Genetic model of MS severity predicts future accumulation of disability

Abstract

No genetic modifiers of multiple sclerosis (MS) severity have been independently validated, leading to a lack of insight into genetic determinants of the rate of disability progression. We investigated genetic modifiers of MS severity in prospectively acquired training (N = 205) and validation (N = 94) cohorts, using the following advances:(1) We focused on 113 genetic variants previously identified as related to MS severity; (2) We used a novel, sensitive outcome: MS Disease Severity Scale (MS-DSS);(3) Instead of validating individual alleles, we used a machine learning technique (random forest) that captures linear and complex nonlinear effects between alleles to derive a single Genetic Model of MS Severity (GeM-MSS). The GeM-MSS consists of 19 variants located in vicinity of 12 genes implicated in regulating cytotoxicity of immune cells, complement activation, neuronal functions, and fibrosis. GeM-MSS correlates with MS-DSS (r = 0.214; p = 0.043) in a validation cohort that was not used in the modeling steps. The recognized biology identifies novel therapeutic targets for inhibiting MS disability progression.

Genetic factors for susceptibility to and manifestations of neuromyelitis optica

“…10,13 Genetic loci associated with disability in MS have not been confirmed, although some candidate loci are involved in glutamateinduced cell-death or remyelination independent from loci associated with susceptibility. 22 Our study had some limitations. First, etiological backgrounds among patients with NMOSD could be heterogeneous because anti-AQP4 antibody-seronegative patients, who might be anti-MOG antibody-positive, were included in our cohort.…”

“…For example, in MS, some HLA alleles and the MHC regions are associated with susceptibility but not disability 10,13 . Genetic loci associated with disability in MS have not been confirmed, although some candidate loci are involved in glutamate‐induced cell‐death or remyelination independent from loci associated with susceptibility 22 …”

“…The risk loci for disability might be different from those for susceptibility, as shown in MS and other autoimmune diseases. 10,13,22 Therefore, in the present study, we aimed to identify genetic factors associated with the susceptibility and clinical features of NMOSD using genome-wide genotyped single nucleotide polymorphisms (SNPs) and genotyped HLA-DRB1 and -DPB1 alleles in Japanese patients with NMOSD. We also studied MSGB scores to elucidate the differences or similarities in the pathomechanisms of NMOSD and MS.…”

“…However, any genetic effects on these features have not been identified in NMOSD. The risk loci for disability might be different from those for susceptibility, as shown in MS and other autoimmune diseases 10,13,22 . Therefore, in the present study, we aimed to identify genetic factors associated with the susceptibility and clinical features of NMOSD using genome‐wide genotyped single nucleotide polymorphisms (SNPs) and genotyped HLA‐DRB1 and ‐ DPB1 alleles in Japanese patients with NMOSD.…”

Machine Learning Use for Prognostic Purposes in Multiple Sclerosis

“…Gene expression has been analyzed using machine learning approaches in at least two studies [ 30 , 31 ]. In line with the idea that polygenic scores are important to understand complex diseases [ 32 ], a genetic model of MS severity has been obtained that identifies linear and complex nonlinear effects between alleles by means of a random forest ML technique [ 31 ]. It will be interesting to see how predictions from gene expression match or complement those derived from other types of data.…”