Presentation is loading. Please wait.

Presentation is loading. Please wait.

University of Texas at Austin Machine Learning Group Integrating Co-occurrence Statistics with IE for Robust Retrieval of Protein Interactions from Medline.

Similar presentations


Presentation on theme: "University of Texas at Austin Machine Learning Group Integrating Co-occurrence Statistics with IE for Robust Retrieval of Protein Interactions from Medline."— Presentation transcript:

1 University of Texas at Austin Machine Learning Group Integrating Co-occurrence Statistics with IE for Robust Retrieval of Protein Interactions from Medline Razvan C. Bunescu Raymond J. Mooney Machine Learning Group Department of Computer Sciences University of Texas at Austin {razvan, mooney}@cs.utexas.edu Arun K. Ramani Edward M. Marcotte Institute for Cellular and Molecular Biology Center for Computational Biology and Bioinformatics University of Texas at Austin {arun, marcotte}@icmb.utexas.edu

2 2 University of Texas at Austin Machine Learning Group Introduction Two orthogonal approaches to mining binary relations from a collection of documents: –Information Extraction: Relation Extraction from individual sentences; Aggregation of the results over the entire collection. –Co-occurrence Statistics: Compute (co-)occurrence counts over the entire corpus; Use statistical tests to detect whether co-occurrence is due to chance. Aim: Combine the two approaches into an integrated extraction model.

3 3 University of Texas at Austin Machine Learning Group Outline Introduction. Two approaches to relation extraction: –Information Extraction. –Co-occurrence Statistics. Integrated Model. Evaluation Corpus. Experimental Results. Future Work & Conclusion.

4 4 University of Texas at Austin Machine Learning Group Information Extraction Most IE systems detect relations only between entities mentioned in the same sentence. The existence & type of the relationship is based on lexico-semantic cues inferred from the sentence context. Given a pair of entities, corpus-level results are assembled by combining the confidence scores that the IE system associates with each occurrence. In synchronized human osteosarcoma cells, cyclin D1 is induced in early G1 and becomes associated with p9Ckshs1, a Cdk-binding subunit.

5 5 University of Texas at Austin Machine Learning Group Relation Extraction using a Subsequence Kernel Subsequences of words and POS tags are used as Implicit Features. Assumes the entities have already been annotated. Exponential penalty factor is used to downweigh longer word gaps. Generalization of the extraction system from [Blaschke et al., 2001]. The system is trained to ouput a normalized confidence value for each extraction. interaction of (3) PROT (3) with PROT [Bunescu et al., 2005].

6 6 University of Texas at Austin Machine Learning Group Aggregating Corpus-Level Results S1S1 S2S2 SnSn...... Information ExtractionSentences......Confidences Aggregation

7 7 University of Texas at Austin Machine Learning Group Aggregation Operators Maximum Noisy-OR Average AND

8 8 University of Texas at Austin Machine Learning Group Outline Introduction. Two approaches to relation extraction: Information Extraction. –Co-occurrence Statistics. Integrated Model. Evaluation Corpus. Experimental Results. Future Work & Conclusion.

9 9 University of Texas at Austin Machine Learning Group Co-occurrence Statistics Compute (co-)occurrence counts for the two entities in the entire corpus. Based on these counts, detect if the co-occurrence of the two entities is due to chance, or to an underlying relationship. Can use various statistical measures: –Pointwise Mutual Information (PMI) –Chi-square Test (  2 ) –Log-Likelihood Ratio (LLR)

10 10 University of Texas at Austin Machine Learning Group Pointwise Mutual Information N : the total number of protein pairs co-occurring in the same sentence in the entire corpus. P(p 1,p 2 )  n 12 /N : the probability that p 1 and p 2 co-occur in the same sentence. P(p 1, p)  n 1 /N : the probability that p 1 co-occurs with any protein in the same sentence. P(p 2, p)  n 2 /N : the probability that p 2 co-occurs with any protein in the same sentence. The higher the sPMI(p 1, p 2 ) value, the less likely it is that p 1 and p 2 co- occurred by chance => they may be interacting.

11 11 University of Texas at Austin Machine Learning Group Outline Introduction. Two approaches to relation extraction: Information Extraction. Co-occurrence Statistics. Integrated Model. Evaluation Corpus. Experimental Results. Future Work & Conclusion.

12 12 University of Texas at Austin Machine Learning Group Integrated Model [Local] The sentence-level Relation Extraction (SSK) uses information that is local to one occurrence of a pair of entities (p 1,p 2 ). [Global] The corpus-level Co-occurrence Statistics (PMI) are based on counting all occurrences of a pair of entities (p 1,p 2 ). [Local & Global] Achieve a more reliable extraction performance by combining the two orthogonal approaches into an integrated model.

13 13 University of Texas at Austin Machine Learning Group Integrated Model Rewrite sPMI as: Instead of counting 1 for each co-occurrence, use the confidence ouput by the IE system => a weighted PMI: Can use any aggregation operator:

14 14 University of Texas at Austin Machine Learning Group Outline Introduction. Two approaches to relation extraction: Information Extraction. Co-occurrence Statistics. Integrated Model. Evaluation Corpus. Experimental Results. Future Work & Conclusion.

15 15 University of Texas at Austin Machine Learning Group Evaluation Corpus An evaluation corpus needs to provide two types of information: –The complete list of interactions mentioned in the corpus. –Annotations of protein mentions, together with their gene identifiers. The corpus was compiled based on the HPRD [www.hprd.org] and NCBI [www.ncbi.nih.gov] databases: –Every interaction is linked to a set of Medline articles that report the corresponding experiment. –An interaction is specified as a tuple containing: The LocusLink (EntrezGene) identifiers of the proteins involved. The PubMed identifiers of the corresponding Medline articles.

16 16 University of Texas at Austin Machine Learning Group Evaluation Corpus (cont’ed) FNLC filamin C, gamma ABPA ABPL FNL2 gamma filamin filamin 2 filamin C, gamma MYOZ1 myozenin 1... FATZ … Participant Genes (XML) (NCBI) 2318 58529 10984498 11171996 Interactions (XML) (HPRD) 10984498 We found that this protein binds to three other Z-dics proteins; therefore we have named it FATZ, gamma-filamin, alpha-actinin and telethonin binding protein of the Z-disc. Medline Abstracts (XML) (NCBI)

17 17 University of Texas at Austin Machine Learning Group Gene Name Annotation and Normalization NCBI provides a comprehensive dictionary of human genes, where each gene specifies is specified by its unique identifier, and qualified with: –an official name, –a description, –a list of synonyms, –a list of protein names. All these names (including the description) are considered as referring to the same entity. Use a dictionary-based annotation, similar to [Cohen, 2005].

18 18 University of Texas at Austin Machine Learning Group Gene Name Annotation and Normalization Each name is reduced to a normal form, by: 1)Replacing dashes with spaces 2)Introducing spaces between letters and digits 3)Replacing Greek letters with their Latin counterparts 4)Substituting Roman numerals with Arabic numerals 5)Decapitalizing the first word (if capitalized). The names are further tokenized, and checked against a dictionary of 100K English nouns. Names associated with more than one gene identifier (i.e. ambiguous names) are ignored. The final gene name dictionary is implemented as a trie-like structure.

19 19 University of Texas at Austin Machine Learning Group Outline Introduction. Two approaches to relation extraction: Information Extraction. Co-occurrence Statistics. Integrated Model. Evaluation Corpus. Experimental Results. Future Work & Conclusion.

20 20 University of Texas at Austin Machine Learning Group Experimental Results Compare four methods on the task of interaction extraction: –Information Extraction: [SSK.Max] Relation extraction with the subsequence kernel (SSK), followed by an aggregation of corpus-level results using Max. –Co-occurrence Statistics: [PMI] Pointwise Mutual Information. [HG] The HyperGeometric distribution method from [Ramani et al., 2005]. –Integrated Model: [PMI.SSK.Max]The combined model of PMI & SSK. Draw Precision vs. Recall graphs, by ranking the extractions and choosing only the top N interactions, while N is varying.

21 21 University of Texas at Austin Machine Learning Group Experimental Results

22 22 University of Texas at Austin Machine Learning Group Future Work Derive an evaluation corpus from a potentially more accurate database (Reactome). Investigate combining IE with other statistical tests (LLR,  2 ). Design an IE method that is trained to do corpus-level extraction (as opposed to sentence-level extraction).

23 23 University of Texas at Austin Machine Learning Group Conclusion Introduced an integrated model that combines two orthogonal approaches to corpus-level relation extraction: –Information Extraction (SSK). –Co-occurrence Statistics (PMI). Derived an evaluation corpus from the HPRD and NCBI databases. Experimental results show a more consistent performance across the PR curve.

24 24 University of Texas at Austin Machine Learning Group Aggregating Corpus-Level Results Two entities p 1 and p 2 are mentioned in a corpus C of n sentences, C  {S 1, …, S n }. The IE system outputs a confidence value for each of the n occurrences: The corpus-level confidence value is computed using an aggregation operator  :

25 25 University of Texas at Austin Machine Learning Group Experimental Results Compare [PMI] and [HG] on the task of extracting interactions from the entire Medline. Use the shared protein function benchmark from [Ramani et al. 2005]. –Calculate the extent to which interactions partners share functional annotations, as specified in the KEGG and GO databases. –Use a Log-Likelihood Ratio (LLR) scoring scheme to rank the interactions: Also plot the scores associated with the HPRD, BIND and Reactome databases.

26 26 University of Texas at Austin Machine Learning Group Experimental Results


Download ppt "University of Texas at Austin Machine Learning Group Integrating Co-occurrence Statistics with IE for Robust Retrieval of Protein Interactions from Medline."

Similar presentations


Ads by Google