Mingon Kang

PINT: Pathway-pathway interactions for predicting interpretable clinical outcomes from gene expression

PINT predicts clinical outcomes from gene expression by modeling pathway-pathway interactions, outperforming benchmarks and revealing biologically meaningful pathway relationships.

Multi-modal Graph Integration for Biologically Interpretable Domain Identification Using Spatial Transcriptomics

This study introduces BIGraph-ST, a method that integrates pathway activity and histological features to improve spatial domain identification in spatial transcriptomics, showing better performance in cancer tissues.

Knowledge-Guided Learning with Curated Prior Genetic Biomarkers for Robust Model Interpretation

This paper introduces BioExPL, a model-agnostic framework that integrates curated genetic biomarkers into neural networks to improve predictive performance and model interpretability.

Fairness-aware Supervised Hierarchical Contrastive Semantic Learning for Sexual Dimorphism Analysis

This paper introduces FairHICON, a fairness-aware supervised hierarchical contrastive learning method that identifies sex-specific and common genomic drivers, improving predictive performance and reducing sex-based performance gaps in cancer and asthma datasets.

PIMO: Pathway-based Interpretable Multi-Omics interactions for multi-omics integration

PIMO improves multi-omics integration by modeling pathway-based interactions, enhancing survival analysis and interpretability in cancer datasets.

Prediction of bacterial protein-compound interactions with only positive samples

This paper introduces BIN-PU, a PU learning framework for predicting bacterial protein-compound interactions using only positive samples, showing improved performance over existing methods.

Interpretable Kolmogorov-Arnold Networks for Enzyme Commission Number Prediction

This paper integrates Kolmogorov-Arnold Networks (KANs) into deep learning models for EC number prediction, showing improved performance and introducing an interpretation method to identify relevant features.

Stochastic LASSO for extremely high-dimensional genomic data

The paper introduces Stochastic LASSO, a bootstrap-based method for feature selection in high-dimensional genomic data, showing improved performance over existing models in simulation and real cancer data.

Plastic-hydrolytic enzyme classification using explainable deep learning

This paper introduces PEPIC, an explainable deep learning model for classifying plastic-hydrolytic enzymes from protein sequences, showing improved performance and biological validation.

HIT-EC: Trustworthy prediction of enzyme commission numbers using a hierarchical interpretable transformer

HIT-EC improves EC number prediction with a hierarchical transformer model, showing better performance and interpretability than existing methods.

Hi-LASSO: High-performance Python and Apache spark packages for feature selection with high-dimensional data

Hi-LASSO provides Python and Apache Spark packages for efficient feature selection in high-dimensional data, with improved performance and scalability through parallel implementation and parametric statistical tests.