About: A deep learning framework for high-throughput mechanism-driven phenotype compound screening

Facets (new session)
Description
Metadata
Settings
- owl:sameAs
- Inference Rule:

About: A deep learning framework for high-throughput mechanism-driven phenotype compound screening Goto Sponge NotDistinct Permalink

An Entity of Type : schema:ScholarlyArticle, within Data Space : wasabi.inria.fr associated with source document(s)

Attributes	Values
type	Academic Article research paper schema:ScholarlyArticle
isDefinedBy	Covid-on-the-Web dataset
has title	A deep learning framework for high-throughput mechanism-driven phenotype compound screening
Creator	Zhang, Ping Pham, Thai-Hoang Qiu, Yue Xie, Lei Zeng, Jucheng
Source	BioRxiv; Medline; PMC
abstract	Target-based high-throughput compound screening dominates conventional one-drug-one-gene drug discovery process. However, the readout from the chemical modulation of a single protein is poorly correlated with phenotypic response of organism, leading to high failure rate in drug development. Chemical-induced gene expression profile provides an attractive solution to phenotype-based screening. However, the use of such data is currently limited by their sparseness, unreliability, and relatively low throughput. Several methods have been proposed to impute missing values for gene expression datasets. However, few existing methods can perform de novo chemical compound screening. In this study, we propose a mechanism-driven neural network-based method named DeepCE (Deep Chemical Expression) which utilizes graph convolutional neural network to learn chemical representation and multi-head attention mechanism to model chemical substructure-gene and gene-gene feature associations. In addition, we propose a novel data augmentation method which extracts useful information from unreliable experiments in L1000 dataset. The experimental results show that DeepCE achieves the superior performances not only in de novo chemical setting but also in traditional imputation setting compared to state-of-the-art baselines for the prediction of chemical-induced gene expression. We further verify the effectiveness of gene expression profiles generated from DeepCE by comparing them with gene expression profiles in L1000 dataset for downstream classification tasks including drug-target and disease predictions. To demonstrate the value of DeepCE, we apply it to patient-specific drug repurposing of COVID-19 for the first time, and generate novel lead compounds consistent with clinical evidences. Thus, DeepCE provides a potentially powerful framework for robust predictive modeling by utilizing noisy omics data as well as screening novel chemicals for the modulation of systemic response to disease.
has issue date	2020-07-20(xsd:dateTime)
bibo:doi	10.1101/2020.07.19.211235
bibo:pmid	32743586
has license	cc-by-nd
sha1sum (hex)	3827be71e6af6745d67a2dcc0d5743bc64b143c2
schema:url	https://doi.org/10.1101/2020.07.19.211235
resource representing a document's title	A deep learning framework for high-throughput mechanism-driven phenotype compound screening
has PubMed Central identifier	PMC7386506
has PubMed identifier	32743586
schema:publication	bioRxiv
resource representing a document's body	covid:3827be71e6af6745d67a2dcc0d5743bc64b143c2#body_text
is schema:about of	named entity 'algorithms' named entity 'phenotype' named entity 'COMPOUND' named entity 'document' named entity 'phenotype' named entity 'deep learning' named entity 'high-throughput' named entity 'deep learning' named entity 'Drug-target' named entity 'Data processing' named entity 'algorithm' named entity 'gene' named entity 'gene expression profiles' named entity 'data processing' named entity 'Data processing' named entity 'Pytorch' named entity 'Drugbank' named entity 'z-score' named entity 'logistic regression' named entity 'High-quality' named entity 'drug-target' named entity 'probability' named entity 'chemical compounds' named entity 'interaction information' named entity 'cheminformatics' named entity 'gene expression profiles' named entity 'gene' named entity 'bioactivity' named entity 'z-scores' named entity 'drug-target' named entity 'training set' named entity 'HTR2A' named entity 'data augmentation' named entity 'Drugbank' named entity 'high-quality' named entity 'cell lines' named entity 'cell lines' named entity 'density function' named entity 'high-quality' named entity 'one-hot' named entity 'gene expression profile' named entity 'PubChem' named entity 'chemical compound' named entity 'support vector machine' named entity 'z-score' named entity 'kNN' named entity 'Python 3' named entity 'Tesla P100' named entity 'probability distribution' named entity 'normalized' named entity 'gene expression profiles' named entity 'gene expression profiles' named entity 'HT29' named entity 'HRH1' named entity 'cell lines' named entity 'Bayesian' named entity 'PC3' named entity 'assay' named entity 'cell lines' named entity 'high-quality' named entity 'binary classification' named entity 'protein-protein interaction network' named entity 'Pearson correlation' named entity 'training set' named entity 'weighted average' named entity 'scikit-learn' named entity 'chemical compound' named entity 'training set' named entity 'gene expression' named entity 'ATC codes' named entity 'chemical compound' named entity 'training set' named entity 'bioactivity' named entity 'neural network' named entity 'neural network' named entity '0.01' named entity 'chemical compound'

Faceted Search & Find service v1.13.91 as of Mar 24 2020

Alternative Linked Data Documents: Sponger | ODE Content Formats:

RDF

ODATA

Microdata

About

OpenLink Virtuoso version 07.20.3229 as of Jul 10 2020, on Linux (x86_64-pc-linux-gnu), Single-Server Edition (94 GB total memory)
Data on this page belongs to its respective rights holders.
Virtuoso Faceted Browser Copyright © 2009-2024 OpenLink Software