Differential Treatments Based on Drug-induced Gene Expression Signatures and Longitudinal Systemic Lupus Erythematosus Stratification

Daniel Toro-Domínguez, Raúl Lopez-Domínguez, Adrián García Moreno, Juan A. Villatoro-García, Jordi Martorell-Marugán, Daniel Goldman, Michelle Petri, Daniel Wojdyla, Bernardo A. Pons-Estel, David Isenberg, Gabriela Morales-Montes de Oca, María Isabel Trejo-Zambrano, Benjamín García González, Florencia Rosetti, Diana Gómez-Martín, Juanita Romero-Díaz, Pedro Carmona-Sáez, Marta E. Alarcón-Riquelme

Research output: Contribution to journalArticle

Abstract

Systemic lupus erythematosus (SLE) is a heterogeneous disease with unpredictable patterns of activity. Patients with similar activity levels may have different prognosis and molecular abnormalities. In this study, we aimed to measure the main differences in drug-induced gene expression signatures across SLE patients and to evaluate the potential for clinical data to build a machine learning classifier able to predict the SLE subset for individual patients. SLE transcriptomic data from two cohorts were compared with drug-induced gene signatures from the CLUE database to compute a connectivity score that reflects the capability of a drug to revert the patient signatures. Patient stratification based on drug connectivity scores revealed robust clusters of SLE patients identical to the clusters previously obtained through longitudinal gene expression data, implying that differential treatment depends on the cluster to which patients belongs. The best drug candidates found, mTOR inhibitors or those reducing oxidative stress, showed stronger cluster specificity. We report that drug patterns for reverting disease gene expression follow the cell-specificity of the disease clusters. We used 2 cohorts to train and test a logistic regression model that we employed to classify patients from 3 independent cohorts into the SLE subsets and provide a clinically useful model to predict subset assignment and drug efficacy.

Original languageEnglish (US)
Article number15502
JournalScientific reports
Volume9
Issue number1
DOIs
StatePublished - Dec 1 2019

Fingerprint

Transcriptome
Systemic Lupus Erythematosus
Pharmaceutical Preparations
Therapeutics
Logistic Models
Gene Expression
Oxidative Stress
Databases
Genes

ASJC Scopus subject areas

  • General

Cite this

Toro-Domínguez, D., Lopez-Domínguez, R., García Moreno, A., Villatoro-García, J. A., Martorell-Marugán, J., Goldman, D., ... Alarcón-Riquelme, M. E. (2019). Differential Treatments Based on Drug-induced Gene Expression Signatures and Longitudinal Systemic Lupus Erythematosus Stratification. Scientific reports, 9(1), [15502]. https://doi.org/10.1038/s41598-019-51616-9

Differential Treatments Based on Drug-induced Gene Expression Signatures and Longitudinal Systemic Lupus Erythematosus Stratification. / Toro-Domínguez, Daniel; Lopez-Domínguez, Raúl; García Moreno, Adrián; Villatoro-García, Juan A.; Martorell-Marugán, Jordi; Goldman, Daniel; Petri, Michelle; Wojdyla, Daniel; Pons-Estel, Bernardo A.; Isenberg, David; Morales-Montes de Oca, Gabriela; Trejo-Zambrano, María Isabel; García González, Benjamín; Rosetti, Florencia; Gómez-Martín, Diana; Romero-Díaz, Juanita; Carmona-Sáez, Pedro; Alarcón-Riquelme, Marta E.

In: Scientific reports, Vol. 9, No. 1, 15502, 01.12.2019.

Research output: Contribution to journalArticle

Toro-Domínguez, D, Lopez-Domínguez, R, García Moreno, A, Villatoro-García, JA, Martorell-Marugán, J, Goldman, D, Petri, M, Wojdyla, D, Pons-Estel, BA, Isenberg, D, Morales-Montes de Oca, G, Trejo-Zambrano, MI, García González, B, Rosetti, F, Gómez-Martín, D, Romero-Díaz, J, Carmona-Sáez, P & Alarcón-Riquelme, ME 2019, 'Differential Treatments Based on Drug-induced Gene Expression Signatures and Longitudinal Systemic Lupus Erythematosus Stratification', Scientific reports, vol. 9, no. 1, 15502. https://doi.org/10.1038/s41598-019-51616-9
Toro-Domínguez, Daniel ; Lopez-Domínguez, Raúl ; García Moreno, Adrián ; Villatoro-García, Juan A. ; Martorell-Marugán, Jordi ; Goldman, Daniel ; Petri, Michelle ; Wojdyla, Daniel ; Pons-Estel, Bernardo A. ; Isenberg, David ; Morales-Montes de Oca, Gabriela ; Trejo-Zambrano, María Isabel ; García González, Benjamín ; Rosetti, Florencia ; Gómez-Martín, Diana ; Romero-Díaz, Juanita ; Carmona-Sáez, Pedro ; Alarcón-Riquelme, Marta E. / Differential Treatments Based on Drug-induced Gene Expression Signatures and Longitudinal Systemic Lupus Erythematosus Stratification. In: Scientific reports. 2019 ; Vol. 9, No. 1.
@article{d559f3eea9264bb08e9d495b4d287863,
title = "Differential Treatments Based on Drug-induced Gene Expression Signatures and Longitudinal Systemic Lupus Erythematosus Stratification",
abstract = "Systemic lupus erythematosus (SLE) is a heterogeneous disease with unpredictable patterns of activity. Patients with similar activity levels may have different prognosis and molecular abnormalities. In this study, we aimed to measure the main differences in drug-induced gene expression signatures across SLE patients and to evaluate the potential for clinical data to build a machine learning classifier able to predict the SLE subset for individual patients. SLE transcriptomic data from two cohorts were compared with drug-induced gene signatures from the CLUE database to compute a connectivity score that reflects the capability of a drug to revert the patient signatures. Patient stratification based on drug connectivity scores revealed robust clusters of SLE patients identical to the clusters previously obtained through longitudinal gene expression data, implying that differential treatment depends on the cluster to which patients belongs. The best drug candidates found, mTOR inhibitors or those reducing oxidative stress, showed stronger cluster specificity. We report that drug patterns for reverting disease gene expression follow the cell-specificity of the disease clusters. We used 2 cohorts to train and test a logistic regression model that we employed to classify patients from 3 independent cohorts into the SLE subsets and provide a clinically useful model to predict subset assignment and drug efficacy.",
author = "Daniel Toro-Dom{\'i}nguez and Ra{\'u}l Lopez-Dom{\'i}nguez and {Garc{\'i}a Moreno}, Adri{\'a}n and Villatoro-Garc{\'i}a, {Juan A.} and Jordi Martorell-Marug{\'a}n and Daniel Goldman and Michelle Petri and Daniel Wojdyla and Pons-Estel, {Bernardo A.} and David Isenberg and {Morales-Montes de Oca}, Gabriela and Trejo-Zambrano, {Mar{\'i}a Isabel} and {Garc{\'i}a Gonz{\'a}lez}, Benjam{\'i}n and Florencia Rosetti and Diana G{\'o}mez-Mart{\'i}n and Juanita Romero-D{\'i}az and Pedro Carmona-S{\'a}ez and Alarc{\'o}n-Riquelme, {Marta E.}",
year = "2019",
month = "12",
day = "1",
doi = "10.1038/s41598-019-51616-9",
language = "English (US)",
volume = "9",
journal = "Scientific Reports",
issn = "2045-2322",
publisher = "Nature Publishing Group",
number = "1",

}

TY - JOUR

T1 - Differential Treatments Based on Drug-induced Gene Expression Signatures and Longitudinal Systemic Lupus Erythematosus Stratification

AU - Toro-Domínguez, Daniel

AU - Lopez-Domínguez, Raúl

AU - García Moreno, Adrián

AU - Villatoro-García, Juan A.

AU - Martorell-Marugán, Jordi

AU - Goldman, Daniel

AU - Petri, Michelle

AU - Wojdyla, Daniel

AU - Pons-Estel, Bernardo A.

AU - Isenberg, David

AU - Morales-Montes de Oca, Gabriela

AU - Trejo-Zambrano, María Isabel

AU - García González, Benjamín

AU - Rosetti, Florencia

AU - Gómez-Martín, Diana

AU - Romero-Díaz, Juanita

AU - Carmona-Sáez, Pedro

AU - Alarcón-Riquelme, Marta E.

PY - 2019/12/1

Y1 - 2019/12/1

N2 - Systemic lupus erythematosus (SLE) is a heterogeneous disease with unpredictable patterns of activity. Patients with similar activity levels may have different prognosis and molecular abnormalities. In this study, we aimed to measure the main differences in drug-induced gene expression signatures across SLE patients and to evaluate the potential for clinical data to build a machine learning classifier able to predict the SLE subset for individual patients. SLE transcriptomic data from two cohorts were compared with drug-induced gene signatures from the CLUE database to compute a connectivity score that reflects the capability of a drug to revert the patient signatures. Patient stratification based on drug connectivity scores revealed robust clusters of SLE patients identical to the clusters previously obtained through longitudinal gene expression data, implying that differential treatment depends on the cluster to which patients belongs. The best drug candidates found, mTOR inhibitors or those reducing oxidative stress, showed stronger cluster specificity. We report that drug patterns for reverting disease gene expression follow the cell-specificity of the disease clusters. We used 2 cohorts to train and test a logistic regression model that we employed to classify patients from 3 independent cohorts into the SLE subsets and provide a clinically useful model to predict subset assignment and drug efficacy.

AB - Systemic lupus erythematosus (SLE) is a heterogeneous disease with unpredictable patterns of activity. Patients with similar activity levels may have different prognosis and molecular abnormalities. In this study, we aimed to measure the main differences in drug-induced gene expression signatures across SLE patients and to evaluate the potential for clinical data to build a machine learning classifier able to predict the SLE subset for individual patients. SLE transcriptomic data from two cohorts were compared with drug-induced gene signatures from the CLUE database to compute a connectivity score that reflects the capability of a drug to revert the patient signatures. Patient stratification based on drug connectivity scores revealed robust clusters of SLE patients identical to the clusters previously obtained through longitudinal gene expression data, implying that differential treatment depends on the cluster to which patients belongs. The best drug candidates found, mTOR inhibitors or those reducing oxidative stress, showed stronger cluster specificity. We report that drug patterns for reverting disease gene expression follow the cell-specificity of the disease clusters. We used 2 cohorts to train and test a logistic regression model that we employed to classify patients from 3 independent cohorts into the SLE subsets and provide a clinically useful model to predict subset assignment and drug efficacy.

UR - http://www.scopus.com/inward/record.url?scp=85074231755&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85074231755&partnerID=8YFLogxK

U2 - 10.1038/s41598-019-51616-9

DO - 10.1038/s41598-019-51616-9

M3 - Article

C2 - 31664045

AN - SCOPUS:85074231755

VL - 9

JO - Scientific Reports

JF - Scientific Reports

SN - 2045-2322

IS - 1

M1 - 15502

ER -