NLP Tools for Biology Literature Mining

1. NLP Tools for Biology Literature Mining Qiaozhu Mei Jing Jiang ChengXiang Zhai Nov 3, 2004

2. What do we have? Biology Literature (huge amount of text) E.g. Mites in the genus Varroa are the primary parasites of honey bees … Ten of 22 transfer RNAs are in different locations relative to hard ticks, and the 12S ribosomal RNA subunit is inverted and separated from the 16S rRNA by a novel non-coding region, a trait not yet seen in other arthropods. … (from Biological Abstracts)

3. What do we want? • Named entities: • gene names, protein names, drugs, etc. • Interaction events between entities: • transcription, translation, post translational modification, etc. • Relationships between basic events: • caused by, inhibited by, etc. (from Hirschman et al. 02)

4. Preliminary System Structure Collections of raw textual data … Text Pre-processing: NLP POS Tagger Parser Entity Extractor NPs, VPs, Relations Nouns, Verbs, etc. Genes, proteins, other entities Pre-processed data ready to mine Text Mining Modules: TM …

5. POS Taggers • Tree Tagger • Brill Tagger • SNoW Tagger • LT Chunk • Stanford Tagger

6. Results of POS Tagging Raw text: Mites in the genus Varroa are the primary parasites of honey bees … Ten of 22 transfer RNAs are in different locations relative to hard ticks, and the 12S ribosomal RNA subunit is inverted and separated from the 16S rRNA by a novel non-coding region, a trait not yet seen in other arthropods. … (from Biological Abstracts)

7. Results of POS Tagging (cont.)

8. Results of POS Tagging (cont.)

9. Comparison of POS Taggers

10. Conclusions • Existing general-purpose POS taggers work fine for our task. • Most nouns and verbs correctly identified • There is still room to improve existing POS taggers for biology data. • E.g. to identify gene and protein names • Speed and adaptability are important.

11. A Little Bit More on SNoW • SNoW has a POS tagger and a shallow parser. • Speed is reasonable. • Software is adaptable as help is available from CCG. • The network model can be trained if we have training data.

12. Result of SNoW Shallow Parser [NP the 12 S ribosomal RNA subunit] [VP is] [ADJP inverted] and [VP separated] [PP from] [NP the 16 S rRNA] [PP by] [NP a novel non-coding region] (from online demo) Problems: • Currently the package is not available for download from the new CCG page. • There is still problem running the old package on our machine. (compilation, path setting, etc.)

13. Parsers • SNoW (already covered) • LT-Chunk • MiniPar • Collins • Stanford

14. Result of LT-Chunk [[ the_DT 12S_JJ ribosomal_JJ RNA_NNP subunit_NN ]] (( is_VBZ inverted_VBN and_CC separated_VBN )) from_IN [[ the_DT 16S_JJ rRNA_NNP ]] by_IN [[ a_DT novel_JJ non-coding_JJ region_NN ]]

15. Result of MiniPar 16 (the ~ Det 20 det (gov subunit)) 17 (12S ~ N 20 nn (gov subunit)) 18 (ribosomal ~ A 20 mod (gov subunit)) 19 (RNA ~ N 20 nn (gov subunit)) 20 (subunit ~ N 22 s (gov invert)) 21 (is be be 22 be (gov invert)) 22 (inverted invert V E0 i (gov fin)) E4 (() subunit N 22 obj (gov invert) 23 (and ~ U 22 lex-mod (gov invert)) 24 (separated separate V 22 lex-dep (gov invert)) 25 (from ~ Prep 22 mod (gov invert)) 26 (the ~ Det 28 det (gov rRNA)) 27 (16S ~ N 28 nn (gov rRNA)) 28 (rRNA ~ N 25 pcomp-n (gov from))

16. Results of Collins Parser (S~is~2~2 (NPB~subunit~5~5 the/DT 12S/CD ribosomal/JJ RNA/NNP subunit/NN ) (VP~is~2~1 is/VBZ (UCP~inverted~3~1 (ADJP~inverted~1~1 inverted/JJ ) and/CC (VP~separated~3~1 separated/VBN (PP~from~2~1 from/IN (NPB~rRNA~3~3 the/DT 16S/CD rRNA/NN ) ) (PP~by~2~1 by/IN (NP~region~2~1 (NPB~region~4~4 a/DT novel/JJ non-coding/JJ region/NN ,/PUNC, )

17. Comparison of Parsers

18. Conclusion on Parsers • MiniPar has advantages so far: • Fast • Outputs dependency & governing info. and useful relations • Provides API • If SNoW is tuned for the task, we can easily plug it into the module.

19. Entity Extractors • Abner: extracts protein, DNA, RNA, cell line, and cell type • Yagi: extracts only gene names, a brother of Abner • LingPipe: Named entity extraction that can be trained for different domains.

20. Result of Abner Ten of <RNA>22 transfer RNAs</RNA> are in different locations relative to hard ticks , and the 12 <protein>S ribosomal RNA subunit</protein> is inverted and separated from the 16 S rRNA by a novel non-coding region, …

21. Result of LingPipe Ten of 22 transfer RNAs are in different locations relative to hard ticks, and the <ENAMEX id="0" type="GENE">12S ribosomal RNA subunit</ENAMEX> is inverted and separated from the <ENAMEX id="1" type="GENE">16S rRNA</ENAMEX> by a novel non-coding region, …

22. Comparison of Entity Extractors

23. Conclusion on Entities Extractors • Still a lot of room to improve. However, with existing extractors we can begin high level text mining work. • Performances over honeybee data need to be evaluated. • As soon as better extractor is constructed, we can plug in easily.

24. Summary • Some Existing NLP tools for supporting Biology Literature Mining:POS Taggers , Parsers and Entity-Extractors are evaluated • Observations along two lines: • Still considerable room of improvement beyond the existing NLP tools, especially customize them for special domains. • We can begin exploring higher-level text mining research with support of these toolkits. • Text Preprocessing Modules are independent, easy to plug and play

25. References • Hirschman, L. et al. Accomplishments and challenges in literature data mining for biology Bioinformatics, 2002 • Dekang Lin. Dependency-based evaluation of MiniPar In Workshop on the Evaluation of Parsing Systems, 1998

26. End of Talk Thank you!