A novel feature selection strategy for enhanced biomedical event extraction using the Turku system

Chinese medical event detection based on event frequency distribution ratio and document consistency

Structured information especially medical events extracted from electronic medical records has extremely practical application value and play a basic role in various intelligent diagnosis and treatment systems. Fine-grained Chinese medical event detection is crucial in the process of structuring Chinese Electronic Medical Record (EMR). The current methods for detecting fine-grained Chinese medical events primarily rely on statistical machine learning and deep learning. However, they have two shortcomings: 1) they neglect to take into account the distribution characteristics of these fine-grained medical events. 2) they overlook the consistency in the distribution of medical events within each individual document. Therefore, this paper presents a fine-grained Chinese medical event detection method, which is based on event frequency distribution ratio and document consistency. To start with, a significant number of Chinese EMR texts are used to adapt the Chinese pre-training model BERT to the domain. Second, based on the fundamental features, the Event Frequency - Event Distribution Ratio (EF-DR) is devised to select distinct event information as supplementary features, taking into account the distribution of events within the EMR. Finally, using EMR document consistency within the model improves the outcome of event detection. Our experiments demonstrate that the proposed method significantly outperforms the baseline model.

LSLSD: Fusion Long Short-Level Semantic Dependency of Chinese EMRs for Event Extraction

Most existing medical event extraction methods have primarily adopted a simplex model based on either pattern matching or deep learning, which ignores the distribution characteristics of entities and events in the medical corpus. They have not categorized the granularity of event elements, leading to the poor generalization ability of the model. This paper proposes a diagnosis and treatment event extraction method in the Chinese language, fusing long short-level semantic dependency of the corpus, LSLSD, for solving these problems. LSLSD can effectively capture different levels of semantic information within and between event sentences in the electronic medical record (EMR) corpus. Moreover, the event arguments are divided into short word-level and long sentence-level, with the sequence annotation and pattern matching combined to realize multi-granularity argument recognition, as well as to improve the generalization ability of the model. Finally, this paper constructs a diagnosis and treatment event data set of Chinese EMRs by proposing a semi-automatic corpus labeling method, and an enormous number of experiment results show that LSLSD can improve the F1-value of event extraction task by 7.1% compared with the several strong baselines.

A Novel Metric to Quantify the Effect of Pathway Enrichment Evaluation With Respect to Biomedical Text-Mined Terms: Development and Feasibility Study

BACKGROUND

Natural language processing has long been applied in various applications for biomedical knowledge inference and discovery. Enrichment analysis based on named entity recognition is a classic application for inferring enriched associations in terms of specific biomedical entities such as gene, chemical, and mutation.

OBJECTIVE

The aim of this study was to investigate the effect of pathway enrichment evaluation with respect to biomedical text-mining results and to develop a novel metric to quantify the effect.

METHODS

Four biomedical text mining methods were selected to represent natural language processing methods on drug-related gene mining. Subsequently, a pathway enrichment experiment was performed by using the mined genes, and a series of inverse pathway frequency (IPF) metrics was proposed accordingly to evaluate the effect of pathway enrichment. Thereafter, 7 IPF metrics and traditional P value metrics were compared in simulation experiments to test the robustness of the proposed metrics.

RESULTS

IPF metrics were evaluated in a case study of rapamycin-related gene set. By applying the best IPF metrics in a pathway enrichment simulation test, a novel discovery of drug efficacy of rapamycin for breast cancer was replicated from the data chosen prior to the year 2000. Our findings show the effectiveness of the best IPF metric in support of knowledge discovery in new drug use. Further, the mechanism underlying the drug-disease association was visualized by Cytoscape.

CONCLUSIONS

The results of this study suggest the effectiveness of the proposed IPF metrics in pathway enrichment evaluation as well as its application in drug use discovery.

Towards Extracting Supporting Information About Predicted Protein-Protein Interactions

One of the goals of relation extraction is to identify protein-protein interactions (PPIs) in biomedical literature. Current systems are capturing binary relations and also the direction and type of an interaction. Besides assisting in the curation PPIs into databases, there has been little real-world application of these algorithms. We describe UPSITE, a text mining tool for extracting evidence in support of a hypothesized interaction. Given a predicted PPI, UPSITE uses a binary relation detector to check whether a PPI is found in abstracts in PubMed. If it is not found, UPSITE retrieves documents relevant to each of the two proteins separately, and extracts contextual information about biological events surrounding each protein, and calculates semantic similarity of the two proteins to provide evidential support for the predicted PPI. In evaluations, relation extraction achieved an Fscore of 0.88 on the HPRD50 corpus, and semantic similarity measured with angular distance was found to be statistically significant. With the development of PPI prediction algorithms, the burden of interpreting the validity and relevance of novel PPIs is on biologists. We suggest that presenting annotations of the two proteins in a PPI side-by-side and a score that quantifies their similarity lessens this burden to some extent.

Knowledge-based biomedical Data Science

Computational manipulation of knowledge is an important, and often under-appreciated, aspect of biomedical Data Science. The first Data Science initiative from the US National Institutes of Health was entitled "Big Data to Knowledge (BD2K)." The main emphasis of the more than $200M allocated to that program has been on "Big Data;" the "Knowledge" component has largely been the implicit assumption that the work will lead to new biomedical knowledge. However, there is long-standing and highly productive work in computational knowledge representation and reasoning, and computational processing of knowledge has a role in the world of Data Science. Knowledge-based biomedical Data Science involves the design and implementation of computer systems that act as if they knew about biomedicine. There are many ways in which a computational approach might act as if it knew something: for example, it might be able to answer a natural language question about a biomedical topic, or pass an exam; it might be able to use existing biomedical knowledge to rank or evaluate hypotheses; it might explain or interpret data in light of prior knowledge, either in a Bayesian or other sort of framework. These are all examples of automated reasoning that act on computational representations of knowledge. After a brief survey of existing approaches to knowledge-based data science, this position paper argues that such research is ripe for expansion, and expanded application.

TEES 2.2: Biomedical Event Extraction for Diverse Corpora

Background

The Turku Event Extraction System (TEES) is a text mining program developed for the extraction of events, complex biomedical relationships, from scientific literature. Based on a graph-generation approach, the system detects events with the use of a rich feature set built via dependency parsing. The TEES system has achieved record performance in several of the shared tasks of its domain, and continues to be used in a variety of biomedical text mining tasks.

Results

The TEES system was quickly adapted to the BioNLP'13 Shared Task in order to provide a public baseline for derived systems. An automated approach was developed for learning the underlying annotation rules of event type, allowing immediate adaptation to the various subtasks, and leading to a first place in four out of eight tasks. The system for the automated learning of annotation rules is further enhanced in this paper to the point of requiring no manual adaptation to any of the BioNLP'13 tasks. Further, the scikit-learn machine learning library is integrated into the system, bringing a wide variety of machine learning methods usable with TEES in addition to the default SVM. A scikit-learn ensemble method is also used to analyze the importances of the features in the TEES feature sets.

Conclusions

The TEES system was introduced for the BioNLP'09 Shared Task and has since then demonstrated good performance in several other shared tasks. By applying the current TEES 2.2 system to multiple corpora from these past shared tasks an overarching analysis of the most promising methods and possible pitfalls in the evolving field of biomedical event extraction are presented.

An Overview of Biomolecular Event Extraction from Scientific Documents

This paper presents a review of state-of-the-art approaches to automatic extraction of biomolecular events from scientific texts. Events involving biomolecules such as genes, transcription factors, or enzymes, for example, have a central role in biological processes and functions and provide valuable information for describing physiological and pathogenesis mechanisms. Event extraction from biomedical literature has a broad range of applications, including support for information retrieval, knowledge summarization, and information extraction and discovery. However, automatic event extraction is a challenging task due to the ambiguity and diversity of natural language and higher-level linguistic phenomena, such as speculations and negations, which occur in biological texts and can lead to misunderstanding or incorrect interpretation. Many strategies have been proposed in the last decade, originating from different research areas such as natural language processing, machine learning, and statistics. This review summarizes the most representative approaches in biomolecular event extraction and presents an analysis of the current state of the art and of commonly used methods, features, and tools. Finally, current research trends and future perspectives are also discussed.