Multi-omics Prediction from High-content Cellular Imaging with Deep Learning

High-content cellular imaging, transcriptomics, and proteomics data provide rich and complementary views on the molecular layers of biology that influence cellular states and function. However, the biological determinants through which changes in multi-omics measurements influence cellular morphology have not yet been systematically explored, and the degree to which cell imaging could potentially enable the prediction of multi-omics directly from cell imaging data is therefore currently unclear. Here, we address the question of whether it is possible to predict bulk multi-omics measurements directly from cell images using Image2Omics -- a deep learning approach that predicts multi-omics in a cell population directly from high-content images stained with multiplexed fluorescent dyes. We perform an experimental evaluation in gene-edited macrophages derived from human induced pluripotent stem cell (hiPSC) under multiple stimulation conditions and demonstrate that Image2Omics achieves significantly better performance in predicting transcriptomics and proteomics measurements directly from cell images than predictors based on the mean observed training set abundance. We observed significant predictability of abundances for 5903 (22.43%; 95% CI: 8.77%, 38.88%) and 5819 (22.11%; 95% CI: 10.40%, 38.08%) transcripts out of 26137 in M1 and M2-stimulated macrophages respectively and for 1933 (38.77%; 95% CI: 36.94%, 39.85%) and 2055 (41.22%; 95% CI: 39.31%, 42.42%) proteins out of 4986 in M1 and M2-stimulated macrophages respectively. Our results show that some transcript and protein abundances are predictable from cell imaging and that cell imaging may potentially, in some settings and depending on the mechanisms of interest and desired performance threshold, even be a scalable and resource-efficient substitute for multi-omics measurements.

[1]  Jakob Nikolas Kather,et al.  Deep learning can predict multi-omic biomarkers from routine pathology images: A systematic large-scale study , 2022, bioRxiv.

[2]  Joshua D. Welch,et al.  MorphNet Predicts Cell Morphology from Single-Cell Gene Expression , 2022, bioRxiv.

[3]  M. Hild,et al.  DRUG-seq Provides Unbiased Biological Activity Readouts for Neuroscience Drug Discovery , 2022, ACS chemical biology.

[4]  Lani F. Wu,et al.  Integrative spatial analysis of cell morphologies and transcriptional states with MUSE , 2022, Nature Biotechnology.

[5]  J. Mar,et al.  Computational Methods for Single-Cell Imaging and Omics Data Integration , 2022, Frontiers in Molecular Biosciences.

[6]  Alan M. Moses,et al.  CytoImageNet: A large-scale pretraining dataset for bioimage transfer learning , 2021, ArXiv.

[7]  Arash Mehrjou,et al.  GeneDisco: A Benchmark for Experimental Design in Drug Discovery , 2021, ICLR.

[8]  Anne E Carpenter,et al.  High-Dimensional Gene Expression and Morphology Profiles of Cells across 28,000 Genetic and Chemical Perturbations , 2021, bioRxiv.

[9]  Nan Rosemary Ke,et al.  Learning Neural Causal Models with Active Interventions , 2021, ArXiv.

[10]  Yen-Wei Chen,et al.  Genotype-Guided Radiomics Signatures for Recurrence Prediction of Non-Small Cell Lung Cancer , 2021, IEEE Access.

[11]  L. Elo,et al.  Computational strategies for single-cell multi-omics integration , 2021, Computational and structural biotechnology journal.

[12]  Kai Tan,et al.  GLUER: integrative analysis of single-cell omics and imaging data by deep neural network , 2021, bioRxiv.

[13]  Dali Li,et al.  Strategies in the delivery of Cas9 ribonucleoprotein for CRISPR/Cas9 genome editing , 2021, Theranostics.

[14]  Sergios Gatidis,et al.  Overcoming barriers to data sharing with medical image generation: a comprehensive evaluation , 2020, npj Digital Medicine.

[15]  Fabian J Theis,et al.  Predicting single-cell gene expression profiles of imaging flow cytometry data with machine learning , 2020, Nucleic acids research.

[16]  Pierre Courtiol,et al.  A deep learning model to predict RNA-Seq expression of tumours from whole slide images , 2020, Nature Communications.

[17]  Anne E Carpenter,et al.  Predicting cell health phenotypes using image-based morphology profiling , 2020, bioRxiv.

[18]  M. Hatt,et al.  Transcriptomics in cancer revealed by Positron Emission Tomography radiomics , 2020, Scientific Reports.

[19]  Sreeram Kannan,et al.  Inferring Causal Gene Regulatory Networks from Coupled Single-Cell Expression Dynamics Using Scribe. , 2020, Cell systems.

[20]  Shiva Kumar,et al.  Multi-omics Data Integration, Interpretation, and Its Application , 2020, Bioinformatics and biology insights.

[21]  Anastasiya Belyaeva,et al.  Multi-domain translation between single-cell imaging and sequencing data using autoencoders , 2019, Nature Communications.

[22]  F. Azuaje,et al.  Connecting Histopathology Imaging and Proteomics in Kidney Cancer through Machine Learning , 2019, bioRxiv.

[23]  David Wishart,et al.  Systems Biology and Multi-Omics Integration: Viewpoints from the Metabolomics Research Community , 2019, Metabolites.

[24]  Lai Guan Ng,et al.  Dimensionality reduction for visualizing single-cell data using UMAP , 2018, Nature Biotechnology.

[25]  Kiyomi Tsuji-Tamura,et al.  Morphology regulation in vascular endothelial cells , 2018, Inflammation and regeneration.

[26]  Marc Berndl,et al.  Improving Phenotypic Measurements in High-Content Imaging Screens , 2017, bioRxiv.

[27]  Devin P. Sullivan,et al.  A subcellular map of the human proteome , 2017, Science.

[28]  A. Lusis,et al.  Multi-omics approaches to disease , 2017, Genome Biology.

[29]  Anne E Carpenter,et al.  A dataset of images and morphological profiles of 30 000 small-molecule treatments using the Cell Painting assay , 2017, GigaScience.

[30]  Ludovic C. Gillet,et al.  Mass Spectrometry Applied to Bottom-Up Proteomics: Entering the High-Throughput Era for Hypothesis Testing. , 2016, Annual review of analytical chemistry.

[31]  Anne E Carpenter,et al.  Cell Painting, a high-content image-based assay for morphological profiling using multiplexed fluorescent dyes , 2016, Nature Protocols.

[32]  Kate Saenko,et al.  Return of Frustratingly Easy Domain Adaptation , 2015, AAAI.

[33]  G. Drewes,et al.  Thermal proteome profiling for unbiased identification of direct and indirect drug targets using multiplexed quantitative mass spectrometry , 2015, Nature Protocols.

[34]  Wendy F. Liu,et al.  Physical and mechanical regulation of macrophage phenotype and function , 2015, Cellular and Molecular Life Sciences.

[35]  James Philbin,et al.  FaceNet: A unified embedding for face recognition and clustering , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[36]  Anne E Carpenter,et al.  Pipeline for illumination correction of images for high-throughput microscopy , 2014, Journal of microscopy.

[37]  R. Kream,et al.  Comparing Bioinformatic Gene Expression Profiling Methods: Microarray and RNA-Seq , 2014, Medical science monitor basic research.

[38]  B. Kuster,et al.  Measuring and managing ratio compression for accurate iTRAQ/TMT quantification. , 2013, Journal of proteome research.

[39]  T. Okano,et al.  Hippo pathway regulation by cell morphology and stress fibers , 2011, Development.

[40]  Frank Fischer,et al.  Targeted data acquisition for improved reproducibility and robustness of proteomic mass spectrometry assays , 2010, Journal of the American Society for Mass Spectrometry.

[41]  R. Pepperkok,et al.  The potential of high‐content high‐throughput microscopy in drug discovery , 2007, British journal of pharmacology.

[42]  Jens M. Rick,et al.  Quantitative mass spectrometry in proteomics: a critical review , 2007, Analytical and bioanalytical chemistry.

[43]  D. Litchfield,et al.  The shape of things to come: an emerging role for protein kinase CK2 in the regulation of cell morphology and the cytoskeleton. , 2006, Cellular signalling.

[44]  G. Hamilton,et al.  Regulation of cell morphology and cytochrome P450 expression in human hepatocytes by extracellular matrix and cell-cell interactions , 2001, Cell and Tissue Research.

[45]  M. Tremblay,et al.  Morphology of Microglia Across Contexts of Health and Disease. , 2019, Methods in molecular biology.

[46]  Mahendra S Rao,et al.  A review of the methods for human iPSC derivation. , 2013, Methods in molecular biology.