Class Configuration
- java.lang.Object
-
- java.util.Dictionary<K,V>
-
- java.util.Hashtable<Object,Object>
-
- java.util.Properties
-
- de.julielab.geneexpbase.configuration.Configuration
-
- de.julielab.genemapper.Configuration
-
- All Implemented Interfaces:
Serializable,Cloneable,Map<Object,Object>
public class Configuration extends de.julielab.geneexpbase.configuration.Configuration- See Also:
- Serialized Form
-
-
Field Summary
-
Fields inherited from class de.julielab.geneexpbase.configuration.Configuration
CONCURRENCY_LEVEL, EHCACHE_CONFIG, GENE_ORTHOLOGS_PATH, KEY_CLASSIFIER, KEY_DATA_ALPHABET, KEY_MAX_RESULT_SCORE, KEY_MIN_RESULT_SCORE, KEY_MINMAX_SCALING_VALUES, KEY_RANKER, KEY_STANDARDIZATION_VALUES, KEY_TARGET_ALPHABET, ML, PARAM_ALGORITHM, PARAM_LTR_ALGORITHM, PARAM_LTR_K, PARAM_LTR_METRIC, PARAM_MINMAX_SCALE_FEATURES, PARAM_ML_USE_ALL_CORPUS_TRAINSPLITS, PARAM_MODEL, PARAM_PYTHON_EXECUTABLE, PARAM_SCALE_RESULT_SCORE, PARAM_STANDARDIZE_FEATURES, PARAM_SVM_C, PARAM_SVM_COEF0, PARAM_SVM_DEGREE, PARAM_SVM_GAMMA, PARAM_SVM_KERNEL_TYPE, PARAM_SVM_TYPE, PYTHON_PROCESS_LIMIT, TRAINING_INSTANCES, VALUE_LTR, VALUE_LUCENE, VALUE_MAXENT, VALUE_SVM, VALUE_TRANSFORMER
-
Fields inherited from class java.util.Properties
defaults
-
-
Constructor Summary
Constructors Constructor Description Configuration()Configuration(de.julielab.geneexpbase.configuration.Configuration baseConfiguration)Configuration(File configurationFile)Configuration(String... parameters)
-
Method Summary
-
Methods inherited from class de.julielab.geneexpbase.configuration.Configuration
dot, getBoolean, getDouble, getInteger, getLong
-
Methods inherited from class java.util.Properties
clear, clone, compute, computeIfAbsent, computeIfPresent, contains, containsKey, containsValue, elements, entrySet, equals, forEach, get, getOrDefault, getProperty, getProperty, hashCode, isEmpty, keys, keySet, list, list, load, load, loadFromXML, merge, propertyNames, put, putAll, putIfAbsent, rehash, remove, remove, replace, replace, replaceAll, save, setProperty, size, store, store, storeToXML, storeToXML, storeToXML, stringPropertyNames, toString, values
-
-
-
-
Field Detail
-
PREFIX_CANDIDATE_RETRIEVAL
public static final String PREFIX_CANDIDATE_RETRIEVAL
- See Also:
- Constant Field Values
-
PREFIX_CANDIDATE_FILTER
public static final String PREFIX_CANDIDATE_FILTER
- See Also:
- Constant Field Values
-
PREFIX_DISAMBIGUATION
public static final String PREFIX_DISAMBIGUATION
- See Also:
- Constant Field Values
-
PREFIX_REJECTION
public static final String PREFIX_REJECTION
- See Also:
- Constant Field Values
-
PREFIX_ANCHORING
public static final String PREFIX_ANCHORING
- See Also:
- Constant Field Values
-
PREFIX_ID_HOMOGENIZATION
public static final String PREFIX_ID_HOMOGENIZATION
- See Also:
- Constant Field Values
-
PREFIX_REJECTION_HOMOGENIZATION
public static final String PREFIX_REJECTION_HOMOGENIZATION
- See Also:
- Constant Field Values
-
PREFIX_RECORD_CONTEXT
public static final String PREFIX_RECORD_CONTEXT
- See Also:
- Constant Field Values
-
USE_LUCENE_CANDIDATES_CACHE
public static final String USE_LUCENE_CANDIDATES_CACHE
- See Also:
- Constant Field Values
-
EXACT_MATCH
public static final String EXACT_MATCH
- See Also:
- Constant Field Values
-
APPROX_MATCH
public static final String APPROX_MATCH
- See Also:
- Constant Field Values
-
PARAM_GENE_RECORDS_FIELD_QUERY_TYPE
public static final String PARAM_GENE_RECORDS_FIELD_QUERY_TYPE
Parameter: Which classification/ranking method to use.
One of:
VALUE_LINEAR_COMBINATION(disambiguation only)Configuration.VALUE_LTRConfiguration.VALUE_LUCENE(candidate retrieval only)Configuration.VALUE_MAXENTConfiguration.VALUE_SVM
- See Also:
- Constant Field Values
-
PARAM_DISMAX_TIE_BREAKER
public static final String PARAM_DISMAX_TIE_BREAKER
- See Also:
- Constant Field Values
-
VALUE_DISMAX
public static final String VALUE_DISMAX
- See Also:
- Constant Field Values
-
VALUE_DISJUNCTION
public static final String VALUE_DISJUNCTION
- See Also:
- Constant Field Values
-
VALUE_LINEAR_COMBINATION
public static final String VALUE_LINEAR_COMBINATION
- See Also:
- Constant Field Values
-
VALUE_NAME_CENTRIC
public static final String VALUE_NAME_CENTRIC
- See Also:
- Constant Field Values
-
VALUE_GENE_RECORDS
public static final String VALUE_GENE_RECORDS
- See Also:
- Constant Field Values
-
CONTEXT_ITEMS_INDEX
public static final String CONTEXT_ITEMS_INDEX
- See Also:
- Constant Field Values
-
SYNONYM_INDEX
public static final String SYNONYM_INDEX
- See Also:
- Constant Field Values
-
CONTEXT_INDEX
public static final String CONTEXT_INDEX
- See Also:
- Constant Field Values
-
WIKIPEDIA_INDEX
public static final String WIKIPEDIA_INDEX
- See Also:
- Constant Field Values
-
FIXED_TAX_ID
public static final String FIXED_TAX_ID
When this parameter is set, the provided value will be used as tax ID for all gene mentions. The special value 'gold' will result in the usage of gold annotations.- See Also:
- Constant Field Values
-
MAPPING_CORE
@Deprecated public static final String MAPPING_CORE
Deprecated.Not a configurable property any more but bound in the MappingModule- See Also:
- Constant Field Values
-
EXACT_SCORER_TYPE
public static final String EXACT_SCORER_TYPE
- See Also:
- Constant Field Values
-
APPROX_SCORER_TYPE
public static final String APPROX_SCORER_TYPE
- See Also:
- Constant Field Values
-
SPELLING_INDEX
public static final String SPELLING_INDEX
- See Also:
- Constant Field Values
-
MENTION_INDEX
public static final String MENTION_INDEX
- See Also:
- Constant Field Values
-
GENE_RECORD_INDEX
public static final String GENE_RECORD_INDEX
- See Also:
- Constant Field Values
-
GENE_RECORD_ORIGINAL_NAMES_INDEX
public static final String GENE_RECORD_ORIGINAL_NAMES_INDEX
- See Also:
- Constant Field Values
-
PARAM_GPU_COMPOSITE_MENTIONS
public static final String PARAM_GPU_COMPOSITE_MENTIONS
Number of the GPU to use for the flair composite mention resolution- See Also:
- Constant Field Values
-
PARAM_GPU_TRANSFORMER_CANDIDATE_RANKING
public static final String PARAM_GPU_TRANSFORMER_CANDIDATE_RANKING
Number of the GPU to use for the transformer-based candiate ranking- See Also:
- Constant Field Values
-
PARAM_COMPOSITE_FLAIR_MODEL
public static final String PARAM_COMPOSITE_FLAIR_MODEL
- See Also:
- Constant Field Values
-
PARAM_USE_GOLD_TAX
public static final String PARAM_USE_GOLD_TAX
- See Also:
- Constant Field Values
-
PARAM_DISAMBIGUATE_BY_MAP_LOCATION
public static final String PARAM_DISAMBIGUATE_BY_MAP_LOCATION
- See Also:
- Constant Field Values
-
PARAM_TRANSFORMER_RANKING_MODEL
public static final String PARAM_TRANSFORMER_RANKING_MODEL
- See Also:
- Constant Field Values
-
PARAM_TRY_ORTHOLOGS
public static final String PARAM_TRY_ORTHOLOGS
Whether to try ortholog genes when the primary species didn't fit- See Also:
- Constant Field Values
-
PARAM_SPLIT_AT_SLASH
public static final String PARAM_SPLIT_AT_SLASH
Whether to invokeDypsisGeneSelector.splitDashGenes(GeneDocument, CandidateRetrieval).- See Also:
- Constant Field Values
-
PARAM_MERGE_CONTINUOUS_GENE_ANNOTATIONS
public static final String PARAM_MERGE_CONTINUOUS_GENE_ANNOTATIONS
Whether to invokeDypsisGeneSelector.mergeContinuousGeneAnnotations(GeneDocument).- See Also:
- Constant Field Values
-
PARAM_REPLACE_ML_MENTIONS_WITH_LONGER_GAZETTEER_MENTIONS
public static final String PARAM_REPLACE_ML_MENTIONS_WITH_LONGER_GAZETTEER_MENTIONS
Whether to invokeDypsisGeneSelector.selectLongerGazetteerMatchesOverFlair(GeneDocument)- See Also:
- Constant Field Values
-
PARAM_SYNONYM_SEARCH_MODE
public static final String PARAM_SYNONYM_SEARCH_MODE
- See Also:
- Constant Field Values
-
VALUE_CNF_RELEVANCE_SIGNAL
public static final String VALUE_CNF_RELEVANCE_SIGNAL
- See Also:
- Constant Field Values
-
VALUE_ADDITIONAL_SEARCH
public static final String VALUE_ADDITIONAL_SEARCH
- See Also:
- Constant Field Values
-
VALUE_ALL
public static final String VALUE_ALL
- See Also:
- Constant Field Values
-
VALUE_NONE
public static final String VALUE_NONE
- See Also:
- Constant Field Values
-
PARAM_ADD_SPECIES_PREFIX_STRIPPED_VARIANT_AS_GENENAME_ALTERNATIVE
public static final String PARAM_ADD_SPECIES_PREFIX_STRIPPED_VARIANT_AS_GENENAME_ALTERNATIVE
- See Also:
- Constant Field Values
-
PARAM_REMOVE_SPECIES_PREFIXES_FOR_CANDIDATE_RETRIEVAL
public static final String PARAM_REMOVE_SPECIES_PREFIXES_FOR_CANDIDATE_RETRIEVAL
- See Also:
- Constant Field Values
-
PARAM_ADD_CONTEXT_GENES_AS_LUCENE_RELEVANCE_SIGNAL
public static final String PARAM_ADD_CONTEXT_GENES_AS_LUCENE_RELEVANCE_SIGNAL
- See Also:
- Constant Field Values
-
PARAM_USE_APPOSITIONS_AS_LUCENE_RELEVANCE_SIGNAL
public static final String PARAM_USE_APPOSITIONS_AS_LUCENE_RELEVANCE_SIGNAL
- See Also:
- Constant Field Values
-
PARAM_SEARCH_TAX_SPECIFIC_CANDIDATES_FIRST
public static final String PARAM_SEARCH_TAX_SPECIFIC_CANDIDATES_FIRST
- See Also:
- Constant Field Values
-
PARAM_STOP_CANDIDATE_SEARCH_ON_EXACT_MATCH
public static final String PARAM_STOP_CANDIDATE_SEARCH_ON_EXACT_MATCH
- See Also:
- Constant Field Values
-
PARAM_DISAMBIGUATE_EXACT_HITS_BY_ORIGINAL_NAME
public static final String PARAM_DISAMBIGUATE_EXACT_HITS_BY_ORIGINAL_NAME
- See Also:
- Constant Field Values
-
PARAM_SORT_EXACT_MATCHES_BY_ORIGINAL_SIMILARITY
public static final String PARAM_SORT_EXACT_MATCHES_BY_ORIGINAL_SIMILARITY
Whether or not to try to disambiguate multiple exact matches with the original names.- See Also:
- Constant Field Values
-
PARAM_LUCENE_SCORE_RATIO_THRESHOLD_FOR_EXACT_MATCH_SORTING
public static final String PARAM_LUCENE_SCORE_RATIO_THRESHOLD_FOR_EXACT_MATCH_SORTING
Prerequisite test forPARAM_SORT_EXACT_MATCHES_BY_ORIGINAL_SIMILARITY: Only candidates whose Lucene score exceed the given ratio to the Lucene score of the best candidate are included in a re-ranking by original name.- See Also:
- Constant Field Values
-
PARAM_SEARCH_GM_NP_MODE
public static final String PARAM_SEARCH_GM_NP_MODE
- See Also:
- Constant Field Values
-
PARAM_ALTERNATIVE_NAMES_SEARCH_MODE
public static final String PARAM_ALTERNATIVE_NAMES_SEARCH_MODE
- See Also:
- Constant Field Values
-
PARAM_DO_RRF_WITH_CANDIDATE_LISTS
public static final String PARAM_DO_RRF_WITH_CANDIDATE_LISTS
Whether to merge all candidate lists created in candidate retrieval (gene records CNF, potentially synonym centric retrieval and ML-based re-ranking) via reciprocal rank fusion for the final candidate list.- See Also:
- Constant Field Values
-
PARAM_USE_QUERY_FIELD_WEIGHTS
public static final String PARAM_USE_QUERY_FIELD_WEIGHTS
Whether to use field weights in the Lucene query to the candidate index.- See Also:
- Constant Field Values
-
PARAM_SORT_CANDIDATES_BY_MATCHED_FIELD
public static final String PARAM_SORT_CANDIDATES_BY_MATCHED_FIELD
- See Also:
- Constant Field Values
-
PARAM_TOP_N_CANDIDATES_RERANKING
public static final String PARAM_TOP_N_CANDIDATES_RERANKING
The top N candidates returned from Lucene to subject to reranking.- See Also:
- Constant Field Values
-
PARAM_USE_JARO_WINKLER_FEATURES
public static final String PARAM_USE_JARO_WINKLER_FEATURES
- See Also:
- Constant Field Values
-
PARAM_USE_TOKEN_JARO_FEATURES
public static final String PARAM_USE_TOKEN_JARO_FEATURES
- See Also:
- Constant Field Values
-
PARAM_USE_LEVENSHTEIN_FEATURES
public static final String PARAM_USE_LEVENSHTEIN_FEATURES
- See Also:
- Constant Field Values
-
PARAM_USE_SMITHWATERMAN_FEATURES
public static final String PARAM_USE_SMITHWATERMAN_FEATURES
- See Also:
- Constant Field Values
-
PARAM_USE_NEEDLEMANWUNSCH_FEATURES
public static final String PARAM_USE_NEEDLEMANWUNSCH_FEATURES
- See Also:
- Constant Field Values
-
PARAM_USE_JACCARD_FEATURES
public static final String PARAM_USE_JACCARD_FEATURES
- See Also:
- Constant Field Values
-
PARAM_USE_TFIDF_FEATURES
public static final String PARAM_USE_TFIDF_FEATURES
- See Also:
- Constant Field Values
-
PARAM_USE_SCORER_AVERAGE
public static final String PARAM_USE_SCORER_AVERAGE
- See Also:
- Constant Field Values
-
PARAM_CONTEXT_GENE_FEATURE_GENERATION
public static final String PARAM_CONTEXT_GENE_FEATURE_GENERATION
How to create feature from the context genes. The issue is that there is no fixed number of such genes. So we need to aggregate the scores for multiple context genes into a single number.
One of
VALUE_SUM,VALUE_MAXorVALUE_NONE.- See Also:
- Constant Field Values
-
PARAM_USE_TOKEN_FEATURES
public static final String PARAM_USE_TOKEN_FEATURES
- See Also:
- Constant Field Values
-
VALUE_SUM
public static final String VALUE_SUM
- See Also:
- Constant Field Values
-
VALUE_MAX
public static final String VALUE_MAX
- See Also:
- Constant Field Values
-
PARAM_USE_GENERIF
public static final String PARAM_USE_GENERIF
- See Also:
- Constant Field Values
-
PARAM_USE_INTERACTION
public static final String PARAM_USE_INTERACTION
- See Also:
- Constant Field Values
-
PARAM_USE_GODESC
public static final String PARAM_USE_GODESC
- See Also:
- Constant Field Values
-
PARAM_USE_SUMMARY
public static final String PARAM_USE_SUMMARY
- See Also:
- Constant Field Values
-
PARAM_USE_APPOSITIONS_ON_GENE_CONTEXT_FEATURES
public static final String PARAM_USE_APPOSITIONS_ON_GENE_CONTEXT_FEATURES
- See Also:
- Constant Field Values
-
PARAM_LUCENE_SCORE_RATIO_THRESHOLD_FOR_RERANKING
public static final String PARAM_LUCENE_SCORE_RATIO_THRESHOLD_FOR_RERANKING
Similar to
PARAM_LUCENE_SCORE_RATIO_THRESHOLD_FOR_EXACT_MATCH_SORTING, this parameter sets a threshold of to be overcome for a candidate to be included in ML-based re-ranking. The value to compare against the threshold is the percentage of the Lucene score of a candidate to the score of the best candidate. The idea is to use the Lucene score ratios as a confidence measure.Meant to be used under an
Configuration.MLconfiguration root.- See Also:
- Constant Field Values
-
PARAM_MAPPING_MODE
public static final String PARAM_MAPPING_MODE
One ofVALUE_GENE_MENTIONSandVALUE_GENESETS- See Also:
- Constant Field Values
-
VALUE_GENE_MENTIONS
public static final String VALUE_GENE_MENTIONS
- See Also:
- Constant Field Values
-
VALUE_GENESETS
public static final String VALUE_GENESETS
- See Also:
- Constant Field Values
-
PARAM_DO_CONTEXTUAL_RANKING
public static final String PARAM_DO_CONTEXTUAL_RANKING
- See Also:
- Constant Field Values
-
PARAM_USE_LUCENE_SYNONYM_SET
public static final String PARAM_USE_LUCENE_SYNONYM_SET
- See Also:
- Constant Field Values
-
PARAM_MAKE_TOKEN_WINDOW_DISTINCT
public static final String PARAM_MAKE_TOKEN_WINDOW_DISTINCT
- See Also:
- Constant Field Values
-
PARAM_TOKEN_WINDOW_GENE_SETS_SIZE
public static final String PARAM_TOKEN_WINDOW_GENE_SETS_SIZE
- See Also:
- Constant Field Values
-
PARAM_EXCLUDE_GENES_FOR_CONTEXT_ITEM_SCORING
public static final String PARAM_EXCLUDE_GENES_FOR_CONTEXT_ITEM_SCORING
- See Also:
- Constant Field Values
-
PARAM_INTERSECTION_FILTER
public static final String PARAM_INTERSECTION_FILTER
- See Also:
- Constant Field Values
-
PARAM_USE_GENE_FAMILY_SCORE_FEATURE
public static final String PARAM_USE_GENE_FAMILY_SCORE_FEATURE
- See Also:
- Constant Field Values
-
PARAM_USE_GNORMPLUS_CHEMICAL_SUFFIX_FEATURES
public static final String PARAM_USE_GNORMPLUS_CHEMICAL_SUFFIX_FEATURES
- See Also:
- Constant Field Values
-
PARAM_USE_GNORMPLUS_MENTION_TYPE_HINT_FEATURES
public static final String PARAM_USE_GNORMPLUS_MENTION_TYPE_HINT_FEATURES
- See Also:
- Constant Field Values
-
PARAM_USE_GNORMPLUS_PROTEIN_SYMBOLS_FEATURES
public static final String PARAM_USE_GNORMPLUS_PROTEIN_SYMBOLS_FEATURES
- See Also:
- Constant Field Values
-
PARAM_USE_LASTWORD_FEATURE
public static final String PARAM_USE_LASTWORD_FEATURE
- See Also:
- Constant Field Values
-
PARAM_USE_OTHER_HAS_SPECIFIER_FEATURE
public static final String PARAM_USE_OTHER_HAS_SPECIFIER_FEATURE
- See Also:
- Constant Field Values
-
PARAM_USE_FAMILY_MATCH_SCORE_FEATURE
public static final String PARAM_USE_FAMILY_MATCH_SCORE_FEATURE
- See Also:
- Constant Field Values
-
PARAM_USE_FAMILY_MATCH_RANK_FEATURE
public static final String PARAM_USE_FAMILY_MATCH_RANK_FEATURE
- See Also:
- Constant Field Values
-
PARAM_USE_FAMILY_MATCH_EXACT_FEATURE
public static final String PARAM_USE_FAMILY_MATCH_EXACT_FEATURE
- See Also:
- Constant Field Values
-
PARAM_USE_FAMILY_MATCH_FRACTION_FEATURE
public static final String PARAM_USE_FAMILY_MATCH_FRACTION_FEATURE
- See Also:
- Constant Field Values
-
PARAM_SORT_ML_BY_EXACT_MATCH_FIRST
public static final String PARAM_SORT_ML_BY_EXACT_MATCH_FIRST
- See Also:
- Constant Field Values
-
PARAM_RANK_BY_SINGLE_FEATURE_VALUE
public static final String PARAM_RANK_BY_SINGLE_FEATURE_VALUE
One ofVALUE_SEMANTIC_CONTEXTorVALUE_NONE.- See Also:
- Constant Field Values
-
VALUE_SEMANTIC_CONTEXT
public static final String VALUE_SEMANTIC_CONTEXT
The disambiguation strategy employed by Li, L., Liu, S., Li, L., Fan, W., Huang, D., & Zhou, H. (2013). A Multistage Gene Normalization System Integrating Multiple Effective Methods. PLoS ONE, 8(12). https://doi.org/10.1371/journal.pone.0081956- See Also:
- Constant Field Values
-
PARAM_LEX_CONTEXT_FUSE_METHOD
public static final String PARAM_LEX_CONTEXT_FUSE_METHOD
- See Also:
- Constant Field Values
-
VALUE_RANK_FUSION
public static final String VALUE_RANK_FUSION
Method to combine lexical and semantic ranking. Uses reciprocal rank fusion. ExcludesVALUE_BALANCED_SCORES.- See Also:
- Constant Field Values
-
VALUE_BALANCED_SCORES
public static final String VALUE_BALANCED_SCORES
Boolean toggle. Method to combine lexical and semantic ranking. ExcludesVALUE_RANK_FUSION. Builds the balanced sum of both in the form balancingFactor*lexicalScore + (1-balancingFactor)*semanticScore where balancing factor isPARAM_LEXICAL_SEMANTIC_BALANCING_FACTOR_EXACTfor exact matches andPARAM_LEXICAL_SEMANTIC_BALANCING_FACTOR_APPROXfor approximate matches.- See Also:
- Constant Field Values
-
VALUE_CONTEXT_SCORES
public static final String VALUE_CONTEXT_SCORES
- See Also:
- Constant Field Values
-
PARAM_LEXICAL_SEMANTIC_BALANCING_FACTOR_EXACT
public static final String PARAM_LEXICAL_SEMANTIC_BALANCING_FACTOR_EXACT
Must be in [0,1]. Used to obtain a final score for a gene candidate that was an exact match as:
factor*lexicalScore + (1-factor)*semanticScore- See Also:
- Constant Field Values
-
PARAM_LEXICAL_SEMANTIC_BALANCING_FACTOR_APPROX
public static final String PARAM_LEXICAL_SEMANTIC_BALANCING_FACTOR_APPROX
Must be in [0,1]. Used to obtain a final score for a gene candidate that was an approximate match as:
factor*lexicalScore + (1-factor)*semanticScore- See Also:
- Constant Field Values
-
PARAM_NORMALIZE_LUCENE_SYNONYM_SCORES
public static final String PARAM_NORMALIZE_LUCENE_SYNONYM_SCORES
- See Also:
- Constant Field Values
-
PARAM_NORMALIZE_JARO_WINKLER_SYNONYM_SCORES
public static final String PARAM_NORMALIZE_JARO_WINKLER_SYNONYM_SCORES
- See Also:
- Constant Field Values
-
PARAM_USE_LUCENE_EXACT_SCORES
public static final String PARAM_USE_LUCENE_EXACT_SCORES
- See Also:
- Constant Field Values
-
PARAM_USE_JARO_WINKLER_EXACT_SCORES
public static final String PARAM_USE_JARO_WINKLER_EXACT_SCORES
- See Also:
- Constant Field Values
-
PARAM_USE_LUCENE_APPROX_SCORES
public static final String PARAM_USE_LUCENE_APPROX_SCORES
- See Also:
- Constant Field Values
-
PARAM_USE_JARO_WINKLER_APPROX_SCORES
public static final String PARAM_USE_JARO_WINKLER_APPROX_SCORES
- See Also:
- Constant Field Values
-
PARAM_SCORE_GSCONTEXT_ON_GENERIFS_LUCENE
public static final String PARAM_SCORE_GSCONTEXT_ON_GENERIFS_LUCENE
- See Also:
- Constant Field Values
-
PARAM_SCORE_GSCONTEXT_ON_GENERIFS_JARO_WINKLER
public static final String PARAM_SCORE_GSCONTEXT_ON_GENERIFS_JARO_WINKLER
- See Also:
- Constant Field Values
-
PARAM_SCORE_GSCONTEXT_ON_INTERACTIONS_LUCENE
public static final String PARAM_SCORE_GSCONTEXT_ON_INTERACTIONS_LUCENE
- See Also:
- Constant Field Values
-
PARAM_SCORE_GSCONTEXT_ON_INTERACTIONS_JARO_WINKLER
public static final String PARAM_SCORE_GSCONTEXT_ON_INTERACTIONS_JARO_WINKLER
- See Also:
- Constant Field Values
-
PARAM_SCORE_GSCONTEXT_ON_SUMMARIES_LUCENE
public static final String PARAM_SCORE_GSCONTEXT_ON_SUMMARIES_LUCENE
- See Also:
- Constant Field Values
-
PARAM_SCORE_GSCONTEXT_ON_SUMMARIES_JARO_WINKLER
public static final String PARAM_SCORE_GSCONTEXT_ON_SUMMARIES_JARO_WINKLER
- See Also:
- Constant Field Values
-
PARAM_SCORE_GSCONTEXT_ON_DESCRIPTIONS_LUCENE
public static final String PARAM_SCORE_GSCONTEXT_ON_DESCRIPTIONS_LUCENE
- See Also:
- Constant Field Values
-
PARAM_SCORE_GSCONTEXT_ON_DESCRIPTIONS_JARO_WINKLER
public static final String PARAM_SCORE_GSCONTEXT_ON_DESCRIPTIONS_JARO_WINKLER
- See Also:
- Constant Field Values
-
PARAM_SCORE_SYNONYMS_ON_GENERIFS_LUCENE
public static final String PARAM_SCORE_SYNONYMS_ON_GENERIFS_LUCENE
- See Also:
- Constant Field Values
-
PARAM_SCORE_SYNONYMS_ON_GENERIFS_JARO_WINKLER
public static final String PARAM_SCORE_SYNONYMS_ON_GENERIFS_JARO_WINKLER
- See Also:
- Constant Field Values
-
PARAM_SCORE_SYNONYMS_ON_INTERACTIONS_LUCENE
public static final String PARAM_SCORE_SYNONYMS_ON_INTERACTIONS_LUCENE
- See Also:
- Constant Field Values
-
PARAM_SCORE_SYNONYMS_ON_INTERACTIONS_JARO_WINKLER
public static final String PARAM_SCORE_SYNONYMS_ON_INTERACTIONS_JARO_WINKLER
- See Also:
- Constant Field Values
-
PARAM_SCORE_SYNONYMS_ON_SUMMARIES_LUCENE
public static final String PARAM_SCORE_SYNONYMS_ON_SUMMARIES_LUCENE
- See Also:
- Constant Field Values
-
PARAM_SCORE_SYNONYMS_ON_SUMMARIES_JARO_WINKLER
public static final String PARAM_SCORE_SYNONYMS_ON_SUMMARIES_JARO_WINKLER
- See Also:
- Constant Field Values
-
PARAM_SCORE_SYNONYMS_ON_DESCRIPTIONS_LUCENE
public static final String PARAM_SCORE_SYNONYMS_ON_DESCRIPTIONS_LUCENE
- See Also:
- Constant Field Values
-
PARAM_SCORE_SYNONYMS_ON_DESCRIPTIONS_JARO_WINKLER
public static final String PARAM_SCORE_SYNONYMS_ON_DESCRIPTIONS_JARO_WINKLER
- See Also:
- Constant Field Values
-
PARAM_SCORE_GSCONTEXT_ON_SYNONYMS_LUCENE
public static final String PARAM_SCORE_GSCONTEXT_ON_SYNONYMS_LUCENE
- See Also:
- Constant Field Values
-
PARAM_SCORE_GSCONTEXT_ON_SYNONYMS_JARO_WINKLER
public static final String PARAM_SCORE_GSCONTEXT_ON_SYNONYMS_JARO_WINKLER
- See Also:
- Constant Field Values
-
PARAM_SCALE_FAMILY_NAME_MATCH_SCORE
public static final String PARAM_SCALE_FAMILY_NAME_MATCH_SCORE
- See Also:
- Constant Field Values
-
PARAM_SCORE_FAMILY_NAMES_WITH_JARO_WINKLER
public static final String PARAM_SCORE_FAMILY_NAMES_WITH_JARO_WINKLER
- See Also:
- Constant Field Values
-
KEY_MAX_FAMILY_MATCH_SCORE
public static final String KEY_MAX_FAMILY_MATCH_SCORE
- See Also:
- Constant Field Values
-
KEY_MIN_FAMILY_MATCH_SCORE
public static final String KEY_MIN_FAMILY_MATCH_SCORE
- See Also:
- Constant Field Values
-
PARAM_DO_LOW_SCORE_REJECTION
public static final String PARAM_DO_LOW_SCORE_REJECTION
- See Also:
- Constant Field Values
-
PARAM_DO_FAMILY_REJECTION
public static final String PARAM_DO_FAMILY_REJECTION
- See Also:
- Constant Field Values
-
PARAM_THRESHOLD_EXACT_MATCHES
public static final String PARAM_THRESHOLD_EXACT_MATCHES
- See Also:
- Constant Field Values
-
PARAM_THRESHOLD_APPROX_MATCHES
public static final String PARAM_THRESHOLD_APPROX_MATCHES
- See Also:
- Constant Field Values
-
PARAM_THRESHOLD_GS_REJECTION
public static final String PARAM_THRESHOLD_GS_REJECTION
Used to homogenize gene set rejection where some members have been rejected and others haven't. One homogenization method is to calculate the mean overall score of all members and compare this against this threshold.
-
PARAM_THRESHOLD_APPROX_LENGTH_DIFF_PENALTY_FACTOR
public static final String PARAM_THRESHOLD_APPROX_LENGTH_DIFF_PENALTY_FACTOR
The approx. penalty is subtracted from the overall score value following the formula:
effective_score = overallscore - log(|symmetricDifferenceGeneTokens&SynhitTokens|) * penalty
Thus, if this parameter is set to 0, the number of tokens is ignored.- See Also:
- Constant Field Values
-
PARAM_DISAMBIGUATION_LINCOMB_MAX_VALUES
public static final String PARAM_DISAMBIGUATION_LINCOMB_MAX_VALUES
-
PARAM_DISAMBIGUATION_LINCOMB_MIN_VALUES
public static final String PARAM_DISAMBIGUATION_LINCOMB_MIN_VALUES
-
PARAM_TRAIN_MODE
public static final String PARAM_TRAIN_MODE
- See Also:
- Constant Field Values
-
PARAM_GS_HOMOGENIZATION_METHOD
public static final String PARAM_GS_HOMOGENIZATION_METHOD
The method of GeneSet ID homogenization. Of oneVALUE_MAJORITY_VOTE,VALUE_MAX_BALANCED_SCOREandVALUE_MAX_BALANCED_SCORE_SUM.
-
VALUE_MAJORITY_VOTE
public static final String VALUE_MAJORITY_VOTE
- See Also:
- Constant Field Values
-
PARAM_GS_MAJORITY_HOMOGENIZATION_TIE_BREAKER_METHOD
public static final String PARAM_GS_MAJORITY_HOMOGENIZATION_TIE_BREAKER_METHOD
The method to solve majority voting ties. Of oneVALUE_MAX_BALANCED_SCOREandVALUE_MAX_BALANCED_SCORE_SUM.
-
VALUE_MAX_BALANCED_SCORE
public static final String VALUE_MAX_BALANCED_SCORE
- See Also:
- Constant Field Values
-
VALUE_MAX_BALANCED_SCORE_SUM
public static final String VALUE_MAX_BALANCED_SCORE_SUM
- See Also:
- Constant Field Values
-
VALUE_NO_GS_HOMOGENIZATION
public static final String VALUE_NO_GS_HOMOGENIZATION
- See Also:
- Constant Field Values
-
PARAM_GS_HOMOGENIZATION_BY_ABBREVIATION
public static final String PARAM_GS_HOMOGENIZATION_BY_ABBREVIATION
-
PARAM_GS_HOMOGENIZATION_BY_LONGFORM
public static final String PARAM_GS_HOMOGENIZATION_BY_LONGFORM
-
PARAM_GS_HOMOGENIZATION_ALLOW_CANDIDATE_TRANSFER
public static final String PARAM_GS_HOMOGENIZATION_ALLOW_CANDIDATE_TRANSFER
Whether we allow the transfer of candidates from accepted gene mentions to other mentions that have been rejected because they don't have candidates.
-
PARAM_GS_REJECTION_HOMOGENIZATION_METHOD
public static final String PARAM_GS_REJECTION_HOMOGENIZATION_METHOD
What to do when some genes in a gene set have been rejected and others have not? This is checked when doing gene set ID homogenization. One ofVALUE_MAJORITY_VOTEandVALUE_MEAN_SCORE.
-
VALUE_MEAN_SCORE
public static final String VALUE_MEAN_SCORE
Gene set rejection homogenization method that calculates the mean score of the gene mentions in the set and compares this against the rejection threshold.- See Also:
- Constant Field Values
-
PARAM_REJECTION_FAMILY_HIT_RANK_EXACT_MATCH
public static final String PARAM_REJECTION_FAMILY_HIT_RANK_EXACT_MATCH
-
PARAM_REJECTION_FAMILY_HIT_RANK_APPROX_MATCH
public static final String PARAM_REJECTION_FAMILY_HIT_RANK_APPROX_MATCH
-
PARAM_REJECT_FAMILY_IN_NP
public static final String PARAM_REJECT_FAMILY_IN_NP
-
-
Constructor Detail
-
Configuration
public Configuration(de.julielab.geneexpbase.configuration.Configuration baseConfiguration)
-
Configuration
public Configuration()
-
Configuration
public Configuration(String... parameters)
-
Configuration
public Configuration(File configurationFile) throws IOException
- Throws:
IOException
-
-