Shinjae Yoo

PEACE improves effector protein prediction by using contrastive embeddings and prototype-aware training, outperforming EffectorP 3.0 on fungal and fungi+oomycete datasets.

The paper introduces SCALE, a pipeline for longitudinal cell painting analysis, demonstrating its ability to handle imaging variability and enable consistent comparisons across time points.

The paper develops ESMBind, a workflow combining evolutionary and physics-based modeling to predict metal-binding proteins and their structures, showing improved performance over existing methods.

This paper introduces SwiFUN, a deep-learning framework for predicting task-related brain activity from resting-state fMRI, achieving higher accuracy than existing methods in adults and children.

This work integrates AlphaFold with a deep learning tool, CryoFEM, to improve the accuracy of 3-D atomic models built from cryo-EM maps.

This paper shows that polygenic risk scores (PRS) overestimate predictive accuracy when datasets have overlapping subjects, using Alzheimer's disease and other traits as examples.

This study uses machine learning to predict Alzheimer's disease incidence from administrative health data, achieving moderate accuracy in 1-4 year predictions.

This paper uses multimodal MRI and machine learning to classify Alzheimer's disease and mild cognitive impairment, showing high accuracy in diagnosis and progression prediction.

This paper uses machine learning on brain morphometry and connectomes from MRI to predict Alzheimer's disease risk and progression, achieving high accuracy in both single-site and multi-site datasets.

Open-source KBase platform unites reference genomes and biochemistry, over 70 apps, Jupyter-based Narratives with provenance, and a Docker SDK for reproducible plant and microbial systems biology.

This paper evaluates the impact of long-read sequencing on genome assembly across multiple species and introduces a new error correction algorithm and predictive model.