Browse views: by Year, by Function, by GLF, by Subfunction, by Conference, by Journal

Biologically relevant integration of transcriptomics profiles from cancer cell lines, patient derived xenografts and patient tumors using deep neural networks

Dimitrieva Janeva, Slavica, Janssens, Rens, Li, Gang, Szalata, Artur, Gopal, Raja, Parmar, Chintan, Kauffmann, Audrey and Durand, Eric (2022) Biologically relevant integration of transcriptomics profiles from cancer cell lines, patient derived xenografts and patient tumors using deep neural networks. bioRxiv.

Abstract

Cell lines and patient-derived xenografts are essential to cancer research, however, the results derived from such models often lack clinical translatability, primarily due to the fact that these models do not fully recapitulate the complex cancer biology. It is therefore critically important to better understand the systematic differences between cell lines, xenografts and clinical tumors, and to be able to identify pre-clinical models that sufficiently resemble the biological characteristics of clinical tumors across different cancers. On another side, direct comparison of transcriptional profiles from pre-clinical models and clinical tumors is infeasible due to the mixture of technical artifacts and inherent biological signals.
To address these challenges, we developed MOBER, Multi-Origin Batch Effect Removal method, to simultaneously extract biologically meaningful embeddings and remove batch effects from transcriptomic datasets of different origin. MOBER consists of two neural networks: conditional variational autoencoder and source discriminator neural network that is trained in adversarial fashion. We applied MOBER on transcriptional profiles from 932 cancer cell lines, 434 patient-derived xenografts and 11159 clinical tumors and identified pre-clinical models with greatest transcriptional fidelity to clinical tumors, and models that are transcriptionally unrepresentative of their respective clinical tumors. We demonstrate that MOBER can conserve the biological signals from the original datasets, while generating embeddings that do not encode confounder information. In addition, it allows for transformation of transcriptional profiles of pre-clinical models into clinical tumors and we show how it can be used to improve the clinical translation of insights gained from pre-clinical models.
As a batch effect removal method, MOBER confers superior performance over the state-of-the-art methods, while allowing for integration of multiple datasets simultaneously.

Item Type: Article
Keywords: deep learning, pre-clinical and clinical model alignment, MOBER
Date Deposited: 04 Jul 2023 00:45
Last Modified: 04 Jul 2023 00:45
URI: https://oak.novartis.com/id/eprint/48282

Search