Merge pull request #4259 from gregvonkuster/ptkscmp

Add ptkscmp datatype

config/datatypes_conf.xml.sample

@@ -608,6 +608,7 @@
     <datatype extension="ptaligntrimmedca" type="galaxy.datatypes.plant_tribes:PlantTribesMultipleSequenceAlignmentTrimmedCodonAlignment" />
     <datatype extension="ptalignfiltered" type="galaxy.datatypes.plant_tribes:PlantTribesMultipleSequenceAlignmentFiltered" />
     <datatype extension="ptalignfilteredca" type="galaxy.datatypes.plant_tribes:PlantTribesMultipleSequenceAlignmentFilteredCodonAlignment" />
+    <datatype extension="ptkscmp" type="galaxy.datatypes.plant_tribes:PlantTribesKsComponents" display_in_upload="true"/>
     <datatype extension="ptortho" type="galaxy.datatypes.plant_tribes:PlantTribesOrtho" />
     <datatype extension="ptorthocs" type="galaxy.datatypes.plant_tribes:PlantTribesOrthoCodingSequence" />
     <datatype extension="ptphylip" type="galaxy.datatypes.plant_tribes:PlantTribesPhylip" />
@@ -623,6 +624,7 @@
     defined format first, followed by next-most rigidly defined,
     and so on.
     -->
+    <sniffer type="galaxy.datatypes.plant_tribes:PlantTribesKsComponents"/>
     <sniffer type="galaxy.datatypes.plant_tribes:Smat"/>
     <sniffer type="galaxy.datatypes.mothur:Sabund"/>
     <sniffer type="galaxy.datatypes.mothur:Otu"/>

lib/galaxy/datatypes/plant_tribes.py

@@ -4,6 +4,8 @@ import re
 
 from galaxy.datatypes.data import get_file_peek, Text
 from galaxy.datatypes.metadata import MetadataElement, MetadataParameter
+from galaxy.datatypes.sniff import get_headers
+from galaxy.datatypes.tabular import Tabular
 from galaxy.datatypes.text import Html
 from galaxy.util import nice_size
 
@@ -89,6 +91,66 @@ class PlantTribes(Html):
             log.warning("set_meta fname: %s %s" % (dataset.file_name if dataset and dataset.file_name else 'Unkwown', str(e)))
 
 
+class PlantTribesKsComponents(Tabular):
+    file_ext = "ptkscmp"
+    MetadataElement(name="number_comp", default=0, desc="Number of significant components in the Ks distribution", readonly=True, visible=True, no_value=0)
+
+    def display_peek(self, dataset):
+        try:
+            return dataset.peek
+        except:
+            return "Significant components in the Ks distribution (%s)" % (nice_size(dataset.get_size()))
+
+    def set_meta(self, dataset, **kwd):
+        """
+        Set the number of significant components in the Ks distribution.
+        The dataset will always be on the order of less than 10 lines.
+        """
+        super(PlantTribesKsComponents, self).set_meta(dataset, **kwd)
+        significant_components = []
+        with open(dataset.file_name) as fh:
+            for i, line in enumerate(fh):
+                if i == 0:
+                    # Skip the first line.
+                    continue
+                line = line.strip()
+                items = line.split()
+                try:
+                    # Could be \t.
+                    significant_components.append(int(items[2]))
+                except Exception:
+                    continue
+        if len(significant_components) > 0:
+            dataset.metadata.number_comp = max(significant_components)
+
+    def set_peek(self, dataset, is_multi_byte=False):
+        if not dataset.dataset.purged:
+            dataset.peek = get_file_peek(dataset.file_name, is_multi_byte=is_multi_byte)
+            if (dataset.metadata.number_comp == 1):
+                dataset.blurb = "1 significant component"
+            else:
+                dataset.blurb = "%s significant components" % dataset.metadata.number_comp
+        else:
+            dataset.peek = 'file does not exist'
+            dataset.blurb = 'file purged from disk'
+
+    def sniff(self, filename):
+        """
+        >>> from galaxy.datatypes.sniff import get_test_fname
+        >>> fname = get_test_fname('test_tab.bed')
+        >>> PlantTribesKsComponents().sniff(fname)
+        False
+        >>> fname = get_test_fname('1.ptkscmp')
+        >>> PlantTribesKsComponents().sniff(fname)
+        True
+        """
+        try:
+            line_item_str = get_headers(filename, '\\t', 1)[0][0]
+            return line_item_str == 'species\tn\tnumber_comp\tlnL\tAIC\tBIC\tmean\tvariance\tporportion'
+        except Exception:
+            return False
+
+
 class PlantTribesOrtho(PlantTribes):
     """
     PlantTribes sequences classified into precomputed, orthologous gene family

lib/galaxy/datatypes/test/1.ptkscmp

@@ -0,0 +1,11 @@
+species	n	number_comp	lnL	AIC	BIC	mean	variance	porportion
+species1	1184	1	-1527.4110	3058.82	3068.98	0.4656	0.1675	1.00
+species1	1184	2	-1490.7280	2991.46	3016.84	0.1718	0.0035	0.22
+						0.6173	0.2275	0.78
+species1	1184	3	-1471.6980	2959.40	3000.01	0.6921	0.1806	0.65
+						5.9251	3.0703	0.02
+						0.1887	0.0054	0.33
+species1	1184	4	-1443.1050	2908.21	2964.05	0.1219	0.0002	0.10
+						0.2589	0.0093	0.38
+						0.7900	0.1030	0.42
+						1.5944	1.7482	0.10