scholarly journals Exploiting Gene Expression Profiles for the Automated Prediction of Connectivity between Brain Regions

2019 ◽  
Vol 20 (8) ◽  
pp. 2035 ◽  
Author(s):  
Ilaria Roberti ◽  
Marta Lovino ◽  
Santa Di Cataldo ◽  
Elisa Ficarra ◽  
Gianvito Urgese
Keyword(s):  
Gene Expression ◽  
Neural Networks ◽  
Expression Profiles ◽  
Brain Area ◽  
Gene Expression Profiles ◽  
Brain Structures ◽  
Brain Regions ◽  
Brain Atlas ◽  
Data Driven Approach ◽  
Prediction Problems

The brain comprises a complex system of neurons interconnected by an intricate network of anatomical links. While recent studies demonstrated the correlation between anatomical connectivity patterns and gene expression of neurons, using transcriptomic information to automatically predict such patterns is still an open challenge. In this work, we present a completely data-driven approach relying on machine learning (i.e., neural networks) to learn the anatomical connection directly from a training set of gene expression data. To do so, we combined gene expression and connectivity data from the Allen Mouse Brain Atlas to generate thousands of gene expression profile pairs from different brain regions. To each pair, we assigned a label describing the physical connection between the corresponding brain regions. Then, we exploited these data to train neural networks, designed to predict brain area connectivity. We assessed our solution on two prediction problems (with three and two connectivity class categories) involving cortical and cerebellum regions. As demonstrated by our results, we distinguish between connected and unconnected regions with 85% prediction accuracy and good balance of precision and recall. In our future work we may extend the analysis to more complex brain structures and consider RNA-Seq data as additional input to our model.

scholarly journals Dynamical consequences of regional heterogeneity in the brain’s transcriptional landscape

2020 ◽  
Author(s):  
Gustavo Deco ◽  
Kevin Aquino ◽  
Aurina Arnatkevičiūtė ◽  
Stuart Oldham ◽  
Kristina Sabaroedin ◽  
...  
Keyword(s):  
Gene Expression ◽  
Large Scale ◽  
Expression Profiles ◽  
Gene Expression Profiles ◽  
Global Gene Expression ◽  
Brain Regions ◽  
Biophysical Model ◽  
Neuronal Dynamics ◽  
Regional Heterogeneity ◽  
Magnetic Resonance Imaging Mri

AbstractBrain regions vary in their molecular and cellular composition, but how this heterogeneity shapes neuronal dynamics is unclear. Here, we investigate the dynamical consequences of regional heterogeneity using a biophysical model of whole-brain functional magnetic resonance imaging (MRI) dynamics in humans. We show that models in which transcriptional variations in excitatory and inhibitory receptor (E:I) gene expression constrain regional heterogeneity more accurately reproduce the spatiotemporal structure of empirical functional connectivity estimates than do models constrained by global gene expression profiles and MRI-derived estimates of myeloarchitecture. We further show that regional heterogeneity is essential for yielding both ignition-like dynamics, which are thought to support conscious processing, and a wide variance of regional activity timescales, which supports a broad dynamical range. We thus identify a key role for E:I heterogeneity in generating complex neuronal dynamics and demonstrate the viability of using transcriptional data to constrain models of large-scale brain function.

High-throughput single-cell RNA-seq data imputation and characterization with surrogate-assisted automated deep learning

2021 ◽  
Author(s):  
Xiangtao Li ◽  
Shaochuan Li ◽  
Lei Huang ◽  
Shixiong Zhang ◽  
Ka-chun Wong
Keyword(s):  
Gene Expression ◽  
Neural Networks ◽  
Single Cell ◽  
Deep Neural Networks ◽  
Expression Profiles ◽  
Marker Gene ◽  
Gene Expression Profiles ◽  
Underlying Mechanisms ◽  
Cell Data ◽  
Gene Expression Levels

Abstract Single-cell RNA sequencing (scRNA-seq) technologies have been heavily developed to probe gene expression profiles at single-cell resolution. Deep imputation methods have been proposed to address the related computational challenges (e.g. the gene sparsity in single-cell data). In particular, the neural architectures of those deep imputation models have been proven to be critical for performance. However, deep imputation architectures are difficult to design and tune for those without rich knowledge of deep neural networks and scRNA-seq. Therefore, Surrogate-assisted Evolutionary Deep Imputation Model (SEDIM) is proposed to automatically design the architectures of deep neural networks for imputing gene expression levels in scRNA-seq data without any manual tuning. Moreover, the proposed SEDIM constructs an offline surrogate model, which can accelerate the computational efficiency of the architectural search. Comprehensive studies show that SEDIM significantly improves the imputation and clustering performance compared with other benchmark methods. In addition, we also extensively explore the performance of SEDIM in other contexts and platforms including mass cytometry and metabolic profiling in a comprehensive manner. Marker gene detection, gene ontology enrichment and pathological analysis are conducted to provide novel insights into cell-type identification and the underlying mechanisms. The source code is available at https://github.com/li-shaochuan/SEDIM.

scholarly journals Cell Identity Codes: Understanding Cell Identity from Gene Expression Profiles using Deep Neural Networks

2019 ◽  
Vol 9 (1) ◽  
Author(s):  
Farzad Abdolhosseini ◽  
Behrooz Azarkhalili ◽  
Abbas Maazallahi ◽  
Aryan Kamal ◽  
Seyed Abolfazl Motahari ◽  
...  
Keyword(s):  
Gene Expression ◽  
Neural Networks ◽  
Deep Neural Networks ◽  
Expression Profiles ◽  
Gene Expression Profiles ◽  
Cell Identity

scholarly journals On transformative adaptive activation functions in neural networks for gene expression inference

PLoS ONE ◽  
2021 ◽  
Vol 16 (1) ◽  
pp. e0243915
Author(s):  
Vladimír Kunc ◽  
Jiří Kléma
Keyword(s):  
Gene Expression ◽  
Neural Networks ◽  
Mean Absolute Error ◽  
Expression Profiles ◽  
Gene Expression Profiles ◽  
Cost Effective ◽  
Absolute Error ◽  
Activation Function ◽  
Training Procedure ◽  
Activation Functions

Gene expression profiling was made more cost-effective by the NIH LINCS program that profiles only ∼1, 000 selected landmark genes and uses them to reconstruct the whole profile. The D–GEX method employs neural networks to infer the entire profile. However, the original D–GEX can be significantly improved. We propose a novel transformative adaptive activation function that improves the gene expression inference even further and which generalizes several existing adaptive activation functions. Our improved neural network achieves an average mean absolute error of 0.1340, which is a significant improvement over our reimplementation of the original D–GEX, which achieves an average mean absolute error of 0.1637. The proposed transformative adaptive function enables a significantly more accurate reconstruction of the full gene expression profiles with only a small increase in the complexity of the model and its training procedure compared to other methods.

scholarly journals Distinct properties in ventral pallidum projection neuron subtypes

2021 ◽  
Author(s):  
Nimrod Bernat ◽  
Rianne Campbell ◽  
Hyungwoo Nam ◽  
Mahashweta Basu ◽  
Tal Odesser ◽  
...  
Keyword(s):  
Gene Expression ◽  
Expression Profiles ◽  
Expression Patterns ◽  
Critical Role ◽  
Gene Expression Profiles ◽  
Cell Types ◽  
Projection Neuron ◽  
Brain Regions ◽  
Ventral Pallidum ◽  
Lateral Habenula

The ventral pallidum (VP), a major component of the basal ganglia, plays a critical role in motivational disorders. It sends projections to many different brain regions but it is not yet known whether and how these projections differ in their cellular properties, gene expression patterns, connectivity and role in reward seeking. In this study, we focus on four major outputs of the VP - to the lateral hypothalamus (LH), ventral tegmental area (VTA), mediodorsal thalamus (MDT), and lateral habenula (LHb) - and examine the differences between them in 1) baseline gene expression profiles using projection-specific RNA-sequencing; 2) physiological parameters using whole-cell patch clamp; and 3) their influence on cocaine reward using chemogenetic tools. We show that these four VP efferents differ in all three aspects and highlight specifically differences between the projections to the LH and the VTA. These two projections originate largely from separate populations of neurons, express distinct sets of genes related to neurobiological functions, and show opposite physiological and behavioral properties. Collectively, our data demonstrates for the first time that VP neurons exhibit distinct molecular and cellular profiles in a projection-specific manner, suggesting that they represent different cell types.

scholarly journals Adversarial Deconfounding Autoencoder for Learning Robust Gene Expression Embeddings

2020 ◽  
Author(s):  
Ayse B. Dincer ◽  
Joseph D. Janizek ◽  
Su-In Lee
Keyword(s):  
Gene Expression ◽  
Neural Networks ◽  
Expression Profiles ◽  
Gene Expression Profiles ◽  
Batch Effects ◽  
Biological Variables ◽  
Large Numbers ◽  
Latent Space ◽  
Complex Models ◽  
Unsupervised Neural Networks

AbstractMotivationIncreasing number of gene expression profiles has enabled the use of complex models, such as deep unsupervised neural networks, to extract a latent space from these profiles. However, expression profiles, especially when collected in large numbers, inherently contain variations introduced by technical artifacts (e.g., batch effects) and uninteresting biological variables (e.g., age) in addition to the true signals of interest. These sources of variations, called confounders, produce embeddings that fail to transfer to different domains, i.e., an embedding learned from one dataset with a specific confounder distribution does not generalize to different distributions. To remedy this problem, we attempt to disentangle confounders from true signals to generate biologically informative embeddings.ResultsIn this paper, we introduce the AD-AE (Adversarial Deconfounding AutoEncoder) approach to deconfounding gene expression latent spaces. The AD-AE model consists of two neural networks: (i) an autoencoder to generate an embedding that can reconstruct original measurements, and (ii) an adversary trained to predict the confounder from that embedding. We jointly train the networks to generate embeddings that can encode as much information as possible without encoding any confounding signal. By applying AD-AE to two distinct gene expression datasets, we show that our model can (1) generate embeddings that do not encode confounder information, (2) conserve the biological signals present in the original space, and (3) generalize successfully across different confounder domains. We demonstrate that AD-AE outperforms standard autoencoder and other deconfounding approaches.AvailabilityOur code and data are available at https://gitlab.cs.washington.edu/abdincer/[email protected]; [email protected]

Sign in / Sign up

Export Citation Format

Share Document