A Dependency Parsing Approach to Biomedical Text Mining

Biomedical research is currently facing a new type of challenge: an excess of information, both in terms of raw data from experiments and in the number of scientific publications describing their results. Mirroring the focus on data mining techniques to address the issues of structured data, there has recently been great interest in the development and application of text mining techniques to make more effective use of the knowledge contained in biomedical scientific publications, accessible only in the form of natural human language. This thesis describes research done in the broader scope of projects aiming to develop methods, tools and techniques for text mining tasks in general and for the biomedical domain in particular. The work described here involves more specifically the goal of extracting information from statements concerning relations of biomedical entities, such as protein-protein interactions. The approach taken is one using full parsing—syntactic analysis of the entire structure of sentences—and machine learning, aiming to develop reliable methods that can further be generalized to apply also to other domains. The five papers at the core of this thesis describe research on a number of distinct but related topics in text mining. In the first of these studies, we assessed the applicability of two popular general English parsers to biomedical text mining and, finding their performance limited, identified several specific challenges to accurate parsing of domain text. In a follow-up study focusing on parsing issues related to specialized domain terminology, we evaluated three lexical adaptation methods. We found that the accurate resolution of unknown words can considerably improve parsing performance and introduced a domain-adapted parser that reduced the error rate of theoriginal by 10% while also roughly halving parsing time. To establish the relative merits of parsers that differ in the applied formalisms and the representation given to their syntactic analyses, we have also developed evaluation methodology, considering different approaches to establishing comparable dependency-based evaluation results. We introduced a methodology for creating highly accurate conversions between different parse representations, demonstrating the feasibility of unification of idiverse syntactic schemes under a shared, application-oriented representation. In addition to allowing formalism-neutral evaluation, we argue that such unification can also increase the value of parsers for domain text mining. As a further step in this direction, we analysed the characteristics of publicly available biomedical corpora annotated for protein-protein interactions and created tools for converting them into a shared form, thus contributing also to the unification of text mining resources. The introduced unified corpora allowed us to perform a task-oriented comparative evaluation of biomedical text mining corpora. This evaluation established clear limits on the comparability of results for text mining methods evaluated on different resources, prompting further efforts toward standardization. To support this and other research, we have also designed and annotated BioInfer, the first domain corpus of its size combining annotation of syntax and biomedical entities with a detailed annotation of their relationships. The corpus represents a major design and development effort of the research group, with manual annotation that identifies over 6000 entities, 2500 relationships and 28,000 syntactic dependencies in 1100 sentences. In addition to combining these key annotations for a single set of sentences, BioInfer was also the first domain resource to introduce a representation of entity relations that is supported by ontologies and able to capture complex, structured relationships. Part I of this thesis presents a summary of this research in the broader context of a text mining system, and Part II contains reprints of the five included publications.

Structural studies on enzymes of biotechnological and biomedical interest

Structural studies of proteins aim at elucidating the atomic details of molecular interactions in biological processes of living organisms. These studies are particularly important in understanding structure, function and evolution of proteins and in defining their roles in complex biological settings. Furthermore, structural studies can be used for the development of novel properties in biomolecules of environmental, industrial and medical importance. X-ray crystallography is an invaluable tool to obtain accurate and precise information about the structure of proteins at the atomic level. Glutathione transferases (GSTs) are amongst the most versatile enzymes in nature. They are able to catalyze a wide variety of conjugation reactions between glutathione (GSH) and non-polar components containing an electrophilic carbon, nitrogen or sulphur atom. Plant GSTs from the Tau class (a poorly characterized class) play an important role in the detoxification of xenobiotics and stress tolerance. Structural studies were performed on a Tau class fluorodifen-inducible glutathione transferase from Glycine max (GmGSTU4-4) complexed with GSH (2.7 Å) and a product analogue Nb-GSH (1.7 Å). The three-dimensional structure of the GmGSTU4-4-GSH complex revealed that GSH binds in different conformations in the two subunits of the dimer: in an ionized form in one subunit and a non-ionized form in the second subunit. Only the ionized form of the substrate may lead to the formation of a catalytically competent complex. Structural comparison between the GSH and Nb-GSH bound complexes revealed significant differences with respect to the hydrogen-bonding, electrostatic interaction pattern, the upper part of -helix H4 and the C-terminus of the enzyme. These differences indicate an intrasubunit modulation between the G-and Hsites suggesting an induced-fit mechanism of xenobiotic substrate binding. A novel binding site on the surface of the enzyme was also revealed. Bacterial type-II L-asparaginases are used in the treatment of haematopoietic diseases such as acute lymphoblastic leukaemia (ALL) and lymphomas due to their ability to catalyze the conversion of L-asparagine to L-aspartate and ammonia. Escherichia coli and Erwinia chrysanthemi asparaginases are employed for the treatment of ALL for over 30 years. However, serious side-effects affecting the liver and pancreas have been observed due to the intrinsic glutaminase activity of the administered enzymes. Structural studies on Helicobacter pylori L-asparaginase (HpA) were carried out in an effort to discover novel L-asparaginases with potential chemotherapeutic utility in ALL treatment. Detailed analysis of the active site geometry revealed structurally significant differences between HpA and other Lasparaginases that may be important for the biological activities of the enzyme and could be further exploited in protein engineering efforts.

Biomedical Event Extraction with Machine Learning

Biomedical natural language processing (BioNLP) is a subfield of natural language processing, an area of computational linguistics concerned with developing programs that work with natural language: written texts and speech. Biomedical relation extraction concerns the detection of semantic relations such as protein-protein interactions (PPI) from scientific texts. The aim is to enhance information retrieval by detecting relations between concepts, not just individual concepts as with a keyword search. In recent years, events have been proposed as a more detailed alternative for simple pairwise PPI relations. Events provide a systematic, structural representation for annotating the content of natural language texts. Events are characterized by annotated trigger words, directed and typed arguments and the ability to nest other events. For example, the sentence “Protein A causes protein B to bind protein C” can be annotated with the nested event structure CAUSE(A, BIND(B, C)). Converted to such formal representations, the information of natural language texts can be used by computational applications. Biomedical event annotations were introduced by the BioInfer and GENIA corpora, and event extraction was popularized by the BioNLP'09 Shared Task on Event Extraction. In this thesis we present a method for automated event extraction, implemented as the Turku Event Extraction System (TEES). A unified graph format is defined for representing event annotations and the problem of extracting complex event structures is decomposed into a number of independent classification tasks. These classification tasks are solved using SVM and RLS classifiers, utilizing rich feature representations built from full dependency parsing. Building on earlier work on pairwise relation extraction and using a generalized graph representation, the resulting TEES system is capable of detecting binary relations as well as complex event structures. We show that this event extraction system has good performance, reaching the first place in the BioNLP'09 Shared Task on Event Extraction. Subsequently, TEES has achieved several first ranks in the BioNLP'11 and BioNLP'13 Shared Tasks, as well as shown competitive performance in the binary relation Drug-Drug Interaction Extraction 2011 and 2013 shared tasks. The Turku Event Extraction System is published as a freely available open-source project, documenting the research in detail as well as making the method available for practical applications. In particular, in this thesis we describe the application of the event extraction method to PubMed-scale text mining, showing how the developed approach not only shows good performance, but is generalizable and applicable to large-scale real-world text mining projects. Finally, we discuss related literature, summarize the contributions of the work and present some thoughts on future directions for biomedical event extraction. This thesis includes and builds on six original research publications. The first of these introduces the analysis of dependency parses that leads to development of TEES. The entries in the three BioNLP Shared Tasks, as well as in the DDIExtraction 2011 task are covered in four publications, and the sixth one demonstrates the application of the system to PubMed-scale text mining.