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 On Transformative Adaptive Activation Functions in Neural Networks for Gene Expression Inference

2019 ◽  
Author(s):  
Vladimír Kunc ◽  
Jiří Kléma
Keyword(s):  
Neural Network ◽  
Gene Expression ◽  
Neural Networks ◽  
Expression Profiling ◽  
Mean Absolute Error ◽  
Absolute Error ◽  
Activation Function ◽  
Activation Functions ◽  
Hyperbolic Tangent ◽  
Sigmoid Activation Function

AbstractMotivationGene expression profiling was made cheaper 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 whole profile. However, the original D–GEX can be further significantly improved.ResultsWe have analyzed the D–GEX method and determined that the inference can be improved using a logistic sigmoid activation function instead of the hyperbolic tangent. Moreover, 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 average mean absolute error of 0.1340 which is a significant improvement over our reimplementation of the original D–GEX which achieves average mean absolute error 0.1637

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 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]

scholarly journals Adversarial deconfounding autoencoder for learning robust gene expression embeddings

2020 ◽  
Vol 36 (Supplement_2) ◽  
pp. i573-i582
Author(s):  
Ayse B Dincer ◽  
Joseph D Janizek ◽  
Su-In Lee
Keyword(s):  
Gene Expression ◽  
Neural Networks ◽  
Expression Profiles ◽  
Gene Expression Profiles ◽  
Supplementary Information ◽  
Biological Variables ◽  
Large Numbers ◽  
Latent Space ◽  
Complex Models ◽  
Unsupervised Neural Networks

Abstract Motivation Increasing 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. Results In this article, we introduce the Adversarial Deconfounding AutoEncoder (AD-AE) 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 (i) generate embeddings that do not encode confounder information, (ii) conserve the biological signals present in the original space and (iii) generalize successfully across different confounder domains. We demonstrate that AD-AE outperforms standard autoencoder and other deconfounding approaches. Availability and implementation Our code and data are available at https://gitlab.cs.washington.edu/abdincer/ad-ae. Contact Supplementary information Supplementary data are available at Bioinformatics online.

scholarly journals OCTAD: an open workplace for virtually screening therapeutics targeting precise cancer patient groups using gene expression features

2019 ◽  
Author(s):  
Billy Zeng ◽  
Benjamin S. Glicksberg ◽  
Patrick Newbury ◽  
Jing Xing ◽  
Ke Liu ◽  
...  
Keyword(s):  
Gene Expression ◽  
Cancer Patient ◽  
Precision Medicine ◽  
Experimental Testing ◽  
Expression Profiles ◽  
Gene Expression Profiles ◽  
Cost Effective ◽  
Specific Expression ◽  
Drug Candidates ◽  
Patient Groups

AbstractOne approach to precision medicine is to discover drugs that target molecularly defined diseases. Voluminous cancer patient gene expression profiles have been accumulated in public databases, enabling the creation of a cancer-specific expression signature. By matching this signature to perturbagen-induced gene expression profiles from large drug libraries, researchers can prioritize small molecules that present high potency to reverse expression of signature genes for further experimental testing of their efficacy. This approach has proven to be an efficient and cost-effective way to identify efficacious drug candidates. However, the success of this approach requires multiscale procedures, imposing significant challenges to many labs. Therefore, we present OCTAD: an open workplace for virtually screening compounds targeting precise cancer patient groups using gene expression features. We release OCTAD as a web portal and standalone R workflow to allow experimental and computational scientists to easily navigate the tool. In this work, we describe this tool and demonstrate its potential for precision medicine.

Sign in / Sign up

Export Citation Format

Share Document