Article

Principled feature attribution for unsupervised gene expression analysis

2022-05-04

Abstract excerpt

As interest in unsupervised deep learning models for the analysis of gene expression data has grown, an increasing number of methods have been developed to make these deep learning models more interpretable. These methods can be separated into two groups: (1) post hoc analyses of black box models through feature attribution methods and (2) approaches to build inherently interpretable models through biologically-c...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: ff4bf336-b770-5b97-b42e-2e5a95de63bc
DOI: 10.1101/2022.05.03.490535

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Principled feature attribution for unsupervised gene expression analysisDOI 10.1101/2022.05.03.490535Read

MultiPLIER: a transfer learning framework for transcriptomics reveals systemic features of rare diseaseSemantic proximity Read

Knowledge-Driven Interpretable Neural Networks for Mechanistic InsightSemantic proximity Read

Interpreting biologically informed neural networks for enhanced biomarker discovery and pathway analysisSemantic proximity Read

A variational autoencoder trained with priors from canonical pathways increases the interpretability of transcriptome dataSemantic proximity Read

Explainable autoencoder-based representation learning for gene expression dataSemantic proximity Read

TDbasedUFE and TDbasedUFEadv: bioconductor packages to perform tensor decomposition based unsupervised feature extractionSemantic proximity Read

Sensitivity based model agnostic scalable explanations of deep learningSemantic proximity Read

Deep GONet: self-explainable deep neural network based on Gene Ontology for phenotype prediction from gene expression data.Semantic proximity Read

The Promise of Explainable Deep Learning for Omics Data Analysis: Adding New Discovery Tools to AISemantic proximity Read

Granular Transcriptomic Signatures Derived from Independent Component Analysis of Bulk Nervous Tissue for Studying Labile Brain PhysiologiesSemantic proximity Read

Machine learning for the exploitation of high throughput omics data : a case study on identifying circadian disruption from human blood transcriptomic dataSemantic proximity Read

Unsupervised Machine Learning for Data Encoding applied to Ovarian Cancer TranscriptomesSemantic proximity Read