S.-i. Lee

Physics of sliding on water predicts morphological and behavioral allometry across a wide range of body sizes in water striders (Gerridae)

The paper models sliding physics on water to predict morphological and behavioral allometry in water striders across body sizes, confirming predictions with species observations.

Predictive and robust gene selection for spatial transcriptomics

The paper introduces PERSIST, a deep learning framework that selects optimal gene panels for spatial transcriptomics using scRNA-seq data, improving prediction accuracy and generalization across technologies.

Automated detection of glaucoma with interpretable machine learning using clinical data and multi-modal retinal images

This paper develops an interpretable machine learning model for glaucoma detection using clinical data and multi-modal retinal images, achieving high accuracy and identifying both known and novel disease-related features.

Uncovering expression signatures of synergistic drug response using an ensemble of explainable AI models

This study uses an ensemble of explainable AI models to uncover expression signatures of synergistic drug response in AML, revealing a hematopoietic differentiation signature as a key factor.

A novel method for robust estimation of ants' walking speed and curvature on convoluted trajectories derived from their gait pattern

This paper introduces a novel algorithm to estimate ants' walking speed and curvature on convoluted trajectories, showing it is more reliable than the conventional SLD method.

Fitness Functions Determine Optimal Parental Allocation: Redefining Trivers Willard Theory

The paper mathematically shows that reversed Trivers-Willard theory can result from parental fitness optimization, depending on the fitness functions used.