An increasing number of children are afflicted by allergies and common signs, such as food sensitivity and eczema, often manifest during the first years of life. The biological mechanisms responsible for allergy development are still unclear but the intrauterine environment is of high importance. One explanation could be that environmental exposures occurring during fetal development, together with reprogramming of epigenetic marks in fetal DNA increases the risk of asthma and allergy. The overall aim of this study is to build a predictive model for identification of children at high risk of asthma and allergy. Taking advantage of NorthPop – a prospective birth cohort in Northern Sweden - this project will include data on air-pollution exposure, chemical exposure, DNA methylation data, GWAS data and outcome data (asthma and allergies) for up to 5000 women and children from the NorthPop birth cohort. Samples and information from the mothers were collected during pregnancy and cord blood was collected from the newborns. Outcomes have been assessed at 18 months and 3 years of age. We are now requesting resources to allow us to proceed with our study by supporting the analysis, development and deployment of machine learning models for asthma and allergy risks. To do this we hereby apply for computational resources including temporal storage, RAM, GPU, Python and machine learning and deep learning libraries to implement and optimize the models.