The chromosome 9p21 amyotrophic lateral sclerosis-frontotemporal dementia (ALS-FTD) locus contains one of the last major unidentified autosomal dominant genes underlying these common neurodegenerative diseases. We have previously shown that a founder haplotype, covering the MOBKL2b, IFNK and C9ORF72 genes, is present in the majority of cases linked to this region. Here we show that there is a large hexanucleotide (GGGGCC) repeat expansion in the first intron of C9ORF72 on the affected haplotype. This repeat expansion segregates perfectly with disease in the Finnish population, underlying 46.0% of familial ALS and 21.1% of sporadic ALS in that population. Taken together with the D90A SOD1 mutation, 87% of familial ALS in Finland is now explained by a simple monogenic cause. The repeat expansion is also present in one third of familial ALS cases of outbred European descent making it the most common genetic cause of these fatal neurodegenerative diseases identified to date.

No abstract

ObjectiveDementia with Lewy bodies is an α-synucleinopathy characterized by neocortical Lewy-related pathology (LRP). We carried out a genome-wide association study (GWAS) on neocortical LRP in a population-based sample of subjects aged 85 or over.MethodsLRP was analyzed in 304 subjects in the Vantaa 85+ sample from Southern Finland. The GWAS included 41 cases with midbrain, hippocampal, and neocortical LRP and 177 controls without midbrain and hippocampal LRP. The Medical Research Council Cognitive Function and Ageing Study (CFAS) material was used for replication (51 cases and 131 controls).ResultsBy analyzing 327,010 markers the top signal was obtained at the HLA-DPA1/DPB1 locus (P = 1.29 × 10−7); five other loci on chromosomes 15q14, 2p21, 2q31, 18p11, and 5q23 were associated with neocortical LRP at P < 10−5. Two loci were marked by multiple markers, 2p21 (P = 3.9 × 10−6, upstream of the SPTBN1 gene), and HLA-DPA1/DPB1; these were tested in the CFAS material. Single marker (P = 0.0035) and haplotype (P = 0.04) associations on 2p21 were replicated in CFAS, whereas HLA-DPA1/DPB1 association was not. Bioinformatic analyses suggest functional effects for the HLA-DPA1/DPB1 markers as well as the 15q14 marker rs8037309.InterpretationWe identified suggestive novel risk factors for neocortical LRP. SPTBN1 is the candidate on 2p21, it encodes beta-spectrin, an α-synuclein binding protein and a component of Lewy bodies. The HLA-DPA1/DPB1 association suggests a role for antigen presentation or alternatively, cis-regulatory effects, one of the regulated neighboring genes identified here (vacuolar protein sorting 52) plays a role in vesicular trafficking and has been shown to interact with α-synuclein in a yeast model.

PURPOSE We have created a cloud-based machine learning system (CLOBNET) that is an open-source, lean infrastructure for electronic health record (EHR) data integration and is capable of extract, transform, and load (ETL) processing. CLOBNET enables comprehensive analysis and visualization of structured EHR data. We demonstrate the utility of CLOBNET by predicting primary therapy outcomes of patients with high-grade serous ovarian cancer (HGSOC) on the basis of EHR data. MATERIALS AND METHODS CLOBNET is built using open-source software to make data preprocessing, analysis, and model training user friendly. The source code of CLOBNET is available in GitHub. The HGSOC data set was based on a prospective cohort of 208 patients with HGSOC who were treated at Turku University Hospital, Finland, from 2009 to 2019 for whom comprehensive clinical and EHR data were available. RESULTS We trained machine learning (ML) models using clinical data, including a herein developed dissemination score that quantifies the disease burden at the time of diagnosis, to identify patients with progressive disease (PD) or a complete response (CR) on the basis of RECIST (version 1.1). The best performance was achieved with a logistic regression model, which resulted in an area under receiver operating characteristic curve (AUROC) of 0.86, with a specificity of 73% and a sensitivity of 89%, when it classified between patients who experienced PD and CR. CONCLUSION We have developed an open-source computational infrastructure, CLOBNET, that enables effective and rapid analysis of EHR and other clinical data. Our results demonstrate that CLOBNET allows predictions to be made on the basis of EHR data to address clinically relevant questions.