Unbiased identification of cell identity in dense mixed neural cultures

• DOI: 10.7554/elife.95273
• Publication Date: 2024-03-13T11:25:06Z
• Authors: Sarah De Beuckeleer; Tim Van De Loover...; Johanna Van Den D...; Peter Ponsaerts; Winnok H De Vos
• Keywords: Identification

Induced pluripotent stem cell (iPSC) technology is revolutionizing biology. However, the variability between individual iPSC lines and lack of efficient to comprehensively characterize iPSC-derived types hinder its adoption in routine preclinical screening settings. To facilitate validation culture composition, we have implemented an imaging assay based on painting convolutional neural networks recognize dense mixed cultures with high fidelity. We benchmarked our approach using pure neuroblastoma astrocytoma attained a classification accuracy above 96%. Through iterative data erosion, found that inputs containing nuclear region interest close environment, allow achieving equally as whole for semi-confluent preserved prediction even very cultures. then applied this regionally restricted profiling evaluate differentiation status cultures, by determining ratio postmitotic neurons progenitors. cell-based significantly outperformed which population-level time was used criterion (96% vs 86%, respectively). In neuronal microglia could be unequivocally discriminated from neurons, regardless their reactivity state, tiered strategy allowed further distinguishing activated non-activated states, albeit lower accuracy. Thus, morphological single-cell provides means quantify composition complex holds promise use quality control models.