Abstract
Medicinal chemistry patents contain rich information about chemical compounds. Although much effort has been devoted to extracting chemical entities from scientific literature, limited numbers of patent mining systems are publically available, probably due to the lack of large manually annotated corpora. To accelerate the development of information extraction systems for medicinal chemistry patents, the 2015 BioCreative V challenge organized a track on Chemical and Drug Named Entity Recognition from patent text (CHEMDNER patents). This track included three individual subtasks: (i) Chemical Entity Mention Recognition in Patents (CEMP), (ii) Chemical Passage Detection (CPD) and (iii) Gene and Protein Related Object task (GPRO). We participated in the two subtasks of CEMP and CPD using machine learning-based systems. Our machine learning-based systems employed the algorithms of conditional random fields (CRF) and structured support vector machines (SSVMs), respectively. To improve the performance of the NER systems, two strategies were proposed for feature engineering: (i) domain knowledge features of dictionaries, chemical structural patterns and semantic type information present in the context of the candidate chemical and (ii) unsupervised feature learning algorithms to generate word representation features by Brown clustering and a novel binarized Word embedding to enhance the generalizability of the system. Further, the system output for the CPD task was yielded based on the patent titles and abstracts with chemicals recognized in the CEMP task.The effects of the proposed feature strategies on both the machine learning-based systems were investigated. Our best system achieved the second best performance among 21 participating teams in CEMP with a precision of 87.18%, a recall of 90.78% and a F-measure of 88.94% and was the top performing system among nine participating teams in CPD with a sensitivity of 98.60%, a specificity of 87.21%, an accuracy of 94.75%, a Matthew’s correlation coefficient (MCC) of 88.24%, a precision at full recall (P_full_R) of 66.57% and an area under the precision-recall curve (AUC_PR) of 0.9347. The SSVM-based CEMP systems outperformed the CRF-based CEMP systems when using the same features. Features generated from both the domain knowledge and unsupervised learning algorithms significantly improved the chemical NER task on patents.Database URL: http:// database. oxfordjournals. org/ content/ 2016/ baw049
Highlights
Chemical compounds and drugs mentioned in scientific text are crucial for many computational applications in the biomedical domain, such as drug repurposing [1] and construction of gene–chemical interaction pathways [2]
In addition to the development of chemical/drug databases such as PubChem [3], ChEBI [4], ChemSpider [5] and DrugBank [6], extensive efforts have been applied for extraction of chemical information from rich textual sources such as biomedical literature
To enlarge the training dataset for patent chemical NER, several studies leveraged the corpora from other resources, such as the CHEMDNER corpus built from biomedical literature [22, 23], and the DDI corpus [20, 23] built from both DrugBank and biomedical literature
Summary
Chemical compounds and drugs mentioned in scientific text are crucial for many computational applications in the biomedical domain, such as drug repurposing [1] and construction of gene–chemical interaction pathways [2]. In addition to the development of chemical/drug databases such as PubChem [3], ChEBI [4], ChemSpider [5] and DrugBank [6], extensive efforts have been applied for extraction of chemical information from rich textual sources such as biomedical literature. The BioCreative IV Chemical and Drug Named Entity Recognition (CHEMDNER) challenge promoted the development of chemical NER systems for scientific literature, by providing a large-scale standard corpus [7]. No comparative evaluation of different chemical NER systems has been conducted on a large annotated corpus of patents. It is not clear how different types of features contribute to the performance of chemical NER systems for patent documents
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.