Merge pull request #117 from McTavishLab/repeat

Repeat

bin/find_trees.py

@@ -0,0 +1,72 @@
+#!/usr/bin/env python
+import argparse
+from opentree import OT
+
+
+
+parser = argparse.ArgumentParser()
+parser.add_argument("-t","--taxon_name", help="Name of search taxon")
+parser.add_argument("-ott","--ott_id", help="Name of search taxon")
+parser.add_argument("-tb","--treebase", action = 'store_true', help="Rturn studies with treebase data only")
+parser.add_argument("-o","--output", help="Output file path")
+args = parser.parse_args()
+
+
+if args.taxon_name:
+    try:
+        ottid = OT.get_ottid_from_name(args.taxon_name)
+    except:
+        sys.stdout.write("no match to taxon name. Try finding your taxon on tree.opentreeoflife.org and inputting the taxon id using -ott")
+
+
+#sys.stdout.write("OTT id of {}")
+phylesystem_studies_resp = OT.find_trees(ottid, search_property ='ot:ottId')
+
+
+studies = dict()
+trees = dict()
+treebase_studies = set()
+for study in phylesystem_studies_resp.response_dict['matched_studies']:
+    study_id = study['ot:studyId']
+    studies[study_id] = dict()
+    study_info = OT.get_study(study_id)
+    nexson = study_info.response_dict['data']
+    data_deposit = nexson['nexml'].get(u'^ot:dataDeposit')
+    data_deposit_url = 'None'
+    if data_deposit:
+        data_deposit_url = data_deposit[u'@href']
+    studies[study_id]['data_deposit_url'] =  data_deposit_url
+    if 'treebase' in data_deposit_url:
+        treebase_studies.add(study_id)
+    trees[study_id] = []
+    for tree in study['matched_trees']:
+        treeid = tree['ot:treeId']
+        trees[study_id].append(treeid)
+    cites = []
+    studies[study_id]['opentree_url'] = "https://tree.opentreeoflife.org/curator/study/view/{}".format(study_id)
+    studies[study_id]['reference'] = nexson['nexml'].get('^ot:studyPublicationReference', 'no ref') 
+    studies[study_id]['doi'] = nexson['nexml'].get('^ot:studyPublication', 'no study pub')
+
+
+cites_phyl = "Members of {} present in the following studies in the OpenTree Phylesystem\n".format(args.taxon_name)
+
+
+if args.treebase:
+    cites_phyl = cites_phyl + "Only returning studies with TreeBase links\n"
+
+for study_id in studies:
+    if args.treebase and study_id not in treebase_studies:
+            continue
+    cites_phyl = cites_phyl + "\nStudy {} tree(s) {}\n".format(study_id, ', '.join(trees[study_id]))
+    cites_phyl = cites_phyl + "OpenTreeUrl: " + studies[study_id]['opentree_url'] + '\n'
+    cites_phyl = cites_phyl + "Reference: " + studies[study_id]['reference'] + '\n'
+    cites_phyl = cites_phyl + "Data Deposit URL: " + studies[study_id]['data_deposit_url'] + '\n'
+
+
+if args.output:
+    ofi = open(args.output, 'w')
+    ofi.write(cites_phyl)
+else:
+    print(cites_phyl)
+
+

bin/physcraper_run.py

@@ -198,15 +198,23 @@
     boot_reps = 100
 
 
+
 run = 1
 if args.repeat:
+    rundir_path = scraper.rundir
+    blast_dir ="{}/blast_run_{}".format(workdir, scraper.data.tag)
+    if not os.path.exists(blast_dir):
+        os.mkdir(blast_dir)    
+    scraper.blast_subdir = blast_dir
     scraper.calculate_final_tree(boot_reps = boot_reps)
-    to_be_blasted = [otu.label for otu in scraper.data.aln if (scraper.data.otu_dict[otu.label]['^physcraper:ingroup'] == True and scraper.data.otu_dict[otu.label]['^physcraper:last_blasted']==None)]
+    to_be_blasted = [otu.label for otu in scraper.data.aln if ((scraper.data.otu_dict[otu.label]['^physcraper:ingroup'] == True) and (scraper.data.otu_dict[otu.label]['^physcraper:last_blasted']==None))]
     while len(to_be_blasted) >= 1:
         run += 1
+        os.rename(scraper.rundir, rundir_path+"_"+str(run))
+        os.mkdir(scraper.rundir)
         scraper.run_blast_wrapper()
         scraper.calculate_final_tree(boot_reps = boot_reps)
-        to_be_blasted = [otu.label for otu in scraper.data.aln if (scraper.data.otu_dict[otu.label]['^physcraper:ingroup'] == True and scraper.data.otu_dict[otu.label]['^physcraper:last_blasted']==None)]
+        to_be_blasted = [otu.label for otu in scraper.data.aln if ((scraper.data.otu_dict[otu.label]['^physcraper:ingroup'] == True) and (scraper.data.otu_dict[otu.label]['^physcraper:last_blasted']==None))]
 elif not args.no_estimate_tree:
 #scraper.read_blast_wrapper()
     scraper.calculate_final_tree(boot_reps = boot_reps)

bin/tree_comparison.py

@@ -26,11 +26,27 @@
 
 args = parser.parse_args()
 
+
+try:
+    assert(args.outputdir)
+except AssertionError:
+    sys.stderr.write("ERROR: Output directory (-o) is required.\n")
+    sys.exit(-1)
+
+
 comparisondir = args.outputdir
 if not os.path.exists(comparisondir):
     os.mkdir(comparisondir)
 
 
+if args.results_dir:
+    assert(os.path_exists(args.results_dir)), "Results directory {} not found\n".format(args.results_dir)
+else:
+    assert(os.path_exists(args.original_tree)), "Original tree {} not found\n".format(args.original_tree)
+    assert(os.path_exists(args.updated_tree)), "Updated tree {} not found\n".format(args.updated_tree)
+    assert(os.path_exists(args.otu_info)), "Otu_info {} not found\n".format(args.otu_info)
+
+
 tns = dendropy.TaxonNamespace()
 
 

docs/source/conf.py

@@ -27,7 +27,7 @@
 # -- Project information -----------------------------------------------------
 
 project = 'physcraper'
-copyright = '2018, McTavish Lab'
+copyright = '2020, McTavish Lab'
 author = 'McTavish Lab'
 
 # The short X.Y version
@@ -46,7 +46,6 @@
 # extensions coming with Sphinx (named 'sphinx.ext.*') or your custom
 # ones.
 extensions = [
-    'm2r',
     'sphinx.ext.autodoc',
     'sphinx.ext.doctest',
     'sphinx.ext.intersphinx',

docs/source/how_to_start.rst

@@ -1,5 +1,5 @@
 How to start
 ============
 
-.. mdinclude:: ../../cruft/How_to_start.md
+.. mdinclude:: ../Tutorial.md
 

physcraper/scrape.py

@@ -26,7 +26,7 @@
 from physcraper import AWSWWW
 
 _VERBOSE = 1
-_DEBUG = 0
+_DEBUG = 1
 def debug(msg):
     """short debugging command
     """

requirements.txt

@@ -18,7 +18,7 @@ pytest
 pytest-cov
 pytest-xdist
 
-m2r; python_version > '2.7.13'
+m2r
 recommonmark
 
 #past

setup.py

@@ -11,6 +11,7 @@
       author='Emily Jane McTavish',
       author_email='ejmctavish@gmail.com',
       packages=['physcraper'],
-      scripts=['bin/physcraper_run.py'],
+      scripts=['bin/physcraper_run.py',
+                'bin/tree_comparison.py'],
       install_requires=[]
      )