Naim Matasci

This study uses AI to identify BMI-associated morphologic features in breast cancer tissue, finding that high BMI is linked to distinct stromal patterns and reduced inter-patient heterogeneity.

The paper introduces a thin plate spline method to model tissue boundaries in organ-on-chip models and quantify tumor cell invasion.

This paper develops a machine learning pipeline to predict antibody developability from sequence, achieving high sensitivity and specificity on a dataset of 2400 antibodies.