arXiv subjects

Woo Youn Kim

Publications and source records attributed to Woo Youn Kim.

29 records · Page 2Linked to original sources

arXiv2021

PIGNet: A physics-informed deep learning model toward generalized drug-target interaction predictions

Recently, deep neural network (DNN)-based drug-target interaction (DTI) models were highlighted for their high accuracy with affordable computational costs. Yet, the models' insufficient generalization remains a challenging problem in the practice of in-silico drug discovery. We propose two key strategies to enhance generalization in the DTI model. The first is to predict the atom-atom pairwise interactions via physics-informed equations parameterized with neural networks and provides the total binding affinity of a protein-ligand complex as their sum. We further improved the model generalization by augmenting a broader range of binding poses and ligands to training data. We validated our model, PIGNet, in the comparative assessment of scoring functions (CASF) 2016, demonstrating the outperforming docking and screening powers than previous methods. Our physics-informing strategy also enables the interpretation of predicted affinities by visualizing the contribution of ligand substructures, providing insights for further ligand optimization.

q-bio.BM↗

arXiv2021

Fragment-based molecular generative model with high generalization ability and synthetic accessibility

Deep generative models are attracting great attention for molecular design with desired properties. Most existing models generate molecules by sequentially adding atoms. This often renders generated molecules with less correlation with target properties and low synthetic accessibility. Molecular fragments such as functional groups are more closely related to molecular properties and synthetic accessibility than atoms. Here, we propose a fragment-based molecular generative model which designs new molecules with target properties by sequentially adding molecular fragments to any given starting molecule. A key feature of our model is a high generalization ability in terms of property control and fragment types. The former becomes possible by learning the contribution of individual fragments to the target properties in an auto-regressive manner. For the latter, we used a deep neural network that predicts the bonding probability of two molecules from the embedding vectors of the two molecules as input. The high synthetic accessibility of the generated molecules is implicitly considered while preparing the fragment library with the BRICS decomposition method. We show that the model can generate molecules with the simultaneous control of multiple target properties at a high success rate. It also works equally well with unseen fragments even in the property range where the training data is rare, verifying the high generalization ability. As a practical application, we demonstrated that the model can generate potential inhibitors with high binding affinities against the 3CL protease of SARS-COV-2 in terms of docking score.

cs.LG↗

arXiv2019

Molecular Generative Model Based On Adversarially Regularized Autoencoder

Deep generative models are attracting great attention as a new promising approach for molecular design. All models reported so far are based on either variational autoencoder (VAE) or generative adversarial network (GAN). Here we propose a new type model based on an adversarially regularized autoencoder (ARAE). It basically uses latent variables like VAE, but the distribution of the latent variables is obtained by adversarial training like in GAN. The latter is intended to avoid both inappropriate approximation of posterior distribution in VAE and difficulty in handling discrete variables in GAN. Our benchmark study showed that ARAE indeed outperformed conventional models in terms of validity, uniqueness, and novelty per generated molecule. We also demonstrated successful conditional generation of drug-like molecules with ARAE for both cases of single and multiple properties control. As a potential real-world application, we could generate EGFR inhibitors sharing the scaffolds of known active molecules while satisfying drug-like conditions simultaneously.

physics.chem-ph↗

arXiv2019

Scaffold-based molecular design using graph generative model

Searching new molecules in areas like drug discovery often starts from the core structures of candidate molecules to optimize the properties of interest. The way as such has called for a strategy of designing molecules retaining a particular scaffold as a substructure. On this account, our present work proposes a scaffold-based molecular generative model. The model generates molecular graphs by extending the graph of a scaffold through sequential additions of vertices and edges. In contrast to previous related models, our model guarantees the generated molecules to retain the given scaffold with certainty. Our evaluation of the model using unseen scaffolds showed the validity, uniqueness, and novelty of generated molecules as high as the case using seen scaffolds. This confirms that the model can generalize the learned chemical rules of adding atoms and bonds rather than simply memorizing the mapping from scaffolds to molecules during learning. Furthermore, despite the restraint of fixing core structures, our model could simultaneously control multiple molecular properties when generating new molecules.

cs.LG↗

arXiv2019

Predicting drug-target interaction using 3D structure-embedded graph representations from graph neural networks

Accurate prediction of drug-target interaction (DTI) is essential for in silico drug design. For the purpose, we propose a novel approach for predicting DTI using a GNN that directly incorporates the 3D structure of a protein-ligand complex. We also apply a distance-aware graph attention algorithm with gate augmentation to increase the performance of our model. As a result, our model shows better performance than docking and other deep learning methods for both virtual screening and pose prediction. In addition, our model can reproduce the natural population distribution of active molecules and inactive molecules.

cs.LG↗

arXiv2019

Uncertainty quantification of molecular property prediction with Bayesian neural networks

Deep neural networks have outperformed existing machine learning models in various molecular applications. In practical applications, it is still difficult to make confident decisions because of the uncertainty in predictions arisen from insufficient quality and quantity of training data. Here, we show that Bayesian neural networks are useful to quantify the uncertainty of molecular property prediction with three numerical experiments. In particular, it enables us to decompose the predictive variance into the model- and data-driven uncertainties, which helps to elucidate the source of errors. In the logP predictions, we show that data noise affected the data-driven uncertainties more significantly than the model-driven ones. Based on this analysis, we were able to find unexpected errors in the Harvard Clean Energy Project dataset. Lastly, we show that the confidence of prediction is closely related to the predictive uncertainty by performing on bio-activity and toxicity classification problems.

cs.LG↗

arXiv2018

Uncertainty quantification of molecular property prediction using Bayesian neural network models

In chemistry, deep neural network models have been increasingly utilized in a variety of applications such as molecular property predictions, novel molecule designs, and planning chemical reactions. Despite the rapid increase in the use of state-of-the-art models and algorithms, deep neural network models often produce poor predictions in real applications because model performance is highly dependent on the quality of training data. In the field of molecular analysis, data are mostly obtained from either complicated chemical experiments or approximate mathematical equations, and then quality of data may be questioned.In this paper, we quantify uncertainties of prediction using Bayesian neural networks in molecular property predictions. We estimate both model-driven and data-driven uncertainties, demonstrating the usefulness of uncertainty quantification as both a quality checker and a confidence indicator with the three experiments. Our results manifest that uncertainty quantification is necessary for more reliable molecular applications and Bayesian neural network models can be a practical approach.

physics.chem-ph↗

arXiv2018

Deeply learning molecular structure-property relationships using attention- and gate-augmented graph convolutional network

Molecular structure-property relationships are key to molecular engineering for materials and drug discovery. The rise of deep learning offers a new viable solution to elucidate the structure-property relationships directly from chemical data. Here we show that the performance of graph convolutional networks (GCNs) for the prediction of molecular properties can be improved by incorporating attention and gate mechanisms. The attention mechanism enables a GCN to identify atoms in different environments. The gated skip-connection further improves the GCN by updating feature maps at an appropriate rate. We demonstrate that the resulting attention- and gate-augmented GCN could extract better structural features related to a target molecular property such as solubility, polarity, synthetic accessibility and photovoltaic efficiency compared to the vanilla GCN. More interestingly, it identified two distinct parts of molecules as essential structural features for high photovoltaic efficiency, and each of them coincided with the areas of donor and acceptor orbitals for charge-transfer excitations, respectively. As a result, the new model could accurately predict molecular properties and place molecules with similar properties close to each other in a well-trained latent space, which is critical for successful molecular engineering.

cs.LG↗

arXiv2018

Molecular generative model based on conditional variational autoencoder for de novo molecular design

We propose a molecular generative model based on the conditional variational autoencoder for de novo molecular design. It is specialized to control multiple molecular properties simultaneously by imposing them on a latent space. As a proof of concept, we demonstrate that it can be used to generate drug-like molecules with five target properties. We were also able to adjust a single property without changing the others and to manipulate it beyond the range of the dataset.

cs.LG↗

arXiv2016

Importance of local exact exchange potential in hybrid functionals for accurate excited states

Density functional theory has been an essential analysis tool for both theoretical and experimental chemists since accurate hybrid functionals were developed. Here we propose a local hybrid method derived from the optimized effective potential (OEP) method and compare its distinct features with conventional nonlocal ones from the Hartree-Fock (HF) exchange operator. Both are formally exact for ground states and thus show similar accuracy for atomization energies and reaction barrier heights. For excited states, the local version yields virtual orbitals with N-electron character, while those of the nonlocal version have mixed characters between N- and (N+1)-electron orbitals. As a result, the orbital energy gaps from the former well approximate excitation energies with a small mean absolute error (MAE = 0.40 eV) for the Caricato benchmark set. The correction from time-dependent density functional theory with a simple local density approximation kernel further improves its accuracy by incorporating multi-configurational effects, resulting in the total MAE of 0.27 eV that outperforms conventional functionals except for MN15.

physics.chem-ph↗

arXiv2007

Carbon nanotube, graphene, nanowire, and molecule-based electron and spin transport phenomena using the non-equilibrium Green function method at the level of first principles theory

Based on density functional theory (DFT), we have developed algorithms and a program code to investigate the electron transport characteristics for a variety of nanometer scaled devices in the presence of an external bias voltage. We employed basis sets comprised of linear combinations of numerical type atomic orbitals and k-point sampling for the realistic modeling of the bulk electrode. The scheme coupled with the matrix version of the non-equilibrium Green function method enables determination of the transmission coefficients at a given energy and voltage in a self-consistent manner, as well as the corresponding current-voltage (I-V) characteristics. This scheme has advantages because it is applicable to large systems, easily transportable to different types of quantum chemistry packages, and extendable to describe time-dependent phenomena or inelastic scatterings. It has been applied to diverse types of practical electronic devices such as carbon nanotubes, graphene nano-ribbons, metallic nanowires, and molecular electronic devices. The quantum conductance phenomena for systems involving quantum point contacts and I-V curves are described for the dithiol-benzene molecule in contact with two Au electrodes using the k-point sampling method.

cond-mat.mes-hall↗