Classes

Class	Line #	Total Statements	Complexity	TOTAL Coverage	Actions
SecondaryStructureDistanceModel	47	99	44	0.058823535.9%	Show methods

Class SecondaryStructureDistanceModel

Class SecondaryStructureDistanceModel	Line # 47	Total Statements 99	Complexity 44	TOTAL Coverage 0.058823535.9%
SecondaryStructureDistanceModel()   SecondaryStructureDistanceModel()	6060	0.00	1.01	-1.0 -1.0 -
getInstance(AlignmentViewPanel) : ScoreModelI   getInstance(AlignmentViewPanel) : ScoreModelI	6565	8.08	3.03	0.0 0.00%
configureFromAlignmentView(AlignmentViewPanel) : boolean   configureFromAlignmentView(AlignmentViewPanel) : boolean	8585	2.02	1.01	0.0 0.00%
expandSeqData(SequenceI[],AlignmentView,SimilarityParamsI,List<String>) : SequenceI[]   expandSeqData(SequenceI[],AlignmentView,SimilarityParamsI,List<String>) : SequenceI[]	9494	29.029	7.07	0.0 0.00%
findDistances(AlignmentView,SimilarityParamsI) : MatrixI   findDistances(AlignmentView,SimilarityParamsI) : MatrixI	183183	48.048	24.024	0.0 0.00%
findSeqsWithoutGapAtColumn(SeqCigar[],int) : Set<SeqCigar>   findSeqsWithoutGapAtColumn(SeqCigar[],int) : Set<SeqCigar>	331331	6.06	2.02	0.0 0.00%
getName() : String   getName() : String	349349	1.01	1.01	1.0 1.0100%
getDescription() : String   getDescription() : String	355355	1.01	1.01	0.0 0.00%
isDNA() : boolean   isDNA() : boolean	361361	1.01	1.01	1.0 1.0100%
isProtein() : boolean   isProtein() : boolean	367367	1.01	1.01	1.0 1.0100%
isSecondaryStructure() : boolean   isSecondaryStructure() : boolean	373373	1.01	1.01	1.0 1.0100%
toString() : String   toString() : String	379379	1.01	1.01	0.0 0.00%

 

Contributing tests

Contributing tests

Select all

	Test contribution	Test	Result	Actions
	0.052287582	jalview.gui.CalculationChooserTest.testGetApplicableScoreModelsjalview.gui.CalculationChooserTest.testGetApplicableScoreModels	1PASS

 

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.analysis.scoremodels;
22
23		import jalview.analysis.AlignmentUtils;
24		import jalview.api.AlignmentViewPanel;
25		import jalview.api.FeatureRenderer;
26		import jalview.api.analysis.ScoreModelI;
27		import jalview.api.analysis.SimilarityParamsI;
28		import jalview.datamodel.AlignmentAnnotation;
29		import jalview.datamodel.AlignmentView;
30		import jalview.datamodel.SeqCigar;
31		import jalview.datamodel.SequenceI;
32		import jalview.math.Matrix;
33		import jalview.math.MatrixI;
34		import jalview.util.Constants;
35		import jalview.util.MessageManager;
36
37		import java.util.ArrayList;
38		import java.util.HashMap;
39		import java.util.HashSet;
40		import java.util.List;
41		import java.util.Map;
42		import java.util.Set;
43
44		/* This class contains methods to calculate distance score between
45		* secondary structure annotations of the sequences.
46		*/
		5.9% Uncovered Elements: 144 (153) Complexity: 44 Complexity Density: 0.44
47		public class SecondaryStructureDistanceModel extends DistanceScoreModel
48		{
49		private static final String NAME = "Secondary Structure Similarity";
50
51		private ScoreMatrix ssRateMatrix;
52
53		private String description;
54
55		FeatureRenderer fr;
56
57		/**
58		* Constructor
59		*/
		- Uncovered Elements: 0 (0) Complexity: 1 Complexity Density: -
60	21	public SecondaryStructureDistanceModel()...
61		{
62
63		}
64
		0% Uncovered Elements: 8 (8) Complexity: 3 Complexity Density: 0.38
65	0	@Override...
66		public ScoreModelI getInstance(AlignmentViewPanel view)
67		{
68	0	SecondaryStructureDistanceModel instance;
69	0	try
70		{
71	0	instance = this.getClass().getDeclaredConstructor().newInstance();
72	0	instance.configureFromAlignmentView(view);
73	0	return instance;
74		} catch (InstantiationException | IllegalAccessException e)
75		{
76	0	jalview.bin.Console.errPrintln("Error in " + getClass().getName()
77		+ ".getInstance(): " + e.getMessage());
78	0	return null;
79		} catch (ReflectiveOperationException roe)
80		{
81	0	return null;
82		}
83		}
84
		0% Uncovered Elements: 2 (2) Complexity: 1 Complexity Density: 0.5
85	0	boolean configureFromAlignmentView(AlignmentViewPanel view)...
86
87		{
88	0	fr = view.cloneFeatureRenderer();
89	0	return true;
90		}
91
92		ArrayList<AlignmentAnnotation> ssForSeqs = null;
93
		0% Uncovered Elements: 39 (39) Complexity: 7 Complexity Density: 0.24
94	0	@Override...
95		public SequenceI[] expandSeqData(SequenceI[] sequences,
96		AlignmentView seqData, SimilarityParamsI scoreParams,
97		List<String> labels)
98		{
99	0	ssForSeqs = new ArrayList<AlignmentAnnotation>();
100	0	List<SequenceI> newSequences = new ArrayList<SequenceI>();
101	0	List<SeqCigar> newCigs = new ArrayList<SeqCigar>();
102	0	int sq = 0;
103
104	0	AlignmentAnnotation[] alignAnnotList = fr.getViewport().getAlignment()
105		.getAlignmentAnnotation();
106
107	0	String ssSource = scoreParams.getSecondaryStructureSource();
108	0	if (ssSource == null || ssSource == "")
109		{
110	0	ssSource = Constants.SS_ALL_PROVIDERS;
111		}
112
113		/*
114		* Add secondary structure annotations that are added to the annotation track
115		* to the map
116		*/
117	0	Map<SequenceI, ArrayList<AlignmentAnnotation>> ssAlignmentAnnotationForSequences = AlignmentUtils
118		.getSequenceAssociatedAlignmentAnnotations(alignAnnotList,
119		ssSource);
120
121	0	for (SeqCigar scig : seqData.getSequences())
122		{
123		// get the next sequence that should be bound to this scig: may be null
124	0	SequenceI alSeq = sequences[sq++];
125	0	List<AlignmentAnnotation> ssec = ssAlignmentAnnotationForSequences
126		.get(scig.getRefSeq());
127	0	if (ssec == null)
128		{
129		// not defined
130	0	newSequences.add(alSeq);
131	0	if (alSeq != null)
132		{
133		//labels.add("No Secondary Structure");
134	0	labels.add(Constants.STRUCTURE_PROVIDERS.get("None"));
135		}
136	0	SeqCigar newSeqCigar = scig; // new SeqCigar(scig);
137	0	newCigs.add(newSeqCigar);
138	0	ssForSeqs.add(null);
139		}
140		else
141		{
142	0	for (int i = 0; i < ssec.size(); i++)
143		{
144	0	if (alSeq != null)
145		{
146	0	String provider = AlignmentUtils.extractSSSourceFromAnnotationDescription(ssec.get(i));
147		//String providerAbbreviation = AlignmentUtils.getProviderKey(provider);
148	0	labels.add(provider);
149		}
150		// newSequences.add(seq);
151	0	newSequences.add(alSeq);
152	0	SeqCigar newSeqCigar = scig; // new SeqCigar(scig);
153	0	newCigs.add(newSeqCigar);
154	0	ssForSeqs.add(ssec.get(i));
155		}
156		}
157		}
158
159	0	seqData.setSequences(newCigs.toArray(new SeqCigar[0]));
160	0	return newSequences.toArray(new SequenceI[0]);
161
162		}
163
164		/**
165		* Calculates distance score [i][j] between each pair of protein sequences
166		* based on their secondary structure annotations (H, E, C). The final score
167		* is normalised by the number of alignment columns processed, providing an
168		* average similarity score.
169		* <p>
170		* The parameters argument can include settings for handling gap-residue
171		* aligned positions and may determine if the score calculation is based on
172		* the longer or shorter sequence in each pair. This can be important for
173		* handling partial alignments or sequences of significantly different
174		* lengths.
175		*
176		* @param seqData
177		* The aligned sequence data including secondary structure
178		* annotations.
179		* @param params
180		* Additional parameters for customising the scoring process, such as
181		* gap handling and sequence length consideration.
182		*/
		0% Uncovered Elements: 78 (78) Complexity: 24 Complexity Density: 0.5
183	0	@Override...
184		public MatrixI findDistances(AlignmentView seqData,
185		SimilarityParamsI params)
186		{
187	0	if (ssForSeqs == null
188		|| ssForSeqs.size() != seqData.getSequences().length)
189		{
190		// expandSeqData needs to be called to initialise the hash
191	0	SequenceI[] sequences = new SequenceI[seqData.getSequences().length];
192		// we throw away the new labels in this case..
193	0	expandSeqData(sequences, seqData, params, new ArrayList<String>());
194		}
195	0	SeqCigar[] seqs = seqData.getSequences();
196	0	int noseqs = seqs.length; // no of sequences
197	0	int cpwidth = 0;
198	0	double[][] similarities = new double[noseqs][noseqs]; // matrix to store
199		// similarity score
200		// secondary structure source parameter selected by the user from the drop
201		// down.
202	0	String ssSource = params.getSecondaryStructureSource();
203	0	if (ssSource == null || ssSource == "")
204		{
205	0	ssSource = Constants.SS_ALL_PROVIDERS;
206		}
207	0	ssRateMatrix = ScoreModels.getInstance().getSecondaryStructureMatrix();
208
209		// need to get real position for view position
210	0	int[] viscont = seqData.getVisibleContigs();
211
212		/*
213		* scan each column, compute and add to each similarity[i, j]
214		* the number of secondary structure annotation that seqi
215		* and seqj do not share
216		*/
217	0	for (int vc = 0; vc < viscont.length; vc += 2)
218		{
219		// Iterates for each column position
220	0	for (int cpos = viscont[vc]; cpos <= viscont[vc + 1]; cpos++)
221		{
222	0	cpwidth++; // used to normalise the similarity score
223
224		/*
225		* get set of sequences without gap in the current column
226		*/
227	0	Set<SeqCigar> seqsWithoutGapAtCol = findSeqsWithoutGapAtColumn(seqs,
228		cpos);
229
230		/*
231		* calculate similarity score for each secondary structure annotation on i'th and j'th
232		* sequence and add this measure to the similarities matrix
233		* for [i, j] for j > i
234		*/
235	0	for (int i = 0; i < (noseqs - 1); i++)
236		{
237	0	AlignmentAnnotation aa_i = ssForSeqs.get(i);
238	0	boolean undefinedSS1 = aa_i == null;
239		// check if the sequence contains gap in the current column
240	0	boolean gap1 = !seqsWithoutGapAtCol.contains(seqs[i]);
241		// secondary structure is fetched only if the current column is not
242		// gap for the sequence
243	0	char ss1 = '*';
244	0	if (!gap1 && !undefinedSS1)
245		{
246		// fetch the position in sequence for the column and finds the
247		// corresponding secondary structure annotation
248		// TO DO - consider based on priority and displayed
249	0	int seqPosition_i = seqs[i].findPosition(cpos);
250	0	if (aa_i != null)
251	0	ss1 = AlignmentUtils.findSSAnnotationForGivenSeqposition(aa_i,
252		seqPosition_i);
253		}
254		// Iterates for each sequences
255	0	for (int j = i + 1; j < noseqs; j++)
256		{
257
258		// check if ss is defined
259	0	AlignmentAnnotation aa_j = ssForSeqs.get(j);
260	0	boolean undefinedSS2 = aa_j == null;
261
262		// Set similarity to max score if both SS are not defined
263	0	if (undefinedSS1 && undefinedSS2)
264		{
265	0	similarities[i][j] += ssRateMatrix.getMaximumScore();
266	0	continue;
267		}
268
269		// Set similarity to minimum score if either one SS is not defined
270	0	else if (undefinedSS1 || undefinedSS2)
271		{
272	0	similarities[i][j] += ssRateMatrix.getMinimumScore();
273	0	continue;
274		}
275
276	0	boolean gap2 = !seqsWithoutGapAtCol.contains(seqs[j]);
277
278		// Variable to store secondary structure at the current column
279	0	char ss2 = '*';
280
281	0	if (!gap2 && !undefinedSS2)
282		{
283	0	int seqPosition = seqs[j].findPosition(cpos);
284
285	0	if (aa_j != null)
286	0	ss2 = AlignmentUtils.findSSAnnotationForGivenSeqposition(
287		aa_j, seqPosition);
288		}
289
290	0	if ((!gap1 && !gap2) || params.includeGaps())
291		{
292		// Calculate similarity score based on the substitution matrix
293	0	double similarityScore = ssRateMatrix.getPairwiseScore(ss1,
294		ss2);
295	0	similarities[i][j] += similarityScore;
296		}
297		}
298		}
299		}
300		}
301
302		/*
303		* normalise the similarity scores (summed over columns) by the
304		* number of visible columns used in the calculation
305		* and fill in the bottom half of the matrix
306		*/
307		// TODO JAL-2424 cpwidth may be out by 1 - affects scores but not tree shape
308
309	0	for (int i = 0; i < noseqs; i++)
310		{
311	0	for (int j = i + 1; j < noseqs; j++)
312		{
313	0	similarities[i][j] /= cpwidth;
314	0	similarities[j][i] = similarities[i][j];
315		}
316		}
317	0	return SimilarityScoreModel
318		.similarityToDistance(new Matrix(similarities));
319
320		}
321
322		/**
323		* Builds and returns a set containing sequences (SeqCigar) which do not have
324		* a gap at the given column position.
325		*
326		* @param seqs
327		* @param columnPosition
328		* (0..)
329		* @return
330		*/
		0% Uncovered Elements: 8 (8) Complexity: 2 Complexity Density: 0.33
331	0	private Set<SeqCigar> findSeqsWithoutGapAtColumn(SeqCigar[] seqs,...
332		int columnPosition)
333		{
334	0	Set<SeqCigar> seqsWithoutGapAtCol = new HashSet<>();
335	0	for (SeqCigar seq : seqs)
336		{
337	0	int spos = seq.findPosition(columnPosition);
338	0	if (spos != -1)
339		{
340		/*
341		* position is not a gap
342		*/
343	0	seqsWithoutGapAtCol.add(seq);
344		}
345		}
346	0	return seqsWithoutGapAtCol;
347		}
348
		100% Uncovered Elements: 0 (1) Complexity: 1 Complexity Density: 1
349	44	@Override...
350		public String getName()
351		{
352	44	return NAME;
353		}
354
		0% Uncovered Elements: 1 (1) Complexity: 1 Complexity Density: 1
355	0	@Override...
356		public String getDescription()
357		{
358	0	return description;
359		}
360
		100% Uncovered Elements: 0 (1) Complexity: 1 Complexity Density: 1
361	4	@Override...
362		public boolean isDNA()
363		{
364	4	return false;
365		}
366
		100% Uncovered Elements: 0 (1) Complexity: 1 Complexity Density: 1
367	2	@Override...
368		public boolean isProtein()
369		{
370	2	return true;
371		}
372
		100% Uncovered Elements: 0 (1) Complexity: 1 Complexity Density: 1
373	2	@Override...
374		public boolean isSecondaryStructure()
375		{
376	2	return true;
377		}
378
		0% Uncovered Elements: 1 (1) Complexity: 1 Complexity Density: 1
379	0	@Override...
380		public String toString()
381		{
382	0	return "Score between sequences based on similarity between binary "
383		+ "vectors marking secondary structure displayed at each column";
384		}
385		}