BLD: Add unifrac

Thanks @mortonjt @wasade! Add bypass-tips
qiime2 · Sep 21, 2017 · e4aa0ef · e4aa0ef
1 parent fb0b28b
commit e4aa0ef
Show file tree

Hide file tree

Showing 3 changed files with 16 additions and 4 deletions.
diff --git a/.travis.yml b/.travis.yml
@@ -15,6 +15,8 @@ install:
   - conda create -q -n test-env --file https://raw.githubusercontent.com/qiime2/environment-files/master/latest/staging/qiime2-latest-conda-linux-64.txt
   - source activate test-env
   - conda install -q pytest-cov
+  # temporary solution while we get this into a permanent channel
+  - conda install -c mortonjt unifrac
   - pip install -q flake8 coveralls
   - pip install -q https://github.com/qiime2/q2lint/archive/master.zip
   - make install

diff --git a/q2_diversity/_beta/_method.py b/q2_diversity/_beta/_method.py
@@ -71,7 +71,8 @@ def beta_phylogenetic(table: biom.Table, phylogeny: skbio.TreeNode,
 def beta_phylogenetic_hpc(table: BIOMV210Format, phylogeny: NewickFormat,
                           metric: str, n_jobs: int=1,
                           variance_adjusted: bool=False,
-                          alpha=1.0) -> skbio.DistanceMatrix:
+                          alpha=1.0,
+                          bypass_tips: bool=False) -> skbio.DistanceMatrix:
     if metric == 'unweighted_unifrac':
         f = unifrac.unweighted
     elif metric == 'weighted_unnormalized_unifrac':
@@ -85,7 +86,7 @@ def beta_phylogenetic_hpc(table: BIOMV210Format, phylogeny: NewickFormat,
 
     # unifrac processes tables and trees should be filenames
     return f(str(table), str(phylogeny), threads=n_jobs,
-             variance_adjusted=variance_adjusted)
+             variance_adjusted=variance_adjusted, bypass_tips=bypass_tips)
 
 
 def beta(table: biom.Table, metric: str, n_jobs: int=1)-> skbio.DistanceMatrix:

diff --git a/q2_diversity/plugin_setup.py b/q2_diversity/plugin_setup.py
@@ -91,7 +91,7 @@
                                          'generalized_unifrac']),
                 'n_jobs': Int,
                 'variance_adjusted': Bool,
-                'alpha': Float},
+                'alpha': Float, 'bypass_tips': Bool},
     outputs=[('distance_matrix', DistanceMatrix % Properties('phylogenetic'))],
     input_descriptions={
         'table': ('The feature table containing the samples over which beta '
@@ -111,7 +111,16 @@
                   'generalized. The value of alpha controls importance of '
                   'sample proportions. 1.0 is weighted normalized UniFrac. '
                   '0.0 is close to unweighted UniFrac, but only if the sample '
-                  'proportions are dichotomized.')
+                  'proportions are dichotomized.'),
+        'bypass_tips': ('Compute will be reduced by ~50% with this option '
+                        'yielding an approximate result. The option '
+                        'disregards computing UniFrac at the tips of the '
+                        'phylogeny and instead only computes it on the '
+                        'internal nodes. In a bifurcating tree, the tips '
+                        'correspond to approximately 50% of the vertices in '
+                        'the tree, which is how the compute time reduction is'
+                        ' achieved. The use of this parameter is analogous '
+                        'in concept to switching from 99% OTUs to 97% OTUs.')
     },
     output_descriptions={'distance_matrix': 'The resulting distance matrix.'},
     name='Beta diversity (phylogenetic) - High Performance Computation',