Forskning
Udskriv Udskriv
Switch language
Region Hovedstaden - en del af Københavns Universitetshospital
Udgivet

Deconvolution of autoencoders to learn biological regulatory modules from single cell mRNA sequencing data

Publikation: Bidrag til tidsskriftTidsskriftartikelpeer review

DOI

  1. I am hiQ—a novel pair of accuracy indices for imputed genotypes

    Publikation: Bidrag til tidsskriftTidsskriftartikelpeer review

  2. Varia: a tool for prediction, analysis and visualisation of variable genes

    Publikation: Bidrag til tidsskriftTidsskriftartikelpeer review

  3. GenAPI: a tool for gene absence-presence identification in fragmented bacterial genome sequences

    Publikation: Bidrag til tidsskriftTidsskriftartikelpeer review

  4. WISH-R- a fast and efficient tool for construction of epistatic networks for complex traits and diseases

    Publikation: Bidrag til tidsskriftTidsskriftartikelpeer review

  5. Stronger findings from mass spectral data through multi-peak modeling

    Publikation: Bidrag til tidsskriftTidsskriftartikelpeer review

  1. MicroRNA-9-3p: a novel predictor of neurological outcome after cardiac arrest

    Publikation: Bidrag til tidsskriftTidsskriftartikelpeer review

  2. DeepLoc 2.0: Multi-label subcellular localization prediction using protein language models

    Publikation: Bidrag til tidsskriftTidsskriftartikelpeer review

  3. SignalP 6.0 predicts all five types of signal peptides using protein language models

    Publikation: Bidrag til tidsskriftTidsskriftartikelpeer review

Vis graf over relationer

BACKGROUND: Unsupervised machine learning methods (deep learning) have shown their usefulness with noisy single cell mRNA-sequencing data (scRNA-seq), where the models generalize well, despite the zero-inflation of the data. A class of neural networks, namely autoencoders, has been useful for denoising of single cell data, imputation of missing values and dimensionality reduction.

RESULTS: Here, we present a striking feature with the potential to greatly increase the usability of autoencoders: With specialized training, the autoencoder is not only able to generalize over the data, but also to tease apart biologically meaningful modules, which we found encoded in the representation layer of the network. Our model can, from scRNA-seq data, delineate biological meaningful modules that govern a dataset, as well as give information as to which modules are active in each single cell. Importantly, most of these modules can be explained by known biological functions, as provided by the Hallmark gene sets.

CONCLUSIONS: We discover that tailored training of an autoencoder makes it possible to deconvolute biological modules inherent in the data, without any assumptions. By comparisons with gene signatures of canonical pathways we see that the modules are directly interpretable. The scope of this discovery has important implications, as it makes it possible to outline the drivers behind a given effect of a cell. In comparison with other dimensionality reduction methods, or supervised models for classification, our approach has the benefit of both handling well the zero-inflated nature of scRNA-seq, and validating that the model captures relevant information, by establishing a link between input and decoded data. In perspective, our model in combination with clustering methods is able to provide information about which subtype a given single cell belongs to, as well as which biological functions determine that membership.

OriginalsprogEngelsk
TidsskriftBMC Bioinformatics
Vol/bind20
Udgave nummer1
Sider (fra-til)379
ISSN1471-2105
DOI
StatusUdgivet - 8 jul. 2019

ID: 58986242