Background Attention-deficit/hyperactivity disorder (ADHD) comorbid with sleep disturbances can produce profound disruption in daily life and negatively impact quality of life of both the child and the family. However, the temporal relationship between ADHD and sleep impairment is unclear, as are underlying common brain mechanisms. Methods This study used data from the Quebec Longitudinal Study of Child Development ( n = 1601, 52% female) and the Adolescent Brain Cognitive Development Study ( n = 3515, 48% female). Longitudinal relationships between symptoms were examined using cross-lagged panel models. Gray matter volume neural correlates were identified using linear regression. The transcriptomic signature of the identified brain-ADHD-sleep relationship was characterized by gene enrichment analysis. Confounding factors, such as stimulant drugs for ADHD and socioeconomic status, were controlled for. Results ADHD symptoms contributed to sleep disturbances at one or more subsequent time points in both cohorts. Lower gray matter volumes in the middle frontal gyrus and inferior frontal gyrus, amygdala, striatum, and insula were associated with both ADHD symptoms and sleep disturbances. ADHD symptoms significantly mediated the link between these structural brain abnormalities and sleep dysregulation, and genes were differentially expressed in the implicated brain regions, including those involved in neurotransmission and circadian entrainment. Conclusions This study indicates that ADHD symptoms and sleep disturbances have common neural correlates, including structural changes of the ventral attention system and frontostriatal circuitry. Leveraging data from large datasets, these results offer new mechanistic insights into this clinically important relationship between ADHD and sleep impairment, with potential implications for neurobiological models and future therapeutic directions.

The prediction of drug-disease associations holds great potential for precision medicine in the era of big data and is important for the identification of new indications for existing drugs. The associations between drugs and diseases can be regarded as a complex heterogeneous network with multiple types of nodes and links. In this paper, we propose a method, namely HED (Heterogeneous network Embedding for Drug-disease association), to predict potential associations between drugs and diseases based on a drug-disease heterogeneous network. Specifically, with the heterogeneous network constructed from known drug-disease associations, HED employs network embedding to characterize drug-disease associations and then trains a classifier to predict novel potential drug-disease associations. The results on two real datasets show that HED outperforms existing popular approaches. Furthermore, some of our predictions have been verified by evidence from literature. For instance, carvedilol, a drug that was originally used for heart failure, left ventricular dysfunction, and hypertension, is predicted to be useful for atrial fibrillation by HED, which is supported by clinical trials.