In:
Molecular Systems Biology, EMBO, Vol. 19, No. 6 ( 2023-06-12)
Abstract:
image The compositional perturbation autoencoder (CPA) is a deep learning model for predicting the transcriptomic responses of single cells to single or combinatorial treatments from drugs and genetic manipulations. CPA can be trained on highly multiplexed, single‐cell experiments with thousands of conditions to predict unmeasured phenotypes (e.g., specific dose responses). It can generalize to predict responses to small molecules never seen in the training by adding priors on chemical space. Validations using a newly generated combinatorial drug perturbation dataset demonstrate the accuracy of CPA in predicting unseen drug combinations. CPA is also applicable to genetic combinatorial screens, as shown by imputing in silico 5,329 missing combinations in a single‐cell perturb‐seq experiment with diverse genetic interactions.
Type of Medium:
Online Resource
ISSN:
1744-4292
,
1744-4292
DOI:
10.15252/msb.202211517
Language:
English
Publisher:
EMBO
Publication Date:
2023
detail.hit.zdb_id:
2193510-5
SSG:
12
