Merge pull request #4 from cpockrandt/develop

GenMap 1.0 release
cpockrandt · May 28, 2019 · b1c9e93 · b1c9e93
2 parents 743b410 + 0692a03
commit b1c9e93
Show file tree

Hide file tree

Showing 6 changed files with 66 additions and 31 deletions.
diff --git a/CMakeLists.txt b/CMakeLists.txt
@@ -17,8 +17,8 @@ project (genmap CXX)
 # ----------------------------------------------------------------------------
 
 # change this after every release
-set (SEQAN_APP_VERSION_MAJOR "0")
-set (SEQAN_APP_VERSION_MINOR "9")
+set (SEQAN_APP_VERSION_MAJOR "1")
+set (SEQAN_APP_VERSION_MINOR "0")
 set (SEQAN_APP_VERSION_PATCH "0")
 # don't change the following
 set (SEQAN_APP_VERSION "${SEQAN_APP_VERSION_MAJOR}.${SEQAN_APP_VERSION_MINOR}.${SEQAN_APP_VERSION_PATCH}")

diff --git a/README.rst b/README.rst
@@ -1,5 +1,8 @@
-GenMap - Fast and Exact Computation of Genome Mappability |buildstatus|
------------------------------------------------------------------------
+GenMap 1.0 |buildstatus|
+------------------------
+
+Fast and Exact Computation of Genome Mappability
+================================================
 
 .. |BUILDSTATUS| image:: https://travis-ci.org/cpockrandt/genmap.svg?branch=master
     :target: https://travis-ci.org/cpockrandt/genmap
@@ -18,10 +21,9 @@ multiple fasta files, please check out our GitHub `Wiki pages <https://github.co
 For questions or feature requests feel free to open an issue on GitHub or send an e-mail to
 ``christopher.pockrandt [ÄT] fu-berlin.de``.
 
-The corresponding paper will be uploaded to biorxiv.org in mid-March.
-Until then major design changes of the interface and minor changes to its specification are possible.
+Christopher Pockrandt, Mai Alzamel, Costas S. Iliopoulos, Knut Reinert. **GenMap: Fast and Exact Computation of Genome Mappability**. `bioRxiv`_, presented on RECOMB-Seq, 2019.
 
-.. x contents:: Table of Contents
+.. _bioRxiv: https://doi.org/10.1101/611160
 
 Binaries
 ^^^^^^^^
@@ -36,22 +38,22 @@ To verify whether your CPU supports these instructions sets you can check the ou
 .. Source of linux.svg: https://svgsilh.com/image/2025536.html
 .. Source of apple.svg: https://svgsilh.com/image/2962084.html
 
-+---------------------------------+---------------------------+-----------------------------+
-| **Platform**                    | **Details**               | **Additional requirements** |
-+---------------------------------+---------------------------+-----------------------------+
-| .. image:: .github/linux.svg    | `Linux 64 bit`_           | \-                          |
-+   :alt: Download Linux binaries +---------------------------+-----------------------------+
-|   :height: 60px                 | `Linux 64 bit optimized`_ | requires up to SSE4         |
-+---------------------------------+---------------------------+-----------------------------+
-| .. image:: .github/apple.svg    | `Mac 64 bit`_             | \-                          |
-+   :alt: Download Mac binaries   +---------------------------+-----------------------------+
-|   :height: 60px                 | `Mac 64 bit optimized`_   | requires up to SSE4         |
-+---------------------------------+---------------------------+-----------------------------+
-
-.. _Linux 64 bit: http://ftp.imp.fu-berlin.de/pub/cpockrandt/genmap/genmap-0.9-Linux-x86_64.zip
-.. _Linux 64 bit optimized: http://ftp.imp.fu-berlin.de/pub/cpockrandt/genmap/genmap-0.9-Linux-x86_64-sse4.zip
-.. _Mac 64 bit: http://ftp.imp.fu-berlin.de/pub/cpockrandt/genmap/genmap-0.9-Darwin-x86_64.zip
-.. _Mac 64 bit optimized: http://ftp.imp.fu-berlin.de/pub/cpockrandt/genmap/genmap-0.9-Darwin-x86_64-sse4.zip
++---------------------------------+---------------------------+------------------+-----------------------------+
+| **Platform**                    | **Download**              | **Version**      | **Additional requirements** |
++---------------------------------+---------------------------+------------------+-----------------------------+
+| .. image:: .github/linux.svg    | `Linux 64 bit`_           | 1.0 (2019-05-27) | \-                          |
++   :alt: Download Linux binaries +---------------------------+------------------+-----------------------------+
+|   :height: 60px                 | `Linux 64 bit optimized`_ | 1.0 (2019-05-27) | requires up to SSE4         |
++---------------------------------+---------------------------+------------------+-----------------------------+
+| .. image:: .github/apple.svg    | `Mac 64 bit`_             | 1.0 (2019-05-27) | \-                          |
++   :alt: Download Mac binaries   +---------------------------+------------------+-----------------------------+
+|   :height: 60px                 | `Mac 64 bit optimized`_   | 1.0 (2019-05-27) | requires up to SSE4         |
++---------------------------------+---------------------------+------------------+-----------------------------+
+
+.. _Linux 64 bit: http://ftp.imp.fu-berlin.de/pub/cpockrandt/genmap/genmap-1.0-Linux-x86_64.zip
+.. _Linux 64 bit optimized: http://ftp.imp.fu-berlin.de/pub/cpockrandt/genmap/genmap-1.0-Linux-x86_64-sse4.zip
+.. _Mac 64 bit: http://ftp.imp.fu-berlin.de/pub/cpockrandt/genmap/genmap-1.0-Darwin-x86_64.zip
+.. _Mac 64 bit optimized: http://ftp.imp.fu-berlin.de/pub/cpockrandt/genmap/genmap-1.0-Darwin-x86_64-sse4.zip
 
 Building from source
 ^^^^^^^^^^^^^^^^^^^^
@@ -213,3 +215,18 @@ If you need other genomes indexed and do not have the computational resources, p
 .. _`dm6 index`:    http://ftp.imp.fu-berlin.de/pub/cpockrandt/genmap/indices/dm6-dna5.tar.gz
 .. _`ce11 index`:   http://ftp.imp.fu-berlin.de/pub/cpockrandt/genmap/indices/ce11-dna5.tar.gz
 .. _`hv index`:     http://ftp.imp.fu-berlin.de/pub/cpockrandt/genmap/indices/hv-dna5.tar.gz
+
+Changelog
+^^^^^^^^^
+
+1.0 (2019-05-27)
+""""""""""""""""
+
+* faster computation of mappability for 3 and 4 errors
+* included the reference to the paper (preprint)
+* minor fixes in documentation and error messages
+
+0.9 (2019-03-23)
+""""""""""""""""
+
+* preliminary version of GenMap released
diff --git a/src/find2_index_approx.hpp b/src/find2_index_approx.hpp
@@ -105,9 +105,9 @@ struct OptimalSearchSchemesGM<3, TVoidType>
 {
     static constexpr std::array<OptimalSearchGM<5>, 4> VALUE
     {{
-        { {{1, 2, 3, 4, 5}}, {{0, 0, 0, 0, 3}}, {{0, 2, 2, 3, 3}}, {{0, 0, 0, 0, 0}}, 0 },
+        { {{1, 2, 3, 4, 5}}, {{0, 0, 0, 0, 3}}, {{0, 1, 2, 3, 3}}, {{0, 0, 0, 0, 0}}, 0 },
         { {{2, 3, 4, 5, 1}}, {{0, 0, 0, 2, 2}}, {{0, 1, 2, 2, 3}}, {{0, 0, 0, 0, 0}}, 0 },
-        { {{3, 4, 5, 2, 1}}, {{0, 0, 1, 1, 1}}, {{0, 1, 1, 2, 3}}, {{0, 0, 0, 0, 0}}, 0 },
+        { {{3, 4, 5, 2, 1}}, {{0, 0, 1, 1, 1}}, {{0, 1, 1, 3, 3}}, {{0, 0, 0, 0, 0}}, 0 },
         { {{5, 4, 3, 2, 1}}, {{0, 0, 0, 0, 0}}, {{0, 0, 3, 3, 3}}, {{0, 0, 0, 0, 0}}, 0 }
     }};
 };
@@ -118,18 +118,20 @@ constexpr std::array<OptimalSearchGM<5>, 4> OptimalSearchSchemesGM<3, TVoidType>
 template <typename TVoidType>
 struct OptimalSearchSchemesGM<4, TVoidType>
 {
-    static constexpr std::array<OptimalSearchGM<6>, 5> VALUE
+    static constexpr std::array<OptimalSearchGM<6>, 7> VALUE
     {{
-        { {{1, 2, 3, 4, 5, 6}}, {{0, 0, 0, 0, 0, 4}}, {{0, 3, 3, 3, 4, 4}}, {{0, 0, 0, 0, 0, 0}}, 0 },
+        { {{1, 2, 3, 4, 5, 6}}, {{0, 0, 0, 0, 0, 4}}, {{0, 2, 3, 3, 4, 4}}, {{0, 0, 0, 0, 0, 0}}, 0 },
+        { {{3, 4, 5, 6, 2, 1}}, {{0, 0, 0, 1, 4, 4}}, {{0, 0, 1, 1, 4, 4}}, {{0, 0, 0, 0, 0, 0}}, 0 },
         { {{2, 3, 4, 5, 6, 1}}, {{0, 0, 0, 0, 0, 0}}, {{0, 2, 2, 3, 3, 4}}, {{0, 0, 0, 0, 0, 0}}, 0 },
-        { {{3, 2, 4, 5, 6, 1}}, {{0, 1, 1, 1, 1, 1}}, {{0, 2, 2, 3, 3, 4}}, {{0, 0, 0, 0, 0, 0}}, 0 },
+        { {{3, 2, 4, 5, 6, 1}}, {{0, 1, 1, 1, 1, 1}}, {{0, 1, 2, 3, 3, 4}}, {{0, 0, 0, 0, 0, 0}}, 0 },
+        { {{4, 3, 2, 5, 6, 1}}, {{0, 0, 2, 2, 2, 2}}, {{0, 0, 2, 3, 3, 4}}, {{0, 0, 0, 0, 0, 0}}, 0 },
         { {{4, 3, 2, 5, 6, 1}}, {{0, 1, 2, 2, 2, 2}}, {{0, 1, 2, 3, 3, 4}}, {{0, 0, 0, 0, 0, 0}}, 0 },
         { {{6, 5, 4, 3, 2, 1}}, {{0, 0, 0, 0, 3, 3}}, {{0, 0, 4, 4, 4, 4}}, {{0, 0, 0, 0, 0, 0}}, 0 }
     }};
 };
 
 template <typename TVoidType>
-constexpr std::array<OptimalSearchGM<6>, 5> OptimalSearchSchemesGM<4, TVoidType>::VALUE;
+constexpr std::array<OptimalSearchGM<6>, 7> OptimalSearchSchemesGM<4, TVoidType>::VALUE;
 
 // Given the blocklengths (absolute, not cumulative values), assign it to all
 // OptimalSearches in a OptimalSearchScheme. The order of blocklength has to be from left to

diff --git a/src/genmap_helper.hpp b/src/genmap_helper.hpp
@@ -16,7 +16,8 @@ void sharedSetup(ArgumentParser & parser)
     setShortCopyright(parser, "2019 Christopher Pockrandt, released under the 3-clause-BSD; "
                               "2016-2019 Knut Reinert and Freie Universität Berlin, released under the 3-clause-BSD");
 
-    setCitation(parser, "Pockrandt et al (2019); doi: TODO");
+    setCitation(parser, "Pockrandt et al (2019). GenMap: Fast and Exact Computation of Genome Mappability.\n"
+                        "doi: https://doi.org/10.1101/611160");
 
     setLongCopyright(parser,
         " Copyright (c) 2019, Christopher Pockrandt\n"

diff --git a/src/indexing.hpp b/src/indexing.hpp
@@ -252,9 +252,25 @@ int indexMain(int const argc, char const ** argv)
     toLower(algorithm);
     options.directory = isSetFastaDirectory;
     if (isSetFastaDirectory)
+    {
         getOptionValue(fastaPath, parser, "fasta-directory");
+        struct stat st;
+        if (!(stat(toCString(fastaPath), &st) == 0 && S_ISDIR(st.st_mode)))
+        {
+            std::cerr << "ERROR: The fasta directory does not exist!\n";
+            return ArgumentParser::PARSE_ERROR;
+        }
+    }
     else
+    {
         getOptionValue(fastaPath, parser, "fasta-file");
+        if (!fileExists(toCString(fastaPath)))
+        {
+            std::cerr << "ERROR: The fasta file does not exist!\n";
+            return ArgumentParser::PARSE_ERROR;
+        }
+    }
+
     options.useRadix = algorithm == "radix";
     options.verbose = isSet(parser, "verbose");
 

diff --git a/src/mappability.hpp b/src/mappability.hpp
@@ -276,7 +276,6 @@ inline void run(Options const & opt, SearchParams const & searchParams)
     {
         std::cerr << "ERROR: EditDistance is not officially supported yet. Coming soon!\n";
         exit(1);
-        // run<TChar, TAllocConfig, EditDistance>(opt, searchParams);
     }
     else
         run<TChar, TAllocConfig, HammingDistance>(opt, searchParams);