skip to main content
US FlagAn official website of the United States government
dot gov icon
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
https lock icon
Secure .gov websites use HTTPS
A lock ( lock ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

Explore Research Products in the PAR
It may take a few hours for recently added research products to appear in PAR search results.


Title: Discovering and interpreting transcriptomic drivers of imaging traits using neural networks
Abstract Motivation Cancer heterogeneity is observed at multiple biological levels. To improve our understanding of these differences and their relevance in medicine, approaches to link organ- and tissue-level information from diagnostic images and cellular-level information from genomics are needed. However, these ‘radiogenomic’ studies often use linear or shallow models, depend on feature selection, or consider one gene at a time to map images to genes. Moreover, no study has systematically attempted to understand the molecular basis of imaging traits based on the interpretation of what the neural network has learned. These studies are thus limited in their ability to understand the transcriptomic drivers of imaging traits, which could provide additional context for determining clinical outcomes. Results We present a neural network-based approach that takes high-dimensional gene expression data as input and performs non-linear mapping to an imaging trait. To interpret the models, we propose gene masking and gene saliency to extract learned relationships from radiogenomic neural networks. In glioblastoma patients, our models outperformed comparable classifiers (>0.10 AUC) and our interpretation methods were validated using a similar model to identify known relationships between genes and molecular subtypes. We found that tumor imaging traits had specific transcription patterns, e.g. edema and genes related to cellular invasion, and 10 radiogenomic traits were significantly predictive of survival. We demonstrate that neural networks can model transcriptomic heterogeneity to reflect differences in imaging and can be used to derive radiogenomic traits with clinical value. Availability and implementation https://github.com/novasmedley/deepRadiogenomics. Contact whsu@mednet.ucla.edu Supplementary information Supplementary data are available at Bioinformatics online.  more » « less
Award ID(s):
1722516
PAR ID:
10179587
Author(s) / Creator(s):
; ; ;
Date Published:
Journal Name:
Bioinformatics
Volume:
36
Issue:
11
ISSN:
1367-4803
Page Range / eLocation ID:
3537 to 3548
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ; ; ; ; (, Bioinformatics)
    Martelli, Pier Luigi (Ed.)
    Abstract Motivation Clustering spatial-resolved gene expression is an essential analysis to reveal gene activities in the underlying morphological context by their functional roles. However, conventional clustering analysis does not consider gene expression co-localizations in tissue for detecting spatial expression patterns or functional relationships among the genes for biological interpretation in the spatial context. In this article, we present a convolutional neural network (CNN) regularized by the graph of protein–protein interaction (PPI) network to cluster spatially resolved gene expression. This method improves the coherence of spatial patterns and provides biological interpretation of the gene clusters in the spatial context by exploiting the spatial localization by convolution and gene functional relationships by graph-Laplacian regularization. Results In this study, we tested clustering the spatially variable genes or all expressed genes in the transcriptome in 22 Visium spatial transcriptomics datasets of different tissue sections publicly available from 10× Genomics and spatialLIBD. The results demonstrate that the PPI-regularized CNN constantly detects gene clusters with coherent spatial patterns and significantly enriched by gene functions with the state-of-the-art performance. Additional case studies on mouse kidney tissue and human breast cancer tissue suggest that the PPI-regularized CNN also detects spatially co-expressed genes to define the corresponding morphological context in the tissue with valuable insights. Availability and implementation Source code is available at https://github.com/kuanglab/CNN-PReg. Supplementary information Supplementary data are available at Bioinformatics online. 
    more » « less
  2. ; ; ; ; ; (, PLOS Computational Biology)
    Borenstein, Elhanan (Ed.)
    Recurrent neural networks with memory and attention mechanisms are widely used in natural language processing because they can capture short and long term sequential information for diverse tasks. We propose an integrated deep learning model for microbial DNA sequence data, which exploits convolutional neural networks, recurrent neural networks, and attention mechanisms to predict taxonomic classifications and sample-associated attributes, such as the relationship between the microbiome and host phenotype, on the read/sequence level. In this paper, we develop this novel deep learning approach and evaluate its application to amplicon sequences. We apply our approach to short DNA reads and full sequences of 16S ribosomal RNA (rRNA) marker genes, which identify the heterogeneity of a microbial community sample. We demonstrate that our implementation of a novel attention-based deep network architecture, Read2Pheno , achieves read-level phenotypic prediction. Training Read2Pheno models will encode sequences (reads) into dense, meaningful representations: learned embedded vectors output from the intermediate layer of the network model, which can provide biological insight when visualized. The attention layer of Read2Pheno models can also automatically identify nucleotide regions in reads/sequences which are particularly informative for classification. As such, this novel approach can avoid pre/post-processing and manual interpretation required with conventional approaches to microbiome sequence classification. We further show, as proof-of-concept, that aggregating read-level information can robustly predict microbial community properties, host phenotype, and taxonomic classification, with performance at least comparable to conventional approaches. An implementation of the attention-based deep learning network is available at https://github.com/EESI/sequence_attention (a python package) and https://github.com/EESI/seq2att (a command line tool). 
    more » « less
  3. ; ; ; ; ; (, Nature Communications)
    The formation of complex traits is the consequence of genotype and activities at multiple molecular levels. However, connecting genotypes and these activities to complex traits remains challenging. Here, we investigate whether integrating genomic, transcriptomic, and methylomic data can improve pre- diction for six Arabidopsis traits. We find that transcriptome- and methylome- based models have performances comparable to those of genome-based models. However, models built for flowering time using different omics data identify different benchmark genes. Nine additional genes identified as important for flowering time from our models are experimentally validated as regulating flowering. Gene contributions to flowering time prediction are accession-dependent and distinct genes contribute to trait prediction in dif- ferent genotypes. Models integrating multi-omics data perform best and reveal known and additional gene interactions, extending knowledge about existing regulatory networks underlying flowering time determination. These results demonstrate the feasibility of revealing molecular mechanisms underlying complex traits through multi-omics data integration. 
    more » « less
  4. ; ; ; ; (, PLOS Computational Biology)
    Nie, Qing (Ed.)
    Single-cell RNA sequencing technology provides an opportunity to study gene expression at single-cell resolution. However, prevalent dropout events result in high data sparsity and noise that may obscure downstream analyses in single-cell transcriptomic studies. We propose a new method, G2S3, that imputes dropouts by borrowing information from adjacent genes in a sparse gene graph learned from gene expression profiles across cells. We applied G2S3 and ten existing imputation methods to eight single-cell transcriptomic datasets and compared their performance. Our results demonstrated that G2S3 has superior overall performance in recovering gene expression, identifying cell subtypes, reconstructing cell trajectories, identifying differentially expressed genes, and recovering gene regulatory and correlation relationships. Moreover, G2S3 is computationally efficient for imputation in large-scale single-cell transcriptomic datasets. 
    more » « less
  5. ; ; (, G3 Genes|Genomes|Genetics)
    Cherry, J M (Ed.)
    Abstract The mechanisms that coordinate cellular gene expression are highly complex and intricately interconnected. Thus, it is necessary to move beyond a fully reductionist approach to understanding genetic information flow and begin focusing on the networked connections between genes that organize cellular function. Continued advancements in computational hardware, coupled with the development of gene correlation network algorithms, provide the capacity to study networked interactions between genes rather than their isolated functions. For example, gene coexpression networks are used to construct gene relationship networks using linear metrics such as Spearman or Pearson correlation. Recently, there have been tools designed to deepen these analyses by differentiating between intrinsic vs extrinsic noise within gene expression values, identifying different modules based on tissue phenotype, and capturing potential nonlinear relationships. In this report, we introduce an algorithm with a novel application of image-based segmentation modalities utilizing blob detection techniques applied for detecting bigenic edges in a gene expression matrix. We applied this algorithm called EdgeCrafting to a bulk RNA-sequencing gene expression matrix comprised of a healthy kidney and cancerous kidney data. We then compared EdgeCrafting against 4 other RNA expression analysis techniques: Weighted Gene Correlation Network Analysis, Knowledge Independent Network Construction, NetExtractor, and Differential gene expression analysis. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email