Search

Multiple sclerosis (MS) is an immune-mediated, demyelinating disease of the central nervous system. In this study, an MS cohort and healthy controls were stratified into Caucasian and African American groups. Patient hematological profiles-composed of complete blood count (CBC) and complete metabolic panel (CMP) test values-were analyzed to identify differences between MS cases and controls and between patients with different MS subtypes. Additionally, random forest models were used to determine the aggregate utility of common hematological tests in determining MS disease status and subtype. The most significant and relevant results were increased bilirubin and creatinine in MS cases. The random forest models achieved some success in differentiating between MS cases and controls (AUC values: 0.725 and 0.710, respectively) but were not successful in differentiating between subtypes. However, larger samples that adjust for possible confounding variables, such as treatment status, may reveal the value of these tests in differentiating between MS subtypes.

Background: A substantial number of patients diagnosed with multiple sclerosis (MS) suffer from depression in addition to physical symptoms and disability. Recent evidence suggests a stronger relationship may exist between MS and depression than previously thought, in which a diagnosis of depression may be prodromic to the development of MS., Methods: A genome-wide association study (GWAS) was performed to identify genetic variants associated with the development of depression in a cohort of MS patients. The control group (n = 1180) was composed of MS patients with no diagnoses of depression as determined by ICD-9 and ICD-10 billing codes present in the electronic health record (EHR). Separate analyses were performed for three different case groups: 1) MS patients having a depression diagnosis at any time (n = 182), 2) MS patients having a depression diagnosis one year pre-MS diagnosis (n = 27), and 3) MS patients having a depression diagnosis one year post-MS diagnosis (n = 130). Logistic regression analyses were also performed to test for associations between the development of depression and an APOE tagging variant, as APOE was previously linked to depressive affect in MS. An additional logistic regression analysis tested for associations between depression in MS patients and SNPs associated with depression in the general population. Pathway enrichment analyses were also conducted to identify pathways that link the two diseases., Results: GWAS identified no novel associations between variants and a diagnosis of depression relative to a diagnosis of MS. One variant, rs1432639, associated with depression in the general population, was significantly associated with the development of depression post-MS diagnosis. The APOE-related SNPs were not associated with depression in this study population. An IGF1 pathway approached statistical significance in patients diagnosed with depression prior to a diagnosis of MS., Conclusion: rs1432639 and the IGF1 pathway provide evidence for a genetic link between MS and depression that warrants further research., (Copyright © 2020 Elsevier B.V. All rights reserved.)

Background: Drug-induced liver injury (DILI) is a serious concern during drug development and the treatment of human disease. The ability to accurately predict DILI risk could yield significant improvements in drug attrition rates during drug development, in drug withdrawal rates, and in treatment outcomes. In this paper, we outline our approach to predicting DILI risk using gene-expression data from Build 02 of the Connectivity Map (CMap) as part of the 2018 Critical Assessment of Massive Data Analysis CMap Drug Safety Challenge., Results: First, we used seven classification algorithms independently to predict DILI based on gene-expression values for two cell lines. Similar to what other challenge participants observed, none of these algorithms predicted liver injury on a consistent basis with high accuracy. In an attempt to improve accuracy, we aggregated predictions for six of the algorithms (excluding one that had performed exceptionally poorly) using a soft-voting method. This approach also failed to generalize well to the test set. We investigated alternative approaches-including a multi-sample normalization method, dimensionality-reduction techniques, a class-weighting scheme, and expanding the number of hyperparameter combinations used as inputs to the soft-voting method. We met limited success with each of these solutions., Conclusions: We conclude that alternative methods and/or datasets will be necessary to effectively predict DILI in patients based on RNA expression levels in cell lines., Reviewers: This article was reviewed by Paweł P Labaj and Aleksandra Gruca (both nominated by David P Kreil).