KSKunyang Sun

Kunyang Sun

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Kunyang Sun has a total of 67 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Exploring transition metal complexes with large language models

    by Yunsheng Liu, Jacob W. Toney, Joseph M. Cavanagh, Kunyang Sun, Andrew L. Smith, Chung-Yueh Yuan, Roland G. St Michel, Paul A. Graggs, Dean Toste, Heather J. Kulik, et al.

    Here we use a large language model for the exploration of chemical space of transition metal complexes (TMCs), fine-tuning the open-source Llama-3.2-1B model with a variation of the SMILES string representation tailored for coordination chemistry.


  • Competing Effects Modulate the Rate of Poly(A) RNA Deadenylation in a Biomolecular Condensate

    by Rose M. Irwin, Robert W. Harkness, Brian Tsang, Zi Hao Liu, Kunyang Sun, Tian Hao Huang, Teresa Head-Gordon, Lewis E. Kay, Julie D. Forman-Kay

    The unique solvent milieu found in biomolecular condensates can control cellular enzymatic reactions and shift reaction kinetics by modulating reactant concentrations, structural dynamics, and enzyme activities. Here, we explore the interplay of multiple regulatory factors within a condensate to control poly(A) RNA deadenylation, the first and rate-limiting step in mRNA turnover. The deadenylase CNOT7, a subunit of the CCR4-NOT deadenylation complex, localizes to protein- and RNA-rich granules and shows increased degradation activity in vitro in condensates formed by the C-terminal low-complexity disordered region of CAPRIN1, a component of many ribonucleoprotein (RNP) granules. We use a combination of enzymatic assays, kinetic modeling, microscopy, nuclear magnetic resonance (NMR) spectroscopy, and molecular dynamics simulations to deconvolute and define the components that underlie this enhancement. We found that enzyme and RNA are concentrated in condensates relative to buffer, which increases CNOT7 activity, while the equilibrium between CNOT7’s active and inactive states remains unchanged. The concentration-dependent increase in enzymatic rates is counterbalanced by a decrease in the enzyme’s catalytic efficiency, likely due to slower diffusion of CNOT7 and RNA within the condensates, which lessens the probability of enzyme–substrate complex formation. Molecular dynamics simulations reveal CNOT7-CAPRIN1 interactions that rely on conserved CAPRIN1 sequence features, hinting at an evolutionarily conserved role for CAPRIN1 condensation. With this quantitative kinetic analysis, we describe the multifaceted mechanism behind regulation of CNOT7 deadenylation by a condensate environment.

  • LinkLlama: Enabling a Large Language Model for Chemically Reasonable Linker Design

    by Kunyang Sun, Yingze Wang, Justin Purnomo, Joseph M. Cavanagh, Giovanni Battista Alteri, Teresa Head-Gordon

    Fragment-based drug discovery (FBDD) relies heavily on the design of chemically viable linkers to connect fragments binding to different pocket regions into potent lead molecules. While recent generative models have advanced spatial fragment linking, they frequently produce linkers characterized by high torsional strain and non-drug-like motifs. In this work, we present LinkLlama, a fine-tuned Meta Llama 3 model that bridges the gap between text-based generation and 3D spatial awareness. By accepting natural language prompts that specify geometric constraints, such as distances and angles, alongside physicochemical targets like Lipinski’s rules and rotatable bond limits, LinkLlama generates highly tailored molecules for the input fragments. Leveraging the inherent chemical grammar captured through supervised fine-tuning on a curated corpus of drug-like molecules from ChEMBL, the model prioritizes chemical validity without requiring complex reinforcement learning loops. Benchmarking on the ZINC and HiQBind data sets demonstrates that LinkLlama maintains competitive geometric fidelity compared to strictly 3D-aware models while achieving a 2-fold increase in the proportion of chemically reasonable designs. This rising success rate, jumping from 35% to over 80%, is defined by strict adherence to comprehensive structural filters including PAINS, non-drug-like chemical patterns, and complex ring systems. We further illustrate the model’s versatility through prospective case studies in novel small-molecule scaffold hopping and PROTAC linker design, validated via molecular docking and molecular dynamics simulations against known crystal poses. Ultimately, LinkLlama demonstrates that large language models can overcome the structural pitfalls of purely 3D-generative methods, offering a highly controllable and chemically robust framework to accelerate linker design and drug discovery in general.

  • Open Access

    Competing effects modulate the rate of poly(A) RNA deadenylation in a biomolecular condensate

    by Rose M Irwin, Robert W Harkness, Zi Hao Liu, Kunyang Sun, Tian Hao Huang, Teresa Head-Gordon, Lewis Kay, Julie Deborah Forman-Kay

    The unique solvent milieu found in biomolecular condensates can control cellular enzymatic reactions and shift reaction kinetics by modulating reactant concentrations, structural dynamics, and enzyme activities. Here we explore the interplay of multiple regulatory factors within a condensate to control poly(A) RNA deadenylation, the first and rate-limiting step in mRNA turnover. The deadenylase CNOT7, a subunit of the CCR4-NOT deadenylation complex, localizes to cytoplasmic RNA granules and shows increased degradation activity in vitro in condensates formed by the C-terminal low complexity disordered region of CAPRIN1, a component of RNA granules. We use a combination of enzymatic assays, kinetic modeling, microscopy, Nuclear Magnetic Resonance (NMR) spectroscopy, and molecular dynamics simulations to deconvolute and define the components that underlie this enhancement. We found that enzyme and RNA are concentrated in condensates relative to buffer, which increases CNOT7 activity, while the equilibrium between CNOT7's active and inactive states remains unchanged. The concentration-dependent increase in enzymatic rates is counterbalanced by a substantial decrease in the enzyme's catalytic efficiency, likely due to slower diffusion of CNOT7 and RNA within the condensates, which lessens the probability of enzyme-substrate complex formation. Molecular dynamics simulations reveal CNOT7-CAPRIN1 interactions that rely on conserved CAPRIN1 sequence features, hinting at an evolutionarily conserved role for CAPRIN1 condensation. With this quantitative kinetic analysis, we describe the multifaceted mechanism behind regulation of CNOT7 deadenylation by a condensate environment.

  • Open Access

    LinkLlama: Enabling Large Language Model for Chemically Reasonable Linker Design

    by Kunyang Sun, Yingze Eric Wang, Justin Clement Purnomo, Joseph M. Cavanagh, Giovanni Battista Alteri, Teresa Head-Gordon

    Fragment-based drug discovery (FBDD) relies heavily on the design of chemically viable linkers to connect fragments binding to different pocket regions into potent lead molecules. While recent generative models have advanced spatial fragment linking, they frequently produce linkers characterized by high torsional strain and non-drug-like motifs. In this work, we present LinkLlama, a fine-tuned Meta Llama 3 model that bridges the gap between text-based generation and 3D spatial awareness. By accepting natural language prompts that specify geometric constraints, such as distances and angles, alongside physicochemical targets like Lipinski’s rules and rotatable bond limits, LinkLlama generates highly tailored molecules for the input fragments. Leveraging the inherent chemical grammar captured through supervised fine-tuning on a curated corpus of drug-like molecules from ChEMBL, the model prioritizes chemical validity without requiring complex reinforcement learning loops. Benchmarking on the ZINC and HiQBind datasets demonstrates that LinkLlama maintains competitive geometric fidelity compared to strictly 3D-aware models while achieving a two-fold increase in the proportion of chemically reasonable designs. This rising success rate, jumping from 35% to over 80%, is defined by strict adherence to comprehensive structural filters including PAINS, non-drug-like chemical patterns and complex ring systems. We further illustrate the model’s versatility through prospective case studies in novel small-molecule scaffold hopping and PROTAC linker design, validated via molecular docking and molecular dynamics simulations against known crystal poses. Ultimately, LinkLlama demonstrates that large language models can overcome the structural pitfalls of purely 3D-generative methods, offering a highly controllable and chemically robust framework to accelerate linker design and drug discovery in general.


  • Open Access

    KinConfBench: A Curated Benchmark for Cofolding Models on Kinase Conformational States

    by Kunyang Sun, Teresa Head-Gordon

    Protein kinases are critical drug targets, requiring therapeutics that can modulate their active and inactive conformational states. While cofolding models can generate global folds directly from kinase sequences and ligand SMILES strings, these models have not yet been tested on their ability to recover ligand induced-fit conformational states of the kinase proteins. Here, we introduce KinConfBench, a curated benchmark of 2,225 high-quality human kinase chains to evaluate the ability of three state-of-the-art cofolding models---Boltz-2, Chai-1, and Protenix---to recover both canonical and rare conformational states. We show that geometric success metrics of a ligand pose in the active site does not correlate strongly with the correct kinase conformational state, motivating a new set of dynamical benchmarks for assessing cofolding models. While all three cofolding models achieve ~65-75% prediction accuracy for kinase conformational classification, they exhibit severe mode collapse when performing multiple inferences, show negligible structural diversity in sampling induced-fit motions, and display a prevalent ``apo-drift'' in which all three cofolding models predominately predict the kinase to be in its ligand-free state. Our results highlight that capturing ligand-induced protein conformational diversity, not just geometric fit, is critical for next-generation structure-based drug discovery.


  • Open Access

    AlphaFlex: Ensembles of the human proteome representing disordered regions

    by Zi Hao Liu, Oufan Zhang, Stefano De Castro, Kunyang Sun, Hamidreza Ghafouri, Omar Abdelghani Attafi, Nicolas L. Fawzi, Silvio C. E. Tosatto, Alexander M. Monzon, Alan M. Moses, et al.

    More than two thirds of proteins in the human proteome are predicted to contain intrinsically disordered regions (IDRs), which lack stable folded structure. IDRs are critical for biological regulation and organization, as targets for post-translational modifications, and as mediators of biomolecular condensates. To address the pressing need for better structural models enabling functional insight, we developed AlphaFlex to model fully atomistic conformer ensembles for proteins predicted to have IDRs, modeled in the context of AlphaFold folded domains and an implicit bilayer for transmembrane proteins. The AlphaFlex resource provides conformational ensembles of human proteins from the AlphaFold database with identified IDRs in the Protein Ensemble Database that is mirrored in UniProt. This transformative resource of AlphaFlex ensembles provides physically and biologically relevant full-length models for IDR proteins, including scaffold proteins, those with IDR:folded-domain interactions, regulatory and condensate proteins requiring exposed binding elements, conditionally folding IDRs, and transmembrane proteins containing IDRs.


  • Open Access

    SynLlama: Generating Synthesizable Molecules and Their Analogs with Large Language Models

    by Kunyang Sun, Dorian Bagni, Joseph M. Cavanagh, Yingze Wang, Jacob M. Sawyer, Bo Zhou, Andrew Gritsevskiy, Oufan Zhang, Teresa Head-Gordon

    Generative machine learning models for exploring chemical space have shown immense promise, but many molecules that they generate are too difficult to synthesize, making them impractical for further investigation or development. In this work, we present a novel approach by fine-tuning Meta’s Llama3 Large Language Models (LLMs) to create SynLlama, which generates full synthetic pathways made of commonly accessible building blocks and robust organic reaction templates. SynLlama explores a large synthesizable space using significantly less data and offers strong performance in both forward and bottom-up synthesis planning compared to other state-of-the-art methods. We find that SynLlama, even without training on external building blocks, can effectively generalize to unseen yet purchasable building blocks, meaning that its reconstruction capabilities extend to a broader synthesizable chemical space than those of the training data. We also demonstrate the use of SynLlama in a pharmaceutical context for synthesis planning of analog molecules and hit expansion leads for proposed inhibitors of target proteins, offering medicinal chemists a valuable tool for discovery.


  • Open Access

    Chiral edge waves in a dance-based human topological insulator

    by Matthew Du, Juan B. Pérez-Sánchez, Jorge A. Campos-Gonzalez-Angulo, Arghadip Koner, Federico Mellini, Sindhana Pannir-Sivajothi, Yong Rui Poh, Kai Schwennicke, Kunyang Sun, Stephan van Den Wildenberg, et al.

    Topological insulators are insulators in the bulk but feature chiral energy propagation along the boundary. This property is topological in nature and therefore robust to disorder. Originally discovered in electronic materials, topologically protected boundary transport has since been observed in many other physical systems. Thus, it is natural to ask whether this phenomenon finds relevance in a broader context. We choreograph a dance in which a group of humans, arranged on a square grid, behave as a topological insulator. The dance features unidirectional flow of movement through dancers on the lattice edge. This effect persists when people are removed from the dance floor. Our work extends the applicability of wave physics to dance.


  • Open Access

    Mining for Potent Inhibitors through Artificial Intelligence and Physics: A Unified Methodology for Ligand Based and Structure Based Drug Design

    by Jie Li, Oufan Zhang, Kunyang Sun, Yingze Wang, Xingyi Guan, Dorian Bagni, Mojtaba Haghighatlari, Fiona L. Kearns, Conor Parks, Rommie E. Amaro, et al.

    Determining the viability of a new drug molecule is a time- and resource-intensive task that makes computer-aided assessments a vital approach to rapid drug discovery. Here we develop a machine learning algorithm, iMiner, that generates novel inhibitor molecules for target proteins by combining deep reinforcement learning with real-time 3D molecular docking using AutoDock Vina, thereby simultaneously creating chemical novelty while constraining molecules for shape and molecular compatibility with target active sites. Moreover, through the use of various types of reward functions, we have introduced novelty in generative tasks for new molecules such as chemical similarity to a target ligand, molecules grown from known protein bound fragments, and creation of molecules that enforce interactions with target residues in the protein active site. The iMiner algorithm is embedded in a composite workflow that filters out Pan-assay interference compounds, Lipinski rule violations, uncommon structures in medicinal chemistry, and poor synthetic accessibility with options for cross-validation against other docking scoring functions and automation of a molecular dynamics simulation to measure pose stability. We also allow users to define a set of rules for the structures they would like to exclude during the training process and postfiltering steps. Because our approach relies only on the structure of the target protein, iMiner can be easily adapted for the future development of other inhibitors or small molecule therapeutics of any target protein.