AlvisNLP

corpus processing engine

Chemspot

Synopsis

Looks for mentions of chemicals and molecule names using Chemspot .

Description

Chemspot runs Chemspot on the sections content, then creates an annotation for each chemical mention in the layer targetLayer . Each annotation will have the feature chemTypeFeature set to the chemical mention type, and one feature for each type of identifier.

Snippet

<chemspot class="Chemspot">
    <chemspotDir></chemspotDir>
</chemspot>

Mandatory parameters

chemspotDir

Mandatory

Chemspot install directory.

Optional parameters

constantAnnotationFeatures

Optional
Type: Mapping

Constant features to add to each annotation created by this module.

casFeature

Default value: `CAS`
Type: String

Feature where to store the CAS identifier.

chebFeature

Default value: `CHEB`
Type: String

Feature where to store the CHEB identifier.

chemTypeFeature

Default value: `chem-type`
Type: String

Feature where to store the chemical type (SYSTEMATIC, IDENTIFIER, FORMULA, TRIVIAL, ABBREVIATION, FAMILY, MULTIPLE, UNKNOWN).

chidFeature

Default value: `CHID`
Type: String

Feature where to store the CHID identifier.

documentFilter

Default value: `true`
Type: Expression

Only process document that satisfy this expression.

drugFeature

Default value: `DRUG`
Type: String

Feature where to store the DRUG identifier.

fdaDateFeature

Default value: `FDA`
Type: String

Feature where to store the FDA_DATE identifier.

fdaFeature

Default value: `FDA_DATE`
Type: String

Feature where to store the FDA identifier.

hmdbFeature

Default value: `HMDB`
Type: String

Feature where to store the HMBD identifier.

inchFeature

Default value: `INCH`
Type: String

Feature where to store the INCH identifier.

javaHome

Default value: `/home/rbossy/dist/jdk1.8.0_121`

Root directory of the Java implementation.

kegdFeature

Default value: `KEGD`
Type: String

Feature where to store the KEGD identifier.

keggFeature

Default value: `KEGG`
Type: String

Feature where to store the KEGG identifier.

meshFeature

Default value: `MESH`
Type: String

Feature where to store the MESH identifier.

noDict

Default value: `false`
Type: Boolean

Do not use lexicons, only the CRF classifier. Uses less memory.

pubcFeature

Default value: `PUBC`
Type: String

Feature where to store the PUBC identifier.

pubsFeature

Default value: `PUBS`
Type: String

Feature where to store the PUBS identifier.

sectionFilter

Default value: `true`
Type: Expression

Process only sections that satisfy this expression.

targetLayer

Default value: `chemspot`
Type: String

Name of the layer where to store annotations created by Chemspot .

Deprecated parameters

casFeatureName

Deprecated
Type: String

Deprecated alias for casFeature .

chebFeatureName

Deprecated
Type: String

Deprecated alias for chebFeature .

chemTypeFeatureName

Deprecated
Type: String

Deprecated alias for chemTypeFeature .

chidFeatureName

Deprecated
Type: String

Deprecated alias for chidFeature .

drugFeatureName

Deprecated
Type: String

Deprecated alias for drugFeature .

fdaDateFeatureName

Deprecated
Type: String

Deprecated alias for fdaDateFeature .

fdaFeatureName

Deprecated
Type: String

Deprecated alias for fdaFeature .

hmdbFeatureName

Deprecated
Type: String

Deprecated alias for hmdbFeature .

inchFeatureName

Deprecated
Type: String

Deprecated alias for inchFeature .

kegdFeatureName

Deprecated
Type: String

Deprecated alias for kegdFeature .

keggFeatureName

Deprecated
Type: String

Deprecated alias for keggFeature .

meshFeatureName

Deprecated
Type: String

Deprecated alias for meshFeature .

pubcFeatureName

Deprecated
Type: String

Deprecated alias for pubcFeature .

pubsFeatureName

Deprecated
Type: String

Deprecated alias for pubsFeature .

targetLayerName

Deprecated
Type: String

Deprecated alias for targetLayer .