Heewook Lee

RulePep: Interpretable ESM-Guided Neural-Symbolic Peptide Classification

RulePep is a neural-symbolic classifier for peptide-function prediction that combines ESM-2 representations with interpretable rules to achieve high performance on three peptide classification tasks.

An AI-Guided Framework Reveals Conserved Features Governing microRNA Strand Selection

This paper develops an AI-driven framework to predict and explain miRNA strand selection across species, revealing conserved rules governing this process.

Self-Contemplating In-Context Learning Enhances T Cell Receptor Generation for Novel Epitopes

This study enhances T cell receptor generation for novel epitopes using in-context learning and self-contemplation prompting, achieving performance comparable to or better than ground-truth TCRs.

Context-Aware Amino Acid Embedding Advances Analysis of TCR-Epitope Interactions

The paper introduces context-aware amino acid embeddings for TCR sequences, showing improved performance in binding affinity prediction and clustering compared to existing methods.

DNA Replication-transcription conflicts do not significantly contribute to spontaneous mutations due to replication errors in Escherichia coli

This study analyzes mutations in E. coli with mismatch repair defects and finds no significant orientation bias in mutation frequencies between genes oriented co-directionally or head-on to replication.

New complexities of SOS-induced untargeted mutagenesis in Escherichia coli as revealed by mutation accumulation and whole-genome sequencing

This study uses mutation accumulation and whole-genome sequencing to reveal new complexities in SOS-induced untargeted mutagenesis in Escherichia coli, showing sequence and DNA-strand bias in transversion mutations.

Determinants of base-pair substitution patterns revealed by whole-genome sequencing of DNA mismatch repair defective Escherichia coli

This study uses whole-genome sequencing of MMR-defective E. coli to identify base-pair substitution patterns and their determinants, revealing context-dependent mutational hotspots and strand bias.

Graph-Guided Assembly For Novel HLA Allele Discovery

This paper introduces a graph-guided assembly method for HLA typing that enables accurate identification of both known and novel alleles from whole genome sequencing data.