Genetic susceptibility to type 2 diabetes is primarily due to β cell dysfunction. However, a genetic study to directly interrogate β cell function ex vivo has never been previously performed. We isolated 233,447 islets from 483 Diversity Outbred (DO) mice maintained on a Western-style diet, and measured insulin secretion in response to a variety of secretagogues. Insulin secretion from DO islets ranged greater than 1000-fold even though none of the mice were diabetic. The insulin secretory response to each secretagogue had a unique genetic architecture; some of the loci were specific for one condition, whereas others overlapped. Human loci that are syntenic to many of the insulin secretion quantitative trait loci (QTL) from mice are associated with diabetes-related SNPs in human genome-wide association studies. We report on 3 genes, Ptpn18, Hunk, and Zfp148, where the phenotype predictions from the genetic screen were fulfilled in our studies of transgenic mouse models. These 3 genes encode a nonreceptor type protein tyrosine phosphatase, a serine/threonine protein kinase, and a Krϋppel-type zinc-finger transcription factor, respectively. Our results demonstrate that genetic variation in insulin secretion that can lead to type 2 diabetes is discoverable in nondiabetic individuals.
Reviewing the metabolomics literature is becoming increasingly difficult because of the rapid expansion of relevant journal literature. Text-mining technologies are therefore needed to facilitate more efficient literature reviews. Here we contribute a standardised corpus of full-text publications from metabolomics studies and describe the development of two metabolite named entity recognition (NER) methods. These methods are based on Bidirectional Long Short-Term Memory (BiLSTM) networks and each incorporate different transfer learning techniques (for tokenisation and word embedding). Our first model (MetaboListem) follows prior methodology using GloVe word embeddings. Our second model exploits BERT and BioBERT for embedding and is named TABoLiSTM (Transformer-Affixed BiLSTM). The methods are trained on a novel corpus annotated using rule-based methods, and evaluated on manually annotated metabolomics articles. MetaboListem (F1-score 0.890, precision 0.892, recall 0.888) and TABoLiSTM (BioBERT version: F1-score 0.909, precision 0.926, recall 0.893) have achieved state-of-the-art performance on metabolite NER. A training corpus with full-text sentences from >1000 full-text Open Access metabolomics publications with 105,335 annotated metabolites was created, as well as a manually annotated test corpus (19,138 annotations). This work demonstrates that deep learning algorithms are capable of identifying metabolite names accurately and efficiently in text. The proposed corpus and NER algorithms can be used for metabolomics text-mining tasks such as information retrieval, document classification and literature-based discovery and are available from the omicsNLP GitHub repository.
Reviewing the metabolomics literature is becoming increasingly difficult because of the rapid expansion of relevant journal literature. Text-mining technologies are therefore needed to facilitate more efficient literature review. Here we contribute a standardised corpus of full-text publications from metabolomics studies and describe the development of two new metabolite named entity recognition (NER) methods. We introduce two deep learning methods for metabolite NER based on Bidirectional Long Short-Term Memory (BiLSTM) networks incorporating different transfer learning techniques. Our first model (MetaboListem) follows prior methodology using GloVe word embeddings. Our second model exploits BERT and BioBERT for embedding and is named TABoLiSTM (Transformer-Affixed BiLSTM). The methods are trained on a novel corpus annotated using rule-based methods, and evaluated on manually annotated metabolomics articles. MetaboListem (F1 score 0.890, precision 0.892, recall 0.888) and TABoLiSTM (BioBERT version: F1 score 0.909, precision 0.926, recall 0.893) have achieved state-of-the-art performance on metabolite NER. A corpus with >1,200 full-text Open Access metabolomics publications and >116,000 annotated metabolites was created. This work demonstrates that deep learning algorithms are capable of identifying metabolite names accurately and efficiently in text. The proposed corpus and NER algorithms can be used for metabolomics text-mining tasks such as information retrieval, document classification and literature-based discovery. Availability The corpus and NER algorithms are freely available with detailed instructions from Github at https://github.com/omicsNLP/MetaboliteNER.
Motivation The availability of improved natural language processing (NLP) algorithms and models enable researchers to analyse larger corpora using open source tools. Text mining of biomedical literature is one area for which NLP has been used in recent years with large untapped potential. However, in order to generate corpora that can be analyzed using machine learning NLP algorithms, these need to be standardized. Summarizing data from literature to be stored into databases typically requires manual curation, especially for extracting data from result tables. Results We present here an automated pipeline that cleans HTML files from biomedical literature. The output is a single JSON file that contains the text for each section, table data in machine-readable format and lists of phenotypes and abbreviations found in the article. We analyzed a total of 2,441 Open Access articles from PubMed Central, from both Genome-Wide and Metabolome-Wide Association Studies, and developed a model to standardize the section headers based on the Information Artifact Ontology. Extraction of table data was developed on PubMed articles and fine-tuned using the equivalent publisher versions. Availability The Auto-CORPus package is freely available with detailed instructions from Github at https://github.com/jmp111/AutoCORPus/.