Browse
Submit Data
Databases
API
Help

Dataset Information

16 Views

0 Connections

0 Citations

0 Reanalyses

0 Downloads

Omics score: 0

Biomedical and clinical English model packages for the Stanza Python NLP library.

ABSTRACT:

Objective

The study sought to develop and evaluate neural natural language processing (NLP) packages for the syntactic analysis and named entity recognition of biomedical and clinical English text.

Materials and methods

We implement and train biomedical and clinical English NLP pipelines by extending the widely used Stanza library originally designed for general NLP tasks. Our models are trained with a mix of public datasets such as the CRAFT treebank as well as with a private corpus of radiology reports annotated with 5 radiology-domain entities. The resulting pipelines are fully based on neural networks, and are able to perform tokenization, part-of-speech tagging, lemmatization, dependency parsing, and named entity recognition for both biomedical and clinical text. We compare our systems against popular open-source NLP libraries such as CoreNLP and scispaCy, state-of-the-art models such as the BioBERT models, and winning systems from the BioNLP CRAFT shared task.

Results

For syntactic analysis, our systems achieve much better performance compared with the released scispaCy models and CoreNLP models retrained on the same treebanks, and are on par with the winning system from the CRAFT shared task. For NER, our systems substantially outperform scispaCy, and are better or on par with the state-of-the-art performance from BioBERT, while being much more computationally efficient.

Conclusions

We introduce biomedical and clinical NLP packages built for the Stanza library. These packages offer performance that is similar to the state of the art, and are also optimized for ease of use. To facilitate research, we make all our models publicly available. We also provide an online demonstration (http://stanza.run/bio).

SUBMITTER: Zhang Y

PROVIDER: S-EPMC8363782 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Json Xml

Similar Datasets

mOWL: Python library for machine learning with biomedical ontologies.

Project description:MotivationOntologies contain formal and structured information about a domain and are widely used in bioinformatics for annotation and integration of data. Several methods use ontologies to provide background knowledge in machine learning tasks, which is of particular importance in bioinformatics. These methods rely on a set of common primitives that are not readily available in a software library; a library providing these primitives would facilitate the use of current machine learning methods with ontologies and the development of novel methods for other ontology-based biomedical applications.ResultsWe developed mOWL, a Python library for machine learning with ontologies formalized in the Web Ontology Language (OWL). mOWL implements ontology embedding methods that map information contained in formal knowledge bases and ontologies into vector spaces while preserving some of the properties and relations in ontologies, as well as methods to use these embeddings for similarity computation, deductive inference and zero-shot learning. We demonstrate mOWL on the knowledge-based prediction of protein-protein interactions using the gene ontology and gene-disease associations using phenotype ontologies.Availability and implementationmOWL is freely available on https://github.com/bio-ontology-research-group/mowl and as a Python package in PyPi.Supplementary informationSupplementary data are available at Bioinformatics online.

| S-EPMC9848046 | biostudies-literature

PeptideBuilder: A simple Python library to generate model peptides.

Project description:We present a simple Python library to construct models of polypeptides from scratch. The intended use case is the generation of peptide models with pre-specified backbone angles. For example, using our library, one can generate a model of a set of amino acids in a specific conformation using just a few lines of python code. We do not provide any tools for energy minimization or rotamer packing, since powerful tools are available for these purposes. Instead, we provide a simple Python interface that enables one to add residues to a peptide chain in any desired conformation. Bond angles and bond lengths can be manipulated if so desired, and reasonable values are used by default.

| S-EPMC3661355 | biostudies-literature

graphkernels: R and Python packages for graph comparison.

Project description:Summary:Measuring the similarity of graphs is a fundamental step in the analysis of graph-structured data, which is omnipresent in computational biology. Graph kernels have been proposed as a powerful and efficient approach to this problem of graph comparison. Here we provide graphkernels, the first R and Python graph kernel libraries including baseline kernels such as label histogram based kernels, classic graph kernels such as random walk based kernels, and the state-of-the-art Weisfeiler-Lehman graph kernel. The core of all graph kernels is implemented in C?++ for efficiency. Using the kernel matrices computed by the package, we can easily perform tasks such as classification, regression and clustering on graph-structured samples. Availability and implementation:The R and Python packages including source code are available at https://CRAN.R-project.org/package=graphkernels and https://pypi.python.org/pypi/graphkernels. Contact:mahito@nii.ac.jp or elisabetta.ghisu@bsse.ethz.ch. Supplementary information:Supplementary data are available online at Bioinformatics.

| S-EPMC5860361 | biostudies-literature

UMLS content views appropriate for NLP processing of the biomedical literature vs. clinical text.

Project description:Identification of medical terms in free text is a first step in such Natural Language Processing (NLP) tasks as automatic indexing of biomedical literature and extraction of patients' problem lists from the text of clinical notes. Many tools developed to perform these tasks use biomedical knowledge encoded in the Unified Medical Language System (UMLS) Metathesaurus. We continue our exploration of automatic approaches to creation of subsets (UMLS content views) which can support NLP processing of either the biomedical literature or clinical text. We found that suppression of highly ambiguous terms in the conservative AutoFilter content view can partially replace manual filtering for literature applications, and suppression of two character mappings in the same content view achieves 89.5% precision at 78.6% recall for clinical applications.

| S-EPMC2890296 | biostudies-literature

COSMOS: Python library for massively parallel workflows.

Project description:Efficient workflows to shepherd clinically generated genomic data through the multiple stages of a next-generation sequencing pipeline are of critical importance in translational biomedical science. Here we present COSMOS, a Python library for workflow management that allows formal description of pipelines and partitioning of jobs. In addition, it includes a user interface for tracking the progress of jobs, abstraction of the queuing system and fine-grained control over the workflow. Workflows can be created on traditional computing clusters as well as cloud-based services.Source code is available for academic non-commercial research purposes. Links to code and documentation are provided at http://lpm.hms.harvard.edu and http://wall-lab.stanford.edu.dpwall@stanford.edu or peter_tonellato@hms.harvard.edu.Supplementary data are available at Bioinformatics online.

| S-EPMC4184253 | biostudies-literature

Matriarch: A Python Library for Materials Architecture.

Project description:Biological materials, such as proteins, often have a hierarchical structure ranging from basic building blocks at the nanoscale (e.g., amino acids) to assembled structures at the macroscale (e.g., fibers). Current software for materials engineering allows the user to specify polypeptide chains and simple secondary structures prior to molecular dynamics simulation, but is not flexible in terms of the geometric arrangement of unequilibrated structures. Given some knowledge of a larger-scale structure, instructing the software to create it can be very difficult and time-intensive. To this end, the present paper reports a mathematical language, using category theory, to describe the architecture of a material, i.e., its set of building blocks and instructions for combining them. While this framework applies to any hierarchical material, here we concentrate on proteins. We implement this mathematical language as an open-source Python library called Matriarch. It is a domain-specific language that gives the user the ability to create almost arbitrary structures with arbitrary amino acid sequences and, from them, generate Protein Data Bank (PDB) files. In this way, Matriarch is more powerful than commercial software now available. Matriarch can be used in tandem with molecular dynamics simulations and helps engineers design and modify biologically inspired materials based on their desired functionality. As a case study, we use our software to alter both building blocks and building instructions for tropocollagen, and determine their effect on its structure and mechanical properties.

| S-EPMC4996638 | biostudies-literature

Assessing citation integrity in biomedical publications: corpus annotation and NLP models.

Project description:MotivationCitations have a fundamental role in scholarly communication and assessment. Citation accuracy and transparency is crucial for the integrity of scientific evidence. In this work, we focus on quotation errors, errors in citation content that can distort the scientific evidence and that are hard to detect for humans. We construct a corpus and propose natural language processing (NLP) methods to identify such errors in biomedical publications.ResultsWe manually annotated 100 highly-cited biomedical publications (reference articles) and citations to them. The annotation involved labeling citation context in the citing article, relevant evidence sentences in the reference article, and the accuracy of the citation. A total of 3063 citation instances were annotated (39.18% with accuracy errors). For NLP, we combined a sentence retriever with a fine-tuned claim verification model to label citations as ACCURATE, NOT_ACCURATE, or IRRELEVANT. We also explored few-shot in-context learning with generative large language models. The best performing model-which uses citation sentences as citation context, the BM25 model with MonoT5 reranker for retrieving top-20 sentences, and a fine-tuned MultiVerS model for accuracy label classification-yielded 0.59 micro-F1 and 0.52 macro-F1 score. GPT-4 in-context learning performed better in identifying accurate citations, but it lagged for erroneous citations (0.65 micro-F1, 0.45 macro-F1). Citation quotation errors are often subtle, and it is currently challenging for NLP models to identify erroneous citations. With further improvements, the models could serve to improve citation quality and accuracy.Availability and implementationWe make the corpus and the best-performing NLP model publicly available at https://github.com/ScienceNLP-Lab/Citation-Integrity/.

| S-EPMC11231046 | biostudies-literature

AESOP: A Python Library for Investigating Electrostatics in Protein Interactions.

Project description:Electric fields often play a role in guiding the association of protein complexes. Such interactions can be further engineered to accelerate complex association, resulting in protein systems with increased productivity. This is especially true for enzymes where reaction rates are typically diffusion limited. To facilitate quantitative comparisons of electrostatics in protein families and to describe electrostatic contributions of individual amino acids, we previously developed a computational framework called AESOP. We now implement this computational tool in Python with increased usability and the capability of performing calculations in parallel. AESOP utilizes PDB2PQR and Adaptive Poisson-Boltzmann Solver to generate grid-based electrostatic potential files for protein structures provided by the end user. There are methods within AESOP for quantitatively comparing sets of grid-based electrostatic potentials in terms of similarity or generating ensembles of electrostatic potential files for a library of mutants to quantify the effects of perturbations in protein structure and protein-protein association.

| S-EPMC5425408 | biostudies-other

PxBLAT: An efficient python binding library for BLAT.

Project description:We introduce PxBLAT, a Python library designed to enhance usability and efficiency in interacting with the BLAST-like alignment tool (BLAT). PxBLAT provides an intuitive Application Programming Interface (API) design, allowing the incorporation of its functionality directly into Python-based bioinformatics workflows. Moreover, PxBLAT's design philosophy emphasizes ease of use, memory efficiency, and the elimination of intermediary files and unnecessary system calls, thereby enhancing computational speed and user experience. Benchmark tests reveal its superior performance across various datasets, illustrating its capacity to maintain correctness. PxBLAT supports Python (version 3.9+), and pre-compiled packages are released via PyPI (https://pypi.org/project/pxblat/) and Bioconda (https://anaconda.org/bioconda/pxblat). The source code and executable are freely available for academic, nonprofit, and personal use. Its documentation is available on ReadTheDocs (https://pxblat.readthedocs.io/en/latest/).

| S-EPMC10418261 | biostudies-literature

GOATOOLS: A Python library for Gene Ontology analyses.

Project description:The biological interpretation of gene lists with interesting shared properties, such as up- or down-regulation in a particular experiment, is typically accomplished using gene ontology enrichment analysis tools. Given a list of genes, a gene ontology (GO) enrichment analysis may return hundreds of statistically significant GO results in a "flat" list, which can be challenging to summarize. It can also be difficult to keep pace with rapidly expanding biological knowledge, which often results in daily changes to any of the over 47,000 gene ontologies that describe biological knowledge. GOATOOLS, a Python-based library, makes it more efficient to stay current with the latest ontologies and annotations, perform gene ontology enrichment analyses to determine over- and under-represented terms, and organize results for greater clarity and easier interpretation using a novel GOATOOLS GO grouping method. We performed functional analyses on both stochastic simulation data and real data from a published RNA-seq study to compare the enrichment results from GOATOOLS to two other popular tools: DAVID and GOstats. GOATOOLS is freely available through GitHub: https://github.com/tanghaibao/goatools .

| S-EPMC6052049 | biostudies-literature

OmicsDI is part of the ELIXIR infrastructure

OmicsDI is an Elixir interoperability service. Learn more ›

Tweets

OmicsDI Databases

PRIDE
PeptideAtlas
MassIVE
JPOST Repository
Physiome Model Repository

EGA
EVA
ENA
LINCS
PAXDB
Cell Collective

MetaboLights
Metabolomics Workbench
MetabolomeExpress
GNPS
BioModels
FAIRDOMHub

ArrayExpress
dbGaP
ExpressionAtlas
GEO
NODE

Information

Databases
Help
API
Contact us
Code on GitHub
Terms of use
Submit Data