Machine learning applied to whole‐blood RNA‐sequencing data uncovers distinct subsets of patients with systemic lupus erythematosus
Abstract Objectives Systemic lupus erythematosus (SLE) is a heterogeneous autoimmune disease that is difficult to treat. There is currently no optimal stratification of patients with SLE, and thus, responses to available treatments are unpredictable. Here, we developed a new stratification scheme fo...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2019-01-01
|
| Series: | Clinical & Translational Immunology |
| Subjects: | |
| Online Access: | https://doi.org/10.1002/cti2.1093 |
| _version_ | 1818332046194376704 |
|---|---|
| author | William A Figgett Katherine Monaghan Milica Ng Monther Alhamdoosh Eugene Maraskovsky Nicholas J Wilson Alberta Y Hoi Eric F Morand Fabienne Mackay |
| author_facet | William A Figgett Katherine Monaghan Milica Ng Monther Alhamdoosh Eugene Maraskovsky Nicholas J Wilson Alberta Y Hoi Eric F Morand Fabienne Mackay |
| author_sort | William A Figgett |
| collection | DOAJ |
| description | Abstract Objectives Systemic lupus erythematosus (SLE) is a heterogeneous autoimmune disease that is difficult to treat. There is currently no optimal stratification of patients with SLE, and thus, responses to available treatments are unpredictable. Here, we developed a new stratification scheme for patients with SLE, based on the computational analysis of patients’ whole‐blood transcriptomes. Methods We applied machine learning approaches to RNA‐sequencing (RNA‐seq) data sets to stratify patients with SLE into four distinct clusters based on their gene expression profiles. A meta‐analysis on three recently published whole‐blood RNA‐seq data sets was carried out, and an additional similar data set of 30 patients with SLE and 29 healthy donors was incorporated in this study; a total of 161 patients with SLE and 57 healthy donors were analysed. Results Examination of SLE clusters, as opposed to unstratified SLE patients, revealed underappreciated differences in the pattern of expression of disease‐related genes relative to clinical presentation. Moreover, gene signatures correlated with flare activity were successfully identified. Conclusion Given that SLE disease heterogeneity is a key challenge hindering the design of optimal clinical trials and the adequate management of patients, our approach opens a new possible avenue addressing this limitation via a greater understanding of SLE heterogeneity in humans. Stratification of patients based on gene expression signatures may be a valuable strategy allowing the identification of separate molecular mechanisms underpinning disease in SLE. Further, this approach may have a use in understanding the variability in responsiveness to therapeutics, thereby improving the design of clinical trials and advancing personalised therapy. |
| first_indexed | 2024-12-13T13:29:31Z |
| format | Article |
| id | doaj.art-24ce743335bc4a30b9ded20c32a67a96 |
| institution | Directory Open Access Journal |
| issn | 2050-0068 |
| language | English |
| last_indexed | 2024-12-13T13:29:31Z |
| publishDate | 2019-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Clinical & Translational Immunology |
| spelling | doaj.art-24ce743335bc4a30b9ded20c32a67a962022-12-21T23:44:12ZengWileyClinical & Translational Immunology2050-00682019-01-01812n/an/a10.1002/cti2.1093Machine learning applied to whole‐blood RNA‐sequencing data uncovers distinct subsets of patients with systemic lupus erythematosusWilliam A Figgett0Katherine Monaghan1Milica Ng2Monther Alhamdoosh3Eugene Maraskovsky4Nicholas J Wilson5Alberta Y Hoi6Eric F Morand7Fabienne Mackay8Department of Microbiology and Immunology University of Melbourne at the Peter Doherty Institute for Infection and Immunity Melbourne VIC AustraliaCSL Limited Parkville VIC AustraliaCSL Limited Parkville VIC AustraliaCSL Limited Parkville VIC AustraliaCSL Limited Parkville VIC AustraliaCSL Limited Parkville VIC AustraliaCentre for Inflammatory Diseases School of Clinical Sciences Monash University Clayton VIC AustraliaCentre for Inflammatory Diseases School of Clinical Sciences Monash University Clayton VIC AustraliaDepartment of Microbiology and Immunology University of Melbourne at the Peter Doherty Institute for Infection and Immunity Melbourne VIC AustraliaAbstract Objectives Systemic lupus erythematosus (SLE) is a heterogeneous autoimmune disease that is difficult to treat. There is currently no optimal stratification of patients with SLE, and thus, responses to available treatments are unpredictable. Here, we developed a new stratification scheme for patients with SLE, based on the computational analysis of patients’ whole‐blood transcriptomes. Methods We applied machine learning approaches to RNA‐sequencing (RNA‐seq) data sets to stratify patients with SLE into four distinct clusters based on their gene expression profiles. A meta‐analysis on three recently published whole‐blood RNA‐seq data sets was carried out, and an additional similar data set of 30 patients with SLE and 29 healthy donors was incorporated in this study; a total of 161 patients with SLE and 57 healthy donors were analysed. Results Examination of SLE clusters, as opposed to unstratified SLE patients, revealed underappreciated differences in the pattern of expression of disease‐related genes relative to clinical presentation. Moreover, gene signatures correlated with flare activity were successfully identified. Conclusion Given that SLE disease heterogeneity is a key challenge hindering the design of optimal clinical trials and the adequate management of patients, our approach opens a new possible avenue addressing this limitation via a greater understanding of SLE heterogeneity in humans. Stratification of patients based on gene expression signatures may be a valuable strategy allowing the identification of separate molecular mechanisms underpinning disease in SLE. Further, this approach may have a use in understanding the variability in responsiveness to therapeutics, thereby improving the design of clinical trials and advancing personalised therapy.https://doi.org/10.1002/cti2.1093autoimmunityRNA‐seqSLEstratificationtranscriptomics |
| spellingShingle | William A Figgett Katherine Monaghan Milica Ng Monther Alhamdoosh Eugene Maraskovsky Nicholas J Wilson Alberta Y Hoi Eric F Morand Fabienne Mackay Machine learning applied to whole‐blood RNA‐sequencing data uncovers distinct subsets of patients with systemic lupus erythematosus Clinical & Translational Immunology autoimmunity RNA‐seq SLE stratification transcriptomics |
| title | Machine learning applied to whole‐blood RNA‐sequencing data uncovers distinct subsets of patients with systemic lupus erythematosus |
| title_full | Machine learning applied to whole‐blood RNA‐sequencing data uncovers distinct subsets of patients with systemic lupus erythematosus |
| title_fullStr | Machine learning applied to whole‐blood RNA‐sequencing data uncovers distinct subsets of patients with systemic lupus erythematosus |
| title_full_unstemmed | Machine learning applied to whole‐blood RNA‐sequencing data uncovers distinct subsets of patients with systemic lupus erythematosus |
| title_short | Machine learning applied to whole‐blood RNA‐sequencing data uncovers distinct subsets of patients with systemic lupus erythematosus |
| title_sort | machine learning applied to whole blood rna sequencing data uncovers distinct subsets of patients with systemic lupus erythematosus |
| topic | autoimmunity RNA‐seq SLE stratification transcriptomics |
| url | https://doi.org/10.1002/cti2.1093 |
| work_keys_str_mv | AT williamafiggett machinelearningappliedtowholebloodrnasequencingdatauncoversdistinctsubsetsofpatientswithsystemiclupuserythematosus AT katherinemonaghan machinelearningappliedtowholebloodrnasequencingdatauncoversdistinctsubsetsofpatientswithsystemiclupuserythematosus AT milicang machinelearningappliedtowholebloodrnasequencingdatauncoversdistinctsubsetsofpatientswithsystemiclupuserythematosus AT montheralhamdoosh machinelearningappliedtowholebloodrnasequencingdatauncoversdistinctsubsetsofpatientswithsystemiclupuserythematosus AT eugenemaraskovsky machinelearningappliedtowholebloodrnasequencingdatauncoversdistinctsubsetsofpatientswithsystemiclupuserythematosus AT nicholasjwilson machinelearningappliedtowholebloodrnasequencingdatauncoversdistinctsubsetsofpatientswithsystemiclupuserythematosus AT albertayhoi machinelearningappliedtowholebloodrnasequencingdatauncoversdistinctsubsetsofpatientswithsystemiclupuserythematosus AT ericfmorand machinelearningappliedtowholebloodrnasequencingdatauncoversdistinctsubsetsofpatientswithsystemiclupuserythematosus AT fabiennemackay machinelearningappliedtowholebloodrnasequencingdatauncoversdistinctsubsetsofpatientswithsystemiclupuserythematosus |