End-to-end training of deep probabilistic CCA for joint modeling of paired biomedical observations

Many diseases are diagnosed by pathologists using key morphological features in imaging data; but the genes that capture the internal state of cells and are therefore associated with specific morphologies are typically unknown. To address this question, the GTEx Consortium [8; 7] has collected data from over 948 autopsy research subjects, including standardized whole tissue slides and RNA sequencing gene expression levels from approximately 50 different human tissues. These multi-subject, multiview data provide an opportunity to develop computational tools that quantify how genome-level associations affect morphological features observable in histology slides.

[1]  Zoubin Ghahramani,et al.  Probabilistic machine learning and artificial intelligence , 2015, Nature.

[2]  John Quackenbush,et al.  Histopathological Image QTL Discovery of Immune Infiltration Variants , 2018, iScience.

[3]  Mohammad Emtiyaz Khan,et al.  Variational Message Passing with Structured Inference Networks , 2018, ICLR.

[4]  Shotaro Akaho,et al.  A kernel method for canonical correlation analysis , 2006, ArXiv.

[5]  B. Engelhardt,et al.  Joint analysis of expression levels and histological images identifies genes associated with tissue morphology , 2018, Nature Communications.

[6]  Zachary Chase Lipton.  The mythos of model interpretability , 2016, ACM Queue.

[7]  Michael I. Jordan,et al.  A Probabilistic Interpretation of Canonical Correlation Analysis , 2005 .

[8]  Jeff A. Bilmes,et al.  Deep Canonical Correlation Analysis , 2013, ICML.

[9]  Sebastian Thrun,et al.  Dermatologist-level classification of skin cancer with deep neural networks , 2017, Nature.

[10]  Honglak Lee,et al.  Deep Variational Canonical Correlation Analysis , 2016, ArXiv.

[11]  Kevin P. Murphy,et al.  Machine learning - a probabilistic perspective , 2012, Adaptive computation and machine learning series.

[12]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[13]  Hayit Greenspan,et al.  Chest pathology detection using deep learning with non-medical training , 2015, 2015 IEEE 12th International Symposium on Biomedical Imaging (ISBI).

[14]  H. Hotelling.  Relations Between Two Sets of Variates , 1936 .

[15]  John Shawe-Taylor,et al.  Canonical Correlation Analysis: An Overview with Application to Learning Methods , 2004, Neural Computation.

[16]  Kyunghyun Cho,et al.  High-Resolution Breast Cancer Screening with Multi-View Deep Convolutional Neural Networks , 2017, ArXiv.

[17]  Geoffrey E. Hinton,et al.  The EM algorithm for mixtures of factor analyzers , 1996 .

[18]  Subhashini Venugopalan,et al.  Development and Validation of a Deep Learning Algorithm for Detection of Diabetic Retinopathy in Retinal Fundus Photographs. , 2016, JAMA.

[19]  Ryan P. Adams,et al.  Composing graphical models with neural networks for structured representations and fast inference , 2016, NIPS.

[20]  LinLin Shen,et al.  Deep Feature Consistent Variational Autoencoder , 2016, 2017 IEEE Winter Conference on Applications of Computer Vision (WACV).

[21]  Nicola J. Rinaldi,et al.  Genetic effects on gene expression across human tissues , 2017, Nature.

[22]  Samuel Kaski,et al.  Bayesian Canonical correlation analysis , 2013, J. Mach. Learn. Res..

[23]  Korbinian Strimmer,et al.  Probabilistic Canonical Correlation Analysis: A Whitening Approach , 2018 .

[24]  William M. Rand,et al.  Objective Criteria for the Evaluation of Clustering Methods , 1971 .

[25]  Ellen T. Gelfand,et al.  A Novel Approach to High-Quality Postmortem Tissue Procurement: The GTEx Project , 2015, Biopreservation and biobanking.

[26]  Max Welling,et al.  Auto-Encoding Variational Bayes , 2013, ICLR.

[27]  Dayong Wang,et al.  Deep learning assessment of tumor proliferation in breast cancer histological images , 2016, 2017 IEEE International Conference on Bioinformatics and Biomedicine (BIBM).