CODEX, a neural network approach to explore signaling dynamics landscapes

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. SYNOPSIS Extracting relevant information from biosensor‐based single‐cell, time‐series data is challenging. CODEX, a data‐driven approach based on convolutional neural networks, identifies patterns in single‐cell trajectories and reveals characteristic motifs of signaling dynamics. CODEX uses convolutional neural networks to provide an intuitive and interpretable overview of single‐cell, biosensor time‐series. CODEX is an “all‐under‐one‐roof” approach that allows exploring data at three levels: low‐dimensional embedding of the entire dataset, prototype identification and characteristic motifs extraction. As a proof of concept, CODEX identifies dynamic signaling patterns in ERK, Akt, TGFβ/SMAD2 and p53 single‐cell time‐series. Graphical Abstract Extracting relevant information from biosensor‐based single‐cell, time‐series data is challenging. CODEX, a data‐driven approach based on convolutional neural networks, identifies patterns in single‐cell trajectories and reveals characteristic motifs of signaling dynamics.