Abstract
A rich source of chemical–protein interactions (CPIs) is locked in the exponentially growing biomedical literature. Automatic extraction of CPIs is a crucial task in biomedical natural language processing (NLP), which has great benefits for pharmacological and clinical research. Deep context representation and multihead attention are recent developments in deep learning and have shown their potential in some NLP tasks. Unlike traditional word embedding, deep context representation has the ability to generate comprehensive sentence representation based on the sentence context. The multihead attention mechanism can effectively learn the important features from different heads and emphasize the relatively important features. Integrating deep context representation and multihead attention with a neural network-based model may improve CPI extraction. We present a deep neural model for CPI extraction based on deep context representation and multihead attention. Our model mainly consists of the following three parts: a deep context representation layer, a bidirectional long short-term memory networks (Bi-LSTMs) layer and a multihead attention layer. The deep context representation is employed to provide more comprehensive feature input for Bi-LSTMs. The multihead attention can effectively emphasize the important part of the Bi-LSTMs output. We evaluated our method on the public ChemProt corpus. These experimental results show that both deep context representation and multihead attention are helpful in CPI extraction. Our method can compete with other state-of-the-art methods on ChemProt corpus.
Highlights
Detecting the interactions between chemicals and proteins is a crucial task that plays a key role in precision medicine, drug discovery and basic clinical research [1]
‘Word + Position + part of speech (POS)’: the input representation of the model is the concatenated of word embedding, position embedding and POS embedding
The best performance of chemical–protein interactions (CPIs) extraction is ∼0.64 in F-score. Both the deep context representation and multihead attention strategies are the most recent advantages of deep learning, which could improve the performance of CPI extraction
Summary
Detecting the interactions between chemicals and proteins is a crucial task that plays a key role in precision medicine, drug discovery and basic clinical research [1]. A large amount of valuable chemical–protein interactions (CPIs) are hidden in the biomedical literature. There is an increasing interest in CPI extraction from the biomedical literature. Segura-Bedmar et al [7] employed linguistic patterns to extract DDIs. Currently, models based on deep neural networks have exhibited surprising potential in biomedical relation extraction [8,9,10]. Rois et al [11] proposed an adversarial domain adaptation method to extract PPIs and DDIs. Zhang et al [12] proposed a hybrid deep neural model for biomedical relation extraction from the biomedical literature, which integrates the advantages of convolutional neural networks (CNNs) and recurrent neural networks (RNNs)
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: 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.
