Browse
Submit Data
Databases
API
Help

Dataset Information

0 Views

0 Connections

0 Citations

0 Reanalyses

0 Downloads

Omics score: 0

The g3mclass is a practical software for multiclass classification on biomarkers

ABSTRACT: The analytes qualified as biomarkers are potent tools to diagnose various diseases, monitor therapy responses, and design therapeutic interventions. The early assessment of the diverseness of human disease is essential for the speedy and cost-efficient implementation of personalized medicine. We developed g3mclass, the Gaussian mixture modeling software for molecular assay data classification. This software automates the validated multiclass classifier applicable to single analyte tests and multiplexing assays. The g3mclass achieves automation using the original semi-constrained expectation-maximization (EM) algorithm that allows inference from the test, control, and query data that human experts cannot interpret. In this study, we used real-world clinical data and gene expression datasets (ERBB2, ESR1, PGR) to provide examples of how g3mclass may help overcome the problems of over-/underdiagnosis and equivocal results in diagnostic tests for breast cancer. We showed the g3mclass output’s accuracy, robustness, scalability, and interpretability. The user-friendly interface and free dissemination of this multi-platform software aim to ease its use by research laboratories, biomedical pharma, companion diagnostic developers, and healthcare regulators. Furthermore, the g3mclass automatic extracting information through probabilistic modeling is adaptable for blending with machine learning and artificial intelligence.

ORGANISM(S): Homo sapiens

PROVIDER: GSE214540 | GEO | 2022/11/09

REPOSITORIES: GEO

ACCESS DATA

Json Xml

Similar Datasets

Generating automated kidney transplant biopsy reports combining molecular measurements with ensembles of machine learning classifiers

Project description:We previously reported a system for assessing rejection in kidney transplant biopsies using microarray-based gene expression data, the Molecular Microscope® Diagnostic System (MMDx). Ensembles generated diagnoses that were both more accurate than the best individual classifiers, and nearly as stable as the best, consistent with expectations from the machine learning literature. Human experts had ~93% agreement (balanced accuracy) signing out the reports, and random forest-based automated sign-outs showed similar levels of agreement with the human experts (92% and 94% for predicting the expert MMDx sign-outs for T cell-mediated (TCMR) and antibody-mediated rejection (ABMR) respectively). In most cases disagreements, whether between experts or between experts and automated sign-outs, were in biopsies near diagnostic thresholds. Considerable disagreement with histology persisted. The balanced accuracies of MMDx sign-outs for histology diagnoses of TCMR and ABMR were 73% and 78% respectively. Disagreement with histology is largely due to the known noise in histology assessments (ClinicalTrials.gov NCT01299168).

2019-11-07 | GSE124203 | GEO

RNA-Sequencing of whole blood samples from children with a range of acute febrile illnesses

Project description:RNA sequencing data were generated from the whole blood of children with a range of acute febrile illnesses. These data were used as the validation cohort for a multiclass diagnostic gene expression signature for the discrimination of 18 infectious and inflammatory diseases which was discovered using publicly available microarray datasets.

2022-11-22 | E-MTAB-11671 | biostudies-arrayexpress

Miyazawa2010 - changing turing patterns by spatial parameter sweep

Project description:Biologists have long been fascinated by the amazing diversity of animal colour patterns. Despite much interest, the underlying evolutionary and developmental mechanisms contributing to their rich variety remain largely unknown, especially the vivid and complex colour patterns seen in vertebrates. The model [1] shows, that complex and camouflaged animal markings can be formed by the ‘blending’ of simple colour patterns. A mathematical model predicts that crossing between animals having inverted spot patterns (for example, ‘light spots on a dark background’ and ‘ dark spots on a light background’ ) will necessarily result in hybrid offspring that have camouflaged labyrinthine patterns as ‘ blended ’ intermediate phenotypes. In [1] the authors confirmed the broad applicability of the model prediction by empirical examination of natural and artificial hybrids of salmonid fish. The results suggest an unexplored evolutionary process by means of ‘pattern blending’, as one of the possible mechanisms underlying colour pattern diversity and hybrid speciation. The model file is in MorpheusML format and can be opened in the free, open-source multicellular modeling software Morpheus (https://morpheus.gitlab.io) to simulate the time course (movie) of the spatio-temporal dynamics. It resembles figure 3a from [1], where a 2D parameter space shows the transition from black to white spots through intermediate labyrinthine patterns. 1. Miyazawa, Okamoto and Kondo, Blending of animal colour patterns by hybridization, Nature Communications, 2010

2023-09-07 | MODEL2304280001 | BioModels

On the relevance of technical variation due to building pools in microarray experiments [Mouse]

2015-09-10 | GSE72861 | GEO

On the relevance of technical variation due to building pools in microarray experiments [Honey bee]

Project description:The objective of the study was to assess the technical error due to blending of individual samples into pools in different experimental data sets. The blending error variance component corresponds to random effects for inaccuracies, which were modeled on the logarithmic scale of normalized gene expression. It's estimation based on a linear mixed model, fitted for each transcript.

2015-09-11 | GSE72943 | GEO

Project description:CRC fecal microbiome (pharma)

| PRJNA747730 | ENA

PFAS non-targeted Leachate - Thermo, IE, DDA, AIF

Project description:We introduce FluoroMatch, which automates file conversion, chromatographic peak picking, blank feature filtering, PFAS annotation based on precursor and fragment masses, and annotation ranking. The software library currently contains about 7000 PFAS fragmentation patterns based on rules derived from standards and literature, and the software automates a process for users to add additional compounds. The use of intelligent data-acquisition methods (iterative exclusion) nearly doubled the number of annotations. The software application is demonstrated by characterizing PFAS in landfill leachate as well as in leachate foam generated to concentrate the compounds for remediation purposes. FluoroMatch had wide coverage, returning 27 PFAS annotations for landfill leachate samples, explaining 71% of the all-ion fragmentation (CF2)n related fragments. By improving the throughput and coverage of PFAS annotation, FluoroMatch will accelerate the discovery of PFAS posing significant human risk.

2023-03-30 | MSV000091594 | MassIVE

Insights into myalgic encephalomyelitis/chronic fatigue syndrome (ME/CFS) phenotypes through comprehensive metabolomics (part II)

Project description:The pathogenesis of ME/CFS, a disease characterized by unexplained debilitating fatigue, cognitive dysfunction, sleep disturbances, orthostatic intolerance, fever, lymphadenopathy and irritable bowel syndrome (IBS), is poorly understood. There are no validated diagnostic tests or interventions to mitigate disease. Here we report association modeling, biomarker discovery, biochemical enrichment analysis and topological network visualization of plasma metabolomic, fecal bacterial metagenomic and clinical data from 50 ME/CFS patients and 50 healthy controls.

2017-07-19 | ST000801 | MetabolomicsWorkbench

A real-world clinical study of the aiding role of intestinal microbiome-associated metabolite in the diagnosis of early colorectal cancer and adenoma and the prediction value of recurrence after endoscopic treatment

Project description:Interventions: modeling group:taking feces and blood sample ;validation group :taking blood sample Primary outcome(s): accuracy;sensitivity;specificity Study Design: Diagnostic test for accuracy

| 38280 | ecrin-mdr-crc

On the relevance of technical variation due to building pools in microarray experiments

Project description:The objective of the study was to assess the technical error due to blending of individual samples into pools in experimental data. The blending error variance component corresponds to random effects for inaccuracies, which were modeled on the logarithmic scale of normalized gene expression. It's estimation based on a linear mixed model, fitted for each transcript. Ovaries from 30 animals of line FL1 and of the control line DUKsi were collected at the metestrous stage. They were combined to 6 pools of 5 individuals each and processed for microarray analysis. Additionally, the 10 individuals used for the first two pools of each line were processed.

2015-09-10 | E-GEOD-72861 | biostudies-arrayexpress

OmicsDI is part of the ELIXIR infrastructure

OmicsDI is an Elixir interoperability service. Learn more ›

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