In this project, we investigate the epigenetic landscapes of Drosophila melanogaster during embryogenesis using single-cell technologies. Specifically, we integrate data from single-cell CUT&Tag (nanoCT), single-cell RNA-seq, and single-cell ATAC-seq to study how chromatin modifications predict gene expression at the single-cell level. We are particularly interested in the mechanisms of Polycomb-mediated repression, its tissue specificity, and the formation of developmental gene-regulatory networks. Another part of the project focuses on the alternative promoter usage and epigenetic regulation of this process. We plan to use scGLUE – a variational autoencoder (VAE)-based framework for: o Integration of scATAC-seq and scCUT&Tag data, o Inference of gene-bin relationships in scRNA-seq, o Construction of gene regulatory networks [1]. We plan to continue using scGLUE for single-cell dataset integration. First, we will perform control comparisons to justify our choice of using a binned genome-based matrix rather than a peak-based matrix. These results will be included in our ongoing manuscript. Second, we aim to integrate datasets generated within the European SCENTINEL Consortium (https://www.twinning-scentinel.eu/), where we contributed by performing nanoCUT&Tag on Drosophila tumour samples. These data will be integrated with existing scRNA-seq and scATAC-seq datasets from the consortium. Third, we plan a new integration study based on our original embryonic dataset, combining it with a 5'-end single-cell dataset from the same embryonic stage. This experiment is planned but has not yet been performed. Because scGLUE requires NVIDIA GPUs, we are unable to run it on Dardel, where our primary compute allocation resides. Following NAISS recommendations, we have applied for a Small Compute project on Alvis, which provides the required GPU infrastructure. Although single-cell integration tasks are relatively short in runtime, the number of iterations needed to achieve biologically meaningful results may vary. As such, our GPU usage on Alvis may fluctuate from month to month depending on the complexity of each dataset. References: 1) Cao, ZJ., Gao, G. Nat Biotechnol (2022). https://pypi.org/project/scglue/