Yassin Refahi

This paper develops a 3D U-net model for segmenting wood cells in confocal images to improve predictions of enzymatic hydrolysis efficiency.

The paper develops a hierarchical modeling framework to predict enzymatic saccharification dynamics by simplifying complex interactions through successive model reductions.

This study develops a pipeline to predict sugar conversion yields during plant cell wall enzymatic hydrolysis using autofluorescence and morphological changes, revealing strong negative correlations with conversion efficiency.

This study identifies a distinct autofluorescence pattern marking enzymatic deconstruction of plant cell walls and develops a computational pipeline to assess hydrolysis impact.

This paper benchmarks deep learning algorithms for 3D instance segmentation of confocal images, showing performance differences and advantages of end-to-end 3D methods.

The paper creates a 4-D atlas of early Arabidopsis flower development and uses computational models to identify gene regulatory hypotheses and growth mechanisms.