Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “Natural Language Processing”

Search indexed PubMed citations on genomics, clinical trials, systematic reviews and public health. Explore titles, authors and supplied subject terms, then open the PubMed record.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 289 records · Page 16Linked to original sources
PubMed2000

Knowledge representation and indexing using the unified medical language system.

Ontologies and semantic frameworks can be used to improve the accuracy and expressiveness of natural language processing for the purpose of extracting meaning from technical documents. This is especially true when a rich ontology such as the Unified Medical Language System (UMLS) is available. This paper reports on some tools being developed to make this possible and on some experience with a user interface based on ontologies and semantic networks that allows for interactive knowledge exploration.

Abstracting and Indexing↗
PubMed2000

EDGAR: extraction of drugs, genes and relations from the biomedical literature.

EDGAR (Extraction of Drugs, Genes and Relations) is a natural language processing system that extracts information about drugs and genes relevant to cancer from the biomedical literature. This automatically extracted information has remarkable potential to facilitate computational analysis in the molecular biology of cancer, and the technology is straightforwardly generalizable to many areas of biomedicine. This paper reports on the mechanisms for automatically generating such assertions and on a simple application, conceptual clustering of documents. The system uses a stochastic part of speech tagger, generates an underspecified syntactic parse and then uses semantic and pragmatic information to construct its assertions. The system builds on two important existing resources: the MEDLINE database of biomedical citations and abstracts and the Unified Medical Language System, which provides syntactic and semantic information about the terms found in biomedical abstracts.

Algorithms↗
PubMed2001

Event extraction from biomedical papers using a full parser.

We have designed and implemented an information extraction system using a full parser to investigate the plausibility of full analysis of text using general-purpose parser and grammar applied to biomedical domain. We partially solved the problems of full parsing of inefficiency, ambiguity, and low coverage by introducing the preprocessors, and proposed the use of modules that handles partial results of parsing for further improvement. Our approach makes it possible to modularize the system, so that the IE system as a whole becomes easy to be tuned to specific domains, and easy to be maintained and improved by incorporating various techniques of disambiguation, speed up, etc. In preliminary experiment, from 133 argument structures that should be extracted from 97 sentences, we obtained 23% uniquely and 24% with ambiguity. And 20% are extractable from not complete but partial results of full parsing.

Databases, Factual↗
PubMedDate not supplied

Hyperad: augmenting and visualizing free text radiology reports.

Hyperad is an automated computer system designed to extract key concepts from thoracic radiology reports and give physicians access to a large database containing the reports and key concepts. The concepts are extracted from textual documents with natural language processing techniques, then stored with the original documents in the database, which can be queried in terms of findings or associated attributes from an intuitive and easily accessible interface. The extracted concepts are represented both textually in a coded hypertext format and graphically on a coronal cross-sectional anatomy atlas, an idealized graphical model of human anatomy. To facilitate implementation, the communication protocols and standards of the World Wide Web (Web) were adopted. The reports and associated forms are encoded in standard hypertext markup language, which makes it possible to use hypermedia links to navigate the Hyperad database with any graphical Web browser. In the future, Hyperad may prove useful for other applications.

Computer Systems↗
PubMed1987

The inhuman computer/the too-human psychotherapist.

There has been an understandable rejection by psychotherapists of any natural language processing (computer/human interaction by means of usual language exchange) which is intended to embrace aspects of psychotherapy. For at least twenty years therapists have experimented with computer programs for specific and general purpose with reported success. This paper describes some of the aspects of artificial intelligence used in computer-mediated or computer-assisted therapy and the utility of such efforts in general reevaluation of human-to-human psychotherapy.

Computers↗
PubMedDate not supplied

Development of a questionnaire for detecting potential adverse drug reactions.

OBJECTIVE: To develop a comprehensive list of symptoms categorized by body system as part of a questionnaire for detecting potential adverse drug reactions. DATA SOURCES: A preliminary list of symptoms in lay terminology was extracted from the "Side Effects" section of all drug monographs contained in the United States Pharmacopeia Dispensing Information (USP DI) computerized database (Volume II, Advice for the Patient) using natural language processing software. The list was sorted alphabetically and duplicate terms were eliminated. Symptoms were then categorized by body system or anatomic region. A preferred term for each symptom was selected when multiple synonyms and related words were listed. Finally, all of the symptom terms were incorporated into a thesaurus from which the questionnaire was derived. RESULTS: The questionnaire will be used as part of a computer-assisted interview, developed to solicit information from patients regarding their medication regimens and to systematically query them regarding the presence of salient symptoms or complaints. The computer system will eventually interface with the USP DI database to identify drugs from a patient's regimen that may be associated with adverse symptoms. The symptom thesaurus will provide the link to the USP DI database. Preliminary experience with the questionnaire in a limited number of patients has been encouraging. CONCLUSIONS: The questionnaire can assist clinicians in identifying drug-related symptoms including unreported adverse clinical effects of newly marketed or investigational therapeutic agents. When the questionnaire is computerized and linked to a comprehensive database, it can be more widely used to alert healthcare providers of potential adverse drug reactions that may otherwise go undetected.

Adverse Drug Reaction Reporting Systems↗
PubMed2004

Tools for loading MEDLINE into a local relational database.

BACKGROUND: Researchers who use MEDLINE for text mining, information extraction, or natural language processing may benefit from having a copy of MEDLINE that they can manage locally. The National Library of Medicine (NLM) distributes MEDLINE in eXtensible Markup Language (XML)-formatted text files, but it is difficult to query MEDLINE in that format. We have developed software tools to parse the MEDLINE data files and load their contents into a relational database. Although the task is conceptually straightforward, the size and scope of MEDLINE make the task nontrivial. Given the increasing importance of text analysis in biology and medicine, we believe a local installation of MEDLINE will provide helpful computing infrastructure for researchers. RESULTS: We developed three software packages that parse and load MEDLINE, and ran each package to install separate instances of the MEDLINE database. For each installation, we collected data on loading time and disk-space utilization to provide examples of the process in different settings. Settings differed in terms of commercial database-management system (IBM DB2 or Oracle 9i), processor (Intel or Sun), programming language of installation software (Java or Perl), and methods employed in different versions of the software. The loading times for the three installations were 76 hours, 196 hours, and 132 hours, and disk-space utilization was 46.3 GB, 37.7 GB, and 31.6 GB, respectively. Loading times varied due to a variety of differences among the systems. Loading time also depended on whether data were written to intermediate files or not, and on whether input files were processed in sequence or in parallel. Disk-space utilization depended on the number of MEDLINE files processed, amount of indexing, and whether abstracts were stored as character large objects or truncated. CONCLUSIONS: Relational database (RDBMS) technology supports indexing and querying of very large datasets, and can accommodate a locally stored version of MEDLINE. RDBMS systems support a wide range of queries and facilitate certain tasks that are not directly supported by the application programming interface to PubMed. Because there is variation in hardware, software, and network infrastructures across sites, we cannot predict the exact time required for a user to load MEDLINE, but our results suggest that performance of the software is reasonable. Our database schemas and conversion software are publicly available at http://biotext.berkeley.edu.

Database Management Systems↗
PubMed2005

A sentence sliding window approach to extract protein annotations from biomedical articles.

BACKGROUND: Within the emerging field of text mining and statistical natural language processing (NLP) applied to biomedical articles, a broad variety of techniques have been developed during the past years. Nevertheless, there is still a great ned of comparative assessment of the performance of the proposed methods and the development of common evaluation criteria. This issue was addressed by the Critical Assessment of Text Mining Methods in Molecular Biology (BioCreative) contest. The aim of this contest was to assess the performance of text mining systems applied to biomedical texts including tools which recognize named entities such as genes and proteins, and tools which automatically extract protein annotations. RESULTS: The "sentence sliding window" approach proposed here was found to efficiently extract text fragments from full text articles containing annotations on proteins, providing the highest number of correctly predicted annotations. Moreover, the number of correct extractions of individual entities (i.e. proteins and GO terms) involved in the relationships used for the annotations was significantly higher than the correct extractions of the complete annotations (protein-function relations). CONCLUSION: We explored the use of averaging sentence sliding windows for information extraction, especially in a context where conventional training data is unavailable. The combination of our approach with more refined statistical estimators and machine learning techniques might be a way to improve annotation extraction for future biomedical text mining applications.

Biomedical Research↗
PubMed2005

Data-poor categorization and passage retrieval for gene ontology annotation in Swiss-Prot.

BACKGROUND: In the context of the BioCreative competition, where training data were very sparse, we investigated two complementary tasks: 1) given a Swiss-Prot triplet, containing a protein, a GO (Gene Ontology) term and a relevant article, extraction of a short passage that justifies the GO category assignment; 2) given a Swiss-Prot pair, containing a protein and a relevant article, automatic assignment of a set of categories. METHODS: Sentence is the basic retrieval unit. Our classifier computes a distance between each sentence and the GO category provided with the Swiss-Prot entry. The Text Categorizer computes a distance between each GO term and the text of the article. Evaluations are reported both based on annotator judgements as established by the competition and based on mean average precision measures computed using a curated sample of Swiss-Prot. RESULTS: Our system achieved the best recall and precision combination both for passage retrieval and text categorization as evaluated by official evaluators. However, text categorization results were far below those in other data-poor text categorization experiments The top proposed term is relevant in less that 20% of cases, while categorization with other biomedical controlled vocabulary, such as the Medical Subject Headings, we achieved more than 90% precision. We also observe that the scoring methods used in our experiments, based on the retrieval status value of our engines, exhibits effective confidence estimation capabilities. CONCLUSION: From a comparative perspective, the combination of retrieval and natural language processing methods we designed, achieved very competitive performances. Largely data-independent, our systems were no less effective that data-intensive approaches. These results suggests that the overall strategy could benefit a large class of information extraction tasks, especially when training data are missing. However, from a user perspective, results were disappointing. Further investigations are needed to design applicable end-user text mining tools for biologists.

Computational Biology↗
PubMed2006

BBP: Brucella genome annotation with literature mining and curation.

BACKGROUND: Brucella species are Gram-negative, facultative intracellular bacteria that cause brucellosis in humans and animals. Sequences of four Brucella genomes have been published, and various Brucella gene and genome data and analysis resources exist. A web gateway to integrate these resources will greatly facilitate Brucella research. Brucella genome data in current databases is largely derived from computational analysis without experimental validation typically found in peer-reviewed publications. It is partially due to the lack of a literature mining and curation system able to efficiently incorporate the large amount of literature data into genome annotation. It is further hypothesized that literature-based Brucella gene annotation would increase understanding of complicated Brucella pathogenesis mechanisms. RESULTS: The Brucella Bioinformatics Portal (BBP) is developed to integrate existing Brucella genome data and analysis tools with literature mining and curation. The BBP InterBru database and Brucella Genome Browser allow users to search and analyze genes of 4 currently available Brucella genomes and link to more than 20 existing databases and analysis programs. Brucella literature publications in PubMed are extracted and can be searched by a TextPresso-powered natural language processing method, a MeSH browser, a keywords search, and an automatic literature update service. To efficiently annotate Brucella genes using the large amount of literature publications, a literature mining and curation system coined Limix is developed to integrate computational literature mining methods with a PubSearch-powered manual curation and management system. The Limix system is used to quickly find and confirm 107 Brucella gene mutations including 75 genes shown to be essential for Brucella virulence. The 75 genes are further clustered using COG. In addition, 62 Brucella genetic interactions are extracted from literature publications. These results make possible more comprehensive investigation of Brucella pathogenesis. Other BBP features include publication email alert service, Brucella researchers' contact database, and discussion forum. CONCLUSION: BBP is a gateway for Brucella researchers to search, analyze, and curate Brucella genome data originated from public databases and literature. Brucella gene mutations and genetic interactions are annotated using Limix leading to better understanding of Brucella pathogenesis.

Algorithms↗
PubMed2006

Tools for knowledge acquisition within the NeuroScholar system and their application to anatomical tract-tracing data.

BACKGROUND: Knowledge bases that summarize the published literature provide useful online references for specific areas of systems-level biology that are not otherwise supported by large-scale databases. In the field of neuroanatomy, groups of small focused teams have constructed medium size knowledge bases to summarize the literature describing tract-tracing experiments in several species. Despite years of collation and curation, these databases only provide partial coverage of the available published literature. Given that the scientists reading these papers must all generate the interpretations that would normally be entered into such a system, we attempt here to provide general-purpose annotation tools to make it easy for members of the community to contribute to the task of data collation. RESULTS: In this paper, we describe an open-source, freely available knowledge management system called 'NeuroScholar' that allows straightforward structured markup of the PDF files according to a well-designed schema to capture the essential details of this class of experiment. Although, the example worked through in this paper is quite specific to neuroanatomical connectivity, the design is freely extensible and could conceivably be used to construct local knowledge bases for other experiment types. Knowledge representations of the experiment are also directly linked to the contributing textual fragments from the original research article. Through the use of this system, not only could members of the community contribute to the collation task, but input data can be gathered for automated approaches to permit knowledge acquisition through the use of Natural Language Processing (NLP). CONCLUSION: We present a functional, working tool to permit users to populate knowledge bases for neuroanatomical connectivity data from the literature through the use of structured questionnaires. This system is open-source, fully functional and available for download from [1].

Journal Article↗
PubMed2005

Consolidating the set of known human protein-protein interactions in preparation for large-scale mapping of the human interactome.

BACKGROUND: Extensive protein interaction maps are being constructed for yeast, worm, and fly to ask how the proteins organize into pathways and systems, but no such genome-wide interaction map yet exists for the set of human proteins. To prepare for studies in humans, we wished to establish tests for the accuracy of future interaction assays and to consolidate the known interactions among human proteins. RESULTS: We established two tests of the accuracy of human protein interaction datasets and measured the relative accuracy of the available data. We then developed and applied natural language processing and literature-mining algorithms to recover from Medline abstracts 6,580 interactions among 3,737 human proteins. A three-part algorithm was used: first, human protein names were identified in Medline abstracts using a discriminator based on conditional random fields, then interactions were identified by the co-occurrence of protein names across the set of Medline abstracts, filtering the interactions with a Bayesian classifier to enrich for legitimate physical interactions. These mined interactions were combined with existing interaction data to obtain a network of 31,609 interactions among 7,748 human proteins, accurate to the same degree as the existing datasets. CONCLUSION: These interactions and the accuracy benchmarks will aid interpretation of current functional genomics data and provide a basis for determining the quality of future large-scale human protein interaction assays. Projecting from the approximately 15 interactions per protein in the best-sampled interaction set to the estimated 25,000 human genes implies more than 375,000 interactions in the complete human protein interaction network. This set therefore represents no more than 10% of the complete network.

Algorithms↗
PubMed2004

Evaluation of emergency medical text processor, a system for cleaning chief complaint text data.

OBJECTIVES: Emergency Medical Text Processor (EMT-P) version 1, a natural language processing system that cleans emergency department text (e.g., chst pn, chest pai), was developed to maximize extraction of standard terms (e.g., chest pain). The authors compared the number of standard terms extracted from raw chief complaint (CC) data with that for CC data cleaned with EMT-P and evaluated the accuracy of EMT-P. METHODS: This cross-sectional observation study included CC text entries for all emergency department visits to three tertiary care centers in 2001. Terms were extracted from CC entries before and after cleaning with EMT-P. Descriptive statistics included number and percentage of all entries (tokens) and all unique entries (types) that matched a standard term from the Unified Medical Language System (UMLS). An expert panel rated the accuracy of the CC-UMLS term matches; inter-rater reliability was measured with kappa. RESULTS: The authors collected 203,509 CC entry tokens, of which 63,946 were unique entry types. For the raw data, 89,337 tokens (44%) and 5,081 types (8%) matched a standard term. After EMT-P cleaning, 168,050 tokens (83%) and 44,430 types (69%) matched a standard term. The expert panel reached consensus on 201 of the 222 CC-UMLS term matches reviewed (kappa=0.69-0.72). Ninety-six percent of the 201 matches were rated equivalent or related. Thirty-eight percent of the nonmatches were found to match UMLS concepts. CONCLUSIONS: EMT-P version 1 is relatively accurate, and cleaning with EMT-P improved the CC-UMLS term match rate over raw data. The authors identified areas for improvement in future EMT-P versions and issues to be resolved in developing a standard CC terminology.

Cohort Studies↗
PubMedDate not supplied

Methods for semi-automated indexing for high precision information retrieval.

OBJECTIVE: To evaluate a new system, ISAID (Internet-based Semi-automated Indexing of Documents), and to generate textbook indexes that are more detailed and more useful to readers. DESIGN: Pilot evaluation: simple, nonrandomized trial comparing ISAID with manual indexing methods. Methods evaluation: randomized, cross-over trial comparing three versions of ISAID and usability survey. PARTICIPANTS: Pilot evaluation: two physicians. Methods evaluation: twelve physicians, each of whom used three different versions of the system for a total of 36 indexing sessions. MEASUREMENTS: Total index term tuples generated per document per minute (TPM), with and without adjustment for concordance with other subjects; inter-indexer consistency; ratings of the usability of the ISAID indexing system. RESULTS: Compared with manual methods, ISAID decreased indexing times greatly. Using three versions of ISAID, inter-indexer consistency ranged from 15% to 65% with a mean of 41%, 31%, and 40% for each of three documents. Subjects using the full version of ISAID were faster (average TPM: 5.6) and had higher rates of concordant index generation. There were substantial learning effects, despite our use of a training/run-in phase. Subjects using the full version of ISAID were much faster by the third indexing session (average TPM: 9.1). There was a statistically significant increase in three-subject concordant indexing rate using the full version of ISAID during the second indexing session (p < 0.05). SUMMARY: Users of the ISAID indexing system create complex, precise, and accurate indexing for full-text documents much faster than users of manual methods. Furthermore, the natural language processing methods that ISAID uses to suggest indexes contributes substantially to increased indexing speed and accuracy.

Abstracting and Indexing↗
PubMedDate not supplied

Automatic resolution of ambiguous terms based on machine learning and conceptual relations in the UMLS.

UNLABELLED: Motivation. The UMLS has been used in natural language processing applications such as information retrieval and information extraction systems. The mapping of free-text to UMLS concepts is important for these applications. To improve the mapping, we need a method to disambiguate terms that possess multiple UMLS concepts. In the general English domain, machine-learning techniques have been applied to sense-tagged corpora, in which senses (or concepts) of ambiguous terms have been annotated (mostly manually). Sense disambiguation classifiers are then derived to determine senses (or concepts) of those ambiguous terms automatically. However, manual annotation of a corpus is an expensive task. We propose an automatic method that constructs sense-tagged corpora for ambiguous terms in the UMLS using MEDLINE abstracts. METHODS: For a term W that represents multiple UMLS concepts, a collection of MEDLINE abstracts that contain W is extracted. For each abstract in the collection, occurrences of concepts that have relations with W as defined in the UMLS are automatically identified. A sense-tagged corpus, in which senses of W are annotated, is then derived based on those identified concepts. The method was evaluated on a set of 35 frequently occurring ambiguous biomedical abbreviations using a gold standard set that was automatically derived. The quality of the derived sense-tagged corpus was measured using precision and recall. RESULTS: The derived sense-tagged corpus had an overall precision of 92.9% and an overall recall of 47.4%. After removing rare senses and ignoring abbreviations with closely related senses, the overall precision was 96.8% and the overall recall was 50.6%. CONCLUSIONS: UMLS conceptual relations and MEDLINE abstracts can be used to automatically acquire knowledge needed for resolving ambiguity when mapping free-text to UMLS concepts.

Abbreviations as Topic↗
PubMed2026

CLASPP: A unified model for predicting post-translational modifications.

Post-Translational Modifications (PTMs) are a fundamental mechanism for regulating cellular pathways and increasing the functional diversity of the proteome. Accurately predicting the PTM types that are likely to occur at a given site in the primary sequence is a key challenge in functional proteomics. Existing PTM prediction models predominantly focus on either single PTM types or employ ensemble methods that combine multiple models to predict different PTM types. This fragmentation is largely driven by the vast imbalance in data availability across PTM types, making it difficult to predict multiple PTM types with a single model. To address this limitation, we present the Contrastively Learned Attention-based Stratified PTM Predictor (CLASPP), a unified PTM prediction model. CLASPP addresses imbalance challenges by leveraging unsupervised clustering-based undersampling and a novel contrastive learning framework tailored to PTM data. Additionally, our hierarchical data organization and curation are shown to improve CLASPP's performance by balancing the representation of individual PTM types and provides a standardized dataset to train and validate future model designs. Drawing inspiration from advancements in image and natural language processing, the CLASPP model employs a multi-stage training strategy and a high-quality, curated training dataset to improve PTM prediction performance. To uncover what is learned during the contrastive learning stage, the CLASPP model is shown to distinguish known protein kinase substrate specificity profiles as a form of explainability. Finally, we evaluate the application of CLASPP in predicting PTMs in different model organisms and experimentally validated ubiquitination sites in the understudied DCLK3 kinase. Overall, CLASPP represents a unified model for PTM prediction that addresses key bottlenecks in data imbalance and offers new strategies for biological data curation, thereby improving PTM-type prediction performance across diverse organisms.

Protein Processing, Post-Translational↗
PubMed2026

EvoSNR-Prom: Predicting promoters at single-nucleotide resolution with label-aware transfer learning of the pretrained EVO model.

The precise identification of promoters is crucial for understanding gene regulation. Deep learning methods have achieved considerable success in promoter prediction, yet most operate at the sequence level with coarse-grained labels. This means they label an entire DNA segment as either a "promoter" or "non-promoter," which results in a lack of the nucleotide-level resolution in prediction. In this study, we propose EvoSNR-Prom, a model designed for promoter prediction at single-nucleotide resolution. EvoSNR-Prom is built on the Evo foundation model and formulates promoter identification as a token-level sequence labeling problem, analogous to named entity recognition in natural language processing. To address the limited contextual information available in single-nucleotide tokenization, we introduce a lexicon-enhanced embedding strategy that incorporates biologically meaningful DNA lexicons, enriching contextual representations and improving the model's ability to capture complex sequence motifs. Furthermore, to enhance predictive performance on small size datasets, we integrate a label-aware transfer learning framework to leverage knowledge from well-annotated source species to a target organism. The results across various prokaryotic datasets show that EvoSNR-Prom achieves excellent performance. This work provides a valuable computational framework for the high-precision analysis of gene regulatory elements, contributing to the advancement of promoter prediction at single-nucleotide resolution.

Promoter Regions, Genetic↗
PubMed2004

Gene structure prediction using an orthologous gene of known exon-intron structure.

Given the availability of complete genome sequences from related organisms, sequence conservation can provide important clues for predicting gene structure. In particular, one should be able to leverage information about known genes in one species to help determine the structures of related genes in another. Such an approach is appealing in that high-quality gene prediction can be achieved for newly sequenced species, such as mouse and puffer fish, using the extensive knowledge that has been accumulated about human genes. This article reports a novel approach to predicting the exon-intron structures of mouse genes by incorporating constraints from orthologous human genes using techniques that have previously been exploited in speech and natural language processing applications. The approach uses a context-free grammar to parse a training corpus of annotated human genes. A statistical training procedure produces a weighted recursive transition network (RTN) intended to capture the general features of a mammalian gene. This RTN is expanded into a finite state transducer (FST) and composed with an FST capturing the specific features of the human orthologue. This model includes a trigram language model on the amino acid sequence as well as exon length constraints. A final stage uses the free software package ClustalW to align the top n candidates in the search space. For a set of 98 orthologous human-mouse pairs, we achieved 96% sensitivity and 97% specificity at the exon level on the mouse genes, given only knowledge gleaned from the annotated human genome.

Algorithms↗