CODEX, a Neural Network Approach to Explore Signaling Dynamics Landscapes

Overview

Journal Mol Syst Biol

Specialty Molecular Biology

Date 2021 Apr 9

PMID 33835701

Citations 13

Authors

Marc-Antoine Jacques

Maciej Dobrzynski

Paolo Armando Gagliardi

Raphael Sznitman

Olivier Pertz

Affiliations

Soon will be listed here.

Abstract

Current studies of cell signaling dynamics that use live cell fluorescent biosensors routinely yield thousands of single-cell, heterogeneous, multi-dimensional trajectories. Typically, the extraction of relevant information from time series data relies on predefined, human-interpretable features. Without a priori knowledge of the system, the predefined features may fail to cover the entire spectrum of dynamics. Here we present CODEX, a data-driven approach based on convolutional neural networks (CNNs) that identifies patterns in time series. It does not require a priori information about the biological system and the insights into the data are built through explanations of the CNNs' predictions. CODEX provides several views of the data: visualization of all the single-cell trajectories in a low-dimensional space, identification of prototypic trajectories, and extraction of distinctive motifs. We demonstrate how CODEX can provide new insights into ERK and Akt signaling in response to various growth factors, and we recapitulate findings in p53 and TGFβ-SMAD2 signaling.

Citing Articles

DynProfiler: a Python package for comprehensive analysis and interpretation of signaling dynamics leveraged by deep learning techniques.

Tsutsui M, Okada M Bioinform Adv. 2024; 4(1):vbae145.

PMID: 39391633 PMC: 11464416. DOI: 10.1093/bioadv/vbae145.

Mathematical Modeling and Inference of Epidermal Growth Factor-Induced Mitogen-Activated Protein Kinase Cell Signaling Pathways.

Feng J, Zhang X, Tian T Int J Mol Sci. 2024; 25(18).

PMID: 39337687 PMC: 11432143. DOI: 10.3390/ijms251810204.

Getting real about synthetic data ethics : Are AI ethics principles a good starting point for synthetic data ethics?.

Shanley D, Hogenboom J, Lysen F, Wee L, Lobo Gomes A, Dekker A EMBO Rep. 2024; 25(5):2152-2155.

PMID: 38388694 PMC: 11094102. DOI: 10.1038/s44319-024-00101-0.

Machine learning inference of continuous single-cell state transitions during myoblast differentiation and fusion.

Shakarchy A, Zarfati G, Hazak A, Mealem R, Huk K, Ziv T Mol Syst Biol. 2024; 20(3):217-241.

PMID: 38238594 PMC: 10912675. DOI: 10.1038/s44320-024-00010-3.

A guide to ERK dynamics, part 1: mechanisms and models.

Ram A, Murphy D, DeCuzzi N, Patankar M, Hu J, Pargett M Biochem J. 2023; 480(23):1887-1907.

PMID: 38038974 PMC: 10754288. DOI: 10.1042/BCJ20230276.

References

Bugaj L, Sabnis A, Mitchell A, Garbarino J, Toettcher J, Bivona T . Cancer mutations and targeted drugs can disrupt dynamic signal encoding by the Ras-Erk pathway. Science. 2018; 361(6405). PMC: 6430110. DOI: 10.1126/science.aao3048. View

Lahav G, Rosenfeld N, Sigal A, Geva-Zatorsky N, Levine A, Elowitz M . Dynamics of the p53-Mdm2 feedback loop in individual cells. Nat Genet. 2004; 36(2):147-50. DOI: 10.1038/ng1293. View

Sampattavanich S, Steiert B, Kramer B, Gyori B, Albeck J, Sorger P . Encoding Growth Factor Identity in the Temporal Dynamics of FOXO3 under the Combinatorial Control of ERK and AKT Kinases. Cell Syst. 2018; 6(6):664-678.e9. PMC: 6322215. DOI: 10.1016/j.cels.2018.05.004. View

Blum Y, Mikelson J, Dobrzynski M, Ryu H, Jacques M, Jeon N . Temporal perturbation of ERK dynamics reveals network architecture of FGF2/MAPK signaling. Mol Syst Biol. 2019; 15(11):e8947. PMC: 6864398. DOI: 10.15252/msb.20198947. View

Ryu H, Chung M, Dobrzynski M, Fey D, Blum Y, Lee S . Frequency modulation of ERK activation dynamics rewires cell fate. Mol Syst Biol. 2015; 11(11):838. PMC: 4670727. DOI: 10.15252/msb.20156458. View

Kholodenko B, Hancock J, Kolch W . Signalling ballet in space and time. Nat Rev Mol Cell Biol. 2010; 11(6):414-26. PMC: 2977972. DOI: 10.1038/nrm2901. View

Mergenthaler P, Hariharan S, Pemberton J, Lourenco C, Penn L, Andrews D . Rapid 3D phenotypic analysis of neurons and organoids using data-driven cell segmentation-free machine learning. PLoS Comput Biol. 2021; 17(2):e1008630. PMC: 7932518. DOI: 10.1371/journal.pcbi.1008630. View

Snijder B, Pelkmans L . Origins of regulated cell-to-cell variability. Nat Rev Mol Cell Biol. 2011; 12(2):119-25. DOI: 10.1038/nrm3044. View

Aoki K, Kondo Y, Naoki H, Hiratsuka T, Itoh R, Matsuda M . Propagating Wave of ERK Activation Orients Collective Cell Migration. Dev Cell. 2017; 43(3):305-317.e5. DOI: 10.1016/j.devcel.2017.10.016. View

10.

Albeck J, Mills G, Brugge J . Frequency-modulated pulses of ERK activity transmit quantitative proliferation signals. Mol Cell. 2012; 49(2):249-61. PMC: 4151532. DOI: 10.1016/j.molcel.2012.11.002. View

11.

Jacques M, Dobrzynski M, Gagliardi P, Sznitman R, Pertz O . CODEX, a neural network approach to explore signaling dynamics landscapes. Mol Syst Biol. 2021; 17(4):e10026. PMC: 8034356. DOI: 10.15252/msb.202010026. View

12.

Gagliardi P, Dobrzynski M, Jacques M, Dessauges C, Ender P, Blum Y . Collective ERK/Akt activity waves orchestrate epithelial homeostasis by driving apoptosis-induced survival. Dev Cell. 2021; 56(12):1712-1726.e6. DOI: 10.1016/j.devcel.2021.05.007. View

13.

Stewart-Ornstein J, Lahav G . p53 dynamics in response to DNA damage vary across cell lines and are shaped by efficiency of DNA repair and activity of the kinase ATM. Sci Signal. 2017; 10(476). PMC: 5504473. DOI: 10.1126/scisignal.aah6671. View

14.

Regot S, Hughey J, Bajar B, Carrasco S, Covert M . High-sensitivity measurements of multiple kinase activities in live single cells. Cell. 2014; 157(7):1724-34. PMC: 4097317. DOI: 10.1016/j.cell.2014.04.039. View

15.

Sharifi-Noghabi H, Zolotareva O, Collins C, Ester M . MOLI: multi-omics late integration with deep neural networks for drug response prediction. Bioinformatics. 2019; 35(14):i501-i509. PMC: 6612815. DOI: 10.1093/bioinformatics/btz318. View

16.

Tay S, Hughey J, Lee T, Lipniacki T, Quake S, Covert M . Single-cell NF-kappaB dynamics reveal digital activation and analogue information processing. Nature. 2010; 466(7303):267-71. PMC: 3105528. DOI: 10.1038/nature09145. View

17.

Berg S, Kutra D, Kroeger T, Straehle C, Kausler B, Haubold C . ilastik: interactive machine learning for (bio)image analysis. Nat Methods. 2019; 16(12):1226-1232. DOI: 10.1038/s41592-019-0582-9. View

18.

Dobrzynski M, Jacques M, Pertz O . Mining single-cell time-series datasets with Time Course Inspector. Bioinformatics. 2023; 36(6):1968-1969. DOI: 10.1093/bioinformatics/btz846. View

19.

McQuin C, Goodman A, Chernyshev V, Kamentsky L, Cimini B, Karhohs K . CellProfiler 3.0: Next-generation image processing for biology. PLoS Biol. 2018; 16(7):e2005970. PMC: 6029841. DOI: 10.1371/journal.pbio.2005970. View

20.

Yarden Y, Pines G . The ERBB network: at last, cancer therapy meets systems biology. Nat Rev Cancer. 2012; 12(8):553-63. DOI: 10.1038/nrc3309. View