Furthering our understanding into the cell’s transcriptional and regulatory mechanisms and how changes in these relate to Alzheimer’s disease (AD), promises to unravel the aetiology of this complex disease, potentially yielding improved therapeutics. However, doing so requires both AD-specific and broader advancements in experimental assays and computational approaches in the field. Here, we attempt to address such shortcomings in computational analyses, covering both the protein coding and non-coding genome. These approaches include the standardisation of processing and quality control of genetic information, the standardisation of analysis for cell type-specific transcriptional changes—both broadly and in the study of AD—prioritising functional and disease-relevant genomic loci in silico using deep learning to link epigenetics to transcription, and predicting cell type-specific effects of genetic variants while accounting for distal regulation with genomic deep learning models. Although the focus of this work is AD, the developed, open-source, computational and deep learning techniques are all broadly applicable to our comprehension of the cis-regulatory code.