From c99feb78c58da43cb018dc3ef109bc3074d3c511 Mon Sep 17 00:00:00 2001 From: Diane Trout Date: Wed, 19 Sep 2012 16:10:57 -0700 Subject: [PATCH] Use htsworkflow ontology to validate various RDF using components. Of course to use the ontology I had to make one first. Unsurprisingly implementing it touched a bunch of code & templates. I tried to be more consisten with using mixed-case names for classes and lower_case names for properties. There's some inconsistencies. like i use the term notes & comments in different areas. Also, should I be using my own terms or do better at reusing more standard ontologies? --- encode_submission/test_encode_find.py | 58 ++- htsworkflow/frontend/experiments/tests.py | 25 +- .../experiments/flowcell_detail.html | 31 +- .../experiments/flowcell_header.html | 8 +- .../experiments/flowcell_lane_detail.html | 12 +- .../frontend/templates/sample_header.html | 4 +- .../templates/samples/library_detail.html | 13 +- htsworkflow/pipelines/sequences.py | 2 +- htsworkflow/pipelines/test/test_sequences.py | 2 +- htsworkflow/submission/condorfastq.py | 6 +- .../submission/test/test_condorfastq.py | 61 +++- htsworkflow/util/schemas/htsworkflow.turtle | 340 ++++++++++++++++++ 12 files changed, 498 insertions(+), 64 deletions(-) create mode 100644 htsworkflow/util/schemas/htsworkflow.turtle diff --git a/encode_submission/test_encode_find.py b/encode_submission/test_encode_find.py index cb62167..0510895 100644 --- a/encode_submission/test_encode_find.py +++ b/encode_submission/test_encode_find.py @@ -7,12 +7,19 @@ import RDF import encode_find from htsworkflow.submission.ucsc import submission_view_url -from htsworkflow.util.rdfhelp import dump_model, get_model, fromTypedNode +from htsworkflow.util.rdfhelp import add_default_schemas, \ + dump_model, get_model, fromTypedNode +from htsworkflow.util.rdfinfer import Infer SOURCE_PATH = os.path.split(os.path.abspath(__file__))[0] print SOURCE_PATH class TestEncodeFind(unittest.TestCase): + def setUp(self): + self.model = get_model() + add_default_schemas(self.model) + self.inference = Infer(self.model) + def test_create_status_node_with_uri(self): subURL = submission_view_url('5136') submissionUri = RDF.Uri(subURL) @@ -35,11 +42,10 @@ class TestEncodeFind(unittest.TestCase): test_file = os.path.join(SOURCE_PATH, 'testdata', '5136SubDetail.html') from lxml.html import parse tree = parse(test_file) - model = get_model() - dates = encode_find.get_creation_dates(model, subNode) + dates = encode_find.get_creation_dates(self.model, subNode) self.assertEqual(len(dates), 0) - encode_find.parse_submission_page(model, tree, subNode) - dates = encode_find.get_creation_dates(model, subNode) + encode_find.parse_submission_page(self.model, tree, subNode) + dates = encode_find.get_creation_dates(self.model, subNode) self.assertEqual(len(dates), 1) object_date = fromTypedNode(dates[0].object) self.assertEqual(object_date, datetime(2011,12,7,15,23,0)) @@ -58,43 +64,54 @@ class TestEncodeFind(unittest.TestCase): libns:total_unique_locations 5789938 . ''', 'http://jumpgate.caltech.edu/library/') + errmsgs = list(self.inference.run_validation()) + self.assertEqual(len(errmsgs), 0) urn = RDF.Node(RDF.Uri('http://jumpgate.caltech.edu/lane/1232')) encode_find.delete_lane(model, urn) self.failUnlessEqual(len(model), 0) def test_delete_lane_with_mapping(self): - model = get_model() + ontology_size = len(self.model) parser = RDF.Parser(name='turtle') - parser.parse_string_into_model(model, '''@prefix rdf: . + parser.parse_string_into_model(self.model, '''@prefix rdf: . @prefix : . @prefix rdfs: . @prefix xsd: . @prefix libns: . + a libns:IlluminaFlowcell . libns:flowcell ; libns:has_mappings _:bnode110110 ; - libns:total_unique_locations 5789938 . + libns:total_unique_locations 5789938 ; + a libns:IlluminaLane . _:bnode110110 + a libns:MappedCount ; libns:mapped_to "newcontam_UK.fa"@en ; libns:reads 42473 . ''', 'http://jumpgate.caltech.edu/library/') - self.failUnlessEqual(len(model), 5) + errmsgs = list(self.inference.run_validation()) + self.assertEqual(len(errmsgs), 0) + self.failUnlessEqual(len(self.model), 8 + ontology_size) urn = RDF.Node(RDF.Uri('http://jumpgate.caltech.edu/lane/1232')) - encode_find.delete_lane(model, urn) - self.failUnlessEqual(len(model), 0) + encode_find.delete_lane(self.model, urn) + self.failUnlessEqual(len(self.model), 1 + ontology_size) + # the flowcell triple wasn't deleted. def test_delete_library(self): - model = get_model() parser = RDF.Parser(name='turtle') - parser.parse_string_into_model(model, '''@prefix rdf: . + parser.parse_string_into_model(self.model, '''@prefix rdf: . @prefix : . @prefix rdfs: . @prefix xsd: . @prefix libns: . + a libns:IlluminaFlowcell . + a libns:IlluminaFlowcell . + + a libns:IlluminaLane ; libns:flowcell ; libns:has_mappings _:bnode110110 ; libns:total_unique_locations 5789938 . @@ -104,14 +121,16 @@ _:bnode110110 libns:has_lane ; libns:library_id "11011"@en ; libns:library_type "None"@en ; - a "libns:library"@en ; + a libns:Library ; , . _:bnode110110 + a libns:MappedCount ; libns:mapped_to "newcontam_UK.fa"@en ; libns:reads 42473 . + a libns:IlluminaLane ; libns:flowcell ; libns:has_mappings _:bnode120970 ; libns:total_unique_locations 39172114 . @@ -120,22 +139,25 @@ _:bnode110110 libns:has_lane ; libns:library_id "12097"@en ; libns:library_type "Paired End (non-multiplexed)"@en ; - a "libns:library"@en . + a libns:Library . _:bnode120970 + a libns:MappedCount ; libns:mapped_to "newcontam_UK.fa"@en ; libns:reads 64 . ''', 'http://jumpgate.caltech.edu/library') + errmsgs = list(self.inference.run_validation()) + self.assertEqual(len(errmsgs), 0) urn = RDF.Node(RDF.Uri('http://jumpgate.caltech.edu/library/11011/')) - encode_find.delete_library(model, urn) + encode_find.delete_library(self.model, urn) q = RDF.Statement(None, encode_find.libraryOntology['reads'], None) - stmts = list(model.find_statements(q)) + stmts = list(self.model.find_statements(q)) self.failUnlessEqual(len(stmts), 1) self.failUnlessEqual(fromTypedNode(stmts[0].object), 64) q = RDF.Statement(None, encode_find.libraryOntology['library_id'], None) - stmts = list(model.find_statements(q)) + stmts = list(self.model.find_statements(q)) self.failUnlessEqual(len(stmts), 1) self.failUnlessEqual(fromTypedNode(stmts[0].object), '12097') diff --git a/htsworkflow/frontend/experiments/tests.py b/htsworkflow/frontend/experiments/tests.py index a728884..93e1f3d 100644 --- a/htsworkflow/frontend/experiments/tests.py +++ b/htsworkflow/frontend/experiments/tests.py @@ -281,7 +281,7 @@ class ExperimentsTestCases(TestCase): failed_fc_span = flowcell_spans[0] failed_fc_a = failed_fc_span.getparent() # make sure some of our RDF made it. - self.assertEqual(failed_fc_a.get('rel'), 'libns:flowcell') + self.assertEqual(failed_fc_a.get('typeof'), 'libns:IlluminaFlowcell') self.assertEqual(failed_fc_a.get('href'), '/flowcell/30012AAXX/') fc_response = self.client.get(failed_fc_a.get('href')) self.assertEqual(fc_response.status_code, 200) @@ -441,7 +441,7 @@ class ExperimentsTestCases(TestCase): select ?flowcell ?flowcell_id ?lane_id ?library_id where { - ?flowcell a libns:illumina_flowcell ; + ?flowcell a libns:IlluminaFlowcell ; libns:flowcell_id ?flowcell_id ; libns:has_lane ?lane . ?lane libns:lane_number ?lane_id ; @@ -590,20 +590,23 @@ class TestSequencer(TestCase): def test_rdf(self): response = self.client.get('/flowcell/FC12150/', apidata) tree = fromstring(response.content) - divs = tree.xpath('//div[@rel="libns:sequenced_by"]', - namespaces=NSMAP) - self.assertEqual(len(divs), 1) - self.assertEqual(divs[0].attrib['rel'], 'libns:sequenced_by') - self.assertEqual(divs[0].attrib['resource'], '/sequencer/2') - - name = divs[0].xpath('./span[@property="libns:sequencer_name"]') + seq_by = tree.xpath('//div[@rel="libns:sequenced_by"]', + namespaces=NSMAP) + self.assertEqual(len(seq_by), 1) + self.assertEqual(seq_by[0].attrib['rel'], 'libns:sequenced_by') + seq = seq_by[0].getchildren() + self.assertEqual(len(seq), 1) + self.assertEqual(seq[0].attrib['about'], '/sequencer/2') + self.assertEqual(seq[0].attrib['typeof'], 'libns:Sequencer') + + name = seq[0].xpath('./span[@property="libns:sequencer_name"]') self.assertEqual(len(name), 1) self.assertEqual(name[0].text, 'Tardigrade') - instrument = divs[0].xpath( + instrument = seq[0].xpath( './span[@property="libns:sequencer_instrument"]') self.assertEqual(len(instrument), 1) self.assertEqual(instrument[0].text, 'ILLUMINA-EC5D15') - model = divs[0].xpath( + model = seq[0].xpath( './span[@property="libns:sequencer_model"]') self.assertEqual(len(model), 1) self.assertEqual(model[0].text, 'Illumina Genome Analyzer IIx') diff --git a/htsworkflow/frontend/templates/experiments/flowcell_detail.html b/htsworkflow/frontend/templates/experiments/flowcell_detail.html index 5ce9fa2..3a3b736 100644 --- a/htsworkflow/frontend/templates/experiments/flowcell_detail.html +++ b/htsworkflow/frontend/templates/experiments/flowcell_detail.html @@ -26,22 +26,37 @@ {% for lane in lanes %} - - - {{lane.lane_number}} - {{lane.library.id}} + + {% endfor %} diff --git a/htsworkflow/frontend/templates/experiments/flowcell_header.html b/htsworkflow/frontend/templates/experiments/flowcell_header.html index 953897c..412d3ac 100644 --- a/htsworkflow/frontend/templates/experiments/flowcell_header.html +++ b/htsworkflow/frontend/templates/experiments/flowcell_header.html @@ -2,9 +2,10 @@

About this Flowcell

Flowcell: {{flowcell.flowcell_id}}{% if user.is_staff %}Edit{% endif%} -
-
+
+
+
Instrument: {{ flowcell.sequencer.name }} {% if flowcell.sequencer.instrument_name %} @@ -15,6 +16,7 @@ {{flowcell.sequencer.model}}
+
{% for datarun in flowcell.datarun_set.all %} Image Analysis: {{datarun.image_software}} diff --git a/htsworkflow/frontend/templates/experiments/flowcell_lane_detail.html b/htsworkflow/frontend/templates/experiments/flowcell_lane_detail.html index 19480ed..6c517e6 100644 --- a/htsworkflow/frontend/templates/experiments/flowcell_lane_detail.html +++ b/htsworkflow/frontend/templates/experiments/flowcell_lane_detail.html @@ -4,27 +4,27 @@ - + {% block additional_javascript %} {% endblock %} {% endblock %} {% block content %} -
+
{% include "experiments/flowcell_header.html" %}

About this lane

- Lane: + Lane: {{lane.lane_number}}
pM: {{ lane.pM }}
Cluster Estimate: {{ lane.cluster_estimate|intcomma }}
- Lane Status: + Lane Status: {{ lane.status }}
- Comments: + Comments: {{ lane.comment }}
@@ -74,7 +74,7 @@ {% endif %} - {% endfor %} + {% endfor %} {% endfor %} diff --git a/htsworkflow/frontend/templates/sample_header.html b/htsworkflow/frontend/templates/sample_header.html index b7454e3..c3d5f97 100644 --- a/htsworkflow/frontend/templates/sample_header.html +++ b/htsworkflow/frontend/templates/sample_header.html @@ -1,4 +1,6 @@ -
+

Library Name

Library ID: diff --git a/htsworkflow/frontend/templates/samples/library_detail.html b/htsworkflow/frontend/templates/samples/library_detail.html index c09a510..66b2cc1 100644 --- a/htsworkflow/frontend/templates/samples/library_detail.html +++ b/htsworkflow/frontend/templates/samples/library_detail.html @@ -126,8 +126,10 @@ {% for lane in lib.lane_set.all %} - {{ lane.flowcell.flowcell_id }} + + + {{lane.flowcell.flowcell_id}} {% if user.is_staff %} {% endif%} - + + + {{ lane.lane_number }} + >{{ lane.lane_number }} + {{ lane.comment }} {% endfor %} diff --git a/htsworkflow/pipelines/sequences.py b/htsworkflow/pipelines/sequences.py index 23e7fe8..479ce3d 100644 --- a/htsworkflow/pipelines/sequences.py +++ b/htsworkflow/pipelines/sequences.py @@ -477,7 +477,7 @@ def guess_library_from_model(model, base_url, flowcell, lane_id): select ?library ?lane where {{ <{flowcell}> libNS:has_lane ?lane ; - a libNS:illumina_flowcell . + a libNS:IlluminaFlowcell . ?lane libNS:lane_number {lane_id} ; libNS:library ?library . }} diff --git a/htsworkflow/pipelines/test/test_sequences.py b/htsworkflow/pipelines/test/test_sequences.py index 34ddeab..e621875 100644 --- a/htsworkflow/pipelines/test/test_sequences.py +++ b/htsworkflow/pipelines/test/test_sequences.py @@ -408,7 +408,7 @@ class SequenceFileTests(unittest.TestCase): libns:has_lane <{base}/lane/1169>, <{base}/lane/1170>, <{base}/lane/1171>, <{base}/lane/1172> ; libns:read_length 75 ; - a libns:illumina_flowcell . + a libns:IlluminaFlowcell . <{base}/lane/1169> libns:lane_number 1 ; libns:library <{base}/library/10923/> . diff --git a/htsworkflow/submission/condorfastq.py b/htsworkflow/submission/condorfastq.py index 9aab790..5ae4b7a 100644 --- a/htsworkflow/submission/condorfastq.py +++ b/htsworkflow/submission/condorfastq.py @@ -169,7 +169,7 @@ class CondorFastqExtract(object): def import_library(self, library): """Import library data into our model if we don't have it already """ - q = RDF.Statement(library, rdfNS['type'], libraryOntology['library']) + q = RDF.Statement(library, rdfNS['type'], libraryOntology['Library']) present = False if not self.model.contains_statement(q): present = True @@ -184,7 +184,7 @@ prefix libns: select distinct ?flowcell ?flowcell_id WHERE { - ?library a libns:library ; + ?library a libns:Library ; libns:has_lane ?lane . ?lane libns:flowcell ?flowcell . ?flowcell libns:flowcell_id ?flowcell_id . @@ -195,7 +195,7 @@ WHERE { LOGGER.debug("Flowcells = %s" %(unicode(flowcell_ids))) flowcell_test = RDF.Statement(r['flowcell'], rdfNS['type'], - libraryOntology['illumina_flowcell']) + libraryOntology['IlluminaFlowcell']) if not self.model.contains_statement(flowcell_test): # we probably lack full information about the flowcell. load_into_model(self.model, 'rdfa', r['flowcell']) diff --git a/htsworkflow/submission/test/test_condorfastq.py b/htsworkflow/submission/test/test_condorfastq.py index 94df7b6..f4d2e2c 100644 --- a/htsworkflow/submission/test/test_condorfastq.py +++ b/htsworkflow/submission/test/test_condorfastq.py @@ -9,7 +9,9 @@ import unittest from htsworkflow.submission.condorfastq import CondorFastqExtract from htsworkflow.submission.results import ResultMap -from htsworkflow.util.rdfhelp import load_string_into_model, dump_model +from htsworkflow.util.rdfhelp import \ + add_default_schemas, load_string_into_model, dump_model +from htsworkflow.util.rdfinfer import Infer FCDIRS = [ 'C02F9ACXX', @@ -96,8 +98,13 @@ lib_turtle = """@prefix : . @prefix seqns: . @prefix invns: . + a libns:Library . + a libns:Library . + a libns:Library . + a libns:Library . + - a libns:illumina_flowcell ; + a libns:IlluminaFlowcell ; libns:read_length 33 ; libns:flowcell_type "Single"@en ; libns:date "2012-01-19T20:23:26"^^xsd:dateTime; @@ -112,18 +119,22 @@ lib_turtle = """@prefix : . libns:flowcell_id "30221AAXX"@en . + a libns:IlluminaLane ; libns:flowcell ; libns:library ; libns:lane_number 1 . + a libns:IlluminaLane ; libns:flowcell ; libns:library ; libns:lane_number 2 . + a libns:IlluminaLane ; libns:flowcell ; libns:library ; libns:lane_number 3 . + a libns:IlluminaLane ; libns:flowcell ; libns:library ; libns:lane_number 4 . @@ -131,24 +142,28 @@ lib_turtle = """@prefix : . # read_length 33; # status "Unknown"@en . + a libns:IlluminaLane ; libns:flowcell ; libns:library ; libns:lane_number 5 . + a libns:IlluminaLane ; libns:flowcell ; libns:library ; libns:lane_number 6 . + a libns:IlluminaLane ; libns:flowcell ; libns:library ; libns:lane_number 7 . + a libns:IlluminaLane ; libns:flowcell ; libns:library ; libns:lane_number 8 . - a libns:illumina_flowcell ; + a libns:IlluminaFlowcell ; libns:read_length 76 ; libns:flowcell_type "Paired"@en ; libns:date "2012-01-19T20:23:26"^^xsd:dateTime; @@ -163,22 +178,27 @@ lib_turtle = """@prefix : . libns:flowcell_id "42JUYAAXX"@en . + a libns:IlluminaLane ; libns:flowcell ; libns:library ; libns:lane_number 1 . + a libns:IlluminaLane ; libns:flowcell ; libns:library ; libns:lane_number 2 . + a libns:IlluminaLane ; libns:flowcell ; libns:library ; libns:lane_number 3 . + a libns:IlluminaLane ; libns:flowcell ; libns:library ; libns:lane_number 4 . + a libns:IlluminaLane ; libns:flowcell ; libns:library ; libns:lane_number 5 . @@ -186,20 +206,23 @@ lib_turtle = """@prefix : . # read_length 76; # status "Unknown"@en . + a libns:IlluminaLane ; libns:flowcell ; libns:library ; libns:lane_number 6 . + a libns:IlluminaLane ; libns:flowcell ; libns:library ; libns:lane_number 7 . + a libns:IlluminaLane ; libns:flowcell ; libns:library ; libns:lane_number 8 . - a libns:illumina_flowcell ; + a libns:IlluminaFlowcell ; libns:read_length 76 ; libns:flowcell_type "Single"@en ; libns:date "2012-01-19T20:23:26"^^xsd:dateTime; @@ -214,26 +237,32 @@ lib_turtle = """@prefix : . libns:flowcell_id "61MJTAAXX"@en . + a libns:IlluminaLane ; libns:flowcell ; libns:library ; libns:lane_number 1 . + a libns:IlluminaLane ; libns:flowcell ; libns:library ; libns:lane_number 2 . + a libns:IlluminaLane ; libns:flowcell ; libns:library ; libns:lane_number 3 . + a libns:IlluminaLane ; libns:flowcell ; libns:library ; libns:lane_number 4 . + a libns:IlluminaLane ; libns:flowcell ; libns:library ; libns:lane_number 5 . + a libns:IlluminaLane ; libns:flowcell ; libns:library ; libns:lane_number 6 . @@ -241,16 +270,18 @@ lib_turtle = """@prefix : . # read_length 76; # status "Unknown"@en . + a libns:IlluminaLane ; libns:flowcell ; libns:library ; libns:lane_number 7 . + a libns:IlluminaLane ; libns:flowcell ; libns:library ; libns:lane_number 8 . - a libns:illumina_flowcell ; + a libns:IlluminaFlowcell ; libns:read_length 76 ; libns:flowcell_type "Paired"@en ; libns:date "2012-01-19T20:23:26"^^xsd:dateTime; @@ -265,34 +296,42 @@ lib_turtle = """@prefix : . libns:flowcell_id "30DY0AAXX"@en . + a libns:IlluminaLane ; libns:flowcell ; libns:library ; libns:lane_number 1 . + a libns:IlluminaLane ; libns:flowcell ; libns:library ; libns:lane_number 2 . + a libns:IlluminaLane ; libns:flowcell ; libns:library ; libns:lane_number 3 . + a libns:IlluminaLane ; libns:flowcell ; libns:library ; libns:lane_number 4 . + a libns:IlluminaLane ; libns:flowcell ; libns:library ; libns:lane_number 5 . + a libns:IlluminaLane ; libns:flowcell ; libns:library ; libns:lane_number 6 . + a libns:IlluminaLane ; libns:flowcell ; libns:library ; libns:lane_number 7 . + a libns:IlluminaLane ; libns:flowcell ; libns:library ; libns:lane_number 8 . @@ -301,7 +340,7 @@ lib_turtle = """@prefix : . # status "Unknown"@en . - a libns:illumina_flowcell ; + a libns:IlluminaFlowcell ; libns:read_length 101 ; libns:flowcell_type "Paired"@en ; libns:date "2012-01-19T20:23:26"^^xsd:dateTime; @@ -310,6 +349,7 @@ lib_turtle = """@prefix : . libns:flowcell_id "C02F9ACXX"@en . + a libns:IlluminaLane ; libns:flowcell ; libns:library ; libns:lane_number 3 . @@ -318,6 +358,7 @@ lib_turtle = """@prefix : . # status "Unknown"@en . + a libns:IlluminaLane ; libns:flowcell ; libns:library ; libns:lane_number 3 . @@ -326,7 +367,7 @@ lib_turtle = """@prefix : . # status "Unknown"@en . - a libns:library ; + a libns:Library ; libns:affiliation "TSR"@en; libns:concentration "29.7"; libns:date "2012-12-28T00:00:00"^^xsd:dateTime ; @@ -350,7 +391,7 @@ lib_turtle = """@prefix : . - a libns:library ; + a libns:Library ; libns:affiliation "TSR"@en; libns:concentration "12.345"; libns:cell_line "Unknown"@en ; @@ -401,6 +442,10 @@ class TestCondorFastq(unittest.TestCase): self.flowcelldir, self.logdir) load_string_into_model(self.extract.model, 'turtle', lib_turtle) + add_default_schemas(self.extract.model) + inference = Infer(self.extract.model) + errmsgs = list(inference.run_validation()) + self.assertEqual(len(errmsgs), 0) def tearDown(self): shutil.rmtree(self.tempdir) diff --git a/htsworkflow/util/schemas/htsworkflow.turtle b/htsworkflow/util/schemas/htsworkflow.turtle new file mode 100644 index 0000000..7319c0c --- /dev/null +++ b/htsworkflow/util/schemas/htsworkflow.turtle @@ -0,0 +1,340 @@ +@prefix rdf: . +@prefix rdfs: . +@prefix owl: . +@prefix dc: . +@prefix xml: . +@prefix xsd: . +@prefix htswlib: . + +# I'm still learning how to do modeling & validation +# this version is just using rdfs:Literal for +# any literal node. + + + dc:title "HTS-Workflow ontology" ; + a owl:Ontology . + +htswlib:Class a rdfs:Class . + +htswlib:IlluminaFlowcell + a rdfs:Class, htswlib:Class ; + rdfs:comment "information about a illumina flowcell" ; + rdfs:label "Flowcell" . + +htswlib:IlluminaLane + a rdfs:Class, htswlib:Class ; + rdfs:comment "information specific to a lane in a flowcell" ; + rdfs:label "Lane" . + +htswlib:Library + a rdfs:Class, htswlib:Class ; + rdfs:comment "a biological library that can be run on a flowcell" ; + rdfs:label "library" . + +htswlib:Sequencer + a rdfs:Class, htswlib:Class; + rdfs:comment "an instrument that converts libraries into sequence reads" ; + rdfs:label "Sequencer" . + +htswlib:Species + a rdfs:Class, htswlib:Class ; + rdfs:comment "What 'species' was our sample created from." ; + rdfs:label "Species" . + +htswlib:MappedCount + a rdfs:Class, htswlib:Class ; + rdfs:comment "Count of reads with locations" ; + rdfs:label "Mapped locations" . + +# reused properties? +htswlib:flowcell + a rdf:Property ; + rdfs:comment "link to our source flowcell" ; + rdfs:label "Flowcell" ; + rdfs:domain htswlib:IlluminaLane ; + rdfs:range htswlib:IlluminaFlowcell . + +htswlib:has_lane + a rdf:Property ; + rdfs:comment "which lanes are attached to a flowcell" ; + rdfs:label "lanes" ; + # cheating, only flowcells & libraries can have lanes + rdfs:domain htswlib:Library ; + rdfs:domain htswlib:IlluminaFlowcell ; + rdfs:range htswlib:IlluminaLane . + +htswlib:date + a rdf:Property ; + rdfs:comment "Date thing was constructed" ; + rdfs:label "made on" ; + rdfs:domain htswlib:IlluminaFlowcell ; + rdfs:domain htswlib:Library ; + rdfs:range rdfs:Literal . + +htswlib:total_unique_locations + a rdf:Property ; + rdfs:comment "How many reads mapped uniquely" ; + rdfs:label "Unique locations" ; + rdfs:domain htswlib:Library ; + rdfs:domain htswlib:IlluminaLane ; + rdfs:range rdfs:Literal . + +htswlib:has_mappings + a rdf:Property ; + rdfs:comment "collection of counts against sequence collections" ; + rdfs:label "Has mapping" ; + rdfs:domain htswlib:Library ; + rdfs:domain htswlib:IlluminaLane ; + rdfs:range htswlib:MappedCount . + +# flowcell properties +htswlib:flowcell_id + a rdf:Property ; + rdfs:comment "Serial number of a flowcell, used as unique key" ; + rdfs:label "Flowcell ID" ; + rdfs:domain htswlib:IlluminaFlowcell ; + rdfs:range rdfs:Literal . + +htswlib:flowcell_notes + a rdf:Property ; + rdfs:comment "Comments about flowcell" ; + rdfs:label "Notes" ; + rdfs:domain htswlib:IlluminaFlowcell ; + rdfs:range rdfs:Literal . + +htswlib:control_lane + a rdf:Property ; + rdfs:comment "Control lane used for image analysis/base calling" ; + rdfs:label "Control Lane" ; + rdfs:domain htswlib:IlluminaFlowcell ; + rdfs:range rdfs:Literal . + +htswlib:read_length + a rdf:Property ; + rdfs:comment "How many cycles did we run the sequencer for" ; + rdfs:label "Read length" ; + rdfs:domain htswlib:IlluminaFlowcell ; + rdfs:range rdfs:Literal . + +htswlib:flowcell_type + a rdf:Property ; + rdfs:comment "What kind of flowcell, e.g. single, paired." ; + rdfs:label "Flowcell Type" ; + rdfs:domain htswlib:IlluminaFlowcell ; + rdfs:range rdfs:Literal . + +htswlib:image_software + a rdf:Property ; + rdfs:comment "Image analysis software name." ; + rdfs:label "Image processor" ; + rdfs:domain htswlib:IlluminaFlowcell ; + rdfs:range rdfs:Literal . + +htswlib:image_version + a rdf:Property ; + rdfs:comment "Image analysis software version identifier." ; + rdfs:label "Image processor version" ; + rdfs:domain htswlib:IlluminaFlowcell ; + rdfs:range rdfs:Literal . + +htswlib:basecall_software + a rdf:Property ; + rdfs:comment "Base caller software name." ; + rdfs:label "Basecaller" ; + rdfs:domain htswlib:IlluminaFlowcell ; + rdfs:range rdfs:Literal . + +htswlib:basecall_version + a rdf:Property ; + rdfs:comment "Base caller software version identifier." ; + rdfs:label "Basecaller Version" ; + rdfs:domain htswlib:IlluminaFlowcell ; + rdfs:range rdfs:Literal . + +htswlib:alignment_software + a rdf:Property ; + rdfs:comment "Alignment software name." ; + rdfs:label "Alignment software" ; + rdfs:domain htswlib:IlluminaFlowcell ; + rdfs:range rdfs:Literal . + +htswlib:alignment_version + a rdf:Property ; + rdfs:comment "Alignment software version identifier." ; + rdfs:label "Aligner" ; + rdfs:domain htswlib:IlluminaFlowcell ; + rdfs:range rdfs:Literal . + +htswlib:sequenced_by + a rdf:Property ; + rdfs:comment "Which sequencer sequenced this flowcell" ; + rdfs:label "Sequenced By" ; + rdfs:domain htswlib:IlluminaFlowcell ; + rdfs:range htswlib:Sequencer . + +htswlib:sequencer_model + a rdf:Property ; + rdfs:comment "What model of sequencer was this flowcell run on." ; + rdfs:label "Sequencer model" ; + rdfs:domain htswlib:Sequencer ; + rdfs:range rdfs:Literal . + +htswlib:sequencer_instrument + a rdf:Property ; + rdfs:comment "Sequencer instrument identifier." ; + rdfs:label "Instrument ID " ; + rdfs:domain htswlib:Sequencer ; + rdfs:range rdfs:Literal . + +htswlib:sequencer_name + a rdf:Property ; + rdfs:comment "Local name for sequencer." ; + rdfs:label "Sequencer name " ; + rdfs:domain htswlib:Sequencer ; + rdfs:range rdfs:Literal . + + +# library only properties +htswlib:library_id + a rdf:Property ; + rdfs:comment "Library unique identifier" ; + rdfs:label "Library ID" ; + rdfs:domain htswlib:Library ; + rdfs:range rdfs:Literal . + +htswlib:name + a rdf:Property ; + rdfs:comment "human readable name" ; + rdfs:label "Name" ; + rdfs:range rdfs:Literal . + +htswlib:library_type + a rdf:Property ; + rdfs:comment """what type of library are we, which is primarily + determined by the type of adaptors ligated onto + sequence fragments.""" ; + rdfs:label "Library Type" ; + rdfs:domain htswlib:Library ; + rdfs:range rdfs:Literal . + +htswlib:stopping_point + a rdf:Property ; + rdfs:comment "Protocol stopping point" ; + rdfs:label "Stopping Point" ; + rdfs:domain htswlib:Library ; + rdfs:range rdfs:Literal . + +htswlib:concentration + a rdf:Property ; + rdfs:comment "Concentration of sample in nanograms per microliter" ; + rdfs:label "Concentration" ; + rdfs:domain htswlib:Library ; + rdfs:range rdfs:Literal . + +htswlib:insert_size + a rdf:Property ; + rdfs:comment "The expected size of the sample sequence" ; + rdfs:label "Insert Size" ; + rdfs:domain htswlib:Library ; + rdfs:range rdfs:Literal . + +htswlib:gel_cut + a rdf:Property ; + rdfs:comment "The estimated fragment sizes cut from gel"; + rdfs:label "Gel Cut" ; + rdfs:domain htswlib:Library ; + rdfs:range rdfs:Literal . + +htswlib:made_by + a rdf:Property ; + rdfs:comment "Name of person who created library" ; + rdfs:label "Made by" ; + rdfs:domain htswlib:Library ; + rdfs:range rdfs:Literal . + +htswlib:multiplex_index + a rdf:Property ; + rdfs:comment "multiplex sequence" ; + rdfs:label "index" ; + rdfs:domain htswlib:Library ; + rdfs:range rdfs:Literal . + +htswlib:cell_line + a rdf:Property ; + rdfs:comment "Description of source material" ; + rdfs:label "cell line" ; + rdfs:domain htswlib:Library ; + rdfs:range rdfs:Literal . + +htswlib:experiment_type + a rdf:Property ; + rdfs:comment "What type of sequencing is this. e.g. RNA-Seq, DeNovo etc." ; + rdfs:label "Experiment Type" ; + rdfs:domain htswlib:Library ; + rdfs:range rdfs:Literal . + +htswlib:affiliation + a rdf:Property ; + rdfs:comment "Entity associated with this sample" ; + rdfs:label "affiliation" ; + rdfs:domain htswlib:Library ; + rdfs:range rdfs:Literal . + +htswlib:species + a rdf:Property ; + rdfs:comment "Scientific name of sample species" ; + rdfs:label "Species" ; + rdfs:domain htswlib:Library ; + #rdfs:domain htswlib:IlluminaLane; + rdfs:range htswlib:Species . + +htswlib:replicate + a rdf:Property ; + rdfs:comment "Which replicate this was" ; + rdfs:label "replicate" ; + rdfs:domain htswlib:Library ; + rdfs:range rdfs:Literal . + +# lane only properties +htswlib:lane_number + a rdf:Property ; + rdfs:comment "Which lane were we run in" ; + rdfs:label "lane id" ; + rdfs:domain htswlib:IlluminaLane ; + rdfs:range rdfs:Literal . + +# FIXME: should this be note? +htswlib:comment + a rdf:Property ; + rdfs:comment "Comment about an object" ; + rdfs:range rdfs:Literal . + +htswlib:library + a rdf:Property ; + rdfs:comment "which library was run on this lane." ; + rdfs:label "Library" ; + rdfs:domain htswlib:IlluminaLane ; + rdfs:range htswlib:Library . + +# species properites +htswlib:species_name + a rdf:Property ; + rdfs:comment "Scientific name of species" ; + rdfs:label "Species" ; + rdfs:domain htswlib:Species ; + rdfs:range rdfs:Literal . + +# mapped count properties +htswlib:mapped_to + a rdf:Property ; + rdfs:comment "A sequence collection, genome, chromosome, spike in, etc."; + rdfs:label "Mapped to" ; + rdfs:domain htswlib:MappedCount ; + rdfs:range rdfs:Literal . + +htswlib:reads + a rdf:Property ; + rdfs:comment "Number of read locations" ; + rdfs:label "Reads" ; + rdfs:domain htswlib:MappedCount ; + rdfs:range rdfs:Literal . \ No newline at end of file -- 2.30.2