diff --git a/plans/entities.plan b/plans/entities.plan
index f98ea1c1a7e009f4d9006ca56f147057fbb3ad01..8523ddb14c67d45b2edc40e07b71539e55ef52cd 100644
--- a/plans/entities.plan
+++ b/plans/entities.plan
@@ -17,6 +17,10 @@
<param name="input-xslt">
<alias module="read.pubmed" param="xslTransform"/>
</param>
+
+ <param name="batch">
+ <alias module="read.pubmed" param="constantDocumentFeatures"/>
+ </param>
<param name="outputDir">
<alias module="output.doc-mesh" param="outDir"/>
@@ -139,8 +143,7 @@
<param name="NCBI_taxa_ontobiotope">
<alias module="habitats.tomap-habitats.map-living-organisms" param="mappingFile"/>
</param>
-
-
+
<!-- habitats-->
<param name="ontobiotope-habitat">
<alias module="habitats.tomap-habitats.concept-names" param="oboFiles"/>
@@ -195,14 +198,15 @@
<read>
<pubmed class="XMLReader">
- <sourcePath>corpora/&corpus;/batches/&batch;/batch.xml</sourcePath>
- <xslTransform>ancillaries/&corpus;-pubmed2alvisnlp.xslt</xslTransform>
+ <sourcePath>corpora/pubmed/batches/0001/batch.xml</sourcePath>
+ <xslTransform>ancillaries/microbes-2019-pubmed2alvisnlp.xslt</xslTransform>
+ <constantDocumentFeatures>batch=0001</constantDocumentFeatures>
</pubmed>
<bionlp-st class="BioNLPSTReader">
<active>true</active>
<sectionName>abstract</sectionName>
- <textDir>corpora/&corpus;/batches/&batch;/bionlp-st</textDir>
+ <textDir>corpora/BioNLP-OST-2019/batches/BB19-kb+ner/bionlp-st</textDir>
</bionlp-st>
</read>
@@ -404,7 +408,7 @@
<!-- Run Yatea term extractor -->
<yatea class="YateaExtractor">
<sectionFilter>@name == "title" or @name == "abstract"</sectionFilter>
- <xmlTermsFile>corpora/&corpus;/batches/&batch;/yatea/candidates.xml</xmlTermsFile>
+ <xmlTermsFile>yatea/candidates.xml</xmlTermsFile>
<posFeature>tt_pos</posFeature>
<configDir>ancillaries/YaTeA/config-habitats</configDir>
<localeDir>ancillaries/YaTeA/locale</localeDir>
@@ -415,7 +419,7 @@
<!-- Run Yatea term extractor on variants -->
<yatea-var class="YateaExtractor">
<sectionFilter>@name == "title" or @name == "abstract"</sectionFilter>
- <xmlTermsFile>corpora/&corpus;/batches/&batch;/yatea-var/candidates.xml</xmlTermsFile>
+ <xmlTermsFile>yatea-var/candidates.xml</xmlTermsFile>
<posFeature>tt_pos</posFeature>
<lemmaFeature>variant</lemmaFeature>
<configDir>ancillaries/YaTeA/config-habitats</configDir>
@@ -669,12 +673,12 @@
<output>
<doc-mesh class="TabularExport">
- <outDir>corpora/&corpus;/batches/&batch;</outDir>
+ <outDir>.</outDir>
<files>$</files>
<fileName>"doc-mesh.txt"</fileName>
<lines>documents.sections:mesh</lines>
<columns separator=";">
- "&batch;";
+ document.@batch;
document.@id;
@UI;
@mesh-name;
@@ -683,12 +687,12 @@
</doc-mesh>
<taxa class="TabularExport">
- <outDir>corpora/&corpus;/batches/&batch;</outDir>
+ <outDir>.</outDir>
<files>$</files>
<fileName>"taxa.txt"</fileName>
<lines>documents.sections.layer:taxa</lines>
<columns separator=";">
- "&batch;";
+ document.@batch;
section.document.@id;
section.@name;
start ^ "-" ^ end;
@@ -702,12 +706,12 @@
</taxa>
<microorganisms class="TabularExport">
- <outDir>corpora/&corpus;/batches/&batch;</outDir>
+ <outDir>.</outDir>
<files>$</files>
<fileName>"microorganisms.txt"</fileName>
<lines>documents.sections.layer:microorganism</lines>
<columns separator=";">
- "&batch;";
+ document.@batch;
section.document.@id;
section.@name;
start ^ "-" ^ end;
@@ -721,12 +725,12 @@
</microorganisms>
<microorganisms-short class="TabularExport">
- <outDir>corpora/&corpus;/batches/&batch;</outDir>
+ <outDir>.</outDir>
<files>$</files>
<fileName>"microorganisms-short.txt"</fileName>
<lines>documents.sections.layer:microorganism[outside:words and not @form == outside:words.@form]</lines>
<columns separator=";">
- "&batch;";
+ document.@batch;
section.document.@id;
section.@name;
start ^ "-" ^ end;
@@ -740,12 +744,12 @@
</microorganisms-short>
<bacteria class="TabularExport">
- <outDir>corpora/&corpus;/batches/&batch;</outDir>
+ <outDir>.</outDir>
<files>$</files>
<fileName>"bacteria.txt"</fileName>
<lines>documents.sections.layer:bacteria</lines>
<columns separator=";">
- "&batch;";
+ document.@batch;
section.document.@id;
section.@name;
start ^ "-" ^ end;
@@ -759,12 +763,12 @@
</bacteria>
<habitats class="TabularExport">
- <outDir>corpora/&corpus;/batches/&batch;</outDir>
+ <outDir>.</outDir>
<files>$</files>
<fileName>"habitats.txt"</fileName>
<lines>documents.sections.layer:habitats</lines>
<columns separator=";">
- "&batch;";
+ document.@batch;
section.document.@id;
section.@name;
start ^ "-" ^ end;
@@ -780,12 +784,12 @@
</habitats>
<phenotypes class="TabularExport">
- <outDir>corpora/&corpus;/batches/&batch;</outDir>
+ <outDir>.</outDir>
<files>$</files>
<fileName>"phenotypes.txt"</fileName>
<lines>documents.sections.layer:phenotypes</lines>
<columns separator=";">
- "&batch;";
+ document.@batch;
section.document.@id;
section.@name;
start ^ "-" ^ end;
@@ -801,12 +805,12 @@
</phenotypes>
<uses class="TabularExport">
- <outDir>corpora/&corpus;/batches/&batch;</outDir>
+ <outDir>.</outDir>
<files>$</files>
<fileName>"uses.txt"</fileName>
<lines>documents.sections.layer:uses</lines>
<columns separator=";">
- "&batch;";
+ document.@batch;
section.document.@id;
section.@name;
start ^ "-" ^ end;
@@ -822,12 +826,12 @@
</uses>
<geo class="TabularExport">
- <outDir>corpora/&corpus;/batches/&batch;</outDir>
+ <outDir>.</outDir>
<files>$</files>
<fileName>"geo.txt"</fileName>
<lines>documents.sections.layer:Geographical</lines>
<columns separator=";">
- "&batch;";
+ document.@batch;
section.document.@id;
section.@name;
start ^ "-" ^ end;
@@ -837,12 +841,12 @@
</geo>
<relations class="TabularExport">
- <outDir>corpora/&corpus;/batches/&batch;</outDir>
+ <outDir>.</outDir>
<files>$</files>
<fileName>"relations.txt"</fileName>
<lines>documents.sections.relations:CooccurrenceLocalization.tuples</lines>
<columns separator=";">
- "&batch;";
+ document.@batch;
section.document.@id;
section.@name;
args:Bacterium.@taxid;
@@ -860,12 +864,12 @@
</relations>
<relations-pheno class="TabularExport">
- <outDir>corpora/&corpus;/batches/&batch;</outDir>
+ <outDir>.</outDir>
<files>$</files>
<fileName>"phenotype-relations.txt"</fileName>
<lines>documents.sections.relations:PhenotypeRelation.tuples</lines>
<columns separator=";">
- "&batch;";
+ document.@batch;
section.document.@id;
section.@name;
args:Microorganism.@taxid;
@@ -883,12 +887,12 @@
</relations-pheno>
<relations-use class="TabularExport">
- <outDir>corpora/&corpus;/batches/&batch;</outDir>
+ <outDir>.</outDir>
<files>$</files>
<fileName>"uses-relations.txt"</fileName>
<lines>documents.sections.relations:UseRelation.tuples</lines>
<columns separator=";">
- "&batch;";
+ document.@batch;
section.document.@id;
section.@name;
args:Microorganism.@taxid;
@@ -974,7 +978,7 @@
</index-sentences>
<sentences class="TabularExport">
- <outDir>corpora/&corpus;/batches/&batch;</outDir>
+ <outDir>.</outDir>
<files>$</files>
<fileName>"sentences.txt"</fileName>
<lines>documents.sections.layer:sentences[@name != "author"]</lines>
@@ -995,7 +999,7 @@
</sentences>
<anaphora class="TabularExport">
- <outDir>corpora/&corpus;/batches/&batch;</outDir>
+ <outDir>.</outDir>
<files>$</files>
<fileName>"anaphora.txt"</fileName>
<lines>documents.sections.relations:coreferences.tuples[args:Ante]</lines>
@@ -1028,7 +1032,7 @@
</anaphora>
<dependencies class="TabularExport">
- <outDir>corpora/&corpus;/batches/&batch;</outDir>
+ <outDir>.</outDir>
<files>$</files>
<fileName>"dependencies.txt"</fileName>
<lines>documents.sections[@name != "author"].relations:dependencies.tuples</lines>
@@ -1247,11 +1251,11 @@
</habitat-ancestors>
<index class="AlvisDBIndexer">
- <indexDir>corpora/&corpus;/batches/&batch;/adb</indexDir>
+ <indexDir>adb</indexDir>
<elements>
<relations>
<items>documents.sections.relations:CooccurrenceLocalization.tuples[args:Bacterium[@bacteria == "true"]]</items>
- <id>"&batch;_" ^ id:unique</id>
+ <id>section.document.@batch ^ id:unique</id>
<name>"Localization"</name>
<type>"localization"</type>
<args>args:Bacterium|args:Localization</args>
@@ -1267,7 +1271,7 @@
</adb>
<index class="AlvisIRIndexer">
- <indexDir>corpora/&corpus;/batches/&batch;/index</indexDir>
+ <indexDir>index</indexDir>
<tokenPositionGap>9216</tokenPositionGap>
<fieldNames>title,abstract,author,full-author,pmid,year,journal,mesh,url</fieldNames>
<relations>
@@ -1404,8 +1408,8 @@
</documents>
</index>
- <index-food class="AlvisIRIndexer">
- <indexDir>corpora/&corpus;/batches/&batch;/index-food</indexDir>
+<!-- <index-food class="AlvisIRIndexer">
+ <indexDir>.</indexDir>
<tokenPositionGap>9216</tokenPositionGap>
<fieldNames>title,abstract,author,full-author,pmid,year,journal,mesh,url</fieldNames>
<relations>
@@ -1538,7 +1542,7 @@
<keyword>document.@url</keyword>
</fields>
</documents>
- </index-food>
+ </index-food>-->
<!-- HTML visualization -->
<add-feature class="Action">
@@ -1563,14 +1567,14 @@
</add-feature3>
<html class="QuickHTML">
<active>false</active>
- <outDir>corpora/&corpus;/batches/&batch;/html</outDir>
+ <outDir>./html</outDir>
<classFeature>ne-type</classFeature>
<layers>phenotypes,microorganism,habitats</layers>
<colors>#99cc00,#ffcc99,#ffd333,#ffd666</colors>
</html>
<words class="TabularExport">
- <outDir>corpora/&corpus;/batches/&batch;</outDir>
+ <outDir>.</outDir>
<files>$</files>
<fileName>"words.txt"</fileName>
<lines>documents.sections[@name == "title" or @name == "abstract"].layer:words</lines>
@@ -1582,7 +1586,7 @@
<bionlp-st-a2>
<habitats class="TabularExport">
- <outDir>corpora/&corpus;/batches/&batch;/a2</outDir>
+ <outDir>a2</outDir>
<files>documents.sections</files>
<fileName>document.@id ^ ".a2"</fileName>
<lines>layer:habitats</lines>
@@ -1595,7 +1599,7 @@
<phenotypes class="TabularExport">
<append/>
- <outDir>corpora/&corpus;/batches/&batch;/a2</outDir>
+ <outDir>a2</outDir>
<files>documents.sections</files>
<fileName>document.@id ^ ".a2"</fileName>
<lines>layer:phenotypes</lines>
@@ -1608,7 +1612,7 @@
<microorganisms class="TabularExport">
<append/>
- <outDir>corpora/&corpus;/batches/&batch;/a2</outDir>
+ <outDir>a2</outDir>
<files>documents.sections</files>
<fileName>document.@id ^ ".a2"</fileName>
<lines>layer:microorganism</lines>
@@ -1621,7 +1625,7 @@
<obt class="TabularExport">
<append/>
- <outDir>corpora/&corpus;/batches/&batch;/a2</outDir>
+ <outDir>a2</outDir>
<files>documents.sections</files>
<fileName>document.@id ^ ".a2"</fileName>
<lines>layer:habitats|layer:phenotypes</lines>
@@ -1633,7 +1637,7 @@
<taxid class="TabularExport">
<append/>
- <outDir>corpora/&corpus;/batches/&batch;/a2</outDir>
+ <outDir>a2</outDir>
<files>documents.sections</files>
<fileName>document.@id ^ ".a2"</fileName>
<lines>layer:microorganism</lines>
@@ -1645,7 +1649,7 @@
<lives-in class="TabularExport">
<append/>
- <outDir>corpora/&corpus;/batches/&batch;/a2</outDir>
+ <outDir>a2</outDir>
<files>documents.sections</files>
<fileName>document.@id ^ ".a2"</fileName>
<lines>relations:CooccurrenceLocalization.tuples[args:Localization.@concept-id != ""]</lines>
@@ -1657,7 +1661,7 @@
<exhibits class="TabularExport">
<append/>
- <outDir>corpora/&corpus;/batches/&batch;/a2</outDir>
+ <outDir>a2</outDir>
<files>documents.sections</files>
<fileName>document.@id ^ ".a2"</fileName>
<lines>relations:PhenotypeRelation.tuples</lines>
@@ -1670,7 +1674,7 @@
<success class="TabularExport">
- <outDir>corpora/&corpus;/batches/&batch;</outDir>
+ <outDir>.</outDir>
<files>$</files>
<fileName>"success.txt"</fileName>
<lines>documents</lines>
diff --git a/plans/map_habitats.plan b/plans/map_habitats.plan
index 07777780e184fa6ede0bf8d55785a7e3a463d7f9..5aff349486ac1d6145c03930300193eeb36b05e4 100644
--- a/plans/map_habitats.plan
+++ b/plans/map_habitats.plan
@@ -168,7 +168,7 @@
<!-- Run Yatea term extractor -->
<yatea class="YateaExtractor">
- <xmlTermsFile>ancillaries/yatea/candidates.xml</xmlTermsFile>
+ <xmlTermsFile>yatea/candidates.xml</xmlTermsFile>
<posFeature>tt_pos</posFeature>
<configDir>ancillaries/YaTeA/config-habitats</configDir>
<localeDir>ancillaries/YaTeA/locale</localeDir>
@@ -178,7 +178,7 @@
<!-- Run Yatea term extractor on variants -->
<yatea-var class="YateaExtractor">
- <xmlTermsFile>ancillaries/yatea-var/candidates.xml</xmlTermsFile>
+ <xmlTermsFile>yatea-var/candidates.xml</xmlTermsFile>
<posFeature>tt_pos</posFeature>
<lemmaFeature>variant</lemmaFeature>
<configDir>ancillaries/YaTeA/config-habitats</configDir>
@@ -258,7 +258,7 @@
<setFeatures/>
</add-score>
- <tomap-habitats file="plans/tomap-habitats-generic.plan"/>
+ <tomap-habitats file="plans/tomap-habitats.plan"/>
<!-- <remove-living-org-overlapping-geo class="Action"> -->
<!-- <target>documents.sections.layer:habitats[@concept-path ?= "OBT:000002" and span:Geographical]</target> -->
diff --git a/plans/tomap-habitats.plan b/plans/tomap-habitats.plan
index 46bbb98d0e1a2aadb023988465071097e7a11a72..da458fd1932cceace194e9cae09134bd2bf10027 100644
--- a/plans/tomap-habitats.plan
+++ b/plans/tomap-habitats.plan
@@ -3,18 +3,18 @@
<!-- ToMap on lemmas -->
<tomap class="TomapProjector">
- <yateaFile output-feed="true">corpora/&corpus;/batches/&batch;/yatea/candidates.xml</yateaFile>
+ <yateaFile output-feed="true">yatea/candidates.xml</yateaFile>
<targetLayerName>habitats</targetLayerName>
<conceptFeature>concept-id</conceptFeature>
<explanationFeaturePrefix>explain_</explanationFeaturePrefix>
- <tomapClassifier empty-words="ancillaries/stopwords_EN.ttg" graylist="ancillaries/graylist_extended.heads" whole-proxy-distance="false">&ontobiotope;-Habitat.tomap</tomapClassifier>
+ <tomapClassifier empty-words="ancillaries/stopwords_EN.ttg" graylist="ancillaries/graylist_extended.heads" whole-proxy-distance="false">ancillaries/BioNLP-OST+EnovFood-Habitat.tomap</tomapClassifier>
<lemmaKeys/>
<subject feature="lemma" layer="words"/>
<scoreFeature>score</scoreFeature>
</tomap>
<concept-names class="OBOMapper">
- <oboFiles>&ontobiotope;-Habitat.obo</oboFiles>
+ <oboFiles>ancillaries/BioNLP-OST+EnovFood-Habitat.obo</oboFiles>
<idKeys/>
<target>documents.sections.layer:habitats</target>
<form>@concept-id</form>
@@ -26,18 +26,18 @@
<tomap-on-alternative-lemmas>
<tomap class="TomapProjector">
- <yateaFile output-feed="true">corpora/&corpus;/batches/&batch;/yatea/candidates.xml</yateaFile>
+ <yateaFile output-feed="true">yatea/candidates.xml</yateaFile>
<targetLayerName>habitats2</targetLayerName>
<conceptFeature>concept-id</conceptFeature>
<explanationFeaturePrefix>explain_</explanationFeaturePrefix>
- <tomapClassifier empty-words="ancillaries/stopwords_EN.ttg" graylist="ancillaries/graylist_extended.heads" whole-proxy-distance="false">&ontobiotope;-Habitat.tomap</tomapClassifier>
+ <tomapClassifier empty-words="ancillaries/stopwords_EN.ttg" graylist="ancillaries/graylist_extended.heads" whole-proxy-distance="false">ancillaries/BioNLP-OST+EnovFood-Habitat.tomap</tomapClassifier>
<lemmaKeys/>
<subject feature="lemma2" layer="words"/>
<scoreFeature>score</scoreFeature>
</tomap>
<concept-names class="OBOMapper">
- <oboFiles>&ontobiotope;-Habitat.obo</oboFiles>
+ <oboFiles>ancillaries/BioNLP-OST+EnovFood-Habitat.obo</oboFiles>
<idKeys/>
<target>documents.sections.layer:habitats2</target>
<form>@concept-id</form>
@@ -58,17 +58,17 @@
<tomap-no-lemmakeys>
<tomap class="TomapProjector">
- <yateaFile output-feed="true">corpora/&corpus;/batches/&batch;/yatea/candidates.xml</yateaFile>
+ <yateaFile output-feed="true">yatea/candidates.xml</yateaFile>
<targetLayerName>habitats3</targetLayerName>
<conceptFeature>concept-id</conceptFeature>
<explanationFeaturePrefix>explain_</explanationFeaturePrefix>
- <tomapClassifier empty-words="ancillaries/stopwords_EN.ttg" graylist="ancillaries/graylist_extended.heads" whole-proxy-distance="false">&ontobiotope;-Habitat.tomap</tomapClassifier>
+ <tomapClassifier empty-words="ancillaries/stopwords_EN.ttg" graylist="ancillaries/graylist_extended.heads" whole-proxy-distance="false">ancillaries/BioNLP-OST+EnovFood-Habitat.tomap</tomapClassifier>
<subject feature="lemma" layer="words"/>
<scoreFeature>score</scoreFeature>
</tomap>
<concept-names class="OBOMapper">
- <oboFiles>&ontobiotope;-Habitat.obo</oboFiles>
+ <oboFiles>ancillaries/BioNLP-OST+EnovFood-Habitat.obo</oboFiles>
<idKeys/>
<target>documents.sections.layer:habitats3</target>
<form>@concept-id</form>
@@ -89,18 +89,18 @@
<tomap-on-variants>
<tomap class="TomapProjector">
- <yateaFile output-feed="true">corpora/&corpus;/batches/&batch;/yatea-var/candidates.xml</yateaFile>
+ <yateaFile output-feed="true">yatea-var/candidates.xml</yateaFile>
<targetLayerName>habitats4</targetLayerName>
<conceptFeature>concept-id</conceptFeature>
<explanationFeaturePrefix>explain_</explanationFeaturePrefix>
- <tomapClassifier empty-words="ancillaries/stopwords_EN.ttg" graylist="ancillaries/graylist_extended.heads" whole-proxy-distance="false">&ontobiotope;-Habitat.tomap</tomapClassifier>
+ <tomapClassifier empty-words="ancillaries/stopwords_EN.ttg" graylist="ancillaries/graylist_extended.heads" whole-proxy-distance="false">ancillaries/BioNLP-OST+EnovFood-Habitat.tomap</tomapClassifier>
<lemmaKeys/>
<subject feature="variant" layer="words"/>
<scoreFeature>score</scoreFeature>
</tomap>
<concept-names class="OBOMapper">
- <oboFiles>&ontobiotope;-Habitat.obo</oboFiles>
+ <oboFiles>ancillaries/BioNLP-OST+EnovFood-Habitat.obo</oboFiles>
<idKeys/>
<target>documents.sections.layer:habitats4</target>
<form>@concept-id</form>
@@ -121,17 +121,17 @@
<tomap-no-lemmakeys-word-form>
<tomap class="TomapProjector">
- <yateaFile output-feed="true">corpora/&corpus;/batches/&batch;/yatea/candidates.xml</yateaFile>
+ <yateaFile output-feed="true">yatea/candidates.xml</yateaFile>
<targetLayerName>habitats5</targetLayerName>
<conceptFeature>concept-id</conceptFeature>
<explanationFeaturePrefix>explain_</explanationFeaturePrefix>
- <tomapClassifier empty-words="ancillaries/stopwords_EN.ttg" graylist="ancillaries/graylist_extended.heads" whole-proxy-distance="false">&ontobiotope;-Habitat.tomap</tomapClassifier>
+ <tomapClassifier empty-words="ancillaries/stopwords_EN.ttg" graylist="ancillaries/graylist_extended.heads" whole-proxy-distance="false">ancillaries/BioNLP-OST+EnovFood-Habitat.tomap</tomapClassifier>
<subject feature="form" layer="words"/>
<scoreFeature>score</scoreFeature>
</tomap>
<concept-names class="OBOMapper">
- <oboFiles>&ontobiotope;-Habitat.obo</oboFiles>
+ <oboFiles>ancillaries/BioNLP-OST+EnovFood-Habitat.obo</oboFiles>
<idKeys/>
<target>documents.sections.layer:habitats5</target>
<form>@concept-id</form>
@@ -196,7 +196,7 @@
<bioyatea-projection class="YateaTermsProjector">
<targetLayerName>yateaTerms</targetLayerName>
<!--<yateaFile inhibitCheck="true">words_prepro/default/xml/candidates_pp.xml</yateaFile>-->
- <yateaFile output-feed="yes">corpora/&corpus;/batches/&batch;/yatea/candidates.xml</yateaFile> <!-- ??? -->
+ <yateaFile output-feed="yes">yatea/candidates.xml</yateaFile> <!-- ??? -->
<subject layer="words"/>
<termLemma>lemma</termLemma>
</bioyatea-projection>
@@ -388,20 +388,20 @@
<removeFromLayer/>
</delete-not-selected>
-<rule-for-food-corpus>
- <tag-overlap-food class="Action">
+ <!-- <rule-for-food-corpus>
+ <tag-overlap-food class="Action"> -->
<!-- <target>documents.sections.layer:habitats[not @concept-path =~ "OBT:000008/"]</target> -->
- <target>documents[@id in "corpora/&corpus;/food-pmids.txt"].sections.layer:habitats[not @concept-path =~ "OBT:000008/"]</target>
+ <!-- <target>documents[@id in "corpora/&corpus;/food-pmids.txt"].sections.layer:habitats[not @concept-path =~ "OBT:000008/"]</target>
<action>set:feat:overlap-food(span:habitats[@score == target.@score and @concept-path =~ "OBT:000008/"])</action>
<setFeatures/>
</tag-overlap-food>
<remove-overlap-food class="Action">
- <target>documents[@id in "corpora/&corpus;/food-pmids.txt"].sections.layer:habitats[not @concept-path =~ "OBT:000008/" and not @overlap-food == ""]</target>
+ <target>documents[@id in "corpora/&corpus;/food-pmids.txt"].sections.layer:habitats[not @concept-path =~ "OBT:000008/" and not @overlap-food == ""]</target>-->
<!-- <target>documents.sections.layer:habitats[not @concept-path =~ "OBT:000008/" and not @overlap-food == ""]</target> -->
- <action>remove:habitats</action>
+ <!-- <action>remove:habitats</action>
<removeFromLayer/>
</remove-overlap-food>
-</rule-for-food-corpus>
+</rule-for-food-corpus>-->
<!-- Keep only the highest scored concepts -->
<keep-highest class="Action">
@@ -714,7 +714,7 @@
<!-- Add concept-path in case some are missing -->
<concept-path class="OBOMapper">
- <oboFiles>&ontobiotope;-Habitat.obo</oboFiles>
+ <oboFiles>ancillaries/BioNLP-OST+EnovFood-Habitat.obo</oboFiles>
<idKeys/>
<target>documents.sections.layer:habitats</target>
<form>@concept-id</form>
diff --git a/plans/tomap-microbial-phenotypes.plan b/plans/tomap-microbial-phenotypes.plan
index 17481643bb3b90c66ab16caa337ee600eb2f1f0f..f55357aa56a7004280b8a5bae6cef17a501a97fe 100644
--- a/plans/tomap-microbial-phenotypes.plan
+++ b/plans/tomap-microbial-phenotypes.plan
@@ -2,18 +2,18 @@
<!-- ToMap on lemmas -->
<tomap class="TomapProjector">
- <yateaFile output-feed="true">corpora/&corpus;/batches/&batch;/yatea/candidates.xml</yateaFile>
+ <yateaFile output-feed="true">yatea/candidates.xml</yateaFile>
<targetLayerName>phenotypes</targetLayerName>
<conceptFeature>concept-id</conceptFeature>
<explanationFeaturePrefix>explain_</explanationFeaturePrefix>
- <tomapClassifier empty-words="ancillaries/stopwords_EN.ttg" whole-proxy-distance="false">&ontobiotope;-Phenotype.tomap</tomapClassifier>
+ <tomapClassifier empty-words="ancillaries/stopwords_EN.ttg" whole-proxy-distance="false">ancillaries/BioNLP-OST+EnovFood-Phenotype.tomap</tomapClassifier>
<lemmaKeys/>
<subject feature="lemma" layer="words"/>
<scoreFeature>score</scoreFeature>
</tomap>
<concept-names class="OBOMapper">
- <oboFiles>&ontobiotope;-Phenotype.obo</oboFiles>
+ <oboFiles>ancillaries/BioNLP-OST+EnovFood-Phenotype.obo</oboFiles>
<idKeys/>
<target>documents.sections.layer:phenotypes</target>
<form>@concept-id</form>
@@ -25,18 +25,18 @@
<tomap-on-alternative-lemmas>
<tomap class="TomapProjector">
- <yateaFile output-feed="true">corpora/&corpus;/batches/&batch;/yatea/candidates.xml</yateaFile>
+ <yateaFile output-feed="true">yatea/candidates.xml</yateaFile>
<targetLayerName>phenotypes2</targetLayerName>
<conceptFeature>concept-id</conceptFeature>
<explanationFeaturePrefix>explain_</explanationFeaturePrefix>
- <tomapClassifier empty-words="ancillaries/stopwords_EN.ttg" whole-proxy-distance="false">&ontobiotope;-Phenotype.tomap</tomapClassifier>
+ <tomapClassifier empty-words="ancillaries/stopwords_EN.ttg" whole-proxy-distance="false">ancillaries/BioNLP-OST+EnovFood-Phenotype.tomap</tomapClassifier>
<lemmaKeys/>
<subject feature="lemma2" layer="words"/>
<scoreFeature>score</scoreFeature>
</tomap>
<concept-names class="OBOMapper">
- <oboFiles>&ontobiotope;-Phenotype.obo</oboFiles>
+ <oboFiles>ancillaries/BioNLP-OST+EnovFood-Phenotype.obo</oboFiles>
<idKeys/>
<target>documents.sections.layer:phenotypes2</target>
<form>@concept-id</form>
@@ -57,17 +57,17 @@
<tomap-no-lemmakeys>
<tomap class="TomapProjector">
- <yateaFile output-feed="true">corpora/&corpus;/batches/&batch;/yatea/candidates.xml</yateaFile>
+ <yateaFile output-feed="true">yatea/candidates.xml</yateaFile>
<targetLayerName>phenotypes3</targetLayerName>
<conceptFeature>concept-id</conceptFeature>
<explanationFeaturePrefix>explain_</explanationFeaturePrefix>
- <tomapClassifier empty-words="ancillaries/stopwords_EN.ttg" whole-proxy-distance="false">&ontobiotope;-Phenotype.tomap</tomapClassifier>
+ <tomapClassifier empty-words="ancillaries/stopwords_EN.ttg" whole-proxy-distance="false">ancillaries/BioNLP-OST+EnovFood-Phenotype.tomap</tomapClassifier>
<subject feature="lemma" layer="words"/>
<scoreFeature>score</scoreFeature>
</tomap>
<concept-names class="OBOMapper">
- <oboFiles>&ontobiotope;-Phenotype.obo</oboFiles>
+ <oboFiles>ancillaries/BioNLP-OST+EnovFood-Phenotype.obo</oboFiles>
<idKeys/>
<target>documents.sections.layer:phenotypes3</target>
<form>@concept-id</form>
@@ -89,18 +89,18 @@
<tomap-on-variants>
<tomap class="TomapProjector">
- <yateaFile output-feed="true">corpora/&corpus;/batches/&batch;/yatea-var/candidates.xml</yateaFile>
+ <yateaFile output-feed="true">yatea-var/candidates.xml</yateaFile>
<targetLayerName>phenotypes4</targetLayerName>
<conceptFeature>concept-id</conceptFeature>
<explanationFeaturePrefix>explain_</explanationFeaturePrefix>
- <tomapClassifier empty-words="ancillaries/stopwords_EN.ttg" whole-proxy-distance="false">&ontobiotope;-Phenotype.tomap</tomapClassifier>
+ <tomapClassifier empty-words="ancillaries/stopwords_EN.ttg" whole-proxy-distance="false">ancillaries/BioNLP-OST+EnovFood-Phenotype.tomap</tomapClassifier>
<lemmaKeys/>
<subject feature="variant" layer="words"/>
<scoreFeature>score</scoreFeature>
</tomap>
<concept-names class="OBOMapper">
- <oboFiles>&ontobiotope;-Phenotype.obo</oboFiles>
+ <oboFiles>ancillaries/BioNLP-OST+EnovFood-Phenotype.obo</oboFiles>
<idKeys/>
<target>documents.sections.layer:phenotypes4</target>
<form>@concept-id</form>
@@ -121,17 +121,17 @@
<tomap-no-lemmakeys-word-form>
<tomap class="TomapProjector">
- <yateaFile output-feed="true">corpora/&corpus;/batches/&batch;/yatea/candidates.xml</yateaFile>
+ <yateaFile output-feed="true">yatea/candidates.xml</yateaFile>
<targetLayerName>phenotypes5</targetLayerName>
<conceptFeature>concept-id</conceptFeature>
<explanationFeaturePrefix>explain_</explanationFeaturePrefix>
- <tomapClassifier empty-words="ancillaries/stopwords_EN.ttg" whole-proxy-distance="false">&ontobiotope;-Phenotype.tomap</tomapClassifier>
+ <tomapClassifier empty-words="ancillaries/stopwords_EN.ttg" whole-proxy-distance="false">ancillaries/BioNLP-OST+EnovFood-Phenotype.tomap</tomapClassifier>
<subject feature="form" layer="words"/>
<scoreFeature>score</scoreFeature>
</tomap>
<concept-names class="OBOMapper">
- <oboFiles>&ontobiotope;-Phenotype.obo</oboFiles>
+ <oboFiles>ancillaries/BioNLP-OST+EnovFood-Phenotype.obo</oboFiles>
<idKeys/>
<target>documents.sections.layer:phenotypes5</target>
<form>@concept-id</form>
@@ -166,7 +166,7 @@
<bioyatea-projection class="YateaTermsProjector">
<targetLayerName>yateaTerms</targetLayerName>
<!--<yateaFile inhibitCheck="true">words_prepro/default/xml/candidates_pp.xml</yateaFile>-->
- <yateaFile output-feed="yes">corpora/&corpus;/batches/&batch;/yatea/candidates.xml</yateaFile> <!-- ??? -->
+ <yateaFile output-feed="yes">yatea/candidates.xml</yateaFile> <!-- ??? -->
<subject layer="words"/>
<termLemma>lemma</termLemma>
</bioyatea-projection>
@@ -394,7 +394,7 @@
<!-- <idFeature>molecule-id</idFeature> -->
<!-- <nameFeature>molecule-name</nameFeature> -->
<!-- <pathFeature>molecule-path</pathFeature> -->
- <!-- <oboFiles>&ontobiotope;-Molecule.obo</oboFiles> -->
+ <!-- <oboFiles>ancillaries/BioNLP-OST+EnovFood-Molecule.obo</oboFiles> -->
<!-- <subject feature="lemma" layer="words"/> -->
<!-- <targetLayerName>molecules</targetLayerName> -->
<!-- </molecule-projection-on-lemmas> -->
@@ -404,7 +404,7 @@
<!-- <idFeature>molecule-id</idFeature> -->
<!-- <nameFeature>molecule-name</nameFeature> -->
<!-- <pathFeature>molecule-path</pathFeature> -->
- <!-- <oboFiles>&ontobiotope;-Molecule.obo</oboFiles> -->
+ <!-- <oboFiles>ancillaries/BioNLP-OST+EnovFood-Molecule.obo</oboFiles> -->
<!-- <subject feature="form" layer="words"/> -->
<!-- <targetLayerName>molecules2</targetLayerName> -->
<!-- </molecule-projection-on-words> -->
@@ -469,7 +469,7 @@
<!-- Add concept-path in case some are missing -->
<concept-path class="OBOMapper">
- <oboFiles>&ontobiotope;-Phenotype.obo</oboFiles>
+ <oboFiles>ancillaries/BioNLP-OST+EnovFood-Phenotype.obo</oboFiles>
<idKeys/>
<target>documents.sections.layer:phenotypes</target>
<form>@concept-id</form>
diff --git a/plans/use-extraction.plan b/plans/use-extraction.plan
index 5d12302993b0490526cb682ad0934cca5820bda1..87195d8d5434aaa4ac887c01765ea83e3c1d4a05 100644
--- a/plans/use-extraction.plan
+++ b/plans/use-extraction.plan
@@ -2,7 +2,7 @@
<alvisnlp-plan id="Use-extraction">
<exact-match class="OBOProjector">
- <oboFiles>&ontobiotope-use;.obo</oboFiles>
+ <oboFiles>ancillaries/Use_V2.obo</oboFiles>
<targetLayerName>uses</targetLayerName>
<subject feature="form" layer="words"/>
<idFeature>concept-id</idFeature>
@@ -12,7 +12,7 @@
</exact-match>
<exact-match-2 class="OBOProjector">
- <oboFiles>&ontobiotope-use;.obo</oboFiles>
+ <oboFiles>ancillaries/Use_V2.obo</oboFiles>
<targetLayerName>uses2</targetLayerName>
<subject feature="lemma" layer="words"/>
<idFeature>concept-id</idFeature>
diff --git a/process-evaluate_BioNLP-OST.snakefile b/process-evaluate_BioNLP-OST.snakefile
index c6b43731d8c0626bc0a5d556b984ed992e41dab2..e50a8be95703306378fc1a5da5719bd885c49691 100644
--- a/process-evaluate_BioNLP-OST.snakefile
+++ b/process-evaluate_BioNLP-OST.snakefile
@@ -39,9 +39,14 @@ rule run_bionlp_prediction:
params:
batch="{B}",
corpus='BioNLP-OST-2019',
- inhibitSyntax='inhibit-syntax',
- onto='ancillaries/BioNLP-OST+EnovFood',
- ontobiotopeUse='ancillaries/Use_V2',
+ inhibitSyntax='inhibit-syntax',
+ onto_habitat='ancillaries/BioNLP-OST+EnovFood-Habitat.obo',
+ tomap_habitat='ancillaries/BioNLP-OST+EnovFood-Habitat.tomap',
+ onto_pheno='ancillaries/BioNLP-OST+EnovFood-Phenotype.obo',
+ tomap_pheno='ancillaries/BioNLP-OST+EnovFood-Phenotype.tomap',
+ graylist='ancillaries/graylist_extended.heads',
+ emptywords='ancillaries/stopwords_EN.ttg',
+ ontobiotopeUse='ancillaries/Use_V2.obo',
plan='plans/entities.plan',
dir='corpora/BioNLP-OST-2019/batches/{B}/',
taxid_microorganisms='ancillaries/extended-microorganisms-taxonomy/taxid_microorganisms.txt',
@@ -52,14 +57,14 @@ rule run_bionlp_prediction:
-log {log} \
-alias format bionlp-st \
-alias input-dir {input.dir} \
- -alias input-xslt {input.xslt} \
- -alias outputDir {params.dir} \
+ -outputDir {params.dir} \
-environmentEntities \
- -entity corpus {params.corpus} \
-feat inhibit-syntax {params.inhibitSyntax} \
- -entity ontobiotope {params.onto} \
- -entity ontobiotope-use {params.ontobiotopeUse} \
- -entity batch {params.batch} \
+ -alias ontobiotope-habitat {params.onto_habitat} \
+ -xalias '<ontobiotope-tomap-habitat empty-words="{params.emptywords}" graylist="{params.graylist}" whole-proxy-distance="false">{params.tomap_habitat}</ontobiotope-tomap-habitat>' \
+ -alias ontobiotope-phenotypes {params.onto_pheno} \
+ -xalias '<ontobiotope-tomap-phenotypes empty-words="{params.emptywords}" whole-proxy-distance="false">{params.tomap_pheno}</ontobiotope-tomap-phenotypes>' \
+ -alias ontobiotope-use {params.ontobiotopeUse} \
-alias taxid_microorganisms {params.taxid_microorganisms} \
-alias taxa+id_full {params.taxa_id_full} \
{params.plan}
diff --git a/process_CIRM_corpus.snakefile b/process_CIRM_corpus.snakefile
index 2b172cf78ac91f2f0387201244ff924c6a48a7ee..f9f49e74a7c963826b96a1eed27b4ebbecd48f8c 100644
--- a/process_CIRM_corpus.snakefile
+++ b/process_CIRM_corpus.snakefile
@@ -24,8 +24,8 @@ rule get_cirm_bia_taxa_habitats:
strain_index='1',
habitat_index='15'
output:
- taxa='corpora/cirm/bia_taxa.txt',
- habitats='corpora/cirm/bia_habitats.txt',
+ taxa='corpora/cirm/bia/bia_taxa.txt',
+ habitats='corpora/cirm/bia/bia_habitats.txt',
tsv='corpora/cirm/BIA_2021/florilege_export_final_17_02_21.tsv'
conda: 'softwares/envs/python3_pandas_env.yaml'
shell: """
@@ -42,8 +42,8 @@ rule get_cirm_yeast_taxa_habitats:
taxa_index='1',
habitat_index='10,11'
output:
- taxa='corpora/cirm/yeast_taxa.txt',
- habitats='corpora/cirm/yeast_habitats.txt',
+ taxa='corpora/cirm/levures/yeast_taxa.txt',
+ habitats='corpora/cirm/levures/yeast_habitats.txt',
tsv='corpora/cirm/Levures_2021/Florilege_21012021.tsv'
conda: 'softwares/envs/python3_pandas_env.yaml'
shell: """
@@ -61,8 +61,8 @@ rule get_cirm_cfbp_taxa_habitats:
strain_index='1',
habitat_index='6,10,13,14'
output:
- taxa='corpora/cirm/cfbp_taxa.txt',
- habitats='corpora/cirm/cfbp_habitats.txt',
+ taxa='corpora/cirm/cfbp/cfbp_taxa.txt',
+ habitats='corpora/cirm/cfbp/cfbp_habitats.txt',
tsv='corpora/cirm/CFBP_2021/20210617_PPortier.tsv'
conda: 'softwares/envs/python3_pandas_env.yaml'
shell: """
@@ -75,9 +75,9 @@ map microorganisms
'''
rule map_cirm_bia_microorganisms:
input:
- taxa='corpora/cirm/bia_taxa.txt'
+ taxa='corpora/cirm/bia/bia_taxa.txt'
output:
- mapped_taxaids='corpora/cirm/mapped_bia_taxa.txt'
+ mapped_taxaids='corpora/cirm/bia/mapped_bia_taxa.txt'
params:
plan='plans/map_microorganisms.plan',
taxid_microorganisms='ancillaries/extended-microorganisms-taxonomy/taxid_microorganisms.txt',
@@ -96,9 +96,9 @@ map microorganisms (CIRM Levures)
'''
rule map_cirm_yeast_microorganisms:
input:
- taxa='corpora/cirm/yeast_taxa.txt'
+ taxa='corpora/cirm/levures/yeast_taxa.txt'
output:
- mapped_taxaids='corpora/cirm/mapped_yeast_taxa.txt'
+ mapped_taxaids='corpora/cirm/levures/mapped_yeast_taxa.txt'
params:
plan='plans/map_microorganisms.plan',
taxid_microorganisms='ancillaries/extended-microorganisms-taxonomy/taxid_microorganisms.txt',
@@ -118,9 +118,9 @@ map microorganisms (CIRM CFBP)
'''
rule map_cirm_cfbp_microorganisms:
input:
- taxa='corpora/cirm/cfbp_taxa.txt'
+ taxa='corpora/cirm/cfbp/cfbp_taxa.txt'
output:
- mapped_taxa='corpora/cirm/mapped_cfbp_taxa.txt'
+ mapped_taxa='corpora/cirm/cfbp/mapped_cfbp_taxa.txt'
params:
plan='plans/map_microorganisms.plan',
taxid_microorganisms='ancillaries/extended-microorganisms-taxonomy/taxid_microorganisms.txt',
@@ -139,19 +139,22 @@ map habitats of microorganisms
'''
rule map_cirm_habitats:
input:
- habitats='corpora/cirm/bia_habitats.txt'
+ habitats='corpora/cirm/bia/bia_habitats.txt'
output:
- mapped_habitats='corpora/cirm/mapped_bia_habitats.txt'
+ mapped_habitats='corpora/cirm/bia/mapped_bia_habitats.txt'
params:
plan='plans/map_habitats.plan',
onto='ancillaries/BioNLP-OST+EnovFood-Habitat.obo',
tomap='ancillaries/BioNLP-OST+EnovFood-Habitat.tomap',
graylist='ancillaries/graylist_extended.heads',
- emptywords='ancillaries/stopwords_EN.ttg'
+ emptywords='ancillaries/stopwords_EN.ttg',
+ outdir='corpora/cirm/bia',
+ outfile='mapped_bia_habitats.txt'
singularity:config["SINGULARITY_IMG"]
shell: """alvisnlp -J-Xmx32g -cleanTmp -verbose \
-alias input {input.habitats} \
- -alias output {output.mapped_habitats} \
+ -outputDir {params.outdir} \
+ -alias output {params.outfile} \
-alias ontobiotope {params.onto} \
-xalias '<ontobiotope-tomap empty-words="{params.emptywords}" graylist="{params.graylist}" whole-proxy-distance="false">{params.tomap}</ontobiotope-tomap>' \
{params.plan}
@@ -162,19 +165,22 @@ map habitats of microorganisms (CIRM Levures)
'''
rule map_cirm_yeast_habitats:
input:
- habitats='corpora/cirm/yeast_habitats.txt'
+ habitats='corpora/cirm/levures/yeast_habitats.txt'
output:
- mapped_habitats='corpora/cirm/mapped_yeast_habitats.txt'
+ mapped_habitats='corpora/cirm/levures/mapped_yeast_habitats.txt'
params:
plan='plans/map_habitats.plan',
onto='ancillaries/BioNLP-OST+EnovFood-Habitat.obo',
tomap='ancillaries/BioNLP-OST+EnovFood-Habitat.tomap',
graylist='ancillaries/graylist_extended.heads',
- emptywords='ancillaries/stopwords_EN.ttg'
+ emptywords='ancillaries/stopwords_EN.ttg',
+ outdir='corpora/cirm/levures',
+ outfile='mapped_yeast_habitats.txt'
singularity:config["SINGULARITY_IMG"]
shell: """alvisnlp -J-Xmx32g -cleanTmp -verbose \
-alias input {input.habitats} \
- -alias output {output.mapped_habitats} \
+ -outputDir {params.outdir} \
+ -alias output {params.outfile} \
-alias ontobiotope {params.onto} \
-xalias '<ontobiotope-tomap empty-words="{params.emptywords}" graylist="{params.graylist}" whole-proxy-distance="false">{params.tomap}</ontobiotope-tomap>' \
{params.plan}
@@ -185,19 +191,22 @@ map habitats of microorganisms (CIRM CFBP)
'''
rule map_cirm_cfbp_habitats:
input:
- habitats='corpora/cirm/cfbp_habitats.txt'
+ habitats='corpora/cirm/cfbp/cfbp_habitats.txt'
output:
- mapped_habitats='corpora/cirm/mapped_cfbp_habitats.txt'
+ mapped_habitats='corpora/cirm/cfbp/mapped_cfbp_habitats.txt'
params:
plan='plans/map_habitats.plan',
onto='ancillaries/BioNLP-OST+EnovFood-Habitat.obo',
tomap='ancillaries/BioNLP-OST+EnovFood-Habitat.tomap',
graylist='ancillaries/graylist_extended.heads',
- emptywords='ancillaries/stopwords_EN.ttg'
+ emptywords='ancillaries/stopwords_EN.ttg',
+ outdir='corpora/cirm/cfbp',
+ outfile='mapped_cfbp_habitats.txt'
singularity:config["SINGULARITY_IMG"]
shell: """alvisnlp -J-Xmx32g -cleanTmp -verbose \
-alias input {input.habitats} \
- -alias output {output.mapped_habitats} \
+ -outputDir {params.outdir} \
+ -alias output {params.outfile} \
-alias ontobiotope {params.onto} \
-xalias '<ontobiotope-tomap empty-words="{params.emptywords}" graylist="{params.graylist}" whole-proxy-distance="false">{params.tomap}</ontobiotope-tomap>' \
{params.plan}
@@ -209,8 +218,8 @@ format results
rule format_cirm_results:
input:
file='corpora/cirm/BIA_2021/florilege_export_final_17_02_21.tsv',
- taxa='corpora/cirm/mapped_bia_taxa.txt',
- habitats='corpora/cirm/mapped_bia_habitats.txt'
+ taxa='corpora/cirm/bia/mapped_bia_taxa.txt',
+ habitats='corpora/cirm/bia/mapped_bia_habitats.txt'
output:
result='corpora/florilege/cirm/cirm-bia-results.txt'
params:
@@ -226,8 +235,8 @@ format results (CIRM Levures)
rule format_cirm_yeast_results:
input:
file='corpora/cirm/Levures_2021/Florilege_21012021.tsv',
- taxa='corpora/cirm/mapped_yeast_taxa.txt',
- habitats='corpora/cirm/mapped_yeast_habitats.txt'
+ taxa='corpora/cirm/levures/mapped_yeast_taxa.txt',
+ habitats='corpora/cirm/levures/mapped_yeast_habitats.txt'
output:
result='corpora/florilege/cirm/cirm-yeast-results.txt'
params:
@@ -242,8 +251,8 @@ format results (CIRM CFBP)
rule format_cirm_cfbp_results:
input:
file='corpora/cirm/CFBP_2021/20210617_PPortier.tsv',
- taxa='corpora/cirm/mapped_cfbp_taxa.txt',
- habitats='corpora/cirm/mapped_cfbp_habitats.txt'
+ taxa='corpora/cirm/cfbp/mapped_cfbp_taxa.txt',
+ habitats='corpora/cirm/cfbp/mapped_cfbp_habitats.txt'
output:
result='corpora/florilege/cirm/cirm-cfbp-results.txt'
params:
diff --git a/process_DSMZ_corpus.snakefile b/process_DSMZ_corpus.snakefile
index b4fa67fa3a0830be87fa78e37a69270333359c55..8fde651932d3c4255ef92b8bbbfb11f822308cf3 100644
--- a/process_DSMZ_corpus.snakefile
+++ b/process_DSMZ_corpus.snakefile
@@ -35,11 +35,14 @@ rule map_dsmz_habitats:
onto='ancillaries/BioNLP-OST+EnovFood-Habitat.obo',
tomap='ancillaries/BioNLP-OST+EnovFood-Habitat.tomap',
graylist='ancillaries/graylist_extended.heads',
- emptywords='ancillaries/stopwords_EN.ttg'
+ emptywords='ancillaries/stopwords_EN.ttg',
+ outdir='corpora/dsmz',
+ outfile='mapped_habitats.txt'
singularity:config["SINGULARITY_IMG"]
shell: """alvisnlp -J-Xmx32g -cleanTmp -verbose \
-alias input {input.habitats} \
- -alias output {output.mapped_habitats} \
+ -outputDir {params.outdir} \
+ -alias output {params.outfile} \
-alias ontobiotope {params.onto} \
-xalias '<ontobiotope-tomap empty-words="{params.emptywords}" graylist="{params.graylist}" whole-proxy-distance="false">{params.tomap}</ontobiotope-tomap>' \
{params.plan}
diff --git a/process_GenBank_corpus.snakefile b/process_GenBank_corpus.snakefile
index 388f9ab1da3af0ffa392a81c44802b85b812d21b..888835e413b1864c216cebcf38a65355270f103e 100644
--- a/process_GenBank_corpus.snakefile
+++ b/process_GenBank_corpus.snakefile
@@ -79,11 +79,14 @@ rule map_genbank_habitats:
tomap='ancillaries/BioNLP-OST+EnovFood-Habitat.tomap',
graylist='ancillaries/graylist_extended.heads',
emptywords='ancillaries/stopwords_EN.ttg',
- inhibitSyntax='inhibit-syntax'
+ inhibitSyntax='inhibit-syntax',
+ outdir='corpora/genbank',
+ outfile='mapped_habitats.txt'
singularity:config["SINGULARITY_IMG"]
shell: """alvisnlp -J-Xmx32g -cleanTmp -verbose \
-alias input {input.habitats} \
- -alias output {output.mapped_habitats}\
+ -outputDir {params.outdir} \
+ -alias output {params.outfile} \
-alias ontobiotope {params.onto} \
-feat inhibit-syntax {params.inhibitSyntax} \
-xalias '<ontobiotope-tomap empty-words="{params.emptywords}" graylist="{params.graylist}" whole-proxy-distance="false">{params.tomap}</ontobiotope-tomap>' \
diff --git a/process_PubMed_corpus.snakefile b/process_PubMed_corpus.snakefile
index 7fd42f33b809b64d119f5f88c543976bf8ebc097..5710034a3d3862750f5fcff9027c2a2411ed89db 100644
--- a/process_PubMed_corpus.snakefile
+++ b/process_PubMed_corpus.snakefile
@@ -46,9 +46,14 @@ rule run_pubmed_entities:
params:
batch="{B}",
corpus='pubmed',
- inhibitSyntax='inhibit-syntax',
- onto='ancillaries/BioNLP-OST+EnovFood',
- ontobiotopeUse='ancillaries/Use_V2',
+ inhibitSyntax='inhibit-syntax',
+ onto_habitat='ancillaries/BioNLP-OST+EnovFood-Habitat.obo',
+ tomap_habitat='ancillaries/BioNLP-OST+EnovFood-Habitat.tomap',
+ onto_pheno='ancillaries/BioNLP-OST+EnovFood-Phenotype.obo',
+ tomap_pheno='ancillaries/BioNLP-OST+EnovFood-Phenotype.tomap',
+ graylist='ancillaries/graylist_extended.heads',
+ emptywords='ancillaries/stopwords_EN.ttg',
+ ontobiotopeUse='ancillaries/Use_V2.obo',
plan='plans/entities.plan',
dir='corpora/pubmed/batches/{B}/',
taxid_microorganisms='ancillaries/extended-microorganisms-taxonomy/taxid_microorganisms.txt',
@@ -61,13 +66,15 @@ rule run_pubmed_entities:
-alias format pubmed \
-alias input {input.file} \
-alias input-xslt {input.xslt} \
- -alias outputDir {params.dir} \
+ -alias batch batch={params.batch} \
+ -outputDir {params.dir} \
-environmentEntities \
- -entity corpus {params.corpus} \
-feat inhibit-syntax {params.inhibitSyntax} \
- -entity ontobiotope {params.onto} \
- -entity ontobiotope-use {params.ontobiotopeUse} \
- -entity batch {params.batch} \
+ -alias ontobiotope-habitat {params.onto_habitat} \
+ -xalias '<ontobiotope-tomap-habitat empty-words="{params.emptywords}" graylist="{params.graylist}" whole-proxy-distance="false">{params.tomap_habitat}</ontobiotope-tomap-habitat>' \
+ -alias ontobiotope-phenotypes {params.onto_pheno} \
+ -xalias '<ontobiotope-tomap-phenotypes empty-words="{params.emptywords}" whole-proxy-distance="false">{params.tomap_pheno}</ontobiotope-tomap-phenotypes>' \
+ -alias ontobiotope-use {params.ontobiotopeUse} \
-alias taxid_microorganisms {params.taxid_microorganisms} \
-alias taxa+id_full {params.taxa_id_full} \
{params.plan}