X-Git-Url: http://source.jalview.org/gitweb/?a=blobdiff_plain;f=src%2Fjalview%2Fdatamodel%2FSequenceI.java;h=11aa4e6a3bf0d3e0c296165a51c670b07d852857;hb=465ec4d5f251d139a207ab5c3280717234b74b7b;hp=fb723e6064c88ee84131f66f360860fe757de049;hpb=a81d34b61544d11e146f2d5cf6558d35bf24533b;p=jalview.git diff --git a/src/jalview/datamodel/SequenceI.java b/src/jalview/datamodel/SequenceI.java index fb723e6..11aa4e6 100755 --- a/src/jalview/datamodel/SequenceI.java +++ b/src/jalview/datamodel/SequenceI.java @@ -20,10 +20,13 @@ */ package jalview.datamodel; +import jalview.datamodel.Sequence.DBModList; import jalview.datamodel.features.SequenceFeaturesI; import jalview.util.MapList; +import jalview.ws.params.InvalidArgumentException; import java.util.BitSet; +import java.util.Iterator; import java.util.List; import java.util.Vector; @@ -45,6 +48,9 @@ public interface SequenceI extends ASequenceI */ public void setName(String name); + public HiddenMarkovModel getHMM(); + + public void setHMM(HiddenMarkovModel hmm); /** * Get the display name */ @@ -111,9 +117,11 @@ public interface SequenceI extends ASequenceI * get a range on the sequence as a string * * @param start - * position relative to start of sequence including gaps (from 0) + * (inclusive) position relative to start of sequence including gaps + * (from 0) * @param end - * position relative to start of sequence including gaps (from 0) + * (exclusive) position relative to start of sequence including gaps + * (from 0) * * @return String containing all gap and symbols in specified range */ @@ -205,14 +213,17 @@ public interface SequenceI extends ASequenceI public int findPosition(int i); /** - * Returns the from-to sequence positions (start..) for the given column - * positions (1..), or null if no residues are included in the range + * Returns the sequence positions for first and last residues lying within the + * given column positions [fromColum,toColumn] (where columns are numbered + * from 1), or null if no residues are included in the range * * @param fromColum + * - first column base 1. (0 and negative positions are rounded up) * @param toColumn - * @return + * - last column, base 1 + * @return null if fromColum>toColumn */ - public Range findPositions(int fromColum, int toColumn); + public ContiguousI findPositions(int fromColum, int toColumn); /** * Returns an int array where indices correspond to each residue in the @@ -224,6 +235,13 @@ public interface SequenceI extends ASequenceI public int[] gapMap(); /** + * Build a bitset corresponding to sequence gaps + * + * @return a BitSet where set values correspond to gaps in the sequence + */ + public BitSet gapBitset(); + + /** * Returns an int array where indices correspond to each position in sequence * char array and the element value gives the result of findPosition for that * index in the sequence. @@ -342,14 +360,17 @@ public interface SequenceI extends ASequenceI /** * set the array of Database references for the sequence. * + * BH 2019.02.04 changes param to DBModlist + * * @param dbs * @deprecated - use is discouraged since side-effects may occur if DBRefEntry * set are not normalised. + * @throws InvalidArgumentException if the is not one created by Sequence itself */ @Deprecated - public void setDBRefs(DBRefEntry[] dbs); + public void setDBRefs(DBModList dbs); - public DBRefEntry[] getDBRefs(); + public DBModList getDBRefs(); /** * add the given entry to the list of DBRefs for this sequence, or replace a @@ -375,6 +396,24 @@ public interface SequenceI extends ASequenceI public SequenceI getDatasetSequence(); /** + * Returns the top grandparent in the dataset sequences hierarchy + * or null if there is no dataset associated with this sequence. + */ + public default SequenceI getRootDatasetSequence() + { + if (getDatasetSequence() == null) + { + return null; + } + var sequence = getDatasetSequence(); + while (sequence.getDatasetSequence() != null) + { + sequence = sequence.getDatasetSequence(); + } + return sequence; + } + + /** * Returns a new array containing this sequence's annotations, or null. */ public AlignmentAnnotation[] getAnnotation(); @@ -428,6 +467,17 @@ public interface SequenceI extends ASequenceI String label); /** + * Returns a (possibly empty) list of any annotations that match on given + * calcId (source), label (type) and description (observation instance). + * Null values do not match. + * + * @param calcId + * @param label + * @param description + */ + public List getAlignmentAnnotations(String calcId, + String label, String description); + /** * create a new dataset sequence (if necessary) for this sequence and sets * this sequence to refer to it. This call will move any features or * references on the sequence onto the dataset. It will also make a duplicate @@ -486,6 +536,11 @@ public interface SequenceI extends ASequenceI * list */ public List getPrimaryDBRefs(); + /** + * Answers true if the sequence has annotation for Hidden Markov Model + * information content, else false + */ + boolean hasHMMAnnotation(); /** * Returns a (possibly empty) list of sequence features that overlap the given @@ -543,4 +598,35 @@ public interface SequenceI extends ASequenceI */ void setGeneLoci(String speciesId, String assemblyId, String chromosomeId, MapList map); + + + /** + * Returns the sequence string constructed from the substrings of a sequence + * defined by the int[] ranges provided by an iterator. E.g. the iterator + * could iterate over all visible regions of the alignment + * + * @param it + * the iterator to use + * @return a String corresponding to the sequence + */ + public String getSequenceStringFromIterator(Iterator it); + + /** + * Locate the first position in this sequence which is not contained in an + * iterator region. If no such position exists, return 0 + * + * @param it + * iterator over regions + * @return first residue not contained in regions + */ + public int firstResidueOutsideIterator(Iterator it); + + + /** + * Answers true if this sequence has an associated Hidden Markov Model + * + * @return + */ + boolean hasHMMProfile(); } +