Unexpected Actors in Inflammatory Bowel Disease Revealed by Machine Learning from Whole-Blood Transcriptomic Data
Abstract
:1. Introduction
2. Materials and Methods
Statistical Analysis
3. Results
4. Discussion
5. Conclusions
Supplementary Materials
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
References
- Charbit-Henrion, F.; Parlato, M.; Hanein, S.; Duclaux-Loras, R.; Nowak, J.; Begue, B.; Rakotobe, S.; Bruneau, J.; Fourrage, C.; Alibeu, O.; et al. Diagnostic Yield of Next-Generation Sequencing in Very Early-Onset Inflammatory Bowel Diseases: A Multicentre Study. J. Crohn’s Colitis 2018, 12, 1104–1112. [Google Scholar] [CrossRef] [PubMed]
- Parlato, M.; Charbit-Henrion, F.; Pan, J.; Romano, C.; Duclaux-Loras, R.; Le Du, M.-H.; Warner, N.; Francalanci, P.; Bruneau, J.; Bras, M.; et al. Human ALPI Deficiency Causes Inflammatory Bowel Disease and Highlights a Key Mechanism of Gut Homeostasis. EMBO Mol. Med. 2018, 10. [Google Scholar] [CrossRef] [PubMed]
- Jostins, L.; Ripke, S.; Weersma, R.K.; Duerr, R.H.; McGovern, D.P.; Hui, K.Y.; Lee, J.C.; Schumm, L.P.; Sharma, Y.; Anderson, C.A.; et al. Host-Microbe Interactions Have Shaped the Genetic Architecture of Inflammatory Bowel Disease. Nature 2012, 491, 119–124. [Google Scholar] [CrossRef] [PubMed]
- Ostrowski, J.; Paziewska, A.; Lazowska, I.; Ambrozkiewicz, F.; Goryca, K.; Kulecka, M.; Rawa, T.; Karczmarski, J.; Dabrowska, M.; Zeber-Lubecka, N.; et al. Genetic Architecture Differences between Pediatric and Adult-Onset Inflammatory Bowel Diseases in the Polish Population. Sci. Rep. 2016, 6, 39831. [Google Scholar] [CrossRef] [PubMed]
- Travis, M.A.; Reizis, B.; Melton, A.C.; Masteller, E.; Tang, Q.; Proctor, J.M.; Wang, Y.; Bernstein, X.; Huang, X.; Reichardt, L.F.; et al. Loss of Integrin α(v)β8 on Dendritic Cells Causes Autoimmunity and Colitis in Mice. Nature 2007, 449, 361–365. [Google Scholar] [CrossRef] [PubMed]
- Momozawa, Y.; Dmitrieva, J.; Théâtre, E.; Deffontaine, V.; Rahmouni, S.; Charloteaux, B.; Crins, F.; Docampo, E.; Elansary, M.; Gori, A.-S.; et al. IBD Risk Loci Are Enriched in Multigenic Regulatory Modules Encompassing Putative Causative Genes. Nat. Commun. 2018, 9, 1–18. [Google Scholar] [CrossRef] [PubMed]
- Kaiko, G.E.; Chen, F.; Lai, C.-W.; Chiang, I.-L.; Perrigoue, J.; Stojmirović, A.; Li, K.; Muegge, B.D.; Jain, U.; VanDussen, K.L.; et al. PAI-1 Augments Mucosal Damage in Colitis. Sci. Transl. Med. 2019, 11, eaat0852. [Google Scholar] [CrossRef]
- Akter, S.; Xu, D.; Nagel, S.C.; Bromfield, J.J.; Pelch, K.; Wilshire, G.B.; Joshi, T. Machine Learning Classifiers for Endometriosis Using Transcriptomics and Methylomics Data. Front. Genet. 2019, 10, 766. [Google Scholar] [CrossRef]
- Hand, D.J. Artificial Intelligence and Medicine: Discussion Paper. J. R. Soc. Med. 1987, 80, 563–565. [Google Scholar] [CrossRef]
- Ostrowski, J.; Dabrowska, M.; Lazowska, I.; Paziewska, A.; Balabas, A.; Kluska, A.; Kulecka, M.; Karczmarski, J.; Ambrozkiewicz, F.; Piatkowska, M.; et al. Redefining the Practical Utility of Blood Transcriptome Biomarkers in Inflammatory Bowel Diseases. J. Crohn’s Colitis 2019, 13, 626–633. [Google Scholar] [CrossRef]
- Anders, S.; Pyl, P.T.; Huber, W. HTSeq—A Python Framework to Work with High-Throughput Sequencing Data. Bioinformatics 2015, 31, 166–169. [Google Scholar] [CrossRef] [PubMed]
- Lichawska-Cieslar, A.; Pietrzycka, R.; Ligeza, J.; Kulecka, M.; Paziewska, A.; Kalita, A.; Dolicka, D.D.; Wilamowski, M.; Miekus, K.; Ostrowski, J.; et al. RNA Sequencing Reveals Widespread Transcriptome Changes in a Renal Carcinoma Cell Line. Oncotarget 2018, 9, 8597–8613. [Google Scholar] [CrossRef] [PubMed]
- Love, M.I.; Huber, W.; Anders, S. Moderated Estimation of Fold Change and Dispersion for RNA-Seq Data with DESeq2. Genome Biol. 2014, 15, 550. [Google Scholar] [CrossRef] [PubMed]
- Fu, R.; Gillen, A.E.; Sheridan, R.M.; Tian, C.; Daya, M.; Hao, Y.; Hesselberth, J.R.; Riemondy, K.A. Clustifyr: An R Package for Automated Single-Cell RNA Sequencing Cluster Classification. F1000Research 2020, 9, 223. [Google Scholar] [CrossRef]
- Friedman, J.H.; Hastie, T.; Tibshirani, R. Regularization Paths for Generalized Linear Models via Coordinate Descent. J. Stat. Softw. 2010, 33, 1–22. [Google Scholar] [CrossRef]
- Subramanian, A.; Tamayo, P.; Mootha, V.K.; Mukherjee, S.; Ebert, B.L.; Gillette, M.A.; Paulovich, A.; Pomeroy, S.L.; Golub, T.R.; Lander, E.S.; et al. Gene Set Enrichment Analysis: A Knowledge-Based Approach for Interpreting Genome-Wide Expression Profiles. Proc. Natl. Acad. Sci. USA 2005, 102, 15545–15550. [Google Scholar] [CrossRef]
- Peters, L.A.; Perrigoue, J.; Mortha, A.; Iuga, A.; Song, W.-M.; Neiman, E.M.; Llewellyn, S.R.; Di Narzo, A.; Kidd, B.A.; Telesco, S.E.; et al. A Functional Genomics Predictive Network Model Identifies Regulators of Inflammatory Bowel Disease. Nat. Genet. 2017, 49, 1437–1449. [Google Scholar] [CrossRef]
- Von Martels, J.Z.H.; Bourgonje, A.R.; Klaassen, M.A.Y.; Alkhalifah, H.A.A.; Sadaghian Sadabad, M.; Vich Vila, A.; Gacesa, R.; Gabriëls, R.Y.; Steinert, R.E.; Jansen, B.H.; et al. Riboflavin Supplementation in Patients with Crohn’s Disease [the RISE-UP Study]. J. Crohn’s Colitis 2020, 14, 595–607. [Google Scholar] [CrossRef]
- Shubhakar, A.; Jansen, B.C.; Adams, A.T.; Reiding, K.R.; Ventham, N.T.; Kalla, R.; Bergemalm, D.; Urbanowicz, P.A.; Gardner, R.A.; Consortium, I.-B.; et al. Serum N-Glycomic Biomarkers Predict Treatment Escalation in Inflammatory Bowel Disease. Res. Sq. 2021. [Google Scholar] [CrossRef]
- Nowak, J.K.; Adams, A.T.; Kalla, R.; Lindstrøm, J.C.; Vatn, S.; Bergemalm, D.; Keita, Å.V.; Gomollón, F.; Jahnsen, J.; Vatn, M.H.; et al. Characterization of the Circulating Transcriptomic Landscape in Inflammatory Bowel Disease Provides Evidence for Dysregulation of Multiple Transcription Factors Including NFE2, SPI1, CEBPB, and IRF2. J. Crohn’s Colitis 2022, 16, jjac033. [Google Scholar] [CrossRef]
- Nowak, J.K.; Kalla, R.; Adams, A.T.; Consortium, I.-C.; Halfvarson, J.; Satsangi, J. Discovery of a Simple Two-Gene Expression Biomarker in Whole Blood Predictive of the Need for Treatment Escalation in Inflammatory Bowel Disease. medRxiv 2021. [Google Scholar] [CrossRef]
- Wu, D.; Chen, D.; Shi, W.; Liu, W.; Zhou, W.; Qian, J. Whole Exome Sequencing Identifies Two Novel Mutations in a Patient with UC Associated with PSC and SSA. Can. J. Gastroenterol. Hepatol. 2021, 2021, 9936932. [Google Scholar] [CrossRef] [PubMed]
- Païdassi, H.; Acharya, M.; Zhang, A.; Mukhopadhyay, S.; Kwon, M.; Chow, C.; Stuart, L.M.; Savill, J.; Lacy–Hulbert, A. Preferential Expression of Integrin Avβ8 Promotes Generation of Regulatory T Cells by Mouse CD103+ Dendritic Cells. Gastroenterology 2011, 141, 1813–1820. [Google Scholar] [CrossRef] [PubMed]
- Castro-Dopico, T.; Dennison, T.W.; Ferdinand, J.R.; Mathews, R.J.; Fleming, A.; Clift, D.; Stewart, B.J.; Jing, C.; Strongili, K.; Labzin, L.I.; et al. Anti-Commensal IgG Drives Intestinal Inflammation and Type 17 Immunity in Ulcerative Colitis. Immunity 2019, 50, 1099–1114. [Google Scholar] [CrossRef] [PubMed]
- Salvador-Martín, S.; Kaczmarczyk, B.; Álvarez, R.; Navas-López, V.M.; Gallego-Fernández, C.; Moreno-Álvarez, A.; Solar-Boga, A.; Sánchez, C.; Tolin, M.; Velasco, M.; et al. Whole Transcription Profile of Responders to Anti-TNF Drugs in Pediatric Inflammatory Bowel Disease. Pharmaceutics 2021, 13, 77. [Google Scholar] [CrossRef]
- Chen, X.; Li, Q.; Zhang, Z.; Yang, M.; Wang, E. Identification of Potential Diagnostic Biomarkers From Circulating Cells During the Course of Sleep Deprivation-Related Myocardial Infarction Based on Bioinformatics Analyses. Front. Cardiovasc. Med. 2022, 9, 843426. [Google Scholar] [CrossRef]
- Zhao, Q.; Wang, F.; Chen, Y.-X.; Chen, S.; Yao, Y.-C.; Zeng, Z.-L.; Jiang, T.-J.; Wang, Y.-N.; Wu, C.-Y.; Jing, Y.; et al. Comprehensive Profiling of 1015 Patients’ Exomes Reveals Genomic-Clinical Associations in Colorectal Cancer. Nat. Commun. 2022, 13, 2342. [Google Scholar] [CrossRef]
- De Lange, K.M.; Moutsianas, L.; Lee, J.C.; Lamb, C.A.; Luo, Y.; Kennedy, N.A.; Jostins, L.; Rice, D.L.; Gutierrez-Achury, J.; Ji, S.-G.; et al. Genome-Wide Association Study Implicates Immune Activation of Multiple Integrin Genes in Inflammatory Bowel Disease. Nat. Genet. 2017, 49, 256–261. [Google Scholar] [CrossRef]
- Singh, V.; Yeoh, B.S.; Carvalho, F.; Gewirtz, A.T.; Vijay-Kumar, M. Proneness of TLR5 Deficient Mice to Develop Colitis Is Microbiota Dependent. Gut Microbes 2015, 6, 279–283. [Google Scholar] [CrossRef]
- Sasson, S.C.; Slevin, S.M.; Cheung, V.T.F.; Nassiri, I.; Olsson-Brown, A.; Fryer, E.; Ferreira, R.C.; Trzupek, D.; Gupta, T.; Al-Hillawi, L.; et al. Interferon-Gamma-Producing CD8+ Tissue Resident Memory T Cells Are a Targetable Hallmark of Immune Checkpoint Inhibitor-Colitis. Gastroenterology 2021, 161, 1229–1244. [Google Scholar] [CrossRef]
IBD | Ulcerative Colitis | Crohn’s Disease | |||
---|---|---|---|---|---|
AUC = 0.85 (0.79–0.92), λ = 0.11 | AUC = 0.87 (0.79–0.95), λ = 0.16 | AUC = 0.83 (0.75–0.83), λ = 0.14 | |||
Gene | Coefficient, n | Gene | Coefficient, n | Gene | Coefficient, n |
(Intercept) | 0.79 | (Intercept) | 0.06 | PGF | 0.05, 218 |
SERINC2 | 0.05, 122 | TTC14 | −0.01, 38 | YWHAG | 0.05, 164 |
GALNT14 | 0.05, 112 | RBBP6 | −0.01, 8 | THEM5 | 0.05, 153 |
BLVRB | 0.05, 105 | TAS2R31 | −0.01, 44 | (Intercept) | 0.04 |
PGF | 0.03, 110 | YBX3P1 | −0.02, 146 | EMC3 | 0.02, 104 |
TK1 | 0.02, 89 | TOP2B | −0.05, 50 | DUSP3 | 0.00, 19 |
BCAM | 0.01, 108 | STIM2 | −0.05, 195 | PIK3C2A | −0.02, 44 |
MSMP | −0.03, 66 | CHML | −0.05, 159 | MSMP | −0.05, 140 |
LINC00938 | −0.04, 44 | PURA | −0.05, 297 | PARP15 | −0.05, 95 |
UBR7 | −0.04, 93 | CYSLTR1 | −0.05, 153 | ANKRD36 | −0.05, 91 |
TAS2R31 | −0.04, 30 | ARAP2 | −0.05, 150 | PEG10 | −0.05, 112 |
SP140L | −0.05, 30 | SP140L | −0.05, 129 | KIR2DL1 | −0.05, 94 |
FLJ40194 | −0.05, 92 | STXBP4 | −0.05, 164 | ERMARD | −0.05, 101 |
STIM2 | −0.05, 105 | SNORA19 | −0.05, 233 | YBX3P1 | −0.05, 141 |
PIK3C2A | −0.05, 135 | NPSR1−AS1 | −0.05, 138 | PAXIP1−AS1 | −0.05, 69 |
CYSLTR1 | −0.05, 129 | LINC00938 | −0.05, 44 | ||
SMG6 | −0.05, 142 | FLJ40194 | −0.05, 161 | ||
RTTN | −0.05, 127 | ||||
SYTL2 | −0.05, 160 | ||||
NPSR1-AS1 | −0.05, 125 | ||||
YBX3P1 | −0.05, 141 |
Severe IBD | Severe Ulcerative Colitis | Severe Crohn’s Disease | |||
---|---|---|---|---|---|
AUC = 0.91 (0.83–0.98), λ = 0.13 | AUC = 0.90 (0.73–1.0), λ = 0.15 | AUC = 0.92 (0.79–1.0), λ = 0.25 | |||
Gene | Coefficient, n | Gene | Coefficient, n | Gene | Coefficient, n |
ITGB4 | 0.05, 171 | ITGB4 | 0.05, 196 | FCGR1A | 0.05, 270 |
FCGR1A | 0.05, 275 | BIK | 0.05, 234 | DUSP3 | 0.05, 141 |
FCGR1B | 0.05, 116 | CACNA1E | 0.05, 193 | (Intercept) | −0.97 |
SEMA4A | 0.05, 60 | PGLYRP1 | 0.05, 138 | ||
CACNA1E | 0.05, 219 | DOK4 | 0.05, 131 | ||
PLP2 | 0.05, 93 | LRRC61 | 0.05, 122 | ||
TK1 | 0.05, 143 | GALNT14 | 0.05, 251 | ||
TLR5 | 0.05, 67 | TXNDC5 | 0.05, 129 | ||
CD274 | 0.05, 119 | JCHAIN | 0.05, 152 | ||
OPLAH | 0.05, 77 | NATD1 | 0.05, 88 | ||
DOK4 | 0.05, 137 | FCGR1A | 0.03, 117 | ||
GALNT14 | 0.05, 300 | NQO2 | 0.02, 84 | ||
JCHAIN | 0.05, 216 | IGLL5 | 0.01, 96 | ||
THEM5 | 0.05, 124 | SMARCAD1 | −0.01, 63 | ||
IGLL5 | 0.01, 96 | LYPD2 | −0.03, 73 | ||
GPR160 | 0.00, 44 | PIK3C2A | −0.05, 108 | ||
RAD23A | 0.00, 93 | PURA | −0.05, 265 | ||
TAS2R31 | 0.00, 47 | SNORA19 | −0.05, 183 | ||
DDX12P | −0.03, 122 | NPSR1−AS1 | −0.05, 185 | ||
SNORA19 | −0.03, 55 | (Intercept) | −0.97 | ||
CRYGS | −0.04, 93 | ||||
PURA | −0.05, 54 | ||||
LYPD2 | −0.05, 95 | ||||
SCARNA5 | −0.05, 123 | ||||
NPSR1-AS1 | −0.05, 205 | ||||
YBX3P1 | −0.05, 124 | ||||
LOC200772 | −0.05, 142 | ||||
(Intercept) | −0.27 |
IBD Children | IBD Adults | ||
---|---|---|---|
AUC = 0.95 (0.89–1.0), λ = 0.20 | AUC = 0.86 (0.75–0.98), λ = 0.15 | ||
Gene | Coefficient, n | Gene | Coefficient, n |
(Intercept) | 0.78 | (Intercept) | 0.73 |
NBEAL1 | 0.05, 132 | ADAMTS1 | 0.00, 118 |
FNTA | 0.05, 234 | METTL14 | −0.01, 45 |
RAD23A | 0.05, 178 | STIM2 | −0.03, 31 |
BLVRB | 0.02, 137 | SLX4IP | −0.05, 142 |
BCAM | 0.01, 176 | MYBL1 | −0.05, 63 |
BIK | 0.00, 154 | DTHD1 | −0.05, 164 |
BLK | −0.05, 201 | AP3S1 | −0.05, 254 |
TAS2R31 | −0.05, 237 | PIK3C2A | −0.05, 156 |
PAXIP1-AS1 | −0.05, 41 | PURA | −0.05, 174 |
KLRF1 | −0.05, 197 | ||
ERMARD | −0.05, 59 | ||
SP140L | −0.05, 83 | ||
SYTL2 | −0.05, 96 |
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |
© 2022 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Nowak, J.K.; Szymańska, C.J.; Glapa-Nowak, A.; Duclaux-Loras, R.; Dybska, E.; Ostrowski, J.; Walkowiak, J.; Adams, A.T. Unexpected Actors in Inflammatory Bowel Disease Revealed by Machine Learning from Whole-Blood Transcriptomic Data. Genes 2022, 13, 1570. https://doi.org/10.3390/genes13091570
Nowak JK, Szymańska CJ, Glapa-Nowak A, Duclaux-Loras R, Dybska E, Ostrowski J, Walkowiak J, Adams AT. Unexpected Actors in Inflammatory Bowel Disease Revealed by Machine Learning from Whole-Blood Transcriptomic Data. Genes. 2022; 13(9):1570. https://doi.org/10.3390/genes13091570
Chicago/Turabian StyleNowak, Jan K., Cyntia J. Szymańska, Aleksandra Glapa-Nowak, Rémi Duclaux-Loras, Emilia Dybska, Jerzy Ostrowski, Jarosław Walkowiak, and Alex T. Adams. 2022. "Unexpected Actors in Inflammatory Bowel Disease Revealed by Machine Learning from Whole-Blood Transcriptomic Data" Genes 13, no. 9: 1570. https://doi.org/10.3390/genes13091570
APA StyleNowak, J. K., Szymańska, C. J., Glapa-Nowak, A., Duclaux-Loras, R., Dybska, E., Ostrowski, J., Walkowiak, J., & Adams, A. T. (2022). Unexpected Actors in Inflammatory Bowel Disease Revealed by Machine Learning from Whole-Blood Transcriptomic Data. Genes, 13(9), 1570. https://doi.org/10.3390/genes13091570