Dataset Information

Learning the Structure of Biomedical Relationships from Unstructured Text.

ABSTRACT: The published biomedical research literature encompasses most of our understanding of how drugs interact with gene products to produce physiological responses (phenotypes). Unfortunately, this information is distributed throughout the unstructured text of over 23 million articles. The creation of structured resources that catalog the relationships between drugs and genes would accelerate the translation of basic molecular knowledge into discoveries of genomic biomarkers for drug response and prediction of unexpected drug-drug interactions. Extracting these relationships from natural language sentences on such a large scale, however, requires text mining algorithms that can recognize when different-looking statements are expressing similar ideas. Here we describe a novel algorithm, Ensemble Biclustering for Classification (EBC), that learns the structure of biomedical relationships automatically from text, overcoming differences in word choice and sentence structure. We validate EBC's performance against manually-curated sets of (1) pharmacogenomic relationships from PharmGKB and (2) drug-target relationships from DrugBank, and use it to discover new drug-gene relationships for both knowledge bases. We then apply EBC to map the complete universe of drug-gene relationships based on their descriptions in Medline, revealing unexpected structure that challenges current notions about how these relationships are expressed in text. For instance, we learn that newer experimental findings are described in consistently different ways than established knowledge, and that seemingly pure classes of relationships can exhibit interesting chimeric structure. The EBC algorithm is flexible and adaptable to a wide range of problems in biomedical text mining.

SUBMITTER: Percha B

PROVIDER: S-EPMC4517797 | biostudies-literature | 2015 Jul

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Learning the Structure of Biomedical Relationships from Unstructured Text.

Percha Bethany B Altman Russ B RB

PLoS computational biology 20150728 7

The published biomedical research literature encompasses most of our understanding of how drugs interact with gene products to produce physiological responses (phenotypes). Unfortunately, this information is distributed throughout the unstructured text of over 23 million articles. The creation of structured resources that catalog the relationships between drugs and genes would accelerate the translation of basic molecular knowledge into discoveries of genomic biomarkers for drug response and pre ...[more]

PMID: 26219079

Similar Datasets

Project description:BackgroundAlthough there are many studies of drugs and their side effects, the underlying mechanisms of these side effects are not well understood. It is also difficult to understand the specific pathways between drugs and side effects.ObjectiveThe present study seeks to construct putative paths between drugs and their side effects by applying text-mining techniques to free text of biomedical studies, and to develop ranking metrics that could identify the most-likely paths.Materials and methodsWe extracted three types of relationships-drug-protein, protein-protein, and protein?side effect-from biomedical texts by using text mining and predefined relation-extraction rules. Based on the extracted relationships, we constructed whole drug-protein?side effect paths. For each path, we calculated its ranking score by a new ranking function that combines corpus- and ontology-based semantic similarity as well as co-occurrence frequency.ResultsWe extracted 13 plausible biomedical paths connecting drugs and their side effects from cancer-related abstracts in the PubMed database. The top 20 paths were examined, and the proposed ranking function outperformed the other methods tested, including co-occurrence, COALS, and UMLS by P@5-P@20. In addition, we confirmed that the paths are novel hypotheses that are worth investigating further.DiscussionThe risk of side effects has been an important issue for the US Food and Drug Administration (FDA). However, the causes and mechanisms of such side effects have not been fully elucidated. This study extends previous research on understanding drug side effects by using various techniques such as Named Entity Recognition (NER), Relation Extraction (RE), and semantic similarity.ConclusionIt is not easy to reveal the biomedical mechanisms of side effects due to a huge number of possible paths. However, we automatically generated predictable paths using the proposed approach, which could provide meaningful information to biomedical researchers to generate plausible hypotheses for the understanding of such mechanisms.

Project description:MotivationThe biomedical community's collective understanding of how chemicals, genes and phenotypes interact is distributed across the text of over 24 million research articles. These interactions offer insights into the mechanisms behind higher order biochemical phenomena, such as drug-drug interactions and variations in drug response across individuals. To assist their curation at scale, we must understand what relationship types are possible and map unstructured natural language descriptions onto these structured classes. We used NCBI's PubTator annotations to identify instances of chemical, gene and disease names in Medline abstracts and applied the Stanford dependency parser to find connecting dependency paths between pairs of entities in single sentences. We combined a published ensemble biclustering algorithm (EBC) with hierarchical clustering to group the dependency paths into semantically-related categories, which we annotated with labels, or 'themes' ('inhibition' and 'activation', for example). We evaluated our theme assignments against six human-curated databases: DrugBank, Reactome, SIDER, the Therapeutic Target Database, OMIM and PharmGKB.ResultsClustering revealed 10 broad themes for chemical-gene relationships, 7 for chemical-disease, 10 for gene-disease and 9 for gene-gene. In most cases, enriched themes corresponded directly to known database relationships. Our final dataset, represented as a network, contained 37 491 thematically-labeled chemical-gene edges, 2 021 192 chemical-disease edges, 136 206 gene-disease edges and 41 418 gene-gene edges, each representing a single-sentence description of an interaction from somewhere in the literature.Availability and implementationThe complete network is available on Zenodo (https://zenodo.org/record/1035500). We have also provided the full set of dependency paths connecting biomedical entities in Medline abstracts, with associated sentences, for future use by the biomedical research community.Supplementary informationSupplementary data are available at Bioinformatics online.

Project description:The practice of precision medicine will ultimately require databases of genes and mutations for healthcare providers to reference in order to understand the clinical implications of each patient's genetic makeup. Although the highest quality databases require manual curation, text mining tools can facilitate the curation process, increasing accuracy, coverage, and productivity. However, to date there are no available text mining tools that offer high-accuracy performance for extracting such triplets from biomedical literature. In this paper we propose a high-performance machine learning approach to automate the extraction of disease-gene-variant triplets from biomedical literature. Our approach is unique because we identify the genes and protein products associated with each mutation from not just the local text content, but from a global context as well (from the Internet and from all literature in PubMed). Our approach also incorporates protein sequence validation and disease association using a novel text-mining-based machine learning approach. We extract disease-gene-variant triplets from all abstracts in PubMed related to a set of ten important diseases (breast cancer, prostate cancer, pancreatic cancer, lung cancer, acute myeloid leukemia, Alzheimer's disease, hemochromatosis, age-related macular degeneration (AMD), diabetes mellitus, and cystic fibrosis). We then evaluate our approach in two ways: (1) a direct comparison with the state of the art using benchmark datasets; (2) a validation study comparing the results of our approach with entries in a popular human-curated database (UniProt) for each of the previously mentioned diseases. In the benchmark comparison, our full approach achieves a 28% improvement in F1-measure (from 0.62 to 0.79) over the state-of-the-art results. For the validation study with UniProt Knowledgebase (KB), we present a thorough analysis of the results and errors. Across all diseases, our approach returned 272 triplets (disease-gene-variant) that overlapped with entries in UniProt and 5,384 triplets without overlap in UniProt. Analysis of the overlapping triplets and of a stratified sample of the non-overlapping triplets revealed accuracies of 93% and 80% for the respective categories (cumulative accuracy, 77%). We conclude that our process represents an important and broadly applicable improvement to the state of the art for curation of disease-gene-variant relationships.

Project description:Unstructured clinical narratives are continuously being recorded as part of delivery of care in electronic health records, and dedicated tagging staff spend considerable effort manually assigning clinical codes for billing purposes. Despite these efforts, however, label availability and accuracy are both suboptimal. In this retrospective study, we aimed to automate the assignment of top-level International Classification of Diseases version 9 (ICD-9) codes to clinical records from human and veterinary data stores using minimal manual labor and feature curation. Automating top-level annotations could in turn enable rapid cohort identification, especially in a veterinary setting. To this end, we trained long short-term memory (LSTM) recurrent neural networks (RNNs) on 52,722 human and 89,591 veterinary records. We investigated the accuracy of both separate-domain and combined-domain models and probed model portability. We established relevant baseline classification performances by training Decision Trees (DT) and Random Forests (RF). We also investigated whether transforming the data using MetaMap Lite, a clinical natural language processing tool, affected classification performance. We showed that the LSTM-RNNs accurately classify veterinary and human text narratives into top-level categories with an average weighted macro F1 score of 0.74 and 0.68 respectively. In the "neoplasia" category, the model trained on veterinary data had a high validation accuracy in veterinary data and moderate accuracy in human data, with F1 scores of 0.91 and 0.70 respectively. Our LSTM method scored slightly higher than that of the DT and RF models. The use of LSTM-RNN models represents a scalable structure that could prove useful in cohort identification for comparative oncology studies. Digitization of human and veterinary health information will continue to be a reality, particularly in the form of unstructured narratives. Our approach is a step forward for these two domains to learn from and inform one another.

Project description:Computational methods have been used to find duplicate biomedical publications in MEDLINE. Full text articles are becoming increasingly available, yet the similarities among them have not been systematically studied. Here, we quantitatively investigated the full text similarity of biomedical publications in PubMed Central.72,011 full text articles from PubMed Central (PMC) were parsed to generate three different datasets: full texts, sections, and paragraphs. Text similarity comparisons were performed on these datasets using the text similarity algorithm eTBLAST. We measured the frequency of similar text pairs and compared it among different datasets. We found that high abstract similarity can be used to predict high full text similarity with a specificity of 20.1% (95% CI [17.3%, 23.1%]) and sensitivity of 99.999%. Abstract similarity and full text similarity have a moderate correlation (Pearson correlation coefficient: -0.423) when the similarity ratio is above 0.4. Among pairs of articles in PMC, method sections are found to be the most repetitive (frequency of similar pairs, methods: 0.029, introduction: 0.0076, results: 0.0043). In contrast, among a set of manually verified duplicate articles, results are the most repetitive sections (frequency of similar pairs, results: 0.94, methods: 0.89, introduction: 0.82). Repetition of introduction and methods sections is more likely to be committed by the same authors (odds of a highly similar pair having at least one shared author, introduction: 2.31, methods: 1.83, results: 1.03). There is also significantly more similarity in pairs of review articles than in pairs containing one review and one nonreview paper (frequency of similar pairs: 0.0167 and 0.0023, respectively).While quantifying abstract similarity is an effective approach for finding duplicate citations, a comprehensive full text analysis is necessary to uncover all potential duplicate citations in the scientific literature and is helpful when establishing ethical guidelines for scientific publications.

Project description:BackgroundDischarge medical notes written by physicians contain important information about the health condition of patients. Many deep learning algorithms have been successfully applied to extract important information from unstructured medical notes data that can entail subsequent actionable results in the medical domain. This study aims to explore the model performance of various deep learning algorithms in text classification tasks on medical notes with respect to different disease class imbalance scenarios.MethodsIn this study, we employed seven artificial intelligence models, a CNN (Convolutional Neural Network), a Transformer encoder, a pretrained BERT (Bidirectional Encoder Representations from Transformers), and four typical sequence neural networks models, namely, RNN (Recurrent Neural Network), GRU (Gated Recurrent Unit), LSTM (Long Short-Term Memory), and Bi-LSTM (Bi-directional Long Short-Term Memory) to classify the presence or absence of 16 disease conditions from patients' discharge summary notes. We analyzed this question as a composition of 16 binary separate classification problems. The model performance of the seven models on each of the 16 datasets with various levels of imbalance between classes were compared in terms of AUC-ROC (Area Under the Curve of the Receiver Operating Characteristic), AUC-PR (Area Under the Curve of Precision and Recall), F1 Score, and Balanced Accuracy as well as the training time. The model performances were also compared in combination with different word embedding approaches (GloVe, BioWordVec, and no pre-trained word embeddings).ResultsThe analyses of these 16 binary classification problems showed that the Transformer encoder model performs the best in nearly all scenarios. In addition, when the disease prevalence is close to or greater than 50%, the Convolutional Neural Network model achieved a comparable performance to the Transformer encoder, and its training time was 17.6% shorter than the second fastest model, 91.3% shorter than the Transformer encoder, and 94.7% shorter than the pre-trained BERT-Base model. The BioWordVec embeddings slightly improved the performance of the Bi-LSTM model in most disease prevalence scenarios, while the CNN model performed better without pre-trained word embeddings. In addition, the training time was significantly reduced with the GloVe embeddings for all models.ConclusionsFor classification tasks on medical notes, Transformer encoders are the best choice if the computation resource is not an issue. Otherwise, when the classes are relatively balanced, CNNs are a leading candidate because of their competitive performance and computational efficiency.

Dataset Information

Learning the Structure of Biomedical Relationships from Unstructured Text.

Publications

Learning the Structure of Biomedical Relationships from Unstructured Text.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets