VIS-seq, a pooled image-based platform using circular RNA barcodes and anti-silencing expression cassettes, enables high-dimensional morphological profiling of thousands of protein variants in disease-relevant human cell types, revealing that LMNA variants segregate into distinct mechanistic classes including gain-of-function variants that increase nuclear circularity, while PTEN variants associated with autism spectrum disorder exhibit nuclear mislocalization that distinguishes them from tumor syndrome variants, demonstrating that variant effects span a multidimensional phenotypic continuum not captured by single-phenotype assays or computational predictors.

Genetic variants often produce complex phenotypic effects that confound current assays and predictive models. We developed Variant in situ sequencing (VIS-seq), a pooled, image-based method that measures variant effects on molecular and cellular phenotypes in diverse cell types. Applying VIS-seq to ∼3,000 LMNA and PTEN variants yielded high-dimensional morphological profiles that captured variant-driven changes in protein abundance, localization, activity and cell architecture. We identified gain-of-function LMNA variants that reshape the nucleus and autism-associated PTEN variants that mislocalize. Morphological profiles predicted variant pathogenicity with near-perfect accuracy and distinguished autism-linked from tumor syndrome-linked PTEN variants. Most variants impacted a multidimensional continuum of phenotypes not recapitulated by any single functional readout. By linking protein variation to cell images at scale, we illuminate how variant effects cascade from molecular to subcellular to cell morphological phenotypes, providing a framework for resolving the complexity of variant function.