Merge pull request #1192 from smehringer/alignmentIO_cigar_string

Add CIGAR string support to alignment IO
seqan · Oct 9, 2019 · 9f98962 · 9f98962
2 parents 19ab4cd + 1cf7756
commit 9f98962
Show file tree

Hide file tree

Showing 15 changed files with 558 additions and 458 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -31,6 +31,8 @@ If possible, provide tooling that performs the changes, e.g. a shell-script.
 #### Input/Output
 
 * Asynchronous input (background file reading) supported via seqan3::view::async_input_buffer.
+* Reading field::CIGAR into a vector over seqan3::cigar is supported via seqan3::alignment_file_input.
+* Writing field::CIGAR into a vector over seqan3::cigar is supported via seqan3::alignment_file_output.
 
 ## API changes
 

diff --git a/doc/tutorial/alignment_file/alignment_file_read_cigar.cpp b/doc/tutorial/alignment_file/alignment_file_read_cigar.cpp
@@ -0,0 +1,44 @@
+#include <fstream>
+
+#include <seqan3/std/filesystem>
+
+struct write_file_dummy_struct
+{
+    write_file_dummy_struct()
+    {
+
+auto file_raw = R"//![sam_file](
+@HD	VN:1.6	SO:coordinate
+@SQ	SN:ref	LN:45
+r001	99	ref	7	30	8M2I4M1D3M	=	37	39	TTAGATAAAGGATACTG	*
+r003	0	ref	9	30	5S6M	*	0	0	GCCTAAGCTAA	*	SA:Z:ref,29,-,6H5M,17,0;
+r004	0	ref	16	30	6M14N5M	*	0	0	ATAGCTTCAGC	*
+r003	2064	ref	29	17	5M	*	0	0	TAGGC	*	SA:Z:ref,9,+,5S6M,30,1;
+r001	147	ref	37	30	9M	=	7	-39	CAGCGGCAT	*	NM:i:1
+)//![sam_file]";
+
+        std::ofstream file{std::filesystem::temp_directory_path()/"my.sam"};
+        std::string str{file_raw};
+        file << str.substr(1); // skip first newline
+    }
+};
+
+write_file_dummy_struct go{};
+
+//![code]
+#include <seqan3/core/debug_stream.hpp>
+#include <seqan3/io/alignment_file/all.hpp>
+#include <seqan3/std/filesystem>
+
+using namespace seqan3;
+
+int main()
+{
+    std::filesystem::path tmp_dir = std::filesystem::temp_directory_path(); // get the temp directory
+
+    alignment_file_input fin{tmp_dir/"my.sam", fields<field::CIGAR>{}};
+
+    for (auto & [cigar] : fin)
+        debug_stream << cigar << std::endl;
+}
+//![code]
diff --git a/doc/tutorial/alignment_file/index.md b/doc/tutorial/alignment_file/index.md
@@ -80,19 +80,19 @@ but you needn't deal with this field manually.
 Note that some of the fields are specific to the SAM format, while some are specific to BLAST.
 To make things clearer, here is the table of SAM columns connected to the corresponding alignment file field:
 
-| #  | SAM Column ID |  FIELD name                                       |
-|:--:|:--------------|:--------------------------------------------------|
-| 1  | QNAME         | seqan3::field::ID                                 |
-| 2  | FLAG          | seqan3::field::FLAG                               |
-| 3  | RNAME         | seqan3::field::REF_ID                             |
-| 4  | POS           | seqan3::field::REF_OFFSET                         |
-| 5  | MAPQ          | seqan3::field::MAPQ                               |
-| 6  | CIGAR         | implicitly stored in seqan3::field::ALIGNMENT     |
-| 7  | RNEXT         | seqan3::field::MATE (tuple pos 0)                 |
-| 8  | PNEXT         | seqan3::field::MATE (tuple pos 1)                 |
-| 9  | TLEN          | seqan3::field::MATE (tuple pos 2)                 |
-| 10 | SEQ           | seqan3::field::SEQ                                |
-| 11 | QUAL          | seqan3::field::QUAL                               |
+| #  | SAM Column ID |  FIELD name                                                                       |
+|:--:|:--------------|:----------------------------------------------------------------------------------|
+| 1  | QNAME         | seqan3::field::ID                                                                 |
+| 2  | FLAG          | seqan3::field::FLAG                                                               |
+| 3  | RNAME         | seqan3::field::REF_ID                                                             |
+| 4  | POS           | seqan3::field::REF_OFFSET                                                         |
+| 5  | MAPQ          | seqan3::field::MAPQ                                                               |
+| 6  | CIGAR         | implicitly stored in seqan3::field::ALIGNMENT or directly in seqan3::field::CIGAR |
+| 7  | RNEXT         | seqan3::field::MATE (tuple pos 0)                                                 |
+| 8  | PNEXT         | seqan3::field::MATE (tuple pos 1)                                                 |
+| 9  | TLEN          | seqan3::field::MATE (tuple pos 2)                                                 |
+| 10 | SEQ           | seqan3::field::SEQ                                                                |
+| 11 | QUAL          | seqan3::field::QUAL                                                               |
 
 ## File extensions
 
@@ -265,6 +265,13 @@ r004 mapped against 1 with 0 gaps in the read sequence and 0 gaps in the referen
 
 \endsolution
 
+## Reading the CIGAR string
+
+If you are accustomed to the raw CIGAR information, we also provide reading the cigar information into a
+`std::vector<seqan3::cigar>` if you specify the `seqan3::field::CIGAR`.
+
+\snippet doc/tutorial/alignment_file/alignment_file_read_cigar.cpp code
+
 # Writing alignment files
 
 ## Writing records

diff --git a/include/seqan3/io/alignment_file/all.hpp b/include/seqan3/io/alignment_file/all.hpp
@@ -17,6 +17,7 @@
  * \brief Provides files and formats for handling alignment data.
  */
 
+#include <seqan3/io/alignment_file/format_bam.hpp>
 #include <seqan3/io/alignment_file/format_sam.hpp>
 #include <seqan3/io/alignment_file/header.hpp>
 #include <seqan3/io/alignment_file/input.hpp>