Minkyung Baek

Thal-Kak combines five structure predictors to improve sampling but finds confidence scores and quality assessment methods hinder model selection.

The paper uses high-throughput antibody variant analysis and AI models to optimize antibody productivity by navigating fitness landscapes and identifying structurally compatible CDR variants.

The paper predicts 18,316 human protein-protein interactions with 90% precision using enhanced coevolutionary analysis and a new deep learning model.

The paper determines the structure of E. coli LetAB, identifies LetA as a novel transporter family, and proposes a mechanism for lipid transport using proton-motive force.

This study uses deep learning to predict protein-protein interactions in bacterial pathogens, identifying new complexes involving essential genes and virulence factors, with half of tested predictions validated.

This paper applies parameter-efficient fine-tuning methods to proteomics, achieving competitive or better performance than traditional fine-tuning with significantly reduced computational resources.

The paper introduces a method to map antibody-antigen interactions using SPID platform to enhance affinity prediction and optimize antibody design.

This paper introduces RFAA and RFdiffusionAA, models that can predict and design complex biomolecular assemblies including proteins, nucleic acids, small molecules, and covalent modifications.

This paper shows that targeting FAM19A5 with a monoclonal antibody improves synaptic function and cognition in Alzheimer's disease models.

Fine-tuning RoseTTAFold as a diffusion denoiser gives RFdiffusion, a general protein backbone generator; a designed influenza haemagglutinin binder matched its model by cryo-EM.

The paper fine-tunes AlphaFold to predict peptide binding specificity for MHC and other domains, achieving performance comparable to sequence-based methods.

This paper introduces a top-down reinforcement learning approach to design protein nanomaterials, resulting in more compact and robust icosahedral assemblies than previously observed.

One RoseTTAFold-derived network models protein-DNA and protein-RNA complexes plus RNA tertiary structure end to end, returning confidence estimates alongside each 3D model.

The paper introduces a 3-track network for accurate protein structure and interaction prediction, achieving performance close to DeepMind's CASP14 results and enabling rapid modeling of protein complexes from sequence data.

The paper introduces DeepAccNet, a deep learning framework that improves protein structure refinement by estimating accuracy and guiding Rosetta refinement.