Abstract
The increased diversity and scale of published biological data has to led to a growing appreciation for the applications of machine learning and statistical methodologies to gain new insights. Key to achieving this aim is solving the Relationship Extraction problem which specifies the semantic interaction between two or more biological entities in a published study. Here, we employed two deep neural network natural language processing (NLP) methods, namely: the continuous bag of words (CBOW), and the bi-directional long short-term memory (bi-LSTM). These methods were employed to predict relations between entities that describe protein subcellular localisation in plants. We applied our system to 1700 published Arabidopsis protein subcellular studies from the SUBA manually curated dataset. The system combines pre-processing of full-text articles in a machine-readable format with relevant sentence extraction for downstream NLP analysis. Using the SUBA corpus, the neural network classifier predicted interactions between protein name, subcellular localisation and experimental methodology with an average precision, recall rate, accuracy and F1 scores of 95.1%, 82.8%, 89.3% and 88.4% respectively (n = 30). Comparable scoring metrics were obtained using the CropPAL database as an independent testing dataset that stores protein subcellular localisation in crop species, demonstrating wide applicability of prediction model. We provide a framework for extracting protein functional features from unstructured text in the literature with high accuracy, improving data dissemination and unlocking the potential of big data text analytics for generating new hypotheses.
Highlights
The increased diversity and scale of published biological data has to led to a growing appreciation for the applications of machine learning and statistical methodologies to gain new insights
We demonstrate the Bi-LSTM Recurrent Neural Network (RNN) classifier model uses contextual information in the input sentence to predict triplet entity relationships with a high degree of accuracy and can distinguish from input sentences in which the three entities co-occur by chance
This approach can be effective for extracting biological information from unstructured text in a meaningful way that can be made accessible to the research community
Summary
The increased diversity and scale of published biological data has to led to a growing appreciation for the applications of machine learning and statistical methodologies to gain new insights Key to achieving this aim is solving the Relationship Extraction problem which specifies the semantic interaction between two or more biological entities in a published study. We employed two deep neural network natural language processing (NLP) methods, namely: the continuous bag of words (CBOW), and the bi-directional long short-term memory (bi-LSTM) These methods were employed to predict relations between entities that describe protein subcellular localisation in plants. Manual curation makes it difficult for databases to keep up with the ever-increasing amounts of data being generated To address these issues, automated and augmented curation systems for extracting protein functional data from scientific literature are becoming increasingly desired. These types of methods improved the task of relation classification but were suboptimal in the field of relation detection
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
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 call
