Leveraging the Cell Ontology to classify unseen cell types.
Ontology highlight
ABSTRACT:
SUBMITTER: Wang S
PROVIDER: S-EPMC8455606 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:BackgroundAutomatic cell type identification is essential to alleviate a key bottleneck in scRNA-seq data analysis. While most existing classification tools show good sensitivity and specificity, they often fail to adequately not-classify cells that are missing in the used reference. Additionally, many tools do not scale to the continuously increasing size of current scRNA-seq datasets. Therefore, additional tools are needed to solve these challenges.ResultsscAnnotatR is a novel R package that provides a complete framework to classify cells in scRNA-seq datasets using pre-trained classifiers. It supports both Seurat and Bioconductor's SingleCellExperiment and is thereby compatible with the vast majority of R-based analysis workflows. scAnnotatR uses hierarchically organised SVMs to distinguish a specific cell type versus all others. It shows comparable or even superior accuracy, sensitivity and specificity compared to existing tools while being able to not-classify unknown cell types. Moreover, scAnnotatR is the only of the best performing tools able to process datasets containing more than 600,000 cells.ConclusionsscAnnotatR is freely available on GitHub ( https://github.com/grisslab/scAnnotatR ) and through Bioconductor (from version 3.14). It is consistently among the best performing tools in terms of classification accuracy while scaling to the largest datasets.
| S-EPMC8762856 | biostudies-literature
Project description:BACKGROUND:One of the most successful approaches to develop new small molecule therapeutics has been to start from a validated druggable protein target. However, only a small subset of potentially druggable targets has attracted significant research and development resources. The Illuminating the Druggable Genome (IDG) project develops resources to catalyze the development of likely targetable, yet currently understudied prospective drug targets. A central component of the IDG program is a comprehensive knowledge resource of the druggable genome. RESULTS:As part of that effort, we have developed a framework to integrate, navigate, and analyze drug discovery data based on formalized and standardized classifications and annotations of druggable protein targets, the Drug Target Ontology (DTO). DTO was constructed by extensive curation and consolidation of various resources. DTO classifies the four major drug target protein families, GPCRs, kinases, ion channels and nuclear receptors, based on phylogenecity, function, target development level, disease association, tissue expression, chemical ligand and substrate characteristics, and target-family specific characteristics. The formal ontology was built using a new software tool to auto-generate most axioms from a database while supporting manual knowledge acquisition. A modular, hierarchical implementation facilitate ontology development and maintenance and makes use of various external ontologies, thus integrating the DTO into the ecosystem of biomedical ontologies. As a formal OWL-DL ontology, DTO contains asserted and inferred axioms. Modeling data from the Library of Integrated Network-based Cellular Signatures (LINCS) program illustrates the potential of DTO for contextual data integration and nuanced definition of important drug target characteristics. DTO has been implemented in the IDG user interface Portal, Pharos and the TIN-X explorer of protein target disease relationships. CONCLUSIONS:DTO was built based on the need for a formal semantic model for druggable targets including various related information such as protein, gene, protein domain, protein structure, binding site, small molecule drug, mechanism of action, protein tissue localization, disease association, and many other types of information. DTO will further facilitate the otherwise challenging integration and formal linking to biological assays, phenotypes, disease models, drug poly-pharmacology, binding kinetics and many other processes, functions and qualities that are at the core of drug discovery. The first version of DTO is publically available via the website http://drugtargetontology.org/ , Github ( http://github.com/DrugTargetOntology/DTO ), and the NCBO Bioportal ( http://bioportal.bioontology.org/ontologies/DTO ). The long-term goal of DTO is to provide such an integrative framework and to populate the ontology with this information as a community resource.
| S-EPMC5679337 | biostudies-literature
Project description:Purpose: To identify distinct gene expression and functional profiles for the three main cell types (epithelial, keratocyte and endothelial) of the human cornea. Methods: RNA-sequencing was performed using total RNA isolated from ex vivo corneal epithelial cells (evCEpC), keratocytes (evK) and endothelial cells (evCEnC) obtained from 3 donor corneas obtained from a commercial eye bank. Transcriptomic analysis was performed using Kallisto (alignment (hg38) and quantification) and Sleuth (differential gene expression(DGE)), with transcript abundances calculated as transcripts per kilobase million (TPM). Expression was defined as TPM≥7.5 and significant DGE as a fold-change ≥4 and a false-discovery rate adjusted p-value≤0.05. Cell type specificity was defined as genes adhering to the above expression and DGE criteria and not expressed (i.e., TPM<7.5) in the other two cell types. Gene ontology enrichment analysis was performed on the cell type-specific gene lists using the gene group functional profiling (g:GOSt) tool within the web-based g:Profiler suite. Results: We identified 205 genes specific in evCEpC, and enrichment of epithelial-associated GO terms (e.g., cornified envelope, epidermis development, cell-cell adhesion). We identified 76 genes specific in evK, and fibroblast-associated GO terms (e.g., collagen metabolic process, metallopeptidase activity, extracellular matrix organization). We identified 96 genes specific in evCEnC, and at least one CEnC-associated GO term (e.g., cellular cation homeostasis) but several synapse-associated GO terms (e.g., synapse organization, synapse part). Conclusions: The human cornea is comprised of three main cell types that play important roles in maintaining corneal clarity and vision. Our results demonstrate that a small subset (0.4-1%) of the protein-coding genes confers distinct and classic functional properties associated with each cell type. In addition, we identified a novel association and significant functional overlap between CEnC and synapses. This may lead to insights into the molecular mechanisms of transendothelial transport and secretion, which are integral metabolic features of the corneal endothelium.
2019-06-13 | GSE121922 | GEO
Project description:BackgroundNew technologies are focusing on characterizing cell types to better understand their heterogeneity. With large volumes of cellular data being generated, innovative methods are needed to structure the resulting data analyses. Here, we describe an 'Ontologically BAsed Molecular Signature' (OBAMS) method that identifies novel cellular biomarkers and infers biological functions as characteristics of particular cell types. This method finds molecular signatures for immune cell types based on mapping biological samples to the Cell Ontology (CL) and navigating the space of all possible pairwise comparisons between cell types to find genes whose expression is core to a particular cell type's identity.ResultsWe illustrate this ontological approach by evaluating expression data available from the Immunological Genome project (IGP) to identify unique biomarkers of mature B cell subtypes. We find that using OBAMS, candidate biomarkers can be identified at every strata of cellular identity from broad classifications to very granular. Furthermore, we show that Gene Ontology can be used to cluster cell types by shared biological processes in order to find candidate genes responsible for somatic hypermutation in germinal center B cells. Moreover, through in silico experiments based on this approach, we have identified genes sets that represent genes overexpressed in germinal center B cells and identify genes uniquely expressed in these B cells compared to other B cell types.ConclusionsThis work demonstrates the utility of incorporating structured ontological knowledge into biological data analysis - providing a new method for defining novel biomarkers and providing an opportunity for new biological insights.
| S-EPMC3844401 | biostudies-literature
Project description:We develop an algorithm for the integration of single-cell sequencing, RNA-inferred CNVs, and bulk transcriptomic sequencing to improve molecular classification of tumor sub-groups.
2024-04-23 | GSE264680 | GEO
Project description:Alternative splicing is a key player in the creation of complex mammalian transcriptomes and its misregulation is associated with many human diseases. Multiple mRNA isoforms are generated from most human genes, a process mediated by the interplay of various RNA signature elements and trans-acting factors that guide spliceosomal assembly and intron removal. Here, we introduce a splicing predictor that evaluates hundreds of RNA features simultaneously to successfully differentiate between exons that are constitutively spliced, exons that undergo alternative 5' or 3' splice-site selection, and alternative cassette-type exons. Surprisingly, the splicing predictor did not feature strong discriminatory contributions from binding sites for known splicing regulators. Rather, the ability of an exon to be involved in one or multiple types of alternative splicing is dictated by its immediate sequence context, mainly driven by the identity of the exon's splice sites, the conservation around them, and its exon/intron architecture. Thus, the splicing behavior of human exons can be reliably predicted based on basic RNA sequence elements.
| S-EPMC4408789 | biostudies-literature
Project description:There is a high diversity of neuronal types in the mammalian neocortex. To facilitate construction of system models with multiple cell types, we generate a database of point models associated with the Allen Cell Types Database. We construct a set of generalized leaky integrate-and-fire (GLIF) models of increasing complexity to reproduce the spiking behaviors of 645 recorded neurons from 16 transgenic lines. The more complex models have an increased capacity to predict spiking behavior of hold-out stimuli. We use unsupervised methods to classify cell types, and find that high level GLIF model parameters are able to differentiate transgenic lines comparable to electrophysiological features. The more complex model parameters also have an increased ability to differentiate between transgenic lines. Thus, creating simple models is an effective dimensionality reduction technique that enables the differentiation of cell types from electrophysiological responses without the need for a priori-defined features. This database will provide a set of simplified models of multiple cell types for the community to use in network models.
| S-EPMC5818568 | biostudies-literature
Project description:The importance of cell types in understanding brain function is widely appreciated but only a tiny fraction of neuronal diversity has been catalogued. Here we exploit recent progress in genetic definition of cell types in an objective structural approach to neuronal classification. The approach is based on highly accurate quantification of dendritic arbor position relative to neurites of other cells. We test the method on a population of 363 mouse retinal ganglion cells. For each cell, we determine the spatial distribution of the dendritic arbors, or arbor density, with reference to arbors of an abundant, well-defined interneuronal type. The arbor densities are sorted into a number of clusters that is set by comparison with several molecularly defined cell types. The algorithm reproduces the genetic classes that are pure types, and detects six newly clustered cell types that await genetic definition.
| S-EPMC4164236 | biostudies-literature
Project description:Aberrant glycosylation in tumours stem from altered glycosyltransferase (GT) gene expression but can the expression profiles of these signature genes be used to classify cancer types and lead to cancer subtype discovery? The differential structural changes to cellular glycan structures are predominantly regulated by the expression patterns of GT genes and are a hallmark of neoplastic cell metamorphoses. We found that the expression of 210 GT genes taken from 1893 cancer patient samples in The Cancer Genome Atlas (TCGA) microarray data are able to classify six cancers; breast, ovarian, glioblastoma, kidney, colon and lung. The GT gene expression profiles are used to develop cancer classifiers and propose subtypes. The subclassification of breast cancer solid tumour samples illustrates the discovery of subgroups from GT genes that match well against basal-like and HER2-enriched subtypes and correlates to clinical, mutation and survival data. This cancer type glycosyltransferase gene signature finding provides foundational evidence for the centrality of glycosylation in cancer.
| S-EPMC4873817 | biostudies-literature
Project description:BackgroundThe state-of-the-art deep learning based cancer type prediction can only predict cancer types whose samples are available during the training where the sample size is commonly large. In this paper, we consider how to utilize the existing training samples to predict cancer types unseen during the training. We hypothesize the existence of a set of type-agnostic expression representations that define the similarity/dissimilarity between samples of the same/different types and propose a novel one-shot learning model called CancerSiamese to learn this common representation. CancerSiamese accepts a pair of query and support samples (gene expression profiles) and learns the representation of similar or dissimilar cancer types through two parallel convolutional neural networks joined by a similarity function.ResultsWe trained CancerSiamese for cancer type prediction for primary and metastatic tumors using samples from the Cancer Genome Atlas (TCGA) and MET500. Network transfer learning was utilized to facilitate the training of the CancerSiamese models. CancerSiamese was tested for different N-way predictions and yielded an average accuracy improvement of 8% and 4% over the benchmark 1-Nearest Neighbor (1-NN) classifier for primary and metastatic tumors, respectively. Moreover, we applied the guided gradient saliency map and feature selection to CancerSiamese to examine 100 and 200 top marker-gene candidates for the prediction of primary and metastatic cancers, respectively. Functional analysis of these marker genes revealed several cancer related functions between primary and metastatic tumors.ConclusionThis work demonstrated, for the first time, the feasibility of predicting unseen cancer types whose samples are limited. Thus, it could inspire new and ingenious applications of one-shot and few-shot learning solutions for improving cancer diagnosis, prognostic, and our understanding of cancer.
| S-EPMC8117642 | biostudies-literature