A robust mRNA signature obtained via recursive ensemble feature selection predicts the responsiveness of omalizumab in moderate-to-severe asthma.
anti-IgE
asthma
biomarker
machine-learning
omalizumab
Journal
Clinical and translational allergy
ISSN: 2045-7022
Titre abrégé: Clin Transl Allergy
Pays: England
ID NLM: 101576043
Informations de publication
Date de publication:
Nov 2023
Nov 2023
Historique:
revised:
01
09
2023
received:
07
04
2023
accepted:
11
10
2023
medline:
26
11
2023
pubmed:
26
11
2023
entrez:
25
11
2023
Statut:
ppublish
Résumé
Not being well controlled by therapy with inhaled corticosteroids and long-acting β2 agonist bronchodilators is a major concern for severe-asthma patients. The current treatment option for these patients is the use of biologicals such as anti-IgE treatment, omalizumab, as an add-on therapy. Despite the accepted use of omalizumab, patients do not always benefit from it. Therefore, there is a need to identify reliable biomarkers as predictors of omalizumab response. Two novel computational algorithms, machine-learning based Recursive Ensemble Feature Selection (REFS) and rule-based algorithm Logic Explainable Networks (LEN), were used on open accessible mRNA expression data from moderate-to-severe asthma patients to identify genes as predictors of omalizumab response. With REFS, the number of features was reduced from 28,402 genes to 5 genes while obtaining a cross-validated accuracy of 0.975. The 5 responsiveness predictive genes encode the following proteins: Coiled-coil domain- containing protein 113 (CCDC113), Solute Carrier Family 26 Member 8 (SLC26A), Protein Phosphatase 1 Regulatory Subunit 3D (PPP1R3D), C-Type lectin Domain Family 4 member C (CLEC4C) and LOC100131780 (not annotated). The LEN algorithm found 4 identical genes with REFS: CCDC113, SLC26A8 PPP1R3D and LOC100131780. Literature research showed that the 4 identified responsiveness predicting genes are associated with mucosal immunity, cell metabolism, and airway remodeling. Both computational methods show 4 identical genes as predictors of omalizumab response in moderate-to-severe asthma patients. The obtained high accuracy indicates that our approach has potential in clinical settings. Future studies in relevant cohort data should validate our computational approach.
Sections du résumé
BACKGROUND
BACKGROUND
Not being well controlled by therapy with inhaled corticosteroids and long-acting β2 agonist bronchodilators is a major concern for severe-asthma patients. The current treatment option for these patients is the use of biologicals such as anti-IgE treatment, omalizumab, as an add-on therapy. Despite the accepted use of omalizumab, patients do not always benefit from it. Therefore, there is a need to identify reliable biomarkers as predictors of omalizumab response.
METHODS
METHODS
Two novel computational algorithms, machine-learning based Recursive Ensemble Feature Selection (REFS) and rule-based algorithm Logic Explainable Networks (LEN), were used on open accessible mRNA expression data from moderate-to-severe asthma patients to identify genes as predictors of omalizumab response.
RESULTS
RESULTS
With REFS, the number of features was reduced from 28,402 genes to 5 genes while obtaining a cross-validated accuracy of 0.975. The 5 responsiveness predictive genes encode the following proteins: Coiled-coil domain- containing protein 113 (CCDC113), Solute Carrier Family 26 Member 8 (SLC26A), Protein Phosphatase 1 Regulatory Subunit 3D (PPP1R3D), C-Type lectin Domain Family 4 member C (CLEC4C) and LOC100131780 (not annotated). The LEN algorithm found 4 identical genes with REFS: CCDC113, SLC26A8 PPP1R3D and LOC100131780. Literature research showed that the 4 identified responsiveness predicting genes are associated with mucosal immunity, cell metabolism, and airway remodeling.
CONCLUSION AND CLINICAL RELEVANCE
CONCLUSIONS
Both computational methods show 4 identical genes as predictors of omalizumab response in moderate-to-severe asthma patients. The obtained high accuracy indicates that our approach has potential in clinical settings. Future studies in relevant cohort data should validate our computational approach.
Identifiants
pubmed: 38006387
doi: 10.1002/clt2.12306
pmc: PMC10655633
doi:
Types de publication
Journal Article
Langues
eng
Pagination
e12306Informations de copyright
© 2023 The Authors. Clinical and Translational Allergy published by John Wiley & Sons Ltd on behalf of European Academy of Allergy and Clinical Immunology.
Références
N Engl J Med. 2018 Jun 28;378(26):2486-2496
pubmed: 29782217
Cochrane Database Syst Rev. 2006 Apr 19;(2):CD003559
pubmed: 16625585
J Biol Chem. 2015 Jul 3;290(27):16759-71
pubmed: 25995448
Sci Rep. 2021 Feb 25;11(1):4541
pubmed: 33633136
J Allergy Clin Immunol. 2001 Aug;108(2):184-90
pubmed: 11496232
Am J Respir Crit Care Med. 2006 Oct 15;174(8):858-66
pubmed: 16858015
BMC Bioinformatics. 2019 Sep 18;20(1):480
pubmed: 31533612
Am J Respir Crit Care Med. 1996 Dec;154(6 Pt 1):1868-902
pubmed: 8970383
Biologics. 2018 Oct 26;12:135-142
pubmed: 30464389
Am J Respir Crit Care Med. 2014 Dec 15;190(12):1363-72
pubmed: 25338189
EJIFCC. 2009 Jan 20;19(4):203-11
pubmed: 27683318
PLoS Genet. 2021 Mar 4;17(3):e1009388
pubmed: 33661892
J Allergy Clin Immunol. 2018 Jun;141(6):2256-2264.e2
pubmed: 28939411
Exp Mol Med. 2016 Jul 15;48(7):e245
pubmed: 27416781
J Allergy Clin Immunol Pract. 2021 Mar;9(3):1194-1200
pubmed: 33069885
J Thorac Oncol. 2010 Sep;5(9):1315-6
pubmed: 20736804
Allergy. 2004 May;59(5):469-78
pubmed: 15080825
J Allergy Clin Immunol. 2001 Nov;108(5):709-14
pubmed: 11692093
Int Immunopharmacol. 2021 Apr;93:107423
pubmed: 33578181
Eur Respir J. 2017 Feb 8;49(2):
pubmed: 28179442
Genes Dev. 2012 Feb 1;26(3):203-34
pubmed: 22302935
J Allergy Clin Immunol. 2010 Oct;126(4):798-806.e13
pubmed: 20920770
J Biol Chem. 2011 Oct 14;286(41):35329-35333
pubmed: 21880719
J Allergy Clin Immunol. 2018 Feb;141(2):560-570
pubmed: 28528200
MedGenMed. 2005 Jan 27;7(1):27
pubmed: 16369332
Eur Respir J. 2020 Oct 8;56(4):
pubmed: 32513781
Curr Med Res Opin. 2007 Oct;23(10):2379-86
pubmed: 17711616
J Thorac Dis. 2020 Dec;12(12):7097-7105
pubmed: 33447398
Nucleic Acids Res. 2002 Jan 1;30(1):38-41
pubmed: 11752248
J Cell Sci. 2014 Oct 1;127(Pt 19):4128-33
pubmed: 25074808
Nat Commun. 2017 Dec 5;8(1):1943
pubmed: 29203772
Bioinformatics. 2018 Oct 1;34(19):3365-3376
pubmed: 29726967
Ann Allergy Asthma Immunol. 2011 Sep;107(3):273-80.e1
pubmed: 21875548
FEBS Lett. 1997 Nov 24;418(1-2):210-4
pubmed: 9414128
Eur Respir J. 2014 Feb;43(2):343-73
pubmed: 24337046
Clin Exp Allergy. 2020 Sep;50(9):1017-1034
pubmed: 32472607
Eur Respir J. 2017 Jun 29;49(6):
pubmed: 28663317
Oncogene. 2004 Oct 18;23(48):7906-9
pubmed: 15489908
ERJ Open Res. 2020 Aug 11;6(3):
pubmed: 32802826
Respir Res. 2018 Jan 18;19(1):12
pubmed: 29347939
J Allergy Clin Immunol. 2018 Apr;141(4):1169-1179
pubmed: 29627041
J Allergy Clin Immunol. 2002 Jul;110(1):68-71
pubmed: 12110823
J Clin Invest. 2002 Mar;109(5):571-7
pubmed: 11877463
Lancet. 2016 Oct 29;388(10056):2115-2127
pubmed: 27609408
Respir Med. 2007 Jul;101(7):1483-92
pubmed: 17339107
Am J Hum Genet. 2013 May 2;92(5):760-6
pubmed: 23582645
Cancers (Basel). 2020 Jul 03;12(7):
pubmed: 32635415
J Exp Med. 2001 Dec 17;194(12):1823-34
pubmed: 11748283
Arch Dis Child. 2014 Sep;99(9):850-6
pubmed: 24771309
Adv Immunol. 2007;93:63-119
pubmed: 17383539
Allergy. 2005 Mar;60(3):302-8
pubmed: 15679714
J Allergy Clin Immunol. 2011 Jan;127(1):153-60, 160.e1-9
pubmed: 21211650
Respir Med. 2010 Nov;104(11):1608-17
pubmed: 20801010
Pharmacol Res. 2015 Apr;94:9-25
pubmed: 25662515
Front Immunol. 2017 Sep 04;8:1075
pubmed: 28928743
Sci Rep. 2018 Jun 11;8(1):8826
pubmed: 29891868
FASEB J. 2010 Dec;24(12):5080-91
pubmed: 20724523
PLoS One. 2011;6(9):e23944
pubmed: 21915269
J Allergy Clin Immunol. 2005 May;115(5):1076-80
pubmed: 15867869
World Allergy Organ J. 2020 Jan 24;13(1):100095
pubmed: 32015785
Am J Respir Crit Care Med. 2017 May 15;195(10):1311-1320
pubmed: 27925796