Building a protein name dictionary from full text: a machine learning term extraction approach.
Ontology highlight
ABSTRACT: Background
The majority of information in the biological literature resides in full text articles, instead of abstracts. Yet, abstracts remain the focus of many publicly available literature data mining tools. Most literature mining tools rely on pre-existing lexicons of biological names, often extracted from curated gene or protein databases. This is a limitation, because such databases have low coverage of the many name variants which are used to refer to biological entities in the literature.Results
We present an approach to recognize named entities in full text. The approach collects high frequency terms in an article, and uses support vector machines (SVM) to identify biological entity names. It is also computationally efficient and robust to noise commonly found in full text material. We use the method to create a protein name dictionary from a set of 80,528 full text articles. Only 8.3% of the names in this dictionary match SwissProt description lines. We assess the quality of the dictionary by studying its protein name recognition performance in full text.Conclusion
This dictionary term lookup method compares favourably to other published methods, supporting the significance of our direct extraction approach. The method is strong in recognizing name variants not found in SwissProt.
SUBMITTER: Shi L
PROVIDER: S-EPMC1090555 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:Publication metadata help deliver rich analyses of scholarly communication. However, research concepts and ideas are more effectively expressed through unstructured fields such as full texts. Thus, the goals of this paper are to employ a full-text enabled method to extract terms relevant to disciplinary vocabularies, and through them, to understand the relationships between disciplines. This paper uses an efficient, domain-independent term extraction method to extract disciplinary vocabularies from a large multidisciplinary corpus of PLoS ONE publications. It finds a power-law pattern in the frequency distributions of terms present in each discipline, indicating a semantic richness potentially sufficient for further study and advanced analysis. The salient relationships amongst these vocabularies become apparent in application of a principal component analysis. For example, Mathematics and Computer and Information Sciences were found to have similar vocabulary use patterns along with Engineering and Physics; while Chemistry and the Social Sciences were found to exhibit contrasting vocabulary use patterns along with the Earth Sciences and Chemistry. These results have implications to studies of scholarly communication as scholars attempt to identify the epistemological cultures of disciplines, and as a full text-based methodology could lead to machine learning applications in the automated classification of scholarly work according to disciplinary vocabularies.
| S-EPMC5706669 | biostudies-literature
Project description:Text documents can be described by a number of abstract concepts such as semantic category, writing style, or sentiment. Machine learning (ML) models have been trained to automatically map documents to these abstract concepts, allowing to annotate very large text collections, more than could be processed by a human in a lifetime. Besides predicting the text's category very accurately, it is also highly desirable to understand how and why the categorization process takes place. In this paper, we demonstrate that such understanding can be achieved by tracing the classification decision back to individual words using layer-wise relevance propagation (LRP), a recently developed technique for explaining predictions of complex non-linear classifiers. We train two word-based ML models, a convolutional neural network (CNN) and a bag-of-words SVM classifier, on a topic categorization task and adapt the LRP method to decompose the predictions of these models onto words. Resulting scores indicate how much individual words contribute to the overall classification decision. This enables one to distill relevant information from text documents without an explicit semantic information extraction step. We further use the word-wise relevance scores for generating novel vector-based document representations which capture semantic information. Based on these document vectors, we introduce a measure of model explanatory power and show that, although the SVM and CNN models perform similarly in terms of classification accuracy, the latter exhibits a higher level of explainability which makes it more comprehensible for humans and potentially more useful for other applications.
| S-EPMC5553725 | biostudies-other
Project description:BackgroundPhysicians are hesitant to forgo the opportunity of entering unstructured clinical notes for structured data entry in electronic health records. Does free text increase informational value in comparison with structured data?ObjectiveThis study aims to compare information from unstructured text-based chief complaints harvested and processed by a natural language processing (NLP) algorithm with clinician-entered structured diagnoses in terms of their potential utility for automated improvement of patient workflows.MethodsElectronic health records of 293,298 patient visits at the emergency department of a Swiss university hospital from January 2014 to October 2021 were analyzed. Using emergency department overcrowding as a case in point, we compared supervised NLP-based keyword dictionaries of symptom clusters from unstructured clinical notes and clinician-entered chief complaints from a structured drop-down menu with the following 2 outcomes: hospitalization and high Emergency Severity Index (ESI) score.ResultsOf 12 symptom clusters, the NLP cluster was substantial in predicting hospitalization in 11 (92%) clusters; 8 (67%) clusters remained significant even after controlling for the cluster of clinician-determined chief complaints in the model. All 12 NLP symptom clusters were significant in predicting a low ESI score, of which 9 (75%) remained significant when controlling for clinician-determined chief complaints. The correlation between NLP clusters and chief complaints was low (r=-0.04 to 0.6), indicating complementarity of information.ConclusionsThe NLP-derived features and clinicians' knowledge were complementary in explaining patient outcome heterogeneity. They can provide an efficient approach to patient flow management, for example, in an emergency medicine setting. We further demonstrated the feasibility of creating extensive and precise keyword dictionaries with NLP by medical experts without requiring programming knowledge. Using the dictionary, we could classify short and unstructured clinical texts into diagnostic categories defined by the clinician.
| S-EPMC10831590 | biostudies-literature
Project description:BackgroundThe Portable Document Format (PDF) is the most commonly used file format for online scientific publications. The absence of effective means to extract text from these PDF files in a layout-aware manner presents a significant challenge for developers of biomedical text mining or biocuration informatics systems that use published literature as an information source. In this paper we introduce the 'Layout-Aware PDF Text Extraction' (LA-PDFText) system to facilitate accurate extraction of text from PDF files of research articles for use in text mining applications.ResultsOur paper describes the construction and performance of an open source system that extracts text blocks from PDF-formatted full-text research articles and classifies them into logical units based on rules that characterize specific sections. The LA-PDFText system focuses only on the textual content of the research articles and is meant as a baseline for further experiments into more advanced extraction methods that handle multi-modal content, such as images and graphs. The system works in a three-stage process: (1) Detecting contiguous text blocks using spatial layout processing to locate and identify blocks of contiguous text, (2) Classifying text blocks into rhetorical categories using a rule-based method and (3) Stitching classified text blocks together in the correct order resulting in the extraction of text from section-wise grouped blocks. We show that our system can identify text blocks and classify them into rhetorical categories with Precision1 = 0.96% Recall = 0.89% and F1 = 0.91%. We also present an evaluation of the accuracy of the block detection algorithm used in step 2. Additionally, we have compared the accuracy of the text extracted by LA-PDFText to the text from the Open Access subset of PubMed Central. We then compared this accuracy with that of the text extracted by the PDF2Text system, 2commonly used to extract text from PDF. Finally, we discuss preliminary error analysis for our system and identify further areas of improvement.ConclusionsLA-PDFText is an open-source tool for accurately extracting text from full-text scientific articles. The release of the system is available at http://code.google.com/p/lapdftext/.
| S-EPMC3441580 | biostudies-literature
Project description:Protein kinases generate nearly a thousand different protein products and regulate the majority of cellular pathways and signal transduction. It is therefore not surprising that the deregulation of kinases has been implicated in many disease states. In fact, kinase inhibitors are the largest class of new cancer therapies. Understanding polypharmacology within the full kinome, how drugs interact with many different kinases, would allow for the development of safer and more efficacious cancer therapies. A full understanding of these interactions is not experimentally feasible making highly accurate computational predictions extremely useful and important. This work aims at making a machine learning model useful for investigating the full kinome. We evaluate many feature sets for our model and get better performance over molecular docking with all of them. We demonstrate that you can achieve a nearly 60% increase in success rate at identifying binding compounds using our model over molecular docking scores.
| S-EPMC5961802 | biostudies-literature
Project description:In several author name disambiguation studies, some ethnic name groups such as East Asian names are reported to be more difficult to disambiguate than others. This implies that disambiguation approaches might be improved if ethnic name groups are distinguished before disambiguation. We explore the potential of ethnic name partitioning by comparing performance of four machine learning algorithms trained and tested on the entire data or specifically on individual name groups. Results show that ethnicity-based name partitioning can substantially improve disambiguation performance because the individual models are better suited for their respective name group. The improvements occur across all ethnic name groups with different magnitudes. Performance gains in predicting matched name pairs outweigh losses in predicting nonmatched pairs. Feature (e.g., coauthor name) similarities of name pairs vary across ethnic name groups. Such differences may enable the development of ethnicity-specific feature weights to improve prediction for specific ethic name categories. These findings are observed for three labeled data with a natural distribution of problem sizes as well as one in which all ethnic name groups are controlled for the same sizes of ambiguous names. This study is expected to motive scholars to group author names based on ethnicity prior to disambiguation.
| S-EPMC8359369 | biostudies-literature
Project description:As part of its core business of gathering population-based information on new cancer diagnoses, the Belgian Cancer Registry receives free-text pathology reports, describing results of (pre-)malignant specimens. These reports are provided by 82 laboratories and written in 2 national languages, Dutch or French. For breast cancer, the reports characterize the status of estrogen receptor, progesterone receptor, and Erb-b2 receptor tyrosine kinase 2. These biomarkers are related with tumor growth and prognosis and are essential to define therapeutic management. The availability of population-scale information about their status in breast cancer patients can therefore be considered crucial to enrich real-world scientific studies and to guide public health policies regarding personalized medicine. The main objective of this study is to expand the data available at the Belgian Cancer Registry by automatically extracting the status of these biomarkers from the pathology reports. Various types of numeric features are computed from over 1,300 manually annotated reports linked to breast tumors diagnosed in 2014. A range of popular machine learning classifiers, such as support vector machines, random forests and logistic regressions, are trained on this data and compared using their F 1 scores on a separate validation set. On a held-out test set, the best performing classifiers achieve F 1 scores ranging from 0.89 to 0.92 for the four classification tasks. The extraction is thus reliable and allows to significantly increase the availability of this valuable information on breast cancer receptor status at a population level.
| S-EPMC8522027 | biostudies-literature
Project description:Zeolites are porous, aluminosilicate materials with many industrial and "green" applications. Despite their industrial relevance, many aspects of zeolite synthesis remain poorly understood requiring costly trial and error synthesis. In this paper, we create natural language processing techniques and text markup parsing tools to automatically extract synthesis information and trends from zeolite journal articles. We further engineer a data set of germanium-containing zeolites to test the accuracy of the extracted data and to discover potential opportunities for zeolites containing germanium. We also create a regression model for a zeolite's framework density from the synthesis conditions. This model has a cross-validated root mean squared error of 0.98 T/1000 Å3, and many of the model decision boundaries correspond to known synthesis heuristics in germanium-containing zeolites. We propose that this automatic data extraction can be applied to many different problems in zeolite synthesis and enable novel zeolite morphologies.
| S-EPMC6535764 | biostudies-literature
Project description:MOTIVATION:A complete repository of gene-gene interactions is key for understanding cellular processes, human disease and drug response. These gene-gene interactions include both protein-protein interactions and transcription factor interactions. The majority of known interactions are found in the biomedical literature. Interaction databases, such as BioGRID and ChEA, annotate these gene-gene interactions; however, curation becomes difficult as the literature grows exponentially. DeepDive is a trained system for extracting information from a variety of sources, including text. In this work, we used DeepDive to extract both protein-protein and transcription factor interactions from over 100,000 full-text PLOS articles. METHODS:We built an extractor for gene-gene interactions that identified candidate gene-gene relations within an input sentence. For each candidate relation, DeepDive computed a probability that the relation was a correct interaction. We evaluated this system against the Database of Interacting Proteins and against randomly curated extractions. RESULTS:Our system achieved 76% precision and 49% recall in extracting direct and indirect interactions involving gene symbols co-occurring in a sentence. For randomly curated extractions, the system achieved between 62% and 83% precision based on direct or indirect interactions, as well as sentence-level and document-level precision. Overall, our system extracted 3356 unique gene pairs using 724 features from over 100,000 full-text articles. AVAILABILITY AND IMPLEMENTATION:Application source code is publicly available at https://github.com/edoughty/deepdive_genegene_app CONTACT:russ.altman@stanford.edu SUPPLEMENTARY INFORMATION:Supplementary data are available at Bioinformatics online.
| S-EPMC4681986 | biostudies-literature
Project description:The understanding of the nature and structure of energy use in large buildings is vital for defining novel energy and climate change strategies. The advances on metering technology and low-cost devices make it possible to form a submetering network, which measures the main supply and other intermediate points providing information of the behavior of different areas. However, an analysis by means of classical techniques can lead to wrong conclusions if the load is not balanced. This paper proposes the use of a deep convolutional autoencoder to reconstruct the whole consumption measured by the submeters using the learnt features in order to analyze the behavior of different building areas. The display of weights and information of the latent space provided by the autoencoder allows us to obtain precise details of the influence of each area in the whole building consumption and its dependence on external factors such as temperature. A submetering network is deployed in the León University Hospital building in order to test the proposed methodology. The results show different correlations between environmental variables and building areas and indicate that areas can be grouped depending on their function in the building performance. Furthermore, this approach is able to provide discernible results in the presence of large differences with respect to the consumption ranges of the different areas, unlike conventional approaches where the influence of smaller areas is usually hidden.
| S-EPMC7374320 | biostudies-literature