Description:
<jats:title>Abstract</jats:title>
<jats:p>Cancer cells are multi-scale structures with modular organization across at least four orders of magnitude. Two central approaches for mapping this structure – protein fluorescent imaging and protein interaction – each generate extensive datasets but of distinct qualities and resolutions that are typically treated separately. Here, I will describe ongoing efforts to reconcile the large-scale data emerging from protein imaging and protein affinity purification interaction screens to create unified maps of cancer cells. The core concept is to use machine learning to compute a suitable embedding for each dataset, then to use these data embeddings to produce a general measure of protein distance calibrated against cellular components of known size. The evolving map, called the Multi-Scale Integrated Cell (MuSIC 1.0), currently resolves 69 subcellular systems of which approximately half are undocumented. Based on these findings we have performed 134 additional affinity purifications, validating close subunit associations for the majority of systems. I will also discuss how these cell maps can be used to identify protein complexes, and larger-scale systems such as organelles, that are under significant selective pressure for somatic mutations in different tumor types. In many of these cases, the mutation burden of the complex is far more substantial than the mutation frequency of any of the individual genes that encode it. By integration across scales, MuSIC substantially increases the mapping resolution obtained from imaging while giving protein interactions a spatial dimension, paving the way to incorporate many molecular data types in proteome-wide maps of cells. This work is a collaboration between the Cancer Cell Mapping Initiative (CCMI), the Human Protein Atlas (HPA), and the BioPlex Resource.</jats:p>
<jats:p>Citation Format: Trey Ideker. Mapping cell structure across scales by fusing protein images and interactions [abstract]. In: Proceedings of the AACR Virtual Special Conference on Artificial Intelligence, Diagnosis, and Imaging; 2021 Jan 13-14. Philadelphia (PA): AACR; Clin Cancer Res 2021;27(5_Suppl):Abstract nr IA-09.</jats:p>