BelSmile: a biomedical semantic role labeling approach for extracting biological expression language from text

Abstract

Biological expression language (BEL) is one of the most popular languages to represent the causal and correlative relationships among biological events. Automatically extracting and representing biomedical events using BEL can help biologists quickly survey and understand relevant literature. Recently, many researchers have shown interest in biomedical event extraction. However, the task is still a challenge for current systems because of the complexity of integrating different information extraction tasks such as named entity recognition (NER), named entity normalization (NEN) and relation extraction into a single system. In this study, we introduce our BelSmile system, which uses a semantic-role-labeling (SRL)-based approach to extract the NEs and events for BEL statements. BelSmile combines our previous NER, NEN and SRL systems. We evaluate BelSmile using the BioCreative V BEL task dataset. Our system achieved an F-score of 27.8%, ∼7% higher than the top BioCreative V system. The three main contributions of this study are (i) an effective pipeline approach to extract BEL statements, and (ii) a syntactic-based labeler to extract subject–verb–object tuples. We also implement a web-based version of BelSmile (iii) that is publicly available at iisrserv.csie.ncu.edu.tw/belsmile.

Statistical principle-based approach for gene and protein related object recognition

“…The table is constructed by using protein records of UniProt database. To allow more mentions mapped to their IDs, we use heuristic rules [19], like converting to lower cases, removing the symbols, removing the named entity suffix “s” . If two or more matching IDs are found, we use the Entrez homolog dictionary to normalize homolog IDs to human IDs.…”

Navigating the disease landscape: knowledge representations for contextualizing molecular signatures

“…For this reason, TM will be increasingly important for supporting this process [63]. Already existing examples include the BEL Information Extraction workFlow (BELIEF) system and BELSmile [64]. These frameworks work by using automated TM to detect BEL concepts and relationships and then allowing the curators to explore and annotate their biological contexts to create final high-quality networks.…”

“…During the competition, the best result was achieved by the BELMiner framework [122], which used a rule-based approach for extraction of BEL statements from text and got the highest F -measure of 20% for this task. After the challenge, BELSmile system was developed that reached an even better score of 28% on the same dataset [64]. BELSmile implemented a semantic-role-labelling approach, which relies on recognition of verbs (predicates) and assignment of roles to associated subjects/objects relative to that verb.…”

BEL Commons: an environment for exploration and analysis of networks encoded in Biological Expression Language

“…Reading and Assembling Contextual and Holistic Mechanisms from Text (REACH) (6), TRIPS (7), Turku Event Extraction System (TEES) (8), MedScan (9)] and several BEL-specific workflows [e.g. Biological Expression Language Information Extraction WorkFlow (BELIEF) (10), BELMiner (11), BelSmile (12), BELTracker (13)] have been developed to automate biological relation extraction. The limits of the precision and recall of automated techniques, the applicability domains of different modeling languages and the need for expert input motivated the development of semi-automatic and manual curation interfaces [e.g.…”