Literature DB >> 33381839

Conditional out-of-distribution generation for unpaired data using transfer VAE.

Mohammad Lotfollahi1,2, Mohsen Naghipourfar1, Fabian J Theis1,2,3, F Alexander Wolf1.   

Abstract

MOTIVATION: While generative models have shown great success in sampling high-dimensional samples conditional on low-dimensional descriptors (stroke thickness in MNIST, hair color in CelebA, speaker identity in WaveNet), their generation out-of-distribution poses fundamental problems due to the difficulty of learning compact joint distribution across conditions. The canonical example of the conditional variational autoencoder (CVAE), for instance, does not explicitly relate conditions during training and, hence, has no explicit incentive of learning such a compact representation.
RESULTS: We overcome the limitation of the CVAE by matching distributions across conditions using maximum mean discrepancy in the decoder layer that follows the bottleneck. This introduces a strong regularization both for reconstructing samples within the same condition and for transforming samples across conditions, resulting in much improved generalization. As this amount to solving a style-transfer problem, we refer to the model as transfer VAE (trVAE). Benchmarking trVAE on high-dimensional image and single-cell RNA-seq, we demonstrate higher robustness and higher accuracy than existing approaches. We also show qualitatively improved predictions by tackling previously problematic minority classes and multiple conditions in the context of cellular perturbation response to treatment and disease based on high-dimensional single-cell gene expression data. For generic tasks, we improve Pearson correlations of high-dimensional estimated means and variances with their ground truths from 0.89 to 0.97 and 0.75 to 0.87, respectively. We further demonstrate that trVAE learns cell-type-specific responses after perturbation and improves the prediction of most cell-type-specific genes by 65%.
AVAILABILITY AND IMPLEMENTATION: The trVAE implementation is available via github.com/theislab/trvae. The results of this article can be reproduced via github.com/theislab/trvae_reproducibility.
© The Author(s) 2020. Published by Oxford University Press. All rights reserved. For permissions, please e-mail: journals.permissions@oup.com.

Entities:  

Mesh:

Year:  2020        PMID: 33381839     DOI: 10.1093/bioinformatics/btaa800

Source DB:  PubMed          Journal:  Bioinformatics        ISSN: 1367-4803            Impact factor:   6.937


  6 in total

Review 1.  Progress and challenges for the machine learning-based design of fit-for-purpose monoclonal antibodies.

Authors:  Rahmad Akbar; Habib Bashour; Puneet Rawat; Philippe A Robert; Eva Smorodina; Tudor-Stefan Cotet; Karine Flem-Karlsen; Robert Frank; Brij Bhushan Mehta; Mai Ha Vu; Talip Zengin; Jose Gutierrez-Marcos; Fridtjof Lund-Johansen; Jan Terje Andersen; Victor Greiff
Journal:  MAbs       Date:  2022 Jan-Dec       Impact factor: 5.857

2.  Mapping single-cell data to reference atlases by transfer learning.

Authors:  Mohammad Lotfollahi; Mohsen Naghipourfar; Malte D Luecken; Matin Khajavi; Maren Büttner; Marco Wagenstetter; Žiga Avsec; Adam Gayoso; Nir Yosef; Marta Interlandi; Sergei Rybakov; Alexander V Misharin; Fabian J Theis
Journal:  Nat Biotechnol       Date:  2021-08-30       Impact factor: 68.164

3.  Interpretable Autoencoders Trained on Single Cell Sequencing Data Can Transfer Directly to Data from Unseen Tissues.

Authors:  Julie Sparholt Walbech; Savvas Kinalis; Ole Winther; Finn Cilius Nielsen; Frederik Otzen Bagger
Journal:  Cells       Date:  2021-12-28       Impact factor: 6.600

4.  Efficient and precise single-cell reference atlas mapping with Symphony.

Authors:  Ilya Korsunsky; Soumya Raychaudhuri; Joyce B Kang; Aparna Nathan; Kathryn Weinand; Fan Zhang; Nghia Millard; Laurie Rumker; D Branch Moody
Journal:  Nat Commun       Date:  2021-10-07       Impact factor: 17.694

5.  Transfer learning of clinical outcomes from preclinical molecular data, principles and perspectives.

Authors:  Axel Kowald; Israel Barrantes; Steffen Möller; Daniel Palmer; Hugo Murua Escobar; Anne Schwerk; Georg Fuellen
Journal:  Brief Bioinform       Date:  2022-05-13       Impact factor: 13.994

6.  Benchmarking atlas-level data integration in single-cell genomics.

Authors:  Malte D Luecken; M Büttner; K Chaichoompu; A Danese; M Interlandi; M F Mueller; D C Strobl; L Zappia; M Dugas; M Colomé-Tatché; Fabian J Theis
Journal:  Nat Methods       Date:  2021-12-23       Impact factor: 28.547

  6 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.