Cover Image

Biologically informed variational autoencoders allow predictive modeling of genetic and drug-induced perturbations

Variational autoencoders (VAEs) have rapidly increased in popularity in biological applications and have already successfully been used on many omic datasets. Their latent space provides a low-dimensional representation of input data, and VAEs have been applied, e.g. for clustering of single-cell tr...

Full description

Saved in:
Bibliographic Details
Main Authors: Dončević, Daria (Author) , Herrmann, Carl (Author)
Format: Article (Journal)
Language:English
Published: June 2023
In: Bioinformatics
Year: 2023, Volume: 39, Issue: 6, Pages: 1-12
ISSN:1367-4811
DOI:10.1093/bioinformatics/btad387
Online Access:Verlag, kostenfrei, Volltext: https://doi.org/10.1093/bioinformatics/btad387
Get full text
Author Notes:Daria Doncevic and Carl Herrmann

MARC

LEADER 00000caa a2200000 c 4500
001 1856422836
003 DE-627
005 20241107080419.0
007 cr uuu---uuuuu
008 230817s2023 xx |||||o 00| ||eng c
024 7 |a 10.1093/bioinformatics/btad387  |2 doi 
035 |a (DE-627)1856422836 
035 |a (DE-599)KXP1856422836 
035 |a (OCoLC)1425212837 
040 |a DE-627  |b ger  |c DE-627  |e rda 
041 |a eng 
084 |a 32  |2 sdnb 
100 1 |a Dončević, Daria  |d 1994-  |e VerfasserIn  |0 (DE-588)1222980657  |0 (DE-627)1742234496  |4 aut 
245 1 0 |a Biologically informed variational autoencoders allow predictive modeling of genetic and drug-induced perturbations  |c Daria Doncevic and Carl Herrmann 
264 1 |c June 2023 
300 |b Illustrationen 
300 |a 12 
336 |a Text  |b txt  |2 rdacontent 
337 |a Computermedien  |b c  |2 rdamedia 
338 |a Online-Ressource  |b cr  |2 rdacarrier 
500 |a Veröffentlicht: 16. Juni 2023 
500 |a Gesehen am 17.08.2023 
520 |a Variational autoencoders (VAEs) have rapidly increased in popularity in biological applications and have already successfully been used on many omic datasets. Their latent space provides a low-dimensional representation of input data, and VAEs have been applied, e.g. for clustering of single-cell transcriptomic data. However, due to their non-linear nature, the patterns that VAEs learn in the latent space remain obscure. Hence, the lower-dimensional data embedding cannot directly be related to input features.To shed light on the inner workings of VAE and enable direct interpretability of the model through its structure, we designed a novel VAE, OntoVAE (Ontology guided VAE) that can incorporate any ontology in its latent space and decoder part and, thus, provide pathway or phenotype activities for the ontology terms. In this work, we demonstrate that OntoVAE can be applied in the context of predictive modeling and show its ability to predict the effects of genetic or drug-induced perturbations using different ontologies and both, bulk and single-cell transcriptomic datasets. Finally, we provide a flexible framework, which can be easily adapted to any ontology and dataset.OntoVAE is available as a python package under https://github.com/hdsu-bioquant/onto-vae. 
700 1 |a Herrmann, Carl  |d 1971-  |e VerfasserIn  |0 (DE-588)1081750952  |0 (DE-627)846593858  |0 (DE-576)454763409  |4 aut 
773 0 8 |i Enthalten in  |t Bioinformatics  |d Oxford : Oxford Univ. Press, 1998  |g 39(2023), 6 vom: Juni, Artikel-ID btad387, Seite 1-12  |h Online-Ressource  |w (DE-627)266884857  |w (DE-600)1468345-3  |w (DE-576)079420133  |x 1367-4811  |7 nnas  |a Biologically informed variational autoencoders allow predictive modeling of genetic and drug-induced perturbations 
773 1 8 |g volume:39  |g year:2023  |g number:6  |g month:06  |g elocationid:btad387  |g pages:1-12  |g extent:12  |a Biologically informed variational autoencoders allow predictive modeling of genetic and drug-induced perturbations 
856 4 0 |u https://doi.org/10.1093/bioinformatics/btad387  |x Verlag  |x Resolving-System  |z kostenfrei  |3 Volltext 
951 |a AR 
992 |a 20230817 
993 |a Article 
994 |a 2023 
998 |g 1081750952  |a Herrmann, Carl  |m 1081750952:Herrmann, Carl  |d 160000  |d 160100  |e 160000PH1081750952  |e 160100PH1081750952  |k 0/160000/  |k 1/160000/160100/  |p 2  |y j 
998 |g 1222980657  |a Dončević, Daria  |m 1222980657:Dončević, Daria  |d 160000  |d 160100  |e 160000PD1222980657  |e 160100PD1222980657  |k 0/160000/  |k 1/160000/160100/  |p 1  |x j 
999 |a KXP-PPN1856422836  |e 4367012298 
BIB |a Y 
SER |a journal 
JSO |a {"name":{"displayForm":["Daria Doncevic and Carl Herrmann"]},"note":["Veröffentlicht: 16. Juni 2023","Gesehen am 17.08.2023"],"recId":"1856422836","title":[{"title":"Biologically informed variational autoencoders allow predictive modeling of genetic and drug-induced perturbations","title_sort":"Biologically informed variational autoencoders allow predictive modeling of genetic and drug-induced perturbations"}],"person":[{"role":"aut","family":"Dončević","display":"Dončević, Daria","given":"Daria"},{"given":"Carl","family":"Herrmann","display":"Herrmann, Carl","role":"aut"}],"physDesc":[{"noteIll":"Illustrationen","extent":"12 S."}],"relHost":[{"disp":"Biologically informed variational autoencoders allow predictive modeling of genetic and drug-induced perturbationsBioinformatics","pubHistory":["14.1998 -"],"note":["Gesehen am 26.07.2023","Fortsetzung der Druck-Ausgabe"],"recId":"266884857","id":{"zdb":["1468345-3"],"issn":["1367-4811"],"eki":["266884857"]},"type":{"bibl":"periodical","media":"Online-Ressource"},"language":["eng"],"origin":[{"dateIssuedDisp":"1998-","publisherPlace":"Oxford","dateIssuedKey":"1998","publisher":"Oxford Univ. Press"}],"part":{"volume":"39","pages":"1-12","text":"39(2023), 6 vom: Juni, Artikel-ID btad387, Seite 1-12","year":"2023","extent":"12","issue":"6"},"physDesc":[{"extent":"Online-Ressource"}],"titleAlt":[{"title":"Bioinformatics online"}],"title":[{"title_sort":"Bioinformatics","title":"Bioinformatics"}]}],"type":{"bibl":"article-journal","media":"Online-Ressource"},"id":{"doi":["10.1093/bioinformatics/btad387"],"eki":["1856422836"]},"language":["eng"],"origin":[{"dateIssuedDisp":"June 2023","dateIssuedKey":"2023"}]} 
SRT |a DONCEVICDABIOLOGICAL2023 

Similar Items