KYKun Yao

Kun Yao

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

Kun Yao has a total of 252 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Generative Glide: A De Novo Workflow for Ultra-large Library Screening

    by Xingyi Guan, Aditya Kaushik, Jumana Dakka, Himanshu Khanchandani, Zachary Kaplan, Zhe Mei, Kun Yao, Steven V. Jerome

    In the past few years, chemical vendors have embraced enormous virtual spacesoften exceeding 1010 molecules. The sheer size of these spaces presents a formidable computational challenge for traditional structure-based virtual screening. Exhaustive docking of such spaces is computationally prohibitive, and even modern active learning docking algorithms, which leverage fast ligand-based machine learning to identify the most promising candidates for docking, struggle to achieve an acceptable turnaround time. Methods based on de novo molecular generation using the reactions that define the virtual space can bypass the challenge of scoring every molecule in the space, but will often yield candidates where the synthesis as described will not work in the lab. To address these challenges, we present the Generative Glide workflow, an integrated framework that bridges the gap between in silico generation and physical acquisition. Generative Glide employs an ensemble of reinforcement learning agents optimized against a supervised GCN-based QSAR model to navigate toward chemical space regions with improved predicted binding likelihood. We implement a two-tiered strategy to ensure tractability: a high-throughput Bloom filter to rapidly identify molecules within ultra-large commercial catalogs and a retrosynthetic analysis engine to validate novel out-of-library candidates. Deployment across diverse protein targets and multiple ultra-large libraries demonstrates that the workflow consistently achieves a significant shift in docking score distributions toward better scoring compounds while maintaining a high level of scaffold diversity. Notably, the architecture is designed to be light-weight, enabling a relatively fast turnaround time compared to exhaustive enumeration. By incorporating active learning, Generative Glide further refines the scoring model’s predictive accuracy within high-potency domains, enabling the agents to effectively navigate and exploit the extreme negative tail of the docking score distribution that is poorly represented in the initial training data. This workflow provides a scalable, generative solution to augment and accelerate the virtual screening of modern chemical space.

  • DiffDock-Glide: A Hybrid Physics-Based and Data-Driven Approach to Molecular Docking

    by Lukas Herron, Jumana Dakka, Steven V. Jerome, Kun Yao, Da Shi

    Recent years have seen a rise in applications of deep learning to problems in the molecular sciences. Among them, the diffusion model DiffDock stands out as a method for docking small molecules into protein binding sites. But DiffDock struggles to compete with conventional docking methods, especially for targets outside its training set. We develop a hybrid model called DiffDock-Glide which addresses some shortcomings of deep learning docking methods: it uses a modified generative process to generate samples within a binding pocket, and the confidence model is replaced with Glide's postdocking minimization pipeline. We evaluate DiffDock-Glide on the PoseBusters data set and show improved sampling of near-native poses, especially for sequences without homologues in the training set. We also evaluate DiffDock-Glide's performance in virtual screening of compounds from the DUD-E data set against receptor structures generated by AlphaFold2 and report enrichment values that broadly surpass those from traditional Glide.


  • Top Cited Papers

    Efficient Exploration of Chemical Space with Docking and Deep Learning

    by Ying Yang, Kun Yao, Matthew P. Repasky, Karl Leswing, Robert Abel, Brian K. Shoichet, Steven V. Jerome

    With the advent of make-on-demand commercial libraries, the number of purchasable compounds available for virtual screening and assay has grown explosively in recent years, with several libraries eclipsing one billion compounds. Today’s screening libraries are larger and more diverse, enabling the discovery of more-potent hit compounds and unlocking new areas of chemical space, represented by new core scaffolds. Applying physics-based in silico screening methods in an exhaustive manner, where every molecule in the library must be enumerated and evaluated independently, is increasingly cost-prohibitive. Here, we introduce a protocol for machine learning-enhanced molecular docking based on active learning to dramatically increase throughput over traditional docking. We leverage a novel selection protocol that strikes a balance between two objectives: (1) identifying the best scoring compounds and (2) exploring a large region of chemical space, demonstrating superior performance compared to a purely greedy approach. Together with automated redocking of the top compounds, this method captures almost all the high scoring scaffolds in the library found by exhaustive docking. This protocol is applied to our recent virtual screening campaigns against the D4 and AMPC targets that produced dozens of highly potent, novel inhibitors, and a blind test against the MT1 target. Our protocol recovers more than 80% of the experimentally confirmed hits with a 14-fold reduction in compute cost, and more than 90% of the hit scaffolds in the top 5% of model predictions, preserving the diversity of the experimentally confirmed hit compounds.


  • Top Cited Papers
    Open Access

    Software for the frontiers of quantum chemistry: An overview of developments in the Q-Chem 5 package

    by Evgeny Epifanovsky, Andrew T. B. Gilbert, Xintian Feng, Joonho Lee, Yuezhi Mao, Narbe Mardirossian, Pavel Pokhilko, Alec F. White, Marc P. Coons, Adrian L. Dempwolff, et al.

    This article summarizes technical advances contained in the fifth major release of the Q-Chem quantum chemistry program package, covering developments since 2015. A comprehensive library of exchange–correlation functionals, along with a suite of correlated many-body methods, continues to be a hallmark of the Q-Chem software. The many-body methods include novel variants of both coupled-cluster and configuration-interaction approaches along with methods based on the algebraic diagrammatic construction and variational reduced density-matrix methods. Methods highlighted in Q-Chem 5 include a suite of tools for modeling core-level spectroscopy, methods for describing metastable resonances, methods for computing vibronic spectra, the nuclear–electronic orbital method, and several different energy decomposition analysis techniques. High-performance capabilities including multithreaded parallelism and support for calculations on graphics processing units are described. Q-Chem boasts a community of well over 100 active academic developers, and the continuing evolution of the software is supported by an “open teamware” model and an increasingly modular design.


  • Open Access

    Density Region of Low-Threshold Parametric Decay Instabilities in Electron Cyclotron Resonance Heating Experiments in Tokamak

    by Kun Yao

    The density conditions under which low-threshold parametric decay instabilities occur are analyzed by a physical model. Calculations show that low-threshold parametric decay instabilities occur in the density region. Magnetic field effects on the density region are analyzed. The maximum width of the density region is found. The plasma temperature has little effect on the density region. In order to avoid the low-threshold parametric decay instabilities, the daughter wave’s frequency must be far from the UH frequency inside magnetic island. It’s the key to control the magnetic field inside the magnetic island.

  • Compressing physics with an autoencoder: Creating an atomic species representation to improve machine learning models in the chemical sciences

    by John E. Herr, Kevin Koh, Kun Yao, John Parkhill

    We define a vector quantity which corresponds to atomic species identity by compressing a set of physical properties with an autoencoder. This vector, referred to here as the elemental modes, provides many advantages in downstream machine learning tasks. Using the elemental modes directly as the feature vector, we trained a neural network to predict formation energies of elpasolites with improved accuracy over previous works on the same task. Combining the elemental modes with geometric features used in high-dimensional neural network potentials (HD-NNPs) solves many problems of scaling and efficiency in the development of such neural network potentials. Whereas similar models in the past have been limited to typically four atomic species (H, C, N, and O), our implementation does not scale in cost by adding more atomic species and allows us to train an HD-NNP model which treats molecules containing H, C, N, O, F, P, S, Cl, Se, Br, and I. Finally, we establish that our implementation allows us to define feature vectors for alchemical intermediate states in the HD-NNP model, which opens up new possibilities for performing alchemical free energy calculations on systems where bond breaking/forming is important.


  • On the border between localization and delocalization: tris(iminoxolene)titanium(iv)

    by Travis Marshall-Roth, Kun Yao, John A. Parkhill, Seth N. Brown

    The tris(aminophenol) ligand tris(4-methyl-2-(3′,5′-di-tert-butyl-2′-hydroxyphenylamino)phenyl)amine, MeClampH6, reacts with Ti(OiPr)4 to give, after exposure to air, the dark purple, neutral, diamagnetic complex (MeClamp)Ti. The compound is six-coordinate, with an uncoordinated central nitrogen (Ti–N = 2.8274(12) Å), and contains titanium(IV) and a doubly oxidized ligand, formally a bis(iminosemiquinone)-mono(amidophenoxide). The compound is unsymmetrical in the solid state, though the three ligands are equivalent on the NMR timescale in solution. Ab initio calculations indicate that the ground state is a multiconfigurational singlet, with a low-lying multiconfigurational triplet state. Variable-temperature NMR measurements are consistent with a singlet–triplet gap of 1200 ± 70 cm−1, in good agreement with calculations. The distortion from threefold symmetry allows a low-lying, partially populated ligand-centered π nonbonding orbital to mix with largely occupied metal–ligand π bonding orbitals. The energetic accessibility of this distortion is inversely related to the strength of the metal–ligand π bonding interaction.


  • Metadynamics for training neural network model chemistries: A competitive assessment

    by John E. Herr, Kun Yao, Ryker McIntyre, David W. Toth, John Parkhill

    Neural network model chemistries (NNMCs) promise to facilitate the accurate exploration of chemical space and simulation of large reactive systems. One important path to improving these models is to add layers of physical detail, especially long-range forces. At short range, however, these models are data driven and data limited. Little is systematically known about how data should be sampled, and “test data” chosen randomly from some sampling techniques can provide poor information about generality. If the sampling method is narrow, “test error” can appear encouragingly tiny while the model fails catastrophically elsewhere. In this manuscript, we competitively evaluate two common sampling methods: molecular dynamics (MD), normal-mode sampling, and one uncommon alternative, Metadynamics (MetaMD), for preparing training geometries. We show that MD is an inefficient sampling method in the sense that additional samples do not improve generality. We also show that MetaMD is easily implemented in any NNMC software package with cost that scales linearly with the number of atoms in a sample molecule. MetaMD is a black-box way to ensure samples always reach out to new regions of chemical space, while remaining relevant to chemistry near kbT. It is a cheap tool to address the issue of generalization.


  • Top Cited Papers
    Open Access

    The TensorMol-0.1 model chemistry: a neural network augmented with long-range physics

    by Kun Yao, John E. Herr, David W. Toth, Ryker Mckintyre, John Parkhill

    Traditional force fields cannot model chemical reactivity, and suffer from low generality without re-fitting. Neural network potentials promise to address these problems, offering energies and forces with near ab initio accuracy at low cost. However a data-driven approach is naturally inefficient for long-range interatomic forces that have simple physical formulas. In this manuscript we construct a hybrid model chemistry consisting of a nearsighted neural network potential with screened long-range electrostatic and van der Waals physics. This trained potential, simply dubbed “TensorMol-0.1”, is offered in an open-source Python package capable of many of the simulation types commonly used to study chemistry: geometry optimizations, harmonic spectra, open or periodic molecular dynamics, Monte Carlo, and nudged elastic band calculations. We describe the robustness and speed of the package, demonstrating its millihartree accuracy and scalability to tens-of-thousands of atoms on ordinary laptops. We demonstrate the performance of the model by reproducing vibrational spectra, and simulating the molecular dynamics of a protein. Our comparisons with electronic structure theory and experimental data demonstrate that neural network molecular dynamics is poised to become an important tool for molecular simulation, lowering the resource barrier to simulating chemistry.


  • Intrinsic Bond Energies from a Bonds-in-Molecules Neural Network

    by Kun Yao, John E. Herr, Seth N. Brown, John Parkhill

    Neural networks are being used to make new types of empirical chemical models as inexpensive as force fields, but with accuracy similar to the ab initio methods used to build them. In this work, we present a neural network that predicts the energies of molecules as a sum of intrinsic bond energies. The network learns the total energies of the popular GDB9 database to a competitive MAE of 0.94 kcal/mol on molecules outside of its training set, is naturally linearly scaling, and applicable to molecules consisting of thousands of bonds. More importantly, it gives chemical insight into the relative strengths of bonds as a function of their molecular environment, despite only being trained on total energy information. We show that the network makes predictions of relative bond strengths in good agreement with measured trends and human predictions. A Bonds-in-Molecules Neural Network (BIM-NN) learns heuristic relative bond strengths like expert synthetic chemists, and compares well with ab initio bond order measures such as NBO analysis.