ABSTRACT
Neural networks have emerged as immensely powerful tools in predicting functional genomic regions, notably evidenced by recent successes in deciphering gene regulatory logic. However, a systematic evaluation of how model architectures and training strategies impact genomics model performance is lacking. To address this gap, we held a DREAM Challenge where competitors trained models on a dataset of millions of random promoter DNA sequences and corresponding expression levels, experimentally determined in yeast, to best capture the relationship between regulatory DNA and gene expression. For a robust evaluation of the models, we designed a comprehensive suite of benchmarks encompassing various sequence types. While some benchmarks produced similar results across the top-performing models, others differed substantially. All top-performing models used neural networks, but diverged in architectures and novel training strategies, tailored to genomics sequence data. To dissect how architectural and training choices impact performance, we developed the Prix Fixe framework to divide any given model into logically equivalent building blocks. We tested all possible combinations for the top three models and observed performance improvements for each. The DREAM Challenge models not only achieved state-of-the-art results on our comprehensive yeast dataset but also consistently surpassed existing benchmarks on Drosophila and human genomic datasets. Overall, we demonstrate that high-quality gold-standard genomics datasets can drive significant progress in model development.
ABSTRACT
This study evaluated the efficacy and tolerability in the initiation treatment of Concerta (OROS methylphenidate HCl) in Korean children with Attention-Deficit/Hyperactivity Disorder (AD/HD). One hundred and nineteen children with AD/HD were entered into a multi-center, open-label, four-week trial. The dosage of Concerta was adjusted by the investigators based on symptoms and safety assessments performed on a weekly basis. The safety of the drug and its efficacy for attention, behavior, and cognitive function were assessed. The primary outcome measures for efficacy were the Parent and Teacher IOWA Conners Rating Scales, Peer Interaction Items, and the Clinical Global Impression Scale. Cognitive tests (Continuous Performance Test, Matched Familiar Figure Test, Verbal Fluency Test, and Trail Making Test) were included as the secondary outcome measures. In most participants, OROS methylphenidate was well tolerated. There were significant improvements in attention, behavior, and function as measured by parents, teachers, and investigators. The benefit of the initiation of OROS methylphenidate in children with AD/HD was shown on the cognitive tests as well. These data provide support for the benefit of the once-daily methylphenidate preparation, Concerta in the treatment of Korean children with AD/HD. Children were initiated safely in this short-term trial, and its effectiveness was evident in the behavioral, as well as neuropsychological measurements.