3D molecular generative framework for interaction-guided drug design.

Deep generative modeling has a strong potential to accelerate drug design. However, existing generative models often face challenges in generalization due to limited data, leading to less innovative designs with often unfavorable interactions for unseen target proteins. To address these issues, we propose an interaction-aware 3D molecular generative framework that enables interaction-guided drug design inside target binding pockets. By leveraging universal patterns of protein-ligand interactions as prior knowledge, our model can achieve high generalizability with limited experimental data. Its performance has been comprehensively assessed by analyzing generated ligands for unseen targets in terms of binding pose stability, affinity, geometric patterns, diversity, and novelty. Moreover, the effective design of potential mutant-selective inhibitors demonstrates the applicability of our approach to structure-based drug design.

Deep Learning-Based Chemical Similarity for Accelerated Organic Light-Emitting Diode Materials Discovery.

Thermally activated delayed fluorescence (TADF) material has attracted great attention as a promising metal-free organic light-emitting diode material with a high theoretical efficiency. To accelerate the discovery of novel TADF materials, computer-aided material design strategies have been developed. However, they have clear limitations due to the accessibility of only a few computationally tractable properties. Here, we propose TADF-likeness, a quantitative score to evaluate the TADF potential of molecules based on a data-driven concept of chemical similarity to existing TADF molecules. We used a deep autoencoder to characterize the common features of existing TADF molecules with common chemical descriptors. The score was highly correlated with the four essential electronic properties of TADF molecules and had a high success rate in large-scale virtual screening of millions of molecules to identify promising candidates at almost no cost, validating its feasibility for accelerating TADF discovery. The concept of TADF-likeness can be extended to other fields of materials discovery.

Diffusion-based generative AI for exploring transition states from 2D molecular graphs.

The exploration of transition state (TS) geometries is crucial for elucidating chemical reaction mechanisms and modeling their kinetics. Recently, machine learning (ML) models have shown remarkable performance for prediction of TS geometries. However, they require 3D conformations of reactants and products often with their appropriate orientations as input, which demands substantial efforts and computational cost. Here, we propose a generative approach based on the stochastic diffusion method, namely TSDiff, for prediction of TS geometries just from 2D molecular graphs. TSDiff outperforms the existing ML models with 3D geometries in terms of both accuracy and efficiency. Moreover, it enables to sample various TS conformations, because it learns the distribution of TS geometries for diverse reactions in training. Thus, TSDiff finds more favorable reaction pathways with lower barrier heights than those in the reference database. These results demonstrate that TSDiff shows promising potential for an efficient and reliable TS exploration.

Accelerated chemical science with AI.

In light of the pressing need for practical materials and molecular solutions to renewable energy and health problems, to name just two examples, one wonders how to accelerate research and development in the chemical sciences, so as to address the time it takes to bring materials from initial discovery to commercialization. Artificial intelligence (AI)-based techniques, in particular, are having a transformative and accelerating impact on many if not most, technological domains. To shed light on these questions, the authors and participants gathered in person for the ASLLA Symposium on the theme of 'Accelerated Chemical Science with AI' at Gangneung, Republic of Korea. We present the findings, ideas, comments, and often contentious opinions expressed during four panel discussions related to the respective general topics: 'Data', 'New applications', 'Machine learning algorithms', and 'Education'. All discussions were recorded, transcribed into text using Open AI's Whisper, and summarized using LG AI Research's EXAONE LLM, followed by revision by all authors. For the broader benefit of current researchers, educators in higher education, and academic bodies such as associations, publishers, librarians, and companies, we provide chemistry-specific recommendations and summarize the resulting conclusions.

DFRscore: Deep Learning-Based Scoring of Synthetic Complexity with Drug-Focused Retrosynthetic Analysis for High-Throughput Virtual Screening.

Recently emerging generative AI models enable us to produce a vast number of compounds for potential applications. While they can provide novel molecular structures, the synthetic feasibility of the generated molecules is often questioned. To address this issue, a few recent studies have attempted to use deep learning models to estimate the synthetic accessibility of many molecules rapidly. However, retrosynthetic analysis tools used to train the models rely on reaction templates automatically extracted from a large reaction database that are not domain-specific and may exhibit low chemical correctness. To overcome this limitation, we introduce DFRscore (Drug-Focused Retrosynthetic score), a deep learning-based approach for a more practical assessment of synthetic accessibility in drug discovery. The DFRscore model is trained exclusively on drug-focused reactions, providing a predicted number of minimally required synthetic steps for each compound. This approach enables practitioners to filter out compounds that do not meet their desired level of synthetic accessibility at an early stage of high-throughput virtual screening for accelerated drug discovery. The proposed strategy can be easily adapted to other domains by adjusting the synthesis planning setup of the reaction templates and starting materials.

Critical role of electrons in the short lifetime of blue OLEDs.

Designing robust blue organic light-emitting diodes is a long-standing challenge in the display industry. The highly energetic states of blue emitters cause various degradation paths, leading to collective luminance drops in a competitive manner. However, a key mechanism of the operational degradation of organic light-emitting diodes has yet to be elucidated. Here, we show that electron-induced degradation reactions play a critical role in the short lifetime of blue organic light-emitting diodes. Our control experiments demonstrate that the operational lifetime of a whole device can only be explained when excitons and electrons exist together. We examine the atomistic mechanisms of the electron-induced degradation reactions by analyzing their energetic profiles using computational methods. Mass spectrometric analysis of aged devices further confirm the key mechanisms. These results provide new insight into rational design of robust blue organic light-emitting diodes.

Gaussian-Approximated Poisson Preconditioner for Iterative Diagonalization in Real-Space Density Functional Theory.

Various real-space methods optimized on massive parallel computers have been developed for efficient large-scale density functional theory (DFT) calculations of materials and biomolecules. The iterative diagonalization of the Hamiltonian matrix is a computational bottleneck in real-space DFT calculations. Despite the development of various iterative eigensolvers, the absence of efficient real-space preconditioners has hindered their overall efficiency. An efficient preconditioner must satisfy two conditions: appropriate acceleration of the convergence of the iterative process and inexpensive computation. This study proposed a Gaussian-approximated Poisson preconditioner (GAPP) that satisfied both conditions and was suitable for real-space methods. A low computational cost was realized through the Gaussian approximation of a Poisson Green's function. Fast convergence was achieved through the proper determination of Gaussian coefficients to fit the Coulomb energies. The performance of GAPP was evaluated for several molecular and extended systems, and it showed the highest efficiency among the existing preconditioners adopted in real-space codes.

Dynamic Precision Approach for Accelerating Large-Scale Eigenvalue Solvers in Electronic Structure Calculations on Graphics Processing Units.

Single precision (SP) arithmetic can be greatly accelerated as compared to double precision (DP) arithmetic on graphics processing units (GPUs). However, the use of SP in the whole process of electronic structure calculations is inappropriate for the required accuracy. We propose a 3-fold dynamic precision approach for accelerated calculations but still with the accuracy of DP. Here, SP, DP, and mixed precision are dynamically switched during an iterative diagonalization process. We applied this approach to the locally optimal block preconditioned conjugate gradient method to accelerate a large-scale eigenvalue solver for the Kohn-Sham equation. We determined a proper threshold for switching each precision scheme by examining the convergence pattern on the eigenvalue solver only with the kinetic energy operator of the Kohn-Sham Hamiltonian. As a result, we achieved up to 8.53× and 6.60× speedups for band structure and self-consistent field calculations, respectively, for test systems under various boundary conditions on NVIDIA GPUs.

Molecular Generative Model via Retrosynthetically Prepared Chemical Building Block Assembly.

Deep generative models are attracting attention as a smart molecular design strategy. However, previous models often render molecules with low synthesizability, hindering their real-world applications. Here, a novel graph-based conditional generative model which makes molecules by tailoring retrosynthetically prepared chemical building blocks until achieving target properties in an auto-regressive fashion is proposed. This strategy improves the synthesizability and property control of the resulting molecules and also helps learn how to select appropriate building blocks and bind them together to achieve target properties. By applying a negative sampling method to the selection process of building blocks, this model overcame a critical limitation of previous fragment-based models, which can only use molecules from the training set during generation. As a result, the model works equally well with unseen building blocks without sacrificing computational efficiency. It is demonstrated that the model can generate potential inhibitors with high docking scores against the 3CL protease of SARS-COV-2.

Medication-Related Acute Care Admission and Inappropriate Polypharmacy of Nursing Home Residents.

OBJECTIVES: To evaluate the prevalence of medication-related admissions (MRAs) and their association with potentially inappropriate medications (PIMs) used by nursing home residents admitted to the geriatric center of a tertiary hospital. DESIGN: Cross-sectional study. SETTING AND PARTICIPANTS: Older patients admitted from nursing homes to the geriatric center of the Seoul National University Bundang Hospital who had undergone comprehensive geriatric assessment from January 1, 2016, to December 31, 2020. METHODS: MRAs were determined and verified using a previously described MRA adjudication guide. The PIMs in the preadmission medication lists were identified according to each of the following criteria (as well as the combined criteria), the Beers, NORGEP-NH, STOPP/START-NH, and STOPPFrail criteria. Medication use factors associated with MRAs were analyzed using multivariate logistic regression. RESULTS: Among the 304 acute care admissions, 32.2% were MRAs. The main cause of MRAs was acute kidney injury related with use of renin-angiotensin system inhibitors. Approximately 81% of the patients used at least 1 PIM according to the combined criteria. The use of 1 or more PIMs, renin-angiotensin system inhibitors, diuretics, nonsteroidal anti-inflammatory drugs, and benzodiazepines was significantly associated with MRAs. The combined criteria were able to predict MRAs better than the individual criteria. CONCLUSIONS AND IMPLICATIONS: Approximately one-third of acute admissions of nursing home residents may be MRAs. Interventions for the optimal use of medication among nursing home residents are needed.

Neural network-based pseudopotential: development of a transferable local pseudopotential.

Transferable local pseudopotentials (LPPs) are essential for fast quantum simulations of materials. However, various types of LPPs suffer from low transferability, especially since they do not consider the norm-conserving condition. Here we propose a novel approach based on a deep neural network to produce transferable LPPs. We introduced a generalized Kerker method expressed with the deep neural network to represent the norm-conserving pseudo-wavefunctions. Its unique feature is that all necessary conditions of pseudopotentials can be explicitly considered in terms of a loss function. Then, it can be minimized using the back-propagation technique just with single point all-electron atom data. To assess the transferability and accuracy of the neural network-based LPPs (NNLPs), we carried out density functional theory calculations for the s- and p-block elements of the second to the fourth periods. The NNLPs outperformed other types of LPPs in both atomic and bulk calculations for most elements. In particular, they showed good transferability by predicting various properties of bulk systems including binary alloys with higher accuracy than LPPs tailored to bulk data.

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.

System-Specific Separable Basis Based on Tucker Decomposition: Application to Density Functional Calculations.

For fast density functional calculations, a suitable basis that can accurately represent the orbitals within a reasonable number of dimensions is essential. Here, we propose a new type of basis constructed from Tucker decomposition of a finite-difference (FD) Hamiltonian matrix, which is intended to reflect the system information implied in the Hamiltonian matrix and satisfies orthonormality and separability conditions. By introducing the system-specific separable basis, the computation time for FD density functional calculations for seven two- and three-dimensional periodic systems was reduced by a factor of 2-71 times, while the errors in both the atomization energy per atom and the band gap were limited to less than 0.1 eV. The accuracy and speed of the density functional calculations with the proposed basis can be systematically controlled by adjusting the rank size of Tucker decomposition.

Response to Comment on "Reversible disorder-order transitions in atomic crystal nucleation".

Yu et al. suggested calculating precisely the size ranges of the three parts of our figure 3A, adjusting the free-energy levels in figure 3B, and considering the shape effect in the first-principles calculation. The first and second suggestions raise strong concerns for misinterpretation and overinterpretation of our experiments. The original calculation is sufficient to support our claim about crystalline-to-disordered transformations.

Rebamipide as a Potential Alternative Gastroprotective Agent to Proton Pump Inhibitor in Elderly Chronic Nonsteroidal Anti-Inflammatory Drug Users without Risk Factors.

Purpose: The use of proton pump inhibitors (PPI) is recommended to prevent nonsteroidal anti-inflammatory drug (NSAID)-induced gastrointestinal (GI) complications. The incidence of several adverse effects during the long-term use of PPI prompts the search for other alternatives. Limited studies have evaluated the efficacy of rebamipide, a widely used mucoprotective drug, as a gastroprotective agent (GPA) compared to PPI, focusing on the elderly chronic NSAID users, nor with GI risk stratification. We aimed to determine the population who would get benefit from the use of rebamipide as an alternative to PPI to prevent traditional nonsteroidal anti-inflammatory drug (tNSAID)-associated GI complications. Patients and Methods: We identified 41,889 and 35,708 elderly chronic tNSAID users with PPI and rebamipide co-therapy, respectively, from the national claims database. Outcome was defined as hospitalization or emergency department visits due to serious GI complications. Propensity score-matched cohorts were constructed and compared within risk strata. Results: In high and moderate risk groups with two risk factors, rebamipide showed a higher risk of serious GI complication compared to PPI (aHR 2.63, 95% CI 1.24-5.59 and aHR 2.42, 95% CI 1.21-4.83, respectively). However, in elderly patients without risk factors, there was no significant difference in the risk of serious GI complications between PPI and rebamipide (aHR 0.69, 95% CI 0.27-1.76). Conclusion: This study suggested that rebamipide can be considered as an alternative to PPI in elderly chronic tNSAID users without risk factors. However, elderly patients with other risk factors should use PPI rather than rebamipide. Therefore, the presence of GI risk factors needs to be evaluated in elderly chronic tNSAID users to prescribe the most suitable GPA in clinical practice.

Impact of Preventive Strategies on Gastrointestinal Complications in Elderly Patients on Concomitant Use of Oral Anticoagulants and Nonsteroidal Anti-Inflammatory Drugs: A Nationwide Cohort Study.

INTRODUCTION: Despite growing evidence showing an increased risk of concomitant use of nonsteroidal anti-inflammatory drugs (NSAIDs) and anticoagulants, few studies have investigated whether proton pump inhibitors can prevent gastrointestinal (GI) complications in patients receiving both NSAIDs and anticoagulants. OBJECTIVE: We aimed to evaluate the risk of serious GI complications and the impact of GI preventive strategies on the concomitant use of NSAIDs and anticoagulants. METHODS: Our nationwide cohort study using Korea's claims data included elderly patients (aged ≥ 65 years) who started anticoagulants and NSAIDs from 2016 to 2017. The outcome was serious GI complications defined as hospitalization or emergency department visits with GI bleeding or perforation. A Cox regression analysis was performed using time-dependent variables and propensity score matching. RESULTS: In total, 92,379 patients were identified. Compared with non-prophylaxis, proton pump inhibitors and selective cyclooxygenase-2 inhibitors were associated with a 64% [adjusted hazard ratio, 0.36 (95% confidence interval 0.25-0.53)] and 74% [adjusted hazard ratio, 0.26 (95% confidence interval 0.19-0.36)] lower risk of serious GI complications, respectively. Cyclooxygenase-2 inhibitor use was not different from the use of non-selective NSAIDs with proton pump inhibitors for the prevention of serious GI complications. H2-receptor antagonists did not reduce the risk of serious GI complications compared with non-prophylaxis during concomitant non-selective NSAID and anticoagulant therapy. CONCLUSIONS: Proton pump inhibitors or cyclooxygenase-2 inhibitors used as GI preventive strategies did not completely eliminate but lowered the risk of serious GI complications among elderly patients receiving both NSAIDs and anticoagulants.

Circularly Polarized Light Can Override and Amplify Asymmetry in Supramolecular Helices.

Circularly polarized light (CPL) is an inherently chiral entity and is considered one of the possible deterministic signals that led to the evolution of homochirality. While accumulating examples indicate that chirality beyond the molecular level can be induced by CPL, not much is yet known about circumstances where the spin angular momentum of light competes with existing molecular chiral information during the chirality induction and amplification processes. Here we present a light-triggered supramolecular polymerization system where chiral information can both be transmitted and nonlinearly amplified in a "sergeants-and-soldiers" manner. While matching handedness with CPL resulted in further amplification, we determined that opposite handedness could override molecular information at the supramolecular level when the enantiomeric excess was low. The presence of a critical chiral bias suggests a bifurcation point in the homochirality evolution under random external chiral perturbation. Our results also highlight opportunities for the orthogonal control of supramolecular chirality decoupled from molecular chirality preexisting in the system.

Drug-likeness scoring based on unsupervised learning.

Drug-likeness prediction is important for the virtual screening of drug candidates. It is challenging because the drug-likeness is presumably associated with the whole set of necessary properties to pass through clinical trials, and thus no definite data for regression is available. Recently, binary classification models based on graph neural networks have been proposed but with strong dependency of their performances on the choice of the negative set for training. Here we propose a novel unsupervised learning model that requires only known drugs for training. We adopted a language model based on a recurrent neural network for unsupervised learning. It showed relatively consistent performance across different datasets, unlike such classification models. In addition, the unsupervised learning model provides drug-likeness scores that well separate distributions with increasing mean values in the order of datasets composed of molecules at a later step in a drug development process, whereas the classification model predicted a polarized distribution with two extreme values for all datasets presumably due to the overconfident prediction for unseen data. Thus, this new concept offers a pragmatic tool for drug-likeness scoring and further can be applied to other biochemical applications.

Morphology Transformation of Foldamer Assemblies Triggered by Single Oxygen Atom on Critical Residue Switch.

The synthesis of morphologically well-defined peptidic materials via self-assembly is challenging but demanding for biocompatible functional materials. Moreover, switching morphology from a given shape to other predictable forms by molecular modification of the identical building block is an even more complicated subject because the self-assembly of flexible peptides is prone to diverge upon subtle structural change. To accomplish controllable morphology transformation, systematic self-assembly studies are performed using congener short ß-peptide foldamers to find a minimal structural change that alters the self-assembled morphology. Introduction of oxygen-containing ß-amino acid (ATFC) for subtle electronic perturbation on hydrophobic foldamer induces a previously inaccessible solid-state conformational split to generate the most susceptible modification site for morphology transformation of the foldamer assemblies. The site-dependent morphological switching power of ATFC is further demonstrated by dual substitution experiments and proven by crystallographic analyses. Stepwise morphology transformation is shown by modifying an identical foldamer scaffold. This study will guide in designing peptidic molecules from scratch to create complex and biofunctional assemblies with nonspherical shapes.

Reversible disorder-order transitions in atomic crystal nucleation.

Nucleation in atomic crystallization remains poorly understood, despite advances in classical nucleation theory. The nucleation process has been described to involve a nonclassical mechanism that includes a spontaneous transition from disordered to crystalline states, but a detailed understanding of dynamics requires further investigation. In situ electron microscopy of heterogeneous nucleation of individual gold nanocrystals with millisecond temporal resolution shows that the early stage of atomic crystallization proceeds through dynamic structural fluctuations between disordered and crystalline states, rather than through a single irreversible transition. Our experimental and theoretical analyses support the idea that structural fluctuations originate from size-dependent thermodynamic stability of the two states in atomic clusters. These findings, based on dynamics in a real atomic system, reshape and improve our understanding of nucleation mechanisms in atomic crystallization.