Haibin Liu

BioLemmatizer: a lemmatization tool for morphological processing of biomedical text

BackgroundThe wide variety of morphological variants of domain-specific technical terms contributes to the complexity of performing natural language processing of the scientific literature related to molecular biology. For morphological analysis of these texts, lemmatization has been actively applied in the recent biomedical research.ResultsIn this work, we developed a domain-specific lemmatization tool, BioLemmatizer, for the morphological analysis of biomedical literature. The tool focuses on the inflectional morphology of English and is based on the general English lemmatization tool MorphAdorner. The BioLemmatizer is further tailored to the biological domain through incorporation of several published lexical resources. It retrieves lemmas based on the use of a word lexicon, and defines a set of rules that transform a word to a lemma if it is not encountered in the lexicon. An innovative aspect of the BioLemmatizer is the use of a hierarchical strategy for searching the lexicon, which enables the discovery of the correct lemma even if the input Part-of-Speech information is inaccurate. The BioLemmatizer achieves an accuracy of 97.5% in lemmatizing an evaluation set prepared from the CRAFT corpus, a collection of full-text biomedical articles, and an accuracy of 97.6% on the LLL05 corpus. The contribution of the BioLemmatizer to accuracy improvement of a practical information extraction task is further demonstrated when it is used as a component in a biomedical text mining system.ConclusionsThe BioLemmatizer outperforms other tools when compared with eight existing lemmatizers. The BioLemmatizer is released as an open source software and can be downloaded from http://biolemmatizer.sourceforge.net.

Extracting drug-drug interactions from literature using a rich feature-based linear kernel approach

Identifying unknown drug interactions is of great benefit in the early detection of adverse drug reactions. Despite existence of several resources for drug-drug interaction (DDI) information, the wealth of such information is buried in a body of unstructured medical text which is growing exponentially. This calls for developing text mining techniques for identifying DDIs. The state-of-the-art DDI extraction methods use Support Vector Machines (SVMs) with non-linear composite kernels to explore diverse contexts in literature. While computationally less expensive, linear kernel-based systems have not achieved a comparable performance in DDI extraction tasks. In this work, we propose an efficient and scalable system using a linear kernel to identify DDI information. The proposed approach consists of two steps: identifying DDIs and assigning one of four different DDI types to the predicted drug pairs. We demonstrate that when equipped with a rich set of lexical and syntactic features, a linear SVM classifier is able to achieve a competitive performance in detecting DDIs. In addition, the one-against-one strategy proves vital for addressing an imbalance issue in DDI type classification. Applied to the DDIExtraction 2013 corpus, our system achieves an F1 score of 0.670, as compared to 0.651 and 0.609 reported by the top two participating teams in the DDIExtraction 2013 challenge, both based on non-linear kernel methods.

Approximate Subgraph Matching-Based Literature Mining for Biomedical Events and Relations

The biomedical text mining community has focused on developing techniques to automatically extract important relations between biological components and semantic events involving genes or proteins from literature. In this paper, we propose a novel approach for mining relations and events in the biomedical literature using approximate subgraph matching. Extraction of such knowledge is performed by searching for an approximate subgraph isomorphism between key contextual dependencies and input sentence graphs. Our approach significantly increases the chance of retrieving relations or events encoded within complex dependency contexts by introducing error tolerance into the graph matching process, while maintaining the extraction precision at a high level. When evaluated on practical tasks, it achieves a 51.12% F-score in extracting nine types of biological events on the GE task of the BioNLP-ST 2011 and an 84.22% F-score in detecting protein-residue associations. The performance is comparable to the reported systems across these tasks, and thus demonstrates the generalizability of our proposed approach.

Natural language processing pipelines to annotate BioC collections with an application to the NCBI disease corpus

BioC is a new format and associated code libraries for sharing text and annotations. We have implemented BioC natural language preprocessing pipelines in two popular programming languages: C++ and Java. The current implementations interface with the well-known MedPost and Stanford natural language processing tool sets. The pipeline functionality includes sentence segmentation, tokenization, part-of-speech tagging, lemmatization and sentence parsing. These pipelines can be easily integrated along with other BioC programs into any BioC compliant text mining systems. As an application, we converted the NCBI disease corpus to BioC format, and the pipelines have successfully run on this corpus to demonstrate their functionality. Code and data can be downloaded from http://bioc.sourceforge.net. Database URL: http://bioc.sourceforge.net

Pattern Learning through Distant Supervision for Extraction of Protein-Residue Associations in the Biomedical Literature

We propose a method enabling automatic extraction of protein-specific residues from the biomedical literature. We aim to associate mentions of specific amino acids to the protein of which the residue forms a part. The methods presented in this work will enable improved protein functional site extraction from articles, ultimately supporting protein function prediction. Our method made use of linguistic patterns for identifying the amino acid residue mentions in text. Further, we applied an automated graph-based method to learn syntactic and semantic patterns corresponding to protein-residue pairs mentioned in the text. On a new automatically generated data set of high confidence protein-residue relationship sentences, established through distant supervision, the method achieved a F-measure of 0.78. This work will pave the way to improved extraction of protein functional residues from the literature.

Identifying Interaction Sentences from Biological Literature Using Automatically Extracted Patterns

An important task in information retrieval is to identify sentences that contain important relationships between key concepts. In this work, we propose a novel approach to automatically extract sentence patterns that contain interactions involving concepts of molecular biology. A pattern is defined in this work as a sequence of specialized Part-of-Speech (POS) tags that capture the structure of key sentences in the scientific literature. Each candidate sentence for the classification task is encoded as a POS array and then aligned to a collection of pre-extracted patterns. The quality of the alignment is expressed as a pairwise alignment score. The most innovative component of this work is the use of a Genetic Algorithm (GA) to maximize the classification performance of the alignment scoring scheme. The system achieves an F-score of 0.834 in identifying sentences which describe interactions between biological entities. This performance is mostly affected by the quality of the preprocessing steps such as term identification and POS tagging.

EXPLORING A SUBGRAPH MATCHING APPROACH FOR EXTRACTING BIOLOGICAL EVENTS FROM LITERATURE

An important task in biological information extraction is to identify descriptions of biological relations and events involving genes or proteins. In this work, we propose a graph‐based approach to automatically learn rules for detecting biological events in the life science literature. The event rules are learned by identifying the key contextual dependencies from full parsing of annotated text. The detection is performed by searching for isomorphism between event rules and the dependency graphs of complete sentences. When applying our approach to the data sets of the Task 1 of the BioNLP‐ST 2009, we achieved a 40.71% F‐score in detecting biological events across nine event types. Our 56.32% precision is comparable with the state‐of‐the‐art systems. The approach may also be generalized to extract events from other domains where training data are available because it requires neither manual intervention nor external domain‐specific resources. The subgraph matching algorithm we developed is released under the new BSD license and can be downloaded from http://esmalgorithm.sourceforge.net.

Sentence identification of biological interactions using PATRICIA tree generated patterns and genetic algorithm optimized parameters

An important task in information retrieval is to identify sentences that contain important relationships between key concepts. In this work, we propose a novel approach to automatically extract sentence patterns that contain interactions involving concepts of molecular biology. A pattern is defined in this work as a sequence of specialized Part-of-Speech (POS) tags that capture the structure of key sentences in the scientific literature. Each candidate sentence for the classification task is encoded as a POS array and then aligned to a collection of pre-extracted patterns. The quality of the alignment is expressed as a pairwise alignment score. The most innovative component of this work is the use of a genetic algorithm (GA) to maximize the classification performance of the alignment scoring scheme. The system achieves an average F-score of 0.796 in identifying sentences which describe interactions between co-occurring biological concepts. This performance is mostly affected by the quality of the preprocessing steps such as term identification and POS tagging.

Optimizing graph-based patterns to extract biomedical events from the literature.

In BioNLP-ST 2013We participated in the BioNLP 2013 shared tasks on event extraction. Our extraction method is based on the search for an approximate subgraph isomorphism between key context dependencies of events and graphs of input sentences. Our system was able to address both the GENIA (GE) task focusing on 13 molecular biology related event types and the Cancer Genetics (CG) task targeting a challenging group of 40 cancer biology related event types with varying arguments concerning 18 kinds of biological entities. In addition to adapting our system to the two tasks, we also attempted to integrate semantics into the graph matching scheme using a distributional similarity model for more events, and evaluated the event extraction impact of using paths of all possible lengths as key context dependencies beyond using only the shortest paths in our system. We achieved a 46.38% F-score in the CG task (ranking 3rd) and a 48.93% F-score in the GE task (ranking 4th).After BioNLP-ST 2013We explored three ways to further extend our event extraction system in our previously published work: (1) We allow non-essential nodes to be skipped, and incorporated a node skipping penalty into the subgraph distance function of our approximate subgraph matching algorithm. (2) Instead of assigning a unified subgraph distance threshold to all patterns of an event type, we learned a customized threshold for each pattern. (3) We implemented the well-known Empirical Risk Minimization (ERM) principle to optimize the event pattern set by balancing prediction errors on training data against regularization. When evaluated on the official GE task test data, these extensions help to improve the extraction precision from 62% to 65%. However, the overall F-score stays equivalent to the previous performance due to a 1% drop in recall.

Finding optimal parameters for edit distance based sequence classification is NP-hard

Parametric edit distance based classification has been applied to two significant problems in the bioinformatics area: biological sequence analysis (DNA, RNA, protein), and semantic relationship extraction from biomedical scientific literature. This method is based on the edit distance measure on sequences, with parametric costs for matching, mismatching, inserts, and deletes of letters. We present a proof that finding optimal parameter values for such classification based on training data is an NP-hard problem, which is an important claim to justify the use of heuristic methods for determining the best parameter values.