Skip to main content

Table 4 Best performing parameter combinations for SO, ChEBI, NCBITaxon, and PRO

From: Large-scale biomedical concept recognition: an evaluation of current automatic annotators and their parameters

Sequence Ontology (SO)

NCBO Annotator

 

MetaMap

 

ConceptMapper

 

Parameter

Value

Parameter

Value

Parameter

Value

wholeWordOnly

YES

model

STRICT

searchStrategy

CONTIGUOUS

filterNumber

ANY

gaps

NONE

caseMatch

INSENSITIVE

stopWords

ANY

wordOrder

ANY

stemmer

Porter/BioLemmatizer

SWCaseSensitive

ANY

acronymAbb

DEFAULT/UNIQUE

stopWords

NONE

minTermSize

THREE

derivationalVariants

NONE

orderIndLookup

OFF

withSynonyms

YES

scoreFilter

600

findAllMatches

NO

  

minTermSize

3

synonyms

EXACT ONLY

Protein Ontology (PRO)

NCBO Annotator

 

MetaMap

 

ConceptMapper

 

Parameter

Value

Parameter

Value

Parameter

Value

wholeWordOnly

YES

model

ANY

searchStrategy

ANY

filterNumber

ANY

gaps

NONE

caseMatch

CASE FOLD DIGITS

stopWords

PubMed

wordOrder

ANY

stemmer

NONE

SWCaseSensitive

ANY

acronymAbb

DEFAULT/UNIQUE

stopWords

NONE

minTermSize

ONE/THREE

derivationalVariants

NONE

orderIndLookup

OFF

withSynonyms

YES

scoreFilter

600

findAllMatches

NO

  

minTermSize

3/5

synonyms

ALL

NCBI Taxonomy

NCBO Annotator

 

MetaMap

 

ConceptMapper

 

Parameter

Value

Parameter

Value

Parameter

Value

wholeWordOnly

YES

model

ANY

searchStrategy

SKIP ANY/ALLOW

filterNumber

ANY

gaps

NONE

caseMatch

ANY

stopWords

ANY

wordOrder

ORDER MATTERS

stemmer

BioLemmatizer

SWCaseSensitive

ANY

acronymAbb

DEFAULT/UNIQUE

stopWords

PubMed

minTermSize

FIVE

derivationalVariants

NONE

orderIndLookup

OFF

withSynonyms

ANY

scoreFilter

0/600

findAllMatches

NO

  

minTermSize

3

synonyms

EXACT ONLY

ChEBI

NCBO Annotator

 

MetaMap

 

ConceptMapper

 

Parameter

Value

Parameter

Value

Parameter

Value

wholeWordOnly

YES

model

STRICT

searchStrategy

CONTIGUOUS

filterNumber

ANY

gaps

NONE

caseMatch

ANY

stopWords

ANY

wordOrder

ORDER MATTERS

stemmer

BioLemmatizer

SWCaseSensitive

ANY

acronymAbb

DEFAULT/UNIQUE

stopWords

NONE

minTermSize

ONE/THREE

derivationalVariants

NONE

orderIndLookup

OFF

withSynonyms

YES

scoreFilter

0/600

findAllMatches

YES

  

minTermSize

5

synonyms

EXACT ONLY

  1. Suggested parameters to use that correspond to best score on CRAFT. Parameters where choices don’t seem to make a difference in performance are represented as “ANY”.