Modeling drug mechanism of action with large scale gene-expression profiles using GPAR, an artificial intelligence platform

Abstract Background Querying drug-induced gene expression profiles with machine learning method is an effective way for revealing drug mechanism of actions (MOAs), which is strongly supported by the growth of large scale and high-throughput gene expression databases. However, due to the lack of code-free and user friendly applications, it is not easy for biologists and pharmacologists to model MOAs with state-of-art deep learning approach. Results In this work, a newly developed online collaborative tool, Genetic profile-activity relationship (GPAR) was built to help modeling and predicting MOAs easily via deep learning. The users can use GPAR to customize their training sets to train self-defined MOA prediction models, to evaluate the model performances and to make further predictions automatically. Cross-validation tests show GPAR outperforms Gene set enrichment analysis in predicting MOAs. Conclusion GPAR can serve as a better approach in MOAs prediction, which may facilitate researchers to generate more reliable MOA hypothesis.

Download Full-text

LncGSEA: a versatile tool to infer lncRNA associated pathways from large-scale cancer transcriptome sequencing data

BMC Genomics ◽

10.1186/s12864-021-07900-y ◽

2021 ◽

Vol 22 (1) ◽

Author(s):

Yanan Ren ◽

Ting-You Wang ◽

Leah C. Anderton ◽

Qi Cao ◽

Rendong Yang

Keyword(s):

Gene Expression ◽

Large Scale ◽

Expression Profiles ◽

Gene Expression Profiles ◽

Clinical Samples ◽

Sequencing Data ◽

Multiple Cancer ◽

Regulatory Pathways ◽

Cancer Transcriptome ◽

Versatile Tool

Abstract Background Long non-coding RNAs (lncRNAs) are a growing focus in cancer research. Deciphering pathways influenced by lncRNAs is important to understand their role in cancer. Although knock-down or overexpression of lncRNAs followed by gene expression profiling in cancer cell lines are established approaches to address this problem, these experimental data are not available for a majority of the annotated lncRNAs. Results As a surrogate, we present lncGSEA, a convenient tool to predict the lncRNA associated pathways through Gene Set Enrichment Analysis of gene expression profiles from large-scale cancer patient samples. We demonstrate that lncGSEA is able to recapitulate lncRNA associated pathways supported by literature and experimental validations in multiple cancer types. Conclusions LncGSEA allows researchers to infer lncRNA regulatory pathways directly from clinical samples in oncology. LncGSEA is written in R, and is freely accessible at https://github.com/ylab-hi/lncGSEA.

Download Full-text

Analysis of blood-based gene expression in idiopathic Parkinson disease

Neurology ◽

10.1212/wnl.0000000000004516 ◽

2017 ◽

Vol 89 (16) ◽

pp. 1676-1683 ◽

Cited By ~ 36

Author(s):

Ron Shamir ◽

Christine Klein ◽

David Amar ◽

Eva-Juliane Vollstedt ◽

Michael Bonin ◽

...

Keyword(s):

Gene Expression ◽

Parkinson Disease ◽

Gene Networks ◽

Large Scale ◽

Expression Profiles ◽

Area Under The Curve ◽

Gene Expression Profiles ◽

Gene Signature ◽

Gene Profiles ◽

Independent Test

Objective:To examine whether gene expression analysis of a large-scale Parkinson disease (PD) patient cohort produces a robust blood-based PD gene signature compared to previous studies that have used relatively small cohorts (≤220 samples).Methods:Whole-blood gene expression profiles were collected from a total of 523 individuals. After preprocessing, the data contained 486 gene profiles (n = 205 PD, n = 233 controls, n = 48 other neurodegenerative diseases) that were partitioned into training, validation, and independent test cohorts to identify and validate a gene signature. Batch-effect reduction and cross-validation were performed to ensure signature reliability. Finally, functional and pathway enrichment analyses were applied to the signature to identify PD-associated gene networks.Results:A gene signature of 100 probes that mapped to 87 genes, corresponding to 64 upregulated and 23 downregulated genes differentiating between patients with idiopathic PD and controls, was identified with the training cohort and successfully replicated in both an independent validation cohort (area under the curve [AUC] = 0.79, p = 7.13E–6) and a subsequent independent test cohort (AUC = 0.74, p = 4.2E–4). Network analysis of the signature revealed gene enrichment in pathways, including metabolism, oxidation, and ubiquitination/proteasomal activity, and misregulation of mitochondria-localized genes, including downregulation of COX4I1, ATP5A1, and VDAC3.Conclusions:We present a large-scale study of PD gene expression profiling. This work identifies a reliable blood-based PD signature and highlights the importance of large-scale patient cohorts in developing potential PD biomarkers.

Download Full-text

Discovering Distinct Patterns in Gene Expression Profiles

Journal of Integrative Bioinformatics ◽

10.1515/jib-2008-105 ◽

2008 ◽

Vol 5 (2) ◽

Cited By ~ 1

Author(s):

Li Teng ◽

Laiwan Chan

Keyword(s):

Gene Expression ◽

Large Scale ◽

Expression Profiles ◽

Expression Patterns ◽

Gene Expression Profiles ◽

Clustering Methods ◽

Gene Expressions ◽

Real Gene ◽

Large Scale Dataset ◽

Coexpressed Genes

SummaryTraditional analysis of gene expression profiles use clustering to find groups of coexpressed genes which have similar expression patterns. However clustering is time consuming and could be diffcult for very large scale dataset. We proposed the idea of Discovering Distinct Patterns (DDP) in gene expression profiles. Since patterns showing by the gene expressions reveal their regulate mechanisms. It is significant to find all different patterns existing in the dataset when there is little prior knowledge. It is also a helpful start before taking on further analysis. We propose an algorithm for DDP by iteratively picking out pairs of gene expression patterns which have the largest dissimilarities. This method can also be used as preprocessing to initialize centers for clustering methods, like K-means. Experiments on both synthetic dataset and real gene expression datasets show our method is very effective in finding distinct patterns which have gene functional significance and is also effcient.

Download Full-text

CFTR ΔF508 mutation has minimal effect on the gene expression profile of differentiated human airway epithelia

AJP Lung Cellular and Molecular Physiology ◽

10.1152/ajplung.00065.2005 ◽

2005 ◽

Vol 289 (4) ◽

pp. L545-L553 ◽

Cited By ~ 29

Author(s):

Joseph Zabner ◽

Todd E. Scheetz ◽

Hakeem G. Almabrazi ◽

Thomas L. Casavant ◽

Jian Huang ◽

...

Keyword(s):

Gene Expression ◽

Cystic Fibrosis ◽

Large Scale ◽

Expression Profiles ◽

Expression Patterns ◽

Primary Cultures ◽

Gene Expression Profiles ◽

Filter Method ◽

Tissue Destruction ◽

Airway Epithelia

Cystic fibrosis (CF) is caused by mutations in the cystic fibrosis transmembrane conductance regulator (CFTR), an epithelial chloride channel regulated by phosphorylation. Most of the disease-associated morbidity is the consequence of chronic lung infection with progressive tissue destruction. As an approach to investigate the cellular effects of CFTR mutations, we used large-scale microarray hybridization to contrast the gene expression profiles of well-differentiated primary cultures of human CF and non-CF airway epithelia grown under resting culture conditions. We surveyed the expression profiles for 10 non-CF and 10 ΔF508 homozygote samples. Of the 22,283 genes represented on the Affymetrix U133A GeneChip, we found evidence of significant changes in expression in 24 genes by two-sample t-test ( P < 0.00001). A second, three-filter method of comparative analysis found no significant differences between the groups. The levels of CFTR mRNA were comparable in both groups. There were no significant differences in the gene expression patterns between male and female CF specimens. There were 18 genes with significant increases and 6 genes with decreases in CF relative to non-CF samples. Although the function of many of the differentially expressed genes is unknown, one transcript that was elevated in CF, the KCl cotransporter (KCC4), is a candidate for further study. Overall, the results indicate that CFTR dysfunction has little direct impact on airway epithelial gene expression in samples grown under these conditions.

Download Full-text

Integrative machine learning analysis of multiple gene expression profiles in cervical cancer

PeerJ ◽

10.7717/peerj.5285 ◽

2018 ◽

Vol 6 ◽

pp. e5285 ◽

Cited By ~ 9

Author(s):

Mei Sze Tan ◽

Siow-Wee Chang ◽

Phaik Leng Cheah ◽

Hwa Jen Yap

Keyword(s):

Gene Expression ◽

Machine Learning ◽

Cervical Cancer ◽

Expression Profiles ◽

Gene Expression Profiles ◽

Hpv Infection ◽

Gene Set Enrichment Analysis ◽

Multiple Gene ◽

Cervical Cancers ◽

Learning Analysis

Although most of the cervical cancer cases are reported to be closely related to the Human Papillomavirus (HPV) infection, there is a need to study genes that stand up differentially in the final actualization of cervical cancers following HPV infection. In this study, we proposed an integrative machine learning approach to analyse multiple gene expression profiles in cervical cancer in order to identify a set of genetic markers that are associated with and may eventually aid in the diagnosis or prognosis of cervical cancers. The proposed integrative analysis is composed of three steps: namely, (i) gene expression analysis of individual dataset; (ii) meta-analysis of multiple datasets; and (iii) feature selection and machine learning analysis. As a result, 21 gene expressions were identified through the integrative machine learning analysis which including seven supervised and one unsupervised methods. A functional analysis with GSEA (Gene Set Enrichment Analysis) was performed on the selected 21-gene expression set and showed significant enrichment in a nine-potential gene expression signature, namely PEG3, SPON1, BTD and RPLP2 (upregulated genes) and PRDX3, COPB2, LSM3, SLC5A3 and AS1B (downregulated genes).

Download Full-text

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

10.1101/2020.10.28.359943 ◽

2020 ◽

Cited By ~ 1

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.

Download Full-text

Sex differences in viral entry protein expression and host transcript responses to SARS-CoV-2

10.21203/rs.3.rs-100914/v2 ◽

2020 ◽

Author(s):

Mengying Sun ◽

Rama Shankar ◽

Meehyun Ko ◽

Christopher Daniel Chang ◽

Shan-Ju Yeh ◽

...

Keyword(s):

Gene Expression ◽

Sex Differences ◽

Viral Entry ◽

Large Scale ◽

Expression Profiles ◽

Gene Expression Profiles ◽

Scale Analysis ◽

Transcriptional Responses ◽

Deconvolution Analysis ◽

Large Scale Analysis

Abstract Epidemiological studies suggest that men exhibit a higher mortality rate to COVID-19 than women, yet the underlying biology is largely unknown. Here, we seek to delineate sex differences in the gene expression of viral entry proteins ACE2 and TMPRSS2, and host transcriptional responses to SARS-CoV-2 through large-scale analysis of genomic and clinical data. We first compiled 220,000 human gene expression profiles from three databases and completed the meta-information through machine learning and manual annotation. Large scale analysis of these profiles indicated that male samples show higher expression levels of ACE2 and TMPRSS2 than female samples, especially in the older group (>60 years) and in the kidney. Subsequent analysis of 6,031 COVID-19 patients at Mount Sinai Health System revealed that men have significantly higher creatinine levels, an indicator of impaired kidney function. Further analysis of 782 COVID-19 patient gene expression profiles taken from upper airway and blood suggested men and women present distinct expression changes. Computational deconvolution analysis of these profiles revealed male COVID-19 patients have enriched kidney-specific mesangial cells in blood compared to healthy patients. Together, this study suggests biological differences in the kidney between sexes may contribute to sex disparity in COVID-19.

Download Full-text

Improved Feature Selection by Incorporating Gene Similarity into the LASSO

International Journal of Knowledge Discovery in Bioinformatics ◽

10.4018/jkdb.2012010101 ◽

2012 ◽

Vol 3 (1) ◽

pp. 1-22 ◽

Cited By ~ 1

Author(s):

Christopher E. Gillies ◽

Xiaoli Gao ◽

Nilesh V. Patel ◽

Mohammad-Reza Siadat ◽

George D. Wilson

Keyword(s):

Gene Expression ◽

Feature Selection ◽

Personalized Medicine ◽

Objective Function ◽

Expression Profiles ◽

Gene Expression Profiles ◽

Genetic Profile ◽

Data Set ◽

Coordinate Descent Algorithm ◽

Gene Similarity

Personalized medicine is customizing treatments to a patient’s genetic profile and has the potential to revolutionize medical practice. An important process used in personalized medicine is gene expression profiling. Analyzing gene expression profiles is difficult, because there are usually few patients and thousands of genes, leading to the curse of dimensionality. To combat this problem, researchers suggest using prior knowledge to enhance feature selection for supervised learning algorithms. The authors propose an enhancement to the LASSO, a shrinkage and selection technique that induces parameter sparsity by penalizing a model’s objective function. Their enhancement gives preference to the selection of genes that are involved in similar biological processes. The authors’ modified LASSO selects similar genes by penalizing interaction terms between genes. They devise a coordinate descent algorithm to minimize the corresponding objective function. To evaluate their method, the authors created simulation data where they compared their model to the standard LASSO model and an interaction LASSO model. The authors’ model outperformed both the standard and interaction LASSO models in terms of detecting important genes and gene interactions for a reasonable number of training samples. They also demonstrated the performance of their method on a real gene expression data set from lung cancer cell lines.

Download Full-text

Biological Insights into Chemotherapy Resistance in Ovarian Cancer

International Journal of Molecular Sciences ◽

10.3390/ijms20092131 ◽

2019 ◽

Vol 20 (9) ◽

pp. 2131 ◽

Cited By ~ 2

Author(s):

Michelle A. Glasgow ◽

Peter Argenta ◽

Juan E. Abrahante ◽

Mihir Shetty ◽

Shobhana Talukdar ◽

...

Keyword(s):

Gene Expression ◽

Ovarian Cancer ◽

Expression Profiles ◽

Rna Extraction ◽

Chemotherapy Resistance ◽

Gene Expression Profiles ◽

Gene Set Enrichment Analysis ◽

Before And After ◽

Tumor Gene Expression ◽

Tumor Gene

The majority of patients with high-grade serous ovarian cancer (HGSOC) initially respond to chemotherapy; however, most will develop chemotherapy resistance. Gene signatures may change with the development of chemotherapy resistance in this population, which is important as it may lead to tailored therapies. The objective of this study was to compare tumor gene expression profiles in patients before and after treatment with neoadjuvant chemotherapy (NACT). Tumor samples were collected from six patients diagnosed with HGSOC before and after administration of NACT. RNA extraction and whole transcriptome sequencing was performed. Differential gene expression, hierarchical clustering, gene set enrichment analysis, and pathway analysis were examined in all of the samples. Tumor samples clustered based on exposure to chemotherapy as opposed to patient source. Pre-NACT samples were enriched for multiple pathways involving cell cycle growth. Post-NACT samples were enriched for drug transport and peroxisome pathways. Molecular subtypes based on the pre-NACT sample (differentiated, mesenchymal, proliferative and immunoreactive) changed in four patients after administration of NACT. Multiple changes in tumor gene expression profiles after exposure to NACT were identified from this pilot study and warrant further attention as they may indicate early changes in the development of chemotherapy resistance.

Download Full-text