Pora Kim

This study benchmarks 12 AI-based molecular generation models for drug design across 176 protein-ligand systems, finding no single method optimizes all criteria and proposing a hybrid approach.

AllergenAI predicts allergenicity using protein sequences, identifies a P-A motif in vicilins, and demonstrates potential for incorporating 3D structural data.

This study develops a 2YS logistic regression model using radiogenomics analysis to predict GBM patient survival based on MRI features and gene associations.

This study uses AlphaFold 2 to analyze the structural impact of alternative splicing in 3,000 human genes, identifying structural changes and disease-related mutations.

This study investigates how A-to-I RNA editing affects cancer immunity by modulating interferon pathways and immune cell infiltration.

This study predicts 3D structures of 732 transcription factor fusion proteins and screens FDA-approved drugs against the top five most frequent ones to identify potential therapeutic targets.

The paper identifies 25 RNA editing biomarkers in Parkinson's disease by analyzing their potential impact on miRNA regulations of 133 PD-related genes.

The paper identifies 24,236 potentially functional A-to-I RNA editing events across 33 cancer types from The Cancer Genome Atlas, linking them to tumorigenesis through altered expression, protein function, and miRNA regulation.

The paper identifies genetic variants influencing A-to-I RNA editing in neurodegenerative diseases using large-scale transcriptomic and genetic data from multiple brain tissues.

This study introduces FusionAI, a deep learning model that predicts gene fusion breakpoints from DNA sequences, aiding in the identification of genomic breakage mechanisms.

This study introduces ESOCVD, a computational platform to detect circadian gene expression patterns in AD using untimed transcriptome data, revealing five circadian alteration patterns in AD patients.