output_graph_file << " ";
- }
+ for (const auto& neighbour : neighbours_list_by_id) {
+ output_graph_file << neighbour << " ";
}
output_graph_file << std::endl;
}
+ // End the timer and print the elapsed time
+ end = std::chrono::high_resolution_clock::now();
+ elapsed = end - start;
+ std::cout << elapsed.count() << "s for min_list of graph" << std::endl;
+}
+
+
+void minlist_to_csv(const std::vector<std::vector<int>>& minimizer_list, int reads_number, const std::string& output_file) {
+ // Start the timer
+ auto start = std::chrono::high_resolution_clock::now();
+
+ // Get the number of minimizers
+ int minimizers_number = minimizer_list.size();
+
+ // Create a binary matrix to store the minimizer-read relationships
+ std::vector<std::vector<int>> matrix(minimizers_number, std::vector<int>(reads_number, 0));
+
+ // Iterate over the minimizer list
+ for (int i = 0; i < minimizers_number; i++) {
+ // Iterate over the list of reads that contain the current minimizer
+ for (int read_id : minimizer_list[i]) {
+ // Set the corresponding cell in the matrix to 1
+ matrix[i][read_id] = 1;
+ }
+ }
+
+ // Open the output file
+ std::ofstream outfile(output_file);
+
+ // Write the column headers to the output file
+ outfile << "min,";
+ for (int j = 0; j < reads_number; j++) {
+ outfile << "r" << j;
+ if (j < reads_number - 1) {
+ outfile << ",";
+ }
+ }
+ outfile << "\n";
+
+ // Write the matrix to the output file in CSV format
+ for (int i = 0; i < minimizers_number; i++) {
+ outfile << "m" << i << ",";
+ for (int j = 0; j < reads_number; j++) {
+ outfile << matrix[i][j];
+ if (j < reads_number - 1) {
+ outfile << ",";
+ }
+ }
+ outfile << "\n";
+ }
+
+ // Close the output file
+ outfile.close();
+
// End the timer and print the elapsed time
auto end = std::chrono::high_resolution_clock::now();
std::chrono::duration<double> elapsed = end - start;
- std::cout << elapsed.count() << " min_list of graph" << std::endl;
+ std::cout << elapsed.count() << "s for minlist_to_csv" << std::endl;
}
-int main() {
- std::string filename = "partition_C/shuffled_reads.fastq";
- std::vector<std::vector<int>> minimizer_list = get_minimizers(filename);
- minlist_to_graph(10000, minimizer_list, "partition_C/reads.graph");
+int main(int argc, char* argv[]) {
+
+ // Check if the input and output file paths are provided as arguments
+ if (argc != 3) {
+ std::cerr << "Usage: " << argv[0] << " <input_fastq> <output_file>" << std::endl;
+ return 1;
+ }
+
+ // Get the input and output file paths from the arguments
+ std::string input_fastq = argv[1];
+ std::string output_file = argv[2];
+
+ // get the number of sequences from the fastq
+ std::ifstream file(input_fastq);
+ std::string line;
+ int seq_number = 0;
+
+ while (std::getline(file, line)) {
+ if (line[0] == '@') {
+ seq_number++;
+ }
+ }
+
+ // Extract the minimizers from the input file
+ std::vector<std::vector<int>> minimizer_list = get_minimizers(input_fastq);
+
+ // Write the minimizer matrix to the output file in CSV format
+ //minlist_to_csv(minimizer_list, seq_number, output_file);
+ minlist_to_graph(minimizer_list, seq_number, output_file);
return 0;
}