DeepBrain: Functional Representation of Neural In-Situ Hybridization Images for Gene Ontology Classification Using Deep Convolutional Autoencoders

@article{Cohen2017DeepBrainFR,
  title={DeepBrain: Functional Representation of Neural In-Situ Hybridization Images for Gene Ontology Classification Using Deep Convolutional Autoencoders},
  author={Ido Cohen and Eli David and Nathan S. Netanyahu and Noa Liscovitch and Gal Chechik},
  journal={ArXiv},
  year={2017},
  volume={abs/1711.09663}
}
This paper presents a novel deep learning-based method for learning a functional representation of mammalian neural images. The method uses a deep convolutional denoising autoencoder (CDAE) for generating an invariant, compact representation of in situ hybridization (ISH) images. While most existing methods for bio-imaging analysis were not developed to handle images with highly complex anatomical structures, the results presented in this paper show that functional representation extracted by… 
Supervised and Unsupervised End-to-End Deep Learning for Gene Ontology Classification of Neural In Situ Hybridization Images †
TLDR
An in-depth description of the deep learning-based approach, and extensive experimental results, demonstrating that representations extracted by CDAE can help learn features of functional gene ontology categories for their classification in a highly accurate manner.
Evaluation of deep convolutional neural networks for in situ hybridization gene expression image representation
TLDR
Gene re-identification as a contrastive learning task to compute representations of ISH gene expression images is proposed and evaluated and gene and donor-specific embeddings from the model predict schizophrenia diagnosis at levels similar to that reached with demographic information.
Evaluation of deep convolutional neural networks for in situ hybridization gene expression image representation
TLDR
Gene and donor-specific embeddings from the model predict schizophrenia diagnosis at levels similar to that reached with demographic information, and mutations in the most discriminative gene, SCN4B, may help understand cardiovascular associations with schizophrenia and its treatment.
Unsupervised deep learning with variational autoencoders applied to breast tumor genome-wide DNA methylation data with biologic feature extraction
TLDR
An unsupervised deep learning framework with variational autoencoders (VAEs) is employed to learn latent representations of the DNA methylation landscape from three independent breast tumor datasets to demonstrate the feasibility of VAEs to track representative differential methylation patterns among clinical subtypes of tumors.
retina-VAE: Variationally Decoding the Spectrum of Macular Disease
In this paper, we seek a clinically-relevant latent code for representing the spectrum of macular disease. Towards this end, we construct retina-VAE, a variational autoencoder-based model that
Towards Knowledge Oriented Intelligent Audio Analytics
TLDR
It is argued that a knowledge- integrated DL framework is key to enable smart environments and knowledge can enable high-level reasoning, helping to scale up intelligent systems from sound recognition to event analysis.
An unsupervised deep learning framework with variational autoencoders for genome-wide DNA methylation analysis and biologic feature extraction applied to breast cancer
TLDR
An unsupervised deep learning framework with variational autoencoders (VAEs) is employed to learn latent representations of the DNA methylation landscape from three independent breast tumor datasets to demonstrate the feasibility of VAEs to track representative differential methylation patterns among clinical subtypes of tumors.

References

SHOWING 1-10 OF 30 REFERENCES
FuncISH: learning a functional representation of neural ISH images
TLDR
FuncISH is a method to learn functional representations of neural in situ hybridization (ISH) images that predict several gene interaction properties, such as protein–protein interactions and cell-type specificity, more accurately than competing methods based on global correlations.
GINI: From ISH Images to Gene Interaction Networks
TLDR
GINI, a machine learning system for inferring gene interaction networks from Drosophila embryonic ISH images, built on a computer-vision-inspired vector-space representation of the spatial pattern of gene expression in ISh images; and a new multi-instance-kernel algorithm that learns a sparse Markov network model.
Genome-wide atlas of gene expression in the adult mouse brain
TLDR
An anatomically comprehensive digital atlas containing the expression patterns of ∼20,000 genes in the adult mouse brain is described, providing an open, primary data resource for a wide variety of further studies concerning brain organization and function.
An anatomic gene expression atlas of the adult mouse brain
TLDR
The Anatomic Gene Expression Atlas (AGEA) is a new relational atlas revealing the genetic architecture of the adult C57Bl/6J mouse brain based on spatial correlations across expression data for thousands of genes in the Allen Brain Atlas (ABA).
A tool for identification of genes expressed in patterns of interest using the Allen Brain Atlas
TLDR
An open-source program that searches the ABA for genes that are expressed, enriched, patterned or graded in a user-specified region of interest, and demonstrates the utility of ALLENMINER by identifying genes that exhibit patterned expression in the caudoputamen and neocortex.
Multi-scale correlation structure of gene expression in the brain
Stacked Denoising Autoencoders: Learning Useful Representations in a Deep Network with a Local Denoising Criterion
TLDR
This work clearly establishes the value of using a denoising criterion as a tractable unsupervised objective to guide the learning of useful higher level representations.
Visualizing and Understanding Convolutional Networks
TLDR
A novel visualization technique is introduced that gives insight into the function of intermediate feature layers and the operation of the classifier in large Convolutional Network models, used in a diagnostic role to find model architectures that outperform Krizhevsky et al on the ImageNet classification benchmark.
An Efficient Algorithm to Integrate Network and Attribute Data for Gene Function Prediction
TLDR
An efficient learning algorithm to integrate these two types of heterogeneous data sources to perform binary prediction tasks on node features (e.g., gene prioritization, disease gene prediction) and seamlessly combine feature-based data sources with networks.
High-resolution gene expression atlases for adult and developing mouse brain and spinal cord
TLDR
The Allen Mouse Brain Atlas is presented, covering ~20,000 genes throughout the adult mouse brain; the Allen Developing mouse Brain Atlas, detailing expression of approximately 2,000 important developmental genes across seven embryonic and postnatal stages of brain growth; and the Allen Spinal Cord Atlas, revealing expression for ~20%,000 genes in the adult and neonatal mouse spinal cords.
...
...