Package de.julielab.genemapper.classification

Class TransformerDisambiguationDataUtils

java.lang.Object

de.julielab.genemapper.classification.TransformerDisambiguationDataUtils

public class TransformerDisambiguationDataUtils
extends Object

Field Summary

Fields

Modifier and Type	Field	Description
static boolean	ADD_DESC
static boolean	ADD_GENERIF
static boolean	ADD_INTERACTIONS
static boolean	ADD_NAME_TYPES
static boolean	ADD_SUMMARY
static de.julielab.geneexpbase.configuration.Parameters	CANDIDATE_SETTER_PARAMS
static boolean	EXCLUDE_FP_GM
static int	MAX_DOC_CONTEXT_SIZE
static boolean	NORMALIZE_CONTEXT_GENES
static boolean	ONLY_APPROX_MATCHES
static boolean	ONLY_EXACT_MATCHES
static boolean	USE_GOLD_TAX_FOR_CANDIDATE_RETRIEVAL
static boolean	USE_ORIGINAL_QUERY_NAMES
static int	VERSION

Constructor Summary

Constructors

Constructor	Description
TransformerDisambiguationDataUtils()

Method Summary

Modifier and Type	Method	Description
static void	addDocumentLevelGeneAnnotations(de.julielab.geneexpbase.genemodel.GeneDocument document, com.google.common.collect.Multimap<String,String> docid2geneid)
static String	getCandidateQueryString(de.julielab.geneexpbase.candidateretrieval.SynHit sh, CandidateRetrieval candidateRetrieval)	Creates a single string describing the given gene database candidate.
static String	getGmMarkedDocumentText(de.julielab.geneexpbase.genemodel.GeneMention gm, int maxContextTokens, boolean onlyGenes, boolean uniqueGenes)
static void	writeData(GeneMapper mapper, File outputFile, Stream<de.julielab.geneexpbase.genemodel.GeneDocument> geneDocumentStream)
static void	writeData(BufferedWriter bw, GeneMapper mapper, de.julielab.geneexpbase.genemodel.GeneDocument doc)

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Field Detail

USE_GOLD_TAX_FOR_CANDIDATE_RETRIEVAL

public static final boolean USE_GOLD_TAX_FOR_CANDIDATE_RETRIEVAL

See Also:

Constant Field Values

ADD_GENERIF

public static final boolean ADD_GENERIF

See Also:

Constant Field Values

ADD_INTERACTIONS

public static final boolean ADD_INTERACTIONS

See Also:

Constant Field Values

ADD_SUMMARY

public static final boolean ADD_SUMMARY

See Also:

Constant Field Values

ADD_DESC

public static final boolean ADD_DESC

See Also:

Constant Field Values

MAX_DOC_CONTEXT_SIZE

public static final int MAX_DOC_CONTEXT_SIZE

See Also:

Constant Field Values

ADD_NAME_TYPES

public static final boolean ADD_NAME_TYPES

See Also:

Constant Field Values

USE_ORIGINAL_QUERY_NAMES

public static final boolean USE_ORIGINAL_QUERY_NAMES

See Also:

Constant Field Values

NORMALIZE_CONTEXT_GENES

public static final boolean NORMALIZE_CONTEXT_GENES

See Also:

Constant Field Values

EXCLUDE_FP_GM

public static final boolean EXCLUDE_FP_GM

See Also:

Constant Field Values

ONLY_EXACT_MATCHES

public static final boolean ONLY_EXACT_MATCHES

See Also:

Constant Field Values

ONLY_APPROX_MATCHES

public static final boolean ONLY_APPROX_MATCHES

See Also:

Constant Field Values

VERSION

public static final int VERSION

See Also:

Constant Field Values

CANDIDATE_SETTER_PARAMS

public static final de.julielab.geneexpbase.configuration.Parameters CANDIDATE_SETTER_PARAMS

Constructor Detail

TransformerDisambiguationDataUtils

public TransformerDisambiguationDataUtils()

Method Detail

writeData

public static void writeData(GeneMapper mapper,
                             File outputFile,
                             Stream<de.julielab.geneexpbase.genemodel.GeneDocument> geneDocumentStream)
                      throws IOException,
                             ExecutionException,
                             GeneMapperException

Throws:

IOException

ExecutionException

GeneMapperException

writeData

public static void writeData(BufferedWriter bw,
                             GeneMapper mapper,
                             de.julielab.geneexpbase.genemodel.GeneDocument doc)
                      throws IOException,
                             ExecutionException,
                             GeneMapperException

Throws:

IOException

ExecutionException

GeneMapperException

getGmMarkedDocumentText

public static String getGmMarkedDocumentText(de.julielab.geneexpbase.genemodel.GeneMention gm,
                                             int maxContextTokens,
                                             boolean onlyGenes,
                                             boolean uniqueGenes)

getCandidateQueryString

public static String getCandidateQueryString(de.julielab.geneexpbase.candidateretrieval.SynHit sh,
                                             CandidateRetrieval candidateRetrieval)
                                      throws ExecutionException

Creates a single string describing the given gene database candidate. Those are names and synonyms and optionally textual descriptions of the gene. This string is supposed to serve as a "query" or "question" for the transformer. Given also a part of the document context of the current gene, the transformer should then decide whether the gene description belongs to the current gene or not.

Parameters:

sh - The gene candidate to create a query string for.

Returns:

The candidate "query" to compare to the document context.

Throws:

ExecutionException

addDocumentLevelGeneAnnotations

public static void addDocumentLevelGeneAnnotations(de.julielab.geneexpbase.genemodel.GeneDocument document,
                                                   com.google.common.collect.Multimap<String,String> docid2geneid)