Clover icon

jalviewX

  1. Project Clover database Wed Oct 31 2018 15:13:58 GMT
  2. Package jalview.io.gff

File SequenceOntologyLite.java

 

Coverage histogram

../../../img/srcFileCovDistChart8.png
19% of files have more coverage

Code metrics

14
35
7
1
250
137
15
0.43
5
7
2.14

Classes

Class Line # Actions
SequenceOntologyLite 41 35 15 11
0.803571480.4%
 

Contributing tests

This file is covered by 44 tests. .

Source view

1    /*
2    * Jalview - A Sequence Alignment Editor and Viewer ($$Version-Rel$$)
3    * Copyright (C) $$Year-Rel$$ The Jalview Authors
4    *
5    * This file is part of Jalview.
6    *
7    * Jalview is free software: you can redistribute it and/or
8    * modify it under the terms of the GNU General Public License
9    * as published by the Free Software Foundation, either version 3
10    * of the License, or (at your option) any later version.
11    *
12    * Jalview is distributed in the hope that it will be useful, but
13    * WITHOUT ANY WARRANTY; without even the implied warranty
14    * of MERCHANTABILITY or FITNESS FOR A PARTICULAR
15    * PURPOSE. See the GNU General Public License for more details.
16    *
17    * You should have received a copy of the GNU General Public License
18    * along with Jalview. If not, see <http://www.gnu.org/licenses/>.
19    * The Jalview Authors are detailed in the 'AUTHORS' file.
20    */
21    package jalview.io.gff;
22   
23    import java.util.ArrayList;
24    import java.util.Collections;
25    import java.util.HashMap;
26    import java.util.List;
27    import java.util.Map;
28   
29    /**
30    * An implementation of SequenceOntologyI that hard codes terms of interest.
31    *
32    * Use this in unit testing by calling SequenceOntology.setInstance(new
33    * SequenceOntologyLite()).
34    *
35    * May also become a stand-in for SequenceOntology in the applet if we want to
36    * avoid the additional jars needed for parsing the full SO.
37    *
38    * @author gmcarstairs
39    *
40    */
 
41    public class SequenceOntologyLite implements SequenceOntologyI
42    {
43    /*
44    * initial selection of types of interest when processing Ensembl features
45    * NB unlike the full SequenceOntology we don't traverse indirect
46    * child-parent relationships here so e.g. need to list every sub-type
47    * (direct or indirect) that is of interest
48    */
49    // @formatter:off
50    private final String[][] TERMS = new String[][] {
51   
52    /*
53    * gene sub-types:
54    */
55    { "gene", "gene" },
56    { "ncRNA_gene", "gene" },
57    { "snRNA_gene", "gene" },
58    { "miRNA_gene", "gene" },
59    { "lincRNA_gene", "gene" },
60    { "rRNA_gene", "gene" },
61   
62    /*
63    * transcript sub-types:
64    */
65    { "transcript", "transcript" },
66    { "mature_transcript", "transcript" },
67    { "processed_transcript", "transcript" },
68    { "aberrant_processed_transcript", "transcript" },
69    { "ncRNA", "transcript" },
70    { "snRNA", "transcript" },
71    { "miRNA", "transcript" },
72    { "lincRNA", "transcript" },
73    { "rRNA", "transcript" },
74    { "mRNA", "transcript" },
75    // there are many more sub-types of ncRNA...
76   
77    /*
78    * sequence_variant sub-types
79    */
80    { "sequence_variant", "sequence_variant" },
81    { "structural_variant", "sequence_variant" },
82    { "feature_variant", "sequence_variant" },
83    { "gene_variant", "sequence_variant" },
84    { "transcript_variant", "sequence_variant" },
85    // NB Ensembl uses NMD_transcript_variant as if a 'transcript'
86    // but we model it here correctly as per the SO
87    { "NMD_transcript_variant", "sequence_variant" },
88    { "missense_variant", "sequence_variant" },
89    { "synonymous_variant", "sequence_variant" },
90    { "frameshift_variant", "sequence_variant" },
91    { "5_prime_UTR_variant", "sequence_variant" },
92    { "3_prime_UTR_variant", "sequence_variant" },
93    { "stop_gained", "sequence_variant" },
94    { "stop_lost", "sequence_variant" },
95    { "inframe_deletion", "sequence_variant" },
96    { "inframe_insertion", "sequence_variant" },
97    { "splice_region_variant", "sequence_variant" },
98   
99    /*
100    * no sub-types of exon or CDS yet seen in Ensembl
101    * some added here for testing purposes
102    */
103    { "exon", "exon" },
104    { "coding_exon", "exon" },
105    { "CDS", "CDS" },
106    { "CDS_predicted", "CDS" },
107   
108    /*
109    * terms used in exonerate or PASA GFF
110    */
111    { "protein_match", "protein_match"},
112    { "nucleotide_match", "nucleotide_match"},
113    { "cDNA_match", "nucleotide_match"},
114   
115    /*
116    * used in InterProScan GFF
117    */
118    { "polypeptide", "polypeptide" }
119    };
120    // @formatter:on
121   
122    /*
123    * hard-coded list of any parents (direct or indirect)
124    * that we care about for a term
125    */
126    private Map<String, List<String>> parents;
127   
128    private List<String> termsFound;
129   
130    private List<String> termsNotFound;
131   
 
132  8 toggle public SequenceOntologyLite()
133    {
134  8 termsFound = new ArrayList<>();
135  8 termsNotFound = new ArrayList<>();
136  8 loadStaticData();
137    }
138   
139    /**
140    * Loads hard-coded data into a lookup table of {term, {list_of_parents}}
141    */
 
142  8 toggle private void loadStaticData()
143    {
144  8 parents = new HashMap<>();
145  8 for (String[] pair : TERMS)
146    {
147  320 List<String> p = parents.get(pair[0]);
148  320 if (p == null)
149    {
150  320 p = new ArrayList<>();
151  320 parents.put(pair[0], p);
152    }
153  320 p.add(pair[1]);
154    }
155    }
156   
157    /**
158    * Answers true if 'child' isA 'parent' (including equality). In this
159    * implementation, based only on hard-coded values.
160    */
 
161  250 toggle @Override
162    public boolean isA(String child, String parent)
163    {
164  250 if (child == null || parent == null)
165    {
166  0 return false;
167    }
168  250 if (child.equals(parent))
169    {
170  64 termFound(child);
171  64 return true;
172    }
173   
174  186 List<String> p = parents.get(child);
175  186 if (p == null)
176    {
177  52 termNotFound(child);
178  52 return false;
179    }
180  134 termFound(child);
181  134 if (p.contains(parent))
182    {
183  51 return true;
184    }
185  83 return false;
186    }
187   
188    /**
189    * Records a valid term queried for, for reporting purposes
190    *
191    * @param term
192    */
 
193  198 toggle private void termFound(String term)
194    {
195  198 if (!termsFound.contains(term))
196    {
197  60 synchronized (termsFound)
198    {
199  60 termsFound.add(term);
200    }
201    }
202    }
203   
204    /**
205    * Records an invalid term queried for, for reporting purposes
206    *
207    * @param term
208    */
 
209  52 toggle private void termNotFound(String term)
210    {
211  52 synchronized (termsNotFound)
212    {
213  52 if (!termsNotFound.contains(term))
214    {
215    // suppress logging here as it reports Uniprot sequence features
216    // (which do not use SO terms) when auto-configuring feature colours
217    // System.out.println("SO term " + term
218    // + " not known - add to model if needed in "
219    // + getClass().getName());
220  14 termsNotFound.add(term);
221    }
222    }
223    }
224   
225    /**
226    * Sorts (case-insensitive) and returns the list of valid terms queried for
227    */
 
228  0 toggle @Override
229    public List<String> termsFound()
230    {
231  0 synchronized (termsFound)
232    {
233  0 Collections.sort(termsFound, String.CASE_INSENSITIVE_ORDER);
234  0 return termsFound;
235    }
236    }
237   
238    /**
239    * Sorts (case-insensitive) and returns the list of invalid terms queried for
240    */
 
241  0 toggle @Override
242    public List<String> termsNotFound()
243    {
244  0 synchronized (termsNotFound)
245    {
246  0 Collections.sort(termsNotFound, String.CASE_INSENSITIVE_ORDER);
247  0 return termsNotFound;
248    }
249    }
250    }