We are performing whole genome sequencing (WGS) of families with Autism Spectrum Disorder (ASD) to build a resource, named MSSNG, to enable the sub-categorization of phenotypes and underlying genetic factors involved. Here, we report WGS of 5,205 samples from families with ASD, accompanied by clinical information, creating a database accessible in a cloud platform, and through an internet portal with controlled access. We found an average of 73.8 de novo single nucleotide variants and 12.6 de novo insertion/deletions (indels) or copy number variations (CNVs) per ASD subject. We identified 18 new candidate ASD-risk genes such as MED13 and PHF3, and found that participants bearing mutations in susceptibility genes had significantly lower adaptive ability (p=6×10−4). In 294/2,620 (11.2%) of ASD cases, a molecular basis could be determined and 7.2% of these carried CNV/chromosomal abnormalities, emphasizing the importance of detecting all forms of genetic variation as diagnostic and therapeutic targets in ASD.

De novo mutations (DNMs) are important in autism spectrum disorder (ASD), but so far analyses have mainly been on the ~1.5% of the genome encoding genes. Here, we performed whole-genome sequencing (WGS) of 200 ASD parent–child trios and characterised germline and somatic DNMs. We confirmed that the majority of germline DNMs (75.6%) originated from the father, and these increased significantly with paternal age only (P=4.2×10−10). However, when clustered DNMs (those within 20 kb) were found in ASD, not only did they mostly originate from the mother (P=7.7×10−13), but they could also be found adjacent to de novo copy number variations where the mutation rate was significantly elevated (P=2.4×10−24). By comparing with DNMs detected in controls, we found a significant enrichment of predicted damaging DNMs in ASD cases (P=8.0×10−9; odds ratio=1.84), of which 15.6% (P=4.3×10−3) and 22.5% (P=7.0×10−5) were non-coding or genic non-coding, respectively. The non-coding elements most enriched for DNM were untranslated regions of genes, regulatory sequences involved in exon-skipping and DNase I hypersensitive regions. Using microarrays and a novel outlier detection test, we also found aberrant methylation profiles in 2/185 (1.1%) of ASD cases. These same individuals carried independently identified DNMs in the ASD-risk and epigenetic genes DNMT3A and ADNP. Our data begins to characterize different genome-wide DNMs, and highlight the contribution of non-coding variants, to the aetiology of ASD.

Personalized medicine promises individualized disease prediction and treatment. The convergence of machine learning (ML) and available multimodal data is key moving forward. We build upon previous work to deliver multimodal predictions of Parkinson’s disease (PD) risk and systematically develop a model using GenoML, an automated ML package, to make improved multi-omic predictions of PD, validated in an external cohort. We investigated top features, constructed hypothesis-free disease-relevant networks, and investigated drug–gene interactions. We performed automated ML on multimodal data from the Parkinson’s progression marker initiative (PPMI). After selecting the best performing algorithm, all PPMI data was used to tune the selected model. The model was validated in the Parkinson’s Disease Biomarker Program (PDBP) dataset. Our initial model showed an area under the curve (AUC) of 89.72% for the diagnosis of PD. The tuned model was then tested for validation on external data (PDBP, AUC 85.03%). Optimizing thresholds for classification increased the diagnosis prediction accuracy and other metrics. Finally, networks were built to identify gene communities specific to PD. Combining data modalities outperforms the single biomarker paradigm. UPSIT and PRS contributed most to the predictive power of the model, but the accuracy of these are supplemented by many smaller effect transcripts and risk SNPs. Our model is best suited to identifying large groups of individuals to monitor within a health registry or biobank to prioritize for further testing. This approach allows complex predictive models to be reproducible and accessible to the community, with the package, code, and results publicly available.

A BS TRACT: Background: Whole-genome sequencing data are available from several large studies across a variety of diseases and traits. However, massive storage and computation resources are required to use these data, and to achieve sufficient power for discoveries, harmonization of multiple cohorts is critical. Objectives: The Accelerating Medicines Partnership Parkinson's Disease program has developed a research platform for Parkinson's disease (PD) that integrates the storage and analysis of whole-genome sequencing data, RNA expression data, and clinical data, harmonized across multiple cohort studies. Methods: The version 1 release contains whole-genome sequencing data derived from 3941 participants from 4 cohorts. Samples underwent joint genotyping by the TOPMed Freeze 9 Variant Calling Pipeline. We performed descriptive analyses of these whole-genome sequencing