1. wwmm
  2. chemicaltagger

Overview

HTTPS SSH

ChemicalTagger Overview

ChemicalTagger is a tool for semantic text-mining in chemistry; the associated publication can be found here. It is available on Maven Central:

<dependency>
    <groupId>uk.ac.cam.ch.wwmm</groupId>
    <artifactId>chemicalTagger</artifactId>
    <version>1.4.0</version>
</dependency>

A. Components:

This package is used for marking up experimental sections in chemistry papers: It has 3 main classes:

I. ChemistryPOSTagger:

This class takes a sentence and runs it against (by default) three taggers:

  • OSCAR4 (for chemical entities)
  • Regex (for recognising key words)
  • OpenNLP (for English parts of speech)

II. ChemistrySentenceParser:

This class converts a tagged sentence into a parseTree. It uses a lexer and parser generated by the Antlr grammar.

III. ASTtoXML:

This class converts a parseTree into an XML document.

B. Running ChemicalTagger:

import uk.ac.cam.ch.wwmm.chemicaltagger.POSContainer;
import uk.ac.cam.ch.wwmm.chemicaltagger.ChemistryPOSTagger;
import uk.ac.cam.ch.wwmm.chemicaltagger.ChemistrySentenceParser;
import uk.ac.cam.ch.wwmm.chemicaltagger.Utils;
import nu.xom.Document;

public class ChemicalTaggerTest {

   public static void main(String[] args) {
      String text = "A solution of 124C (7.0 g, 32.4 mmol) in concentrate H2SO4 " +
                "(9.5 mL) was added to a solution of concentrate H2SO4 (9.5 mL) " +
                "and fuming HNO3 (13 mL) and the mixture was heated at 60°C for " +
                "30 min. After cooling to room temperature, the reaction mixture " +
                "was added to iced 6M solution of NaOH (150 mL) and neutralized " +
                "to pH 6 with 1N NaOH solution. The reaction mixture was extracted " +
                "with dichloromethane (4x100 mL). The combined organic phases were " +
                "dried over Na2SO4, filtered and concentrated to give 124D as a solid.";

      // Calling ChemistryPOSTagger
      POSContainer posContainer = ChemistryPOSTagger.getDefaultInstance().runTaggers(text);

      // Returns a string of TAG TOKEN format (e.g.: DT The NN cat VB sat IN on DT the NN matt)
      // Call ChemistrySentenceParser either by passing the POSContainer or by InputStream
      ChemistrySentenceParser chemistrySentenceParser = new ChemistrySentenceParser(posContainer);

      // Create a parseTree of the tagged input
      chemistrySentenceParser.parseTags();

      // Return an XMLDoc
      Document doc = chemistrySentenceParser.makeXMLDocument();

      Utils.writeXMLToFile(doc,"target/file1.xml");

   }
}