added filters in alignment results

README.md

@@ -1,40 +1,32 @@
 # RNAnue - 0.0.1
 
 ## About
-
 RNAnue is a comprehensive analysis to detect RNA-RNA interactions from Direct-Duplex-Detection (DDD) data.
 
 ## Install
-
 ### Dependencies
-
 RNAnue has the following dependencies, whereas the brackets indicate the version RNAnue has 
 been build and tested on. Make sure the requirements are satified by your system. 
 
-* [Boost C++ Libraries](https://www.boost.org/)
+* [Boost C++ Libraries](https://www.boost.org/) (v1.7.2)
 * [SeqAn](https://github.com/seqan/seqan3) (v3.0.2)
 * [Segemehl](http://www.bioinf.uni-leipzig.de/Software/segemehl/) (v0.3.4)
 
-
 ### CMake 
-
 CMake is a cross-platform Makefile generator. For that, we provide the [CMakeLists](./CMakeLists.txt) 
-to simplify the build process. In particular, it utilizes the instructions given in the CMakeLists 
-
+to simplify the build process. In particular, it utilizes the instructions given in the CMakeLists.
 It is recommended to create a "out-of-source build". For that, create a build folder (e.g., ./bin)
 and cmake into the root directory.
-
 ```
-cmake ..\
+cmake ../source/
 ```
+This should be sufficient if the dependencies are located in $PATH. Calling `make` builds RNAnue. 
 
 ## Usage
-
-In principle, the parameters of RNAnue can be specified on the command line.
-However
-
+In principle, the parameters of RNAnue can be specified on the command line. However
 ### Positional Arguments
-RNAnue provides different functional arguments for individual procedures.
+RNAnue provides different functional arguments for individual procedures. These include `RNAnue preproc`, 
+`RNAnue align`, `RNAnue clustering`, `RNAnue analysis`.
 
 ## Parameters
 RNAnue accepts parameter settings both from the commandline and through a configuration file.
@@ -44,13 +36,20 @@ is reduced to the following call.
 ```
 RNAnue subcall --config /path/to/params.cfg
 ```
-However,  
+In any case, the specifying parameters over the command lines has precedence over the config file.
 
-### Availability
+### Docker
+In additon, we provide a ready-to-use Docker container that has RNAnue preconfigured.
+https://hub.docker.com/repository/docker/cobirna/rnanue
 
+### Preproc
 
-## Usage
+### Align
+
+### Clustering
+
+### Analysis
 
-### Configuration
-RNAnue provides several possi
+## Output
 
+# Troubleshooting

include/Align.hpp

@@ -0,0 +1,77 @@
+// boost
+#include <boost/program_options.hpp>
+#include <boost/property_tree/ptree.hpp>
+#include <boost/filesystem.hpp>
+
+#include <iostream>
+#include <sstream>
+#include <stdlib.h>
+#include <stdio.h>
+#include <string.h>
+#include <regex>
+
+#include <seqan3/io/alignment_file/all.hpp>
+#include <seqan3/std/filesystem>
+#include <seqan3/io/alignment_file/sam_tag_dictionary.hpp>
+#include <seqan3/alphabet/nucleotide/dna5.hpp>
+
+#include <seqan3/alphabet/cigar/cigar.hpp>
+#include <seqan3/alphabet/cigar/cigar_op.hpp>
+
+#include <bitset>
+
+namespace pt = boost::property_tree;
+namespace po = boost::program_options;
+namespace fs = boost::filesystem;
+
+using seqan3::operator""_tag;
+using seqan3::operator""_cigar_op;
+using seqan3::operator""_dna5;
+using seqan3::get;
+
+// overload struct to 
+template <> struct seqan3::sam_tag_type<"XX"_tag> { using type = int32_t; };
+template <> struct seqan3::sam_tag_type<"XY"_tag> { using type = int32_t; };
+template <> struct seqan3::sam_tag_type<"XJ"_tag> { using type = int32_t; };
+template <> struct seqan3::sam_tag_type<"XH"_tag> { using type = int32_t; };
+
+typedef std::pair<uint32_t,uint32_t> ReadPos;
+typedef std::pair<uint64_t,uint64_t> GenomePos;
+typedef std::vector<seqan3::cigar> CigarSplt;
+
+
+typedef std::vector<
+	std::tuple<
+		std::string,
+		seqan3::sam_flag, 
+		std::optional<int32_t>,
+		std::optional<int32_t>,
+        std::vector<seqan3::cigar>,
+        seqan3::dna5_vector,
+        seqan3::sam_tag_dictionary>> Splts;
+
+class Align {
+    private:
+        po::variables_map params;
+        std::string index;
+
+
+    public:
+        // constructor
+        Align(po::variables_map params);
+        Align();
+
+        void buildIndex();
+        void alignReads(std::string query, std::string matched, std::string splits);
+        void detSplits(std::string matched, std::string splits);
+
+        double hybridize(std::string rna1, std::string rna2);
+        double complementarity(std::string rna1, std::string rna2);
+
+        void processSplits(auto &splitrecords, auto &splitsfile);
+        std::vector<seqan3::dna5> spanToVec(std::span<seqan3::dna5,-1> seq);
+
+        void constructIndex();
+        void start(pt::ptree sample);
+};
+

include/Data.hpp

@@ -11,7 +11,9 @@
 #include <boost/property_tree/json_parser.hpp>
 #include <boost/foreach.hpp>
 
+
 #include "SeqRickshaw.hpp"
+#include "Align.hpp"
 
 namespace po = boost::program_options;
 namespace fs = boost::filesystem;
@@ -40,6 +42,7 @@ class Data {
         Data(po::variables_map _params);
 
         // getter & setter
+        //
         pt::ptree getDataStructure();
 
         //
@@ -69,6 +72,7 @@ class Data {
         void bla(Callable f);
 
         void preproc();
+        void align();
 };
 
 #endif // DATA_HPP

include/SeqRickshaw.hpp

@@ -28,6 +28,8 @@
 #include <seqan3/range/views/char_to.hpp>
 #include <seqan3/range/views/slice.hpp>  
 
+#include <seqan3/std/ranges>
+
 #include <seqan3/range/views/all.hpp>
 #include <seqan3/std/ranges> // std::ranges::copy
 
@@ -85,32 +87,27 @@ class SeqRickshaw {
         std::size_t calcReadPos(auto& sequence, std::size_t& left, std::pair<std::size_t,std::size_t>& right);
 
 
-        void panic(State state, std::string pattern, char mismatch, int readPos);
 
         void smallestShift(std::string pattern, std::string suffix, int left);
 
         int transition(std::string pattern, std::string suffix, int readPos, std::size_t& left, std::pair<std::size_t,std::size_t>& right);
 
-        int extendblock(std::string pattern, std::string suffix, int& left);
-
+        void merging(auto fwd, auto rev);
 
-        int reoccurrence(std::string pattern, std::string suffix, std::size_t& left); 
 
+        std::string longestCommonSubstr(std::string forward, std::string reverse);
 
 
 
 
         // helper 
         int addState(States &states, State state, States::size_type &size);
         int nextReadPos(std::string state, int currReadPos);
-        std::pair<int,int> countConsecutiveMatches(std::string stateSubstr, int readPos);
         // finds all occurrences of substring in string
         void findAllOcc(std::vector<std::size_t>& fnd, std::string str, std::string substr);
+        void writeLookupTable(std::ofstream &os);
 
         void preprocPattern();
-
-
-        void writeLookupTable(std::ofstream &os);
 
 
         std::size_t boyermoore(auto& read, LookupTable tab, int patlen);