Merge pull request smirarab#28 from kodicollins/master

new sub-aligners within PASTA

README.md

@@ -88,6 +88,11 @@ You need to rename these directories and remove the `-master` part.
 Finally, those with 32-bit Linux machines need to be aware that the master branch has 64-bit binaries.
 32-bit binaries are provided in the `32bit` branch of `sate-tools-linux` git project (so download [this zip file](https://github.com/smirarab/sate-tools-linux/archive/32bit.zip) instead). 
 
+*If you want to use MAFFT-Homologs within PASTA*
+`cd sate-tools-linux` or `cd sate-tools-mac`
+Use `git https://github.com/kodicollins/pasta-databases` or download directly at `https://github.com/kodicollins/pasta-databases.git`
+*Be sure to leave this directory `cd ..` before starting the next step*
+
 4. `cd pasta` (or `cd pasta-master` if you used the zip file instead of clonning the git repository)
 
 5. Then run:
@@ -104,6 +109,14 @@ If you don't have root access, remove the `sudo` part and instead  use  `--user`
  * The `setup.py` script is supposed to install setuptools for you if you don't have it. This sometimes works and sometimes doesn't. If you get an error with a message like ` invalid command 'develop'`, it means that setuptools is not installed. To solve this issue, you can manually install [setup tools](https://pypi.python.org/pypi/setuptools#installation-instructions). For example, on Linux, you can run `curl https://bootstrap.pypa.io/ez_setup.py -o - | sudo python` 
 (but note there are other ways of installing setuptools as well).
 
+6. Pasta now includes additional aligners for Linux and MAC users: mafft-ginsi, mafft-homologs, contralign (version 1), and probcons. In order to use mafft-homologs and contralign, the user must set the environment variable CONTRALIGN_DIR=/dir/to/sate-tools-linux. 
+
+A simple step-by-step for this is as following:
+	a. change your directory to sate-tools-linux (or sate-tools-mac), type `pwd` in the command line, and copy the output
+	b. `vim ~/.bashrc`, press i and then type CONTRALIGN_DIR=(paste the copied output/directory) at the bottom of the text file, the press ESC followed by :wq
+	c. then in the command line type `source ~/.bashrc`
+
+To use these aligners, add the following to your pasta execution --aligner=NAME_OF_ALIGNER, where NAME_OF_ALIGNER now includes (ginsi, homologs, contralign, and probcons)
 
 ### 3. From Virtual Machine (VM)
 

pasta/settings.py

@@ -27,6 +27,12 @@ def __init__(self):
         self._categories.append('probalign')
         self.probcons = UserSettingGroup('probcons')
         self._categories.append('probcons')        
+        self.contralign = UserSettingGroup('contralign')
+        self._categories.append('contralign')        
+        self.ginsi = UserSettingGroup('ginsi')
+        self._categories.append('ginsi')        
+        self.homologs = UserSettingGroup('homologs')
+        self._categories.append('homologs')        
         self.padaligner = UserSettingGroup('padaligner')
         self._categories.append('padaligner')
         self.clustalw2 = UserSettingGroup('clustalw2')
@@ -58,14 +64,20 @@ def __init__(self):
         self.fasttree.add_option('args', StringUserSetting(name='args', default='', short_name=None, help='Arguments to be passed to FastTree.', subcategory=None))
         self.opal.add_option('path', StringUserSetting(name='path', default='', short_name=None, help='Path to Opal jar file', subcategory=None))
         self.opal.add_option('args', StringUserSetting(name='args', default='', short_name=None, help='Arguments to be passed to Opal.', subcategory=None))
-        self.clustalw2.add_option('path', StringUserSetting(name='path', default='', short_name=None, help='Path to clustalw2 exeutable', subcategory=None))
+        self.clustalw2.add_option('path', StringUserSetting(name='path', default='', short_name=None, help='Path to clustalw2 executable', subcategory=None))
         self.clustalw2.add_option('args', StringUserSetting(name='args', default='', short_name=None, help='Arguments to be passed to Clustalw2.', subcategory=None))
-        self.muscle.add_option('path', StringUserSetting(name='path', default='', short_name=None, help='Path to muscle exeutable', subcategory=None))
+        self.muscle.add_option('path', StringUserSetting(name='path', default='', short_name=None, help='Path to muscle executable', subcategory=None))
         self.muscle.add_option('args', StringUserSetting(name='args', default='', short_name=None, help='Arguments to be passed to Muscle.', subcategory=None))
-        self.probalign.add_option('path', StringUserSetting(name='path', default='', short_name=None, help='Path to ProbalignAligner exeutable', subcategory=None))
+        self.probalign.add_option('path', StringUserSetting(name='path', default='', short_name=None, help='Path to ProbalignAligner executable', subcategory=None))
         self.probalign.add_option('args', StringUserSetting(name='args', default='', short_name=None, help='Arguments to be passed to Probalign.', subcategory=None))
-        self.probcons.add_option('path', StringUserSetting(name='path', default='', short_name=None, help='Path to ProbConsAligner exeutable', subcategory=None))
+        self.probcons.add_option('path', StringUserSetting(name='path', default='', short_name=None, help='Path to ProbConsAligner executable', subcategory=None))
         self.probcons.add_option('args', StringUserSetting(name='args', default='', short_name=None, help='Arguments to be passed to ProbCons.', subcategory=None))        
+        self.contralign.add_option('path', StringUserSetting(name='path', default='', short_name=None, help='Path to ProbConsAligner executable', subcategory=None))
+        self.contralign.add_option('args', StringUserSetting(name='args', default='', short_name=None, help='Arguments to be passed to ProbCons.', subcategory=None))        
+        self.ginsi.add_option('path', StringUserSetting(name='path', default='', short_name=None, help='Path to ProbConsAligner executable', subcategory=None))
+        self.ginsi.add_option('args', StringUserSetting(name='args', default='', short_name=None, help='Arguments to be passed to ProbCons.', subcategory=None))        
+        self.homologs.add_option('path', StringUserSetting(name='path', default='', short_name=None, help='Path to ProbConsAligner executable', subcategory=None))
+        self.homologs.add_option('args', StringUserSetting(name='args', default='', short_name=None, help='Arguments to be passed to ProbCons.', subcategory=None))        
         self.commandline.add_option('exportconfig', StringUserSetting(name='exportconfig', default=None, short_name=None, help='Export the configuration to the specified file and exit. This is useful if you want to combine several configurations and command line settings into a single configuration file to be used in other analyses.', subcategory=None))
         self.commandline.add_option('input', StringUserSetting(name='input', default=None, short_name='i', help='input sequence file', subcategory=None))
         self.commandline.add_option('treefile', StringUserSetting(name='treefile', default=None, short_name='t', help='starting tree file', subcategory=None))

pasta/tools.py

@@ -257,6 +257,79 @@ def create_job(self, alignment, guide_tree=None, **kwargs):
                 delete_temps=kwargs.get('delete_temps', self.delete_temps),
                 stdout=alignedfn)
 
+class GinsiAligner(Aligner):
+    section_name = 'ginsi aligner'
+    #url = 'http://align.bmr.kyushu-u.ac.jp/mafft/software'
+    is_bundled = False
+
+    def __init__(self, temp_fs, **kwargs):
+        Aligner.__init__(self, 'ginsi', temp_fs, **kwargs)
+
+    def create_job(self, alignment, guide_tree=None, **kwargs):
+        job_id = kwargs.get('context_str', '') + '_ginsi'
+        if alignment.get_num_taxa() == 0:
+            return FakeJob(alignment, context_str=job_id)
+        new_alignment = alignment.unaligned()
+        if new_alignment.get_num_taxa() < 2:
+            return FakeJob(new_alignment, context_str=job_id)
+        scratch_dir, seqfn, alignedfn = self._prepare_input(new_alignment, **kwargs)
+
+        invoc = []
+        if platform.system() == "Windows":
+            invoc.append(self.exe)
+        else:
+            invoc.extend([self.exe])
+        invoc.extend(['--globalpair', '--maxiterate', '1000'])
+        if '--ep' not in self.user_opts:
+            invoc.extend(['--ep', '0.123'])
+        invoc.extend(['--quiet'])
+        invoc.extend(self.user_opts)
+        invoc.extend(['--thread',str(kwargs.get('num_cpus', 1))])
+        invoc.append(seqfn)
+
+        # The MAFFT job creation is slightly different from the other
+        #   aligners because we redirect and read standard output.
+
+        return self._finish_standard_job(alignedfn=alignedfn,
+                datatype=alignment.datatype,
+                invoc=invoc,
+                scratch_dir=scratch_dir,
+                job_id=job_id,
+                delete_temps=kwargs.get('delete_temps', self.delete_temps),
+                stdout=alignedfn)
+
+class HomologsAligner(Aligner):
+    section_name = 'homologs aligner'
+    #url = 'http://align.bmr.kyushu-u.ac.jp/mafft/software'
+    is_bundled_tool = False
+
+    def __init__(self, temp_fs, **kwargs):
+        Aligner.__init__(self, 'homologs', temp_fs, **kwargs)
+
+    def create_job(self, alignment, guide_tree=None, **kwargs):
+        job_id = kwargs.get('context_str', '') + '_homologs'
+        if alignment.get_num_taxa() == 0:
+            return FakeJob(alignment, context_str=job_id)
+        new_alignment = alignment.unaligned()
+        if new_alignment.get_num_taxa() < 2:
+            return FakeJob(new_alignment, context_str=job_id)
+        scratch_dir, seqfn, alignedfn = self._prepare_input(new_alignment, **kwargs)
+
+        invoc = [self.exe, '-l', seqfn]
+        invoc.extend(['--thread', str(kwargs.get('num_cpus', 1))])
+        invoc.extend(self.user_opts)
+
+        # The probcons job creation is slightly different from the other
+        #   aligners because we redirect and read standard output.
+
+        return self._finish_standard_job(alignedfn=alignedfn,
+                datatype=alignment.datatype,
+                invoc=invoc,
+                scratch_dir=scratch_dir,
+                job_id=job_id,
+                delete_temps=kwargs.get('delete_temps', self.delete_temps),
+                stdout=alignedfn)
+
 
 class OpalAligner(Aligner):
     section_name = 'opal aligner'
@@ -318,6 +391,37 @@ def create_job(self, alignment, guide_tree=None, **kwargs):
                                         job_id=job_id,
                                         delete_temps=kwargs.get('delete_temps', self.delete_temps))
 
+class ContralignAligner(Aligner):
+    section_name = 'contralign aligner'
+    url = 'http://contra.stanford.edu/contralign/'
+    is_bundled_tool = False
+
+    def __init__(self, temp_fs, **kwargs):
+        Aligner.__init__(self, 'contralign', temp_fs, **kwargs)
+
+    def create_job(self, alignment, guide_tree=None, **kwargs):
+        job_id = kwargs.get('context_str', '') + '_contralign'
+        if alignment.get_num_taxa() == 0:
+            return FakeJob(alignment, context_str=job_id)
+        new_alignment = alignment.unaligned()
+        if new_alignment.get_num_taxa() < 2:
+            return FakeJob(new_alignment, context_str=job_id)
+        scratch_dir, seqfn, alignedfn = self._prepare_input(new_alignment, **kwargs)
+
+        invoc = [self.exe, seqfn]
+        invoc.extend(self.user_opts)
+
+        # The probcons job creation is slightly different from the other
+        #   aligners because we redirect and read standard output.
+
+        return self._finish_standard_job(alignedfn=alignedfn,
+                datatype=alignment.datatype,
+                invoc=invoc,
+                scratch_dir=scratch_dir,
+                job_id=job_id,
+                delete_temps=kwargs.get('delete_temps', self.delete_temps),
+                stdout=alignedfn)
+
 class MuscleAligner(Aligner):
     section_name = 'muscle aligner'
     url = 'http://www.drive5.com/muscle'
@@ -970,11 +1074,11 @@ def create_job(self, backbone, query_fn, **kwargs):
                                         delete_temps=kwargs.get('delete_temps', self.delete_temps))
 
 if GLOBAL_DEBUG:
-    AlignerClasses = (ProbalignAligner, Clustalw2Aligner, MafftAligner, PrankAligner, OpalAligner, PadAligner, FakeAligner, CustomAligner, HMMERAlignAligner, ProbconsAligner)
+    AlignerClasses = (GinsiAligner, HomologsAligner, ContralignAligner, ProbalignAligner, Clustalw2Aligner, MafftAligner, PrankAligner, OpalAligner, PadAligner, FakeAligner, CustomAligner, HMMERAlignAligner, ProbconsAligner)
     MergerClasses = (MuscleMerger, OpalMerger)
     TreeEstimatorClasses = (FastTree, Randtree, Raxml, FakeTreeEstimator, CustomTreeEstimator)
 else:
-    AlignerClasses = (ProbalignAligner, Clustalw2Aligner, MafftAligner, PrankAligner, OpalAligner, MuscleAligner, CustomAligner, HMMERAlignAligner)
+    AlignerClasses = (GinsiAligner, HomologsAligner, ContralignAligner, ProbconsAligner, ProbalignAligner, Clustalw2Aligner, MafftAligner, PrankAligner, OpalAligner, MuscleAligner, CustomAligner, HMMERAlignAligner)
     MergerClasses = (MuscleMerger, OpalMerger, CustomMerger)
     TreeEstimatorClasses = (Raxml, FastTree, CustomTreeEstimator)
 

setup.py

@@ -19,7 +19,7 @@
 import platform
 import sys
 import pasta
-
+import tarfile
 script_name = 'run_pasta.py' 
 gui_script_name = 'run_pasta_gui.py'
 
@@ -187,13 +187,24 @@ def create_symlink(src_path, subdir=None):
     for subdir in tools_bin_subdirs:
         if subdir:
             tdir = os.path.join(tools_bin_srcdir, subdir)
+	    #print 'tdir' + str(tdir)
         else:
             tdir = tools_bin_srcdir
         for fpath in os.listdir(tdir):
             src_path = os.path.join(tdir, fpath)
             if os.path.isfile(src_path) and not src_path.endswith('.txt'):
                 create_symlink(src_path, subdir)
-
-
+    #databases in sate-tools-linux holds the swissprot* files for mafft-homologs. They compressed to appease git so we have to extract them to use them.
+    searchDir = os.path.join(tools_bin_srcdir, 'databases')
+    for files in os.listdir(searchDir):
+	fullPath = os.path.join(searchDir, files)
+	if fullPath.endswith("tar.gz"):
+		tar = tarfile.open(fullPath, "r:gz")
+		tar.extractall(searchDir)
+		tar.close()
+
+    mafftDir = os.path.join(tools_bin_srcdir, 'mafft')
+    ginsiDir = os.path.join(DEST_DIR_ROOT, 'ginsi')
+    os.symlink(mafftDir, ginsiDir)
 
 setup(**param)