Merge branch 'titered-strains-only'

blab · Jan 5, 2019 · af3367f · af3367f
1 parent 803f3a6
commit af3367f
Show file tree

Hide file tree

Showing 19 changed files with 6,080 additions and 499,891 deletions.
diff --git a/data/sequences/titered_strains.txt b/data/sequences/titered_strains.txt
@@ -0,0 +1,47 @@
+DENV4/PUERTO_RICO/BIDV2446/1999
+DENV3/NICARAGUA/BIDV4753/2009
+DENV2/BRAZIL/BR161/2004
+DENV4/BRAZIL/NA/2012
+DENV4/MALAYSIA/P731120/1973
+DENV4/PUERTO_RICO/347751/1998
+DENV4/THAILAND/D85052/1985
+DENV4/MYANMAR/81087/2008
+DENV2/INDIA/742295/1974
+DENV3/CAMBODIA/AC23/2011
+DENV2/VIETNAM/AC20/2003
+DENV1/MYANMAR/61117/2005
+DENV1/PERU/IQT6152/2000
+DENV2/PAPUANEWGUINEA/NEWGUINEAC/1944
+DENV3/VIETNAM/BIDV1329/2006
+DENV3/MYANMAR/80931/2008
+DENV1/PUERTO_RICO/BIDV852/2006
+DENV3/PUERTO_RICO/429965/2006
+DENV2/NICARAGUA/BIDV571/2006
+DENV3/FIJI/29472/1992
+DENV1/BOLIVIA/FSB3363/2010
+DENV2/VIETNAM/AC21/2003
+DENV2/GUYANA/08221/2000
+DENV2/MALAYSIA/DKD811/2008
+DENV1/THAILAND/16007/1964
+DENV3/VIETNAM/BIDV1817/2007
+DENV1/VENEZUELA/OBT1298/2000
+DENV2/CAMBODIA/BIDV4265/2007
+DENV1/CAMBODIA/BIDV1995/2003
+DENV3/INDONESIA/SLEMANDELTA30/1978
+DENV2/CAMBODIA/D2T0601085/2009
+DENV3/PUERTO_RICO/S228762/1963
+DENV2/SENEGAL/0674/1970
+DENV4/DOMINICA/814669DELTA30/1981
+DENV2/PERU/IQT2913/1996
+DENV2/NICARAGUA/BIDV533/2005
+DENV4/CAMBODIA/AC33/2011
+DENV1/CAMBODIA/BIDV1991/2003
+DENV1/NAURU/WESTERNPACIFICDELTA30/1974
+DENV2/CAMBODIA/BIDV3924/2008
+DENV4/INDONESIA/AC36/1973
+DENV1/VIETNAM/BIDV1937/2008
+DENV4/NICARAGUA/703/1999
+DENV2/VIETNAM/BIDV735/2006
+DENV4/CAMBODIA/NA/2010
+DENV2/TONGA/DELTA30/1974
+DENV4/INDONESIA/S1228/1978
diff --git a/data/trees/collapsed_antigenic_tree_figtree.nexus b/data/trees/collapsed_antigenic_tree_figtree.nexus
diff --git a/data/trees/dengue.newick b/data/trees/dengue.newick
diff --git a/data/trees/full_titer_tree.nexus b/data/trees/full_titer_tree.nexus
diff --git a/data/trees/genotype_tree.nexus b/data/trees/genotype_tree.nexus
diff --git a/data/trees/interserotype_titer_tree.nexus b/data/trees/interserotype_titer_tree.nexus
diff --git a/data/trees/root-to-tip.ipynb b/data/trees/root-to-tip.ipynb
diff --git a/data/trees/subtree-rooting.ipynb b/data/trees/subtree-rooting.ipynb
diff --git a/data/trees/tip_distances.csv b/data/trees/tip_distances.csv
diff --git a/figures/substitution-model-performance.ipynb b/figures/substitution-model-performance.ipynb
diff --git a/titer_model/implementation-nextstrain-augur/base/auspice_export.py b/titer_model/implementation-nextstrain-augur/base/auspice_export.py
@@ -134,15 +134,15 @@ def export_metadata_json(process, prefix, indent):
     if "defaults" in process.config["auspice"]:
         meta_json["defaults"] = process.config["auspice"]["defaults"]
 
-    try:
-        from pygit2 import Repository, discover_repository
-        current_working_directory = os.getcwd()
-        repository_path = discover_repository(current_working_directory)
-        repo = Repository(repository_path)
-        commit_id = repo[repo.head.target].id
-        meta_json["commit"] = str(commit_id)
-    except ImportError:
-        meta_json["commit"] = "unknown"
+    # try:
+    #     from pygit2 import Repository, discover_repository
+    #     current_working_directory = os.getcwd()
+    #     repository_path = discover_repository(current_working_directory)
+    #     repo = Repository(repository_path)
+    #     # commit_id = repo[repo.head.target].id
+    #     # meta_json["commit"] = str(commit_id)
+    # except ImportError:
+    #     meta_json["commit"] = "unknown"
     if len(process.config["auspice"]["controls"]):
         meta_json["controls"] = process.make_control_json(process.config["auspice"]["controls"])
     meta_json["geo"] = process.lat_longs

diff --git a/titer_model/implementation-nextstrain-augur/base/sequences_prepare.py b/titer_model/implementation-nextstrain-augur/base/sequences_prepare.py
@@ -252,7 +252,7 @@ def write_json(self, fh, config, prefix):
         data["info"] = {
             "n(starting)": self.nstart,
             "n(final)": len(self.seqs),
-            "commit": git.Repo(search_parent_directories=True).head.object.hexsha,
+            # "commit": git.Repo(search_parent_directories=True).head.object.hexsha,
             "date_format": config["date_format"],
             "subsampled": bool(config["subsample"]),
             "traits_are_dates": [],

diff --git a/titer_model/implementation-nextstrain-augur/dengue/dengue.prepare.py b/titer_model/implementation-nextstrain-augur/dengue/dengue.prepare.py
@@ -80,7 +80,7 @@ def make_config(serotype, params):
         file_prefix = "dengue_%s" % serotype
 
     if params.sequences is not None:
-        input_paths = [params.sequences]
+        input_paths = params.sequences
     elif os.path.isfile("../../../../data/sequences/dengue_%s.fasta"%serotype): #is file: # Look for a serotype-specific fasta
         input_paths = ["../../../../data/sequences/dengue_%s.fasta"%serotype]
     else: # If it doesn't exist, try to pull serotype-specific sequences out of the all-serotype fasta (warn the user of this behavior)
@@ -109,12 +109,12 @@ def make_config(serotype, params):
         "input_paths": input_paths,
         "header_fields": {0:'strain', 1:'accession', 2:'date', 3:'region', 4:'country',
                         5:'division', 6: 'location', 7: 'authors', 8: 'url'},
-        "filters": (("Dropped Strains", lambda s: s.id not in [fix_names(x) for x in dropped_strains]),
-            ("Bad Region", lambda s: any([
-                                        s.attributes['region'] not in ['', ' ', '?'],
-                                        s.attributes['accession'] in force_include,
-                                        s.attributes['strain'] in force_include
-                                        ]))),
+        "filters": (),#("Dropped Strains", lambda s: s.id not in [fix_names(x) for x in dropped_strains]),
+            # ("Bad Region", lambda s: any([
+            #                             s.attributes['region'] not in ['', ' ', '?'],
+            #                             s.attributes['accession'] in force_include,
+            #                             s.attributes['strain'] in force_include
+            #                             ]))),
 
         "subsample": dengue_subsampling(params, years_back, titer_values,
         force_include),

diff --git a/titer_model/implementation-nextstrain-augur/dengue/dengue.process.py b/titer_model/implementation-nextstrain-augur/dengue/dengue.process.py
@@ -123,10 +123,17 @@ def is_interserotype(node):
 			for sero, mrca in serotype_mrcas.items():
 				for k in mrca.find_clades(): # pull all descendants (nodes and tips) of the serotype mrca
 					k.sequence = mrca.sequence # set sequence of each descendant to the reconstructed ancestral sequence from the serotype mrca
-
+					k.translations = mrca.translations
+					k.aa_mutations = {}
 			runner.tree.add_translations() # translate and reassign mutations to each branch
 			runner.tree.refine()
 
+			for sero, mrca in serotype_mrcas.items():
+				for k in mrca.find_clades(): # pull all descendants (nodes and tips) of the serotype mrca
+					if k == mrca: continue
+					assert ''.join(k.sequence) == ''.join(mrca.sequence)
+					assert k.translations['E'] == mrca.translations['E']
+					assert len(k.aa_mutations['E']) == 0
 	titer_model(runner, ## Run 10x with a 90:10 training:test split to estimate model performance / error
 				lam_pot = runner.config['titers']['lam_pot'],
 				lam_avi = runner.config['titers']['lam_avi'],