Deep learning predicts DNA methylation regulatory variants in specific brain cell types and enhances fine mapping for brain disorders.

DNA methylation (DNAm) is essential for brain development and function and potentially mediates the effects of genetic risk variants underlying brain disorders. We present INTERACT, a transformer-based deep learning model to predict regulatory variants affecting DNAm levels in specific brain cell types, leveraging existing single-nucleus DNAm data from the human brain. We show that INTERACT accurately predicts cell type-specific DNAm profiles, achieving an average area under the receiver operating characteristic curve of 0.

Incorporating incubation period distributions to precisely estimate the association between rainfall and Legionella infection.

Background: Multiple studies have shown a positive relationship between weather events and, 1 to 2 weeks later, Legionnaires' disease (LD) cases. Narrowing this time window of association can help determine whether the mechanism linking rainfall and relative humidity to sporadic LD is direct or indirect. Due to the large number of daily water interactions and low incidence of LD, we propose a new Bayesian modeling approach to disentangle the potential for a direct vs.

Relating RSV infection kinetics to host infectiousness in different age groups.

Respiratory syncytial virus (RSV) infections are a major public health concern for pediatric populations and older adults. Viral kinetics, the dynamic processes of viral infection within an individual over time, vary across different populations. However, RSV transmission in different age groups is incompletely understood from the perspective of individual-level viral kinetics.

Contact with young children is a major risk factor for pneumococcal colonization in older adults.

Important questions remain about the sources of transmission of pneumococcus to older adults in the community. This is critical for understanding the potential effects of using pneumococcal conjugate vaccines (PCVs) in children and older adults. For non-institutionalized individuals, we hypothesized that the most likely source of adult-to-adult transmission is within the household.