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.

Extensive antibody search with whole spectrum black-box optimization

In designing functional biological sequences with machine learning, the activity predictor tends to be inaccurate due to shortage of data. Top ranked sequences are thus unlikely to contain effective ones. This paper proposes to take prediction stability into account to provide domain experts with a reasonable list of sequences to choose from. In our approach, multiple prediction models are trained by subsampling the training set and the multi-objective optimization problem, where one objective is the average activity and the other is the standard deviation, is solved. The Pareto front represents a list of sequences with the whole spectrum of activity and stability. Using this method, we designed VHH (Variable domain of Heavy chain of Heavy chain) antibodies based on the dataset obtained from deep mutational screening. To solve multi-objective optimization, we employed our sequence design software MOQA that uses quantum annealing. By applying several selection criteria to 19,778 designed sequences, five sequences were selected for wet-lab validation. One sequence, 16 mutations away from the closest training sequence, was successfully expressed and found to possess desired binding specificity. Our whole spectrum approach provides a balanced way of dealing with the prediction uncertainty, and can possibly be applied to extensive search of functional sequences.

Efficient model selection for predictive pattern mining model by safe pattern pruning

Predictive pattern mining is an approach used to construct prediction models when the input is represented by structured data, such as sets, graphs, and sequences. The main idea behind predictive pattern mining is to build a prediction model by considering unified inconsistent notation sub-structures, such as subsets, subgraphs, and subsequences (referred to as patterns), present in the structured data as features of the model. The primary challenge in predictive pattern mining lies in the exponential growth of the number of patterns with the complexity of the structured data. In this study, we propose the safe pattern pruning method to address the explosion of pattern numbers in predictive pattern mining. We also discuss how it can be effectively employed throughout the entire model building process in practical data analysis. To demonstrate the effectiveness of the proposed method, we conduct numerical experiments on regression and classification problems involving sets, graphs, and sequences.

Revealing factors influencing polymer degradation with rank-based machine learning

The efficient treatment of polymer waste is a major challenge for marine sustainability. It is useful to reveal the factors that dominate the degradability of polymer materials for developing polymer materials in the future. The small number of available datasets on degradability and the diversity of their experimental means and conditions hinder large-scale analysis. In this study, we have developed a platform for evaluating the degradability of polymers that is suitable for such data, using a rank-based machine learning technique based on RankSVM. We then made a ranking model to evaluate the degradability of polymers, integrating three datasets on the degradability of polymers that are measured by different means and conditions. Analysis of this ranking model with a decision tree revealed factors that dominate the degradability of polymers.

Koopmans' Theorem-Compliant Long-Range Corrected (KTLC) Density Functional Mediated by Black-Box Optimization and Data-Driven Prediction for Organic Molecules

Density functional theory (DFT) is a significant computational tool that has substantially influenced chemistry, physics, and materials science. DFT necessitates parametrized approximation for determining an expected value. Hence, to predict the properties of a given molecule using DFT, appropriate parameters of the functional should be set for each molecule. Herein, we optimize the parameters of range-separated functionals (LC-BLYP and CAM-B3LYP) via Bayesian optimization (BO) to satisfy Koopmans' theorem. Our results demonstrate the effectiveness of the BO in optimizing functional parameters. Particularly, Koopmans' theorem-compliant LC-BLYP (KTLC-BLYP) shows results comparable to the experimental UV-absorption values. Furthermore, we prepared an optimized parameter dataset of KTLC-BLYP for over 3000 molecules through BO for satisfying Koopmans' theorem. We have developed a machine learning model on this dataset to predict the parameters of the LC-BLYP functional for a given molecule. The prediction model automatically predicts the appropriate parameters for a given molecule and calculates the corresponding values. The approach in this paper would be useful to develop new functionals and to update the previously developed functionals.

Differentiable optimization layers enhance GNN-based mitosis detection

Automatic mitosis detection from video is an essential step in analyzing proliferative behaviour of cells. In existing studies, a conventional object detector such as Unet is combined with a link prediction algorithm to find correspondences between parent and daughter cells. However, they do not take into account the biological constraint that a cell in a frame can correspond to up to two cells in the next frame. Our model called GNN-DOL enables mitosis detection by complementing a graph neural network (GNN) with a differentiable optimization layer (DOL) that implements the constraint. In time-lapse microscopy sequences cultured under four different conditions, we observed that the layer substantially improved detection performance in comparison with GNN-based link prediction. Our results illustrate the importance of incorporating biological knowledge explicitly into deep learning models.

Quantum Annealing Designs Nonhemolytic Antimicrobial Peptides in a Discrete Latent Space

Increasing the variety of antimicrobial peptides is crucial in meeting the global challenge of multi-drug-resistant bacterial pathogens. While several deep-learning-based peptide design pipelines are reported, they may not be optimal in data efficiency. High efficiency requires a well-compressed latent space, where optimization is likely to fail due to numerous local minima. We present a multi-objective peptide design pipeline based on a discrete latent space and D-Wave quantum annealer with the aim of solving the local minima problem. To achieve multi-objective optimization, multiple peptide properties are encoded into a score using non-dominated sorting. Our pipeline is applied to design therapeutic peptides that are antimicrobial and non-hemolytic at the same time. From 200 000 peptides designed by our pipeline, four peptides proceeded to wet-lab validation. Three of them showed high anti-microbial activity, and two are non-hemolytic. Our results demonstrate how quantum-based optimizers can be taken advantage of in real-world medical studies.

3D-Sensitive Encoding of Pharmacophore Features

In the presence of structural data, one sometimes need to compare 3D ligands. We design an overlay-free method to rank order 3D molecules in the pharmacophore feature space. The proposed encoding includes only two fittable parameters, is sparse, and is not too high dimensional. At the cost of an additional parameter, to delineate the binding site from a protein-ligand complex, the method can compare binding sites. The method was benchmarked on the LIT-PCBA data set for ligand-based virtual screening experiments and the sc-PDB and a Vertex data set when comparing binding sites. In similarity searches, the proposed method outperforms an open-source software doing optimal superposition of ligand-based pharmacophores and RDKit's 3D pharmacophore fingerprints. When comparing binding sites, the method is competitive with state of the art approaches. On a single CPU core, up to 374,000 ligand/s or 132,000 binding site/s can be rank ordered. The "AutoCorrelation of Pharmacophore Features" open-source software is released at https://github.com/tsudalab/ACP4.

Exploring the Quantum Chemical Energy Landscape with GNN-Guided Artificial Force

Artificial force has been proven useful to get over energy barriers and quickly search a large portion of the energy landscape. This work proposes a method based on graph neural networks to optimize the choice of transformation patterns to examine and accelerate energy landscape exploration. In open search from glutathione, the search efficiency was largely improved in comparison to random selection. We also applied transfer learning from glutathione to tuftsin, resulting in further efficiency gains.

Probing Conformational Dynamics of Antibodies with Geometric Simulations

This chapter describes the application of constrained geometric simulations for prediction of antibody structural dynamics. We utilize constrained geometric simulations method FRODAN, which is a low computational complexity alternative to molecular dynamics (MD) simulations that can rapidly explore flexible motions in protein structures. FRODAN is highly suited for conformational dynamics analysis of large proteins, complexes, intrinsically disordered proteins, and dynamics that occurs on longer biologically relevant time scales that are normally inaccessible to classical MD simulations. This approach predicts protein dynamics at an all-atom scale while retaining realistic covalent bonding, maintaining dihedral angles in energetically good conformations while avoiding steric clashes in addition to performing other geometric and stereochemical criteria checks. In this chapter, we apply FRODAN to showcase its applicability for probing functionally relevant dynamics of IgG2a, including large-amplitude domain-domain motions and motions of complementarity determining region (CDR) loops. As was suggested in previous experimental studies, our simulations show that antibodies can explore a large range of conformational space.

Selection of target-binding proteins from the information of weakly enriched phage display libraries by deep sequencing and machine learning

Despite the advances in surface-display systems for directed evolution, variants with high affinity are not always enriched due to undesirable biases that increase target-unrelated variants during biopanning. Here, our goal was to design a library containing improved variants from the information of the "weakly enriched" library where functional variants were weakly enriched. Deep sequencing for the previous biopanning result, where no functional antibody mimetics were experimentally identified, revealed that weak enrichment was partly due to undesirable biases during phage infection and amplification steps. The clustering analysis of the deep sequencing data from appropriate steps revealed no distinct sequence patterns, but a Bayesian machine learning model trained with the selected deep sequencing data supplied nine clusters with distinct sequence patterns. Phage libraries were designed on the basis of the sequence patterns identified, and four improved variants with target-specific affinity (EC₅₀ = 80-277 nM) were identified by biopanning. The selection and use of deep sequencing data without undesirable bias enabled us to extract the information on prospective variants. In summary, the use of appropriate deep sequencing data and machine learning with the sequence data has the possibility of finding sequence space where functional variants are enriched.

QCforever: A Quantum Chemistry Wrapper for Everyone to Use in Black-Box Optimization

To obtain observable physical or molecular properties such as ionization potential and fluorescent wavelength with quantum chemical (QC) computation, multi-step computation manipulated by a human is required. Hence, automating the multi-step computational process and making it a black box that can be handled by anybody are important for effective database construction and fast realistic material design through the framework of black-box optimization where machine learning algorithms are introduced as a predictor. Here, we propose a Python library, QCforever, to automate the computation of some molecular properties and chemical phenomena induced by molecules. This tool just requires a molecule file for providing its observable properties, automating the computation process of molecular properties (for ionization potential, fluorescence, etc.) and output analysis for providing their multi-values for evaluating a molecule. Incorporating the tool in black-box optimization, we can explore molecules that have properties we desired within the limitation of QC computation.

Effect of coordinator-based osteoporosis intervention on quality of life in patients with fragility fractures: a prospective randomized trial

We examined the effects of the coordinator-based intervention on quality of life (QOL) in the aftermath of a fragility fracture, as well as factors predictive of post-fracture QOL. The coordinator-based interventions mitigated the decrease in QOL. Secondary fracture after primary fracture, however, was a significant predictor of lower QOL.

PURPOSE

This study aimed to determine the effects of the coordinator-based intervention on QOL in the aftermath of a fragility fracture, as well as factors predictive of post-fracture QOL, in an Asian population.

METHODS

Patients with new fractures in the intervention group received the coordinator-based intervention by a designated nurse certified as a coordinator, within 3 months of injury. QOL was evaluated using the Japanese version of the EuroQol 5 Dimension 5 Level (EQ-5D-5L) scale  before the fracture (through patient recollections) and at 0.5, 1, and 2 years after the primary fracture.

RESULTS

Data for 141 patients were analyzed: 70 in the liaison intervention (LI) group and 71 in the non-LI group. Significant intervention effects on QOL were observed at 6 months after the fracture; the QOL score was 0.079 points higher in the LI group than in the non-LI group (p=0.019). Further, the LI group reported significantly less pain/discomfort at 2 years after the fracture, compared to the non-LI group (p=0.037). In addition, secondary fractures were found to significantly prevent improvement and maintenance of QOL during the recovery period (p=0.015).

CONCLUSION

Short-term intervention effects were observable 6 months after the primary fracture, with the LI group mitigated the decrease in QOL. Few patients in the LI group reported pain/discomfort 2 years after the fracture, but there is uncertainty regarding its clinical significance. Secondary fracture after initial injury was a significant predictor of lower QOL after a fracture.

Understanding the evolution of a de novo molecule generator via characteristic functional group monitoring

Recently, artificial intelligence (AI)-enabled de novo molecular generators (DNMGs) have automated molecular design based on data-driven or simulation-based property estimates. In some domains like the game of Go where AI surpassed human intelligence, humans are trying to learn from AI about the best strategy of the game. To understand DNMG's strategy of molecule optimization, we propose an algorithm called characteristic functional group monitoring (CFGM). Given a time series of generated molecules, CFGM monitors statistically enriched functional groups in comparison to the training data. In the task of absorption wavelength maximization of pure organic molecules (consisting of H, C, N, and O), we successfully identified a strategic change from diketone and aniline derivatives to quinone derivatives. In addition, CFGM led us to a hypothesis that 1,2-quinone is an unconventional chromophore, which was verified with chemical synthesis. This study shows the possibility that human experts can learn from DNMGs to expand their ability to discover functional molecules.

Leveraging algorithmic search in quantum chemical reaction path finding

Reaction path finding methods construct a graph connecting reactants and products in a quantum chemical energy landscape. They are useful in elucidating various reactions and provide footsteps for designing new reactions. Their enormous computational cost, however, limits their application to relatively simple reactions. This paper engages in accelerating reaction path finding by introducing the principles of algorithmic search. A new method called RRT/SC-AFIR is devised by combining rapidly exploring random tree (RRT) and single component artificial force induced reaction (SC-AFIR). Using 96 cores, our method succeeded in constructing a reaction graph for Fritsch-Buttenberg-Wiechell rearrangement within a time limit of 3 days, while the conventional methods could not. Our results illustrate that the algorithm theory provides refreshing and beneficial viewpoints on quantum chemical methodologies.

De novo creation of a naked eye-detectable fluorescent molecule based on quantum chemical computation and machine learning

Designing fluorescent molecules requires considering multiple interrelated molecular properties, as opposed to properties that straightforwardly correlated with molecular structure, such as light absorption of molecules. In this study, we have used a de novo molecule generator (DNMG) coupled with quantum chemical computation (QC) to develop fluorescent molecules, which are garnering significant attention in various disciplines. Using massive parallel computation (1024 cores, 5 days), the DNMG has produced 3643 candidate molecules. We have selected an unreported molecule and seven reported molecules and synthesized them. Photoluminescence spectrum measurements demonstrated that the DNMG can successfully design fluorescent molecules with 75% accuracy (n = 6/8) and create an unreported molecule that emits fluorescence detectable by the naked eye.

Integrating Incompatible Assay Data Sets with Deep Preference Learning

A large amount of bioactivity assay data is already accumulated in public databases, but the integration of these data sets for quantitative structure-activity relationship (QSAR) studies is not straightforward due to differences in experimental methods and settings. We present an efficient deep-learning-based approach called Deep Preference Data Integration (DPDI). For integrating outcome variables of different assay types, a surrogate variable is introduced, and a neural network is trained such that the total order induced by the surrogate variable is maximally consistent with given data sets. In a task of predicting efficacy of factor Xa inhibitors, DPDI successfully integrated 2959 molecules distributed in 129 assay data sets. In most of our experiments, data integration improved prediction accuracy strongly in interpolation and extrapolation tasks, indicating that DPDI is an effective tool for QSAR studies.

Fe-Al-Si Thermoelectric (FAST) Materials and Modules: Diffusion Couple and Machine-Learning-Assisted Materials Development

To lower the introduction and maintenance costs of autonomous power supplies for driving Internet-of-things (IoT) devices, we have developed low-cost Fe-Al-Si-based thermoelectric (FAST) materials and power generation modules. Our development approach combines computational science, experiments, mapping measurements, and machine learning (ML). FAST materials have a good balance of mechanical properties and excellent chemical stability, superior to that of conventional Bi-Te-based materials. However, it remains challenging to enhance the power factor (PF) and lower the thermal conductivity of FAST materials to develop reliable power generation devices. This forum paper describes the current status of materials development based on experiments and ML with limited data, together with power generation module fabrication related to FAST materials with a view to commercialization. Combining bulk combinatorial methods with diffusion couple and mapping measurements could accelerate the search to enhance PF for FAST materials. We report that ML prediction is a powerful tool for finding unexpected off-stoichiometric compositions of the Fe-Al-Si system and dopant concentrations of a fourth element to enhance the PF, i.e., Co substitution for Fe atoms in FAST materials.

Efficient Search for Energetically Favorable Molecular Conformations against Metastable States via Gray-Box Optimization

In order to accurately understand and estimate molecular properties, finding energetically favorable molecular conformations is the most fundamental task for atomistic computational research on molecules and materials. Geometry optimization based on quantum chemical calculations has enabled the conformation prediction of arbitrary molecules, including de novo ones. However, it is computationally expensive to perform geometry optimizations for enormous conformers. In this study, we introduce the gray-box optimization (GBO) framework, which enables optimal control over the entire geometry optimization process, among multiple conformers. Algorithms designed for GBO roughly estimate energetically preferable conformers during their geometry optimization iterations. They then preferentially compute promising conformers. To evaluate the performance of the GBO framework, we applied it to a test set consisting of seven dipeptides and mycophenolic acid to determine their stable conformations at the density functional theory level. We thus preferentially obtained energetically favorable conformations. Furthermore, the computational costs required to find the most stable conformation were significantly reduced (approximately 1% on average, compared to the naive approach for the dipeptides).

Improvement of precision in refinements of structure factors using convergent-beam electron diffraction patterns taken at Bragg-excited conditions

A local structure analysis method based on convergent-beam electron diffraction (CBED) has been used for refining isotropic atomic displacement parameters and five low-order structure factors with sin θ/λ ≤ 0.28 Å^-1 of potassium tantalate (KTaO₃). Comparison between structure factors determined from CBED patterns taken at the zone-axis (ZA) and Bragg-excited conditions is made in order to discuss their precision and sensitivities. Bragg-excited CBED patterns showed higher precision in the refinement of structure factors than ZA patterns. Consistency between higher precision and sensitivity of the Bragg-excited CBED patterns has been found only for structure factors of the outer zeroth-order Laue-zone reflections with larger reciprocal-lattice vectors. Correlation coefficients among the refined structure factors in the refinement of Bragg-excited patterns are smaller than those of the ZA ones. Such smaller correlation coefficients lead to higher precision in the refinement of structure factors.

First-principles study of electronic structures and elasticity of Al2Fe3Si3

Al₂Fe₃Si₃intermetallic compound shows promising application in low-cost and non-toxic thermoelectric device because of its relatively high power factor of ∼700μW m^-1 K^-2at 400 K. Herein we performed the first-principles calculations with the projector augmented-wave (PAW) method to study the formation energies, elastic constants, electronic structures, and electronic transport properties of Al₂Fe₃Si₃. We discussed the thermodynamical stability of Al₂Fe₃Si₃against other ternary crystalline compounds in Al-Fe-Si phase. The band gap of Al₂Fe₃Si₃was particularly examined using the semilocal and hybrid functionals and the on-site Hubbard correction, which were also applied to β-FeSi₂to calibrate the prediction reliability of our employed computational methods. Our calculations show that Al₂Fe₃Si₃is a narrow-gap semiconductor. The semilocal functional within generalized gradient approximation (GGA) shows an exceptional agreement between the predicted band gap of Al₂Fe₃Si₃and the available experiment data, which is in contrast to the typical trend and rationally understood through a comprehensive comparison. We found that both HSE06 and PBE0 hybrid functionals with a standard setup overestimated the band gaps of Al₂Fe₃Si₃and β-FeSi₂too much. The underlying reasons may be ascribed to a large electronic screening, which arises from the unique characteristics of Fe 3dstates appearing in both sides of band gaps of Al₂Fe₃Si₃and β-FeSi₂, and to a reduced delocalization error thanks to the covalent Fe-Si and Si-Si bonding nature. The chemical bonding and elasticity of Al₂Fe₃Si₃were compared with those of β-FeSi₂and FeAl₂. In Al₂Fe₃Si₃the Fe-Al bonding is more ionic and the Fe-Si bonding is more covalent. The elastic moduli of Al₂Fe₃Si₃are comparable to those of β-FeSi₂and larger than those of FeAl₂. Our calculation results indicate that the mechanical strength of Al₂Fe₃Si₃could be strong enough for the practical application in thermoelectric device.

Determinants of bone health in elderly Japanese men: study design and key findings of the Fujiwara-kyo Osteoporosis Risk in Men (FORMEN) cohort study

BACKGROUND

The Fujiwara-kyo Osteoporosis Risk in Men (FORMEN) study was launched to investigate risk factors for osteoporotic fractures, interactions of osteoporosis with other non-communicable chronic diseases, and effects of fracture on QOL and mortality.

METHODS

FORMEN baseline study participants (in 2007 and 2008) included 2012 community-dwelling men (aged 65-93 years) in Nara prefecture, Japan. Clinical follow-up surveys were conducted 5 and 10 years after the baseline survey, and 1539 and 906 men completed them, respectively. Supplemental mail, telephone, and visit surveys were conducted with non-participants to obtain outcome information. Survival and fracture outcomes were determined for 2006 men, with 566 deaths identified and 1233 men remaining in the cohort at 10-year follow-up.

COMMENTS

The baseline survey covered a wide range of bone health-related indices including bone mineral density, trabecular microarchitecture assessment, vertebral imaging for detecting vertebral fractures, and biochemical markers of bone turnover, as well as comprehensive geriatric assessment items. Follow-up surveys were conducted to obtain outcomes including osteoporotic fracture, cardiovascular diseases, initiation of long-term care, and mortality. A complete list of publications relating to the FORMEN study can be found at https://www.med.kindai.ac.jp/pubheal/FORMEN/Publications.html .

Black-Box Optimization for Automated Discovery

In chemistry and materials science, researchers and engineers discover, design, and optimize chemical compounds or materials with their professional knowledge and techniques. At the highest level of abstraction, this process is formulated as black-box optimization. For instance, the trial-and-error process of synthesizing various molecules for better material properties can be regarded as optimizing a black-box function describing the relation between a chemical formula and its properties. Various black-box optimization algorithms have been developed in the machine learning and statistics communities. Recently, a number of researchers have reported successful applications of such algorithms to chemistry. They include the design of photofunctional molecules and medical drugs, optimization of thermal emission materials and high Li-ion conductive solid electrolytes, and discovery of a new phase in inorganic thin films for solar cells.There are a wide variety of algorithms available for black-box optimization, such as Bayesian optimization, reinforcement learning, and active learning. Practitioners need to select an appropriate algorithm or, in some cases, develop novel algorithms to meet their demands. It is also necessary to determine how to best combine machine learning techniques with quantum mechanics- and molecular mechanics-based simulations, and experiments. In this Account, we give an overview of recent studies regarding automated discovery, design, and optimization based on black-box optimization. The Account covers the following algorithms: Bayesian optimization to optimize the chemical or physical properties, an optimization method using a quantum annealer, best-arm identification, gray-box optimization, and reinforcement learning. In addition, we introduce active learning and boundless objective-free exploration, which may not fall into the category of black-box optimization.Data quality and quantity are key for the success of these automated discovery techniques. As laboratory automation and robotics are put forward, automated discovery algorithms would be able to match human performance at least in some domains in the near future.

Comparative Analysis of Patient-Matched PDOs Revealed a Reduction in OLFM4-Associated Clusters in Metastatic Lesions in Colorectal Cancer

Metastasis is the major cause of cancer-related death, but whether metastatic lesions exhibit the same cellular composition as primary tumors has yet to be elucidated. To investigate the cellular heterogeneity of metastatic colorectal cancer (CRC), we established 72 patient-derived organoids (PDOs) from 21 patients. Combined bulk transcriptomic and single-cell RNA-sequencing analysis revealed decreased gene expression of markers for differentiated cells in PDOs derived from metastatic lesions. Paradoxically, expression of potential intestinal stem cell markers was also decreased. We identified OLFM4 as the gene most strongly correlating with a stem-like cell cluster, and found OLFM4⁺ cells to be capable of initiating organoid culture growth and differentiation capacity in primary PDOs. These cells were required for the efficient growth of primary PDOs but dispensable for metastatic PDOs. These observations demonstrate that metastatic lesions have a cellular composition distinct from that of primary tumors; patient-matched PDOs are a useful resource for analyzing metastatic CRC.

•

Seventy-two PDOs were established from 21 stage IV CRC patients

•

Forty-one DEGs were identified between primary and corresponding metastatic PODs

•

scRNA-seq analysis identified OLFM4 as a potential cancer stem cell marker

•

Different roles of OLFM4⁺ cells in primary and metastatic PDOs were demonstrated

Efficiency of coordinator-based osteoporosis intervention in fragility fracture patients: a prospective randomized trial

We examined the effectiveness of coordinators' interventions to prevent secondary fractures in patients with fragility fractures. These coordinator-based interventions improved bone density assessment implementation and treatment rates, and enhanced treatment persistence rates in the early stages following fractures.

INTRODUCTION

This study aimed to determine the efficiency of coordinator-based osteoporosis intervention in fragility fracture patients during a 2-year period.

METHODS

A prospective intervention randomized control study was conducted at seven medical facilities from January 2015 to March 2017. Postmenopausal women and men over 50 years old with fragility fractures were randomly divided into the coordinator intervention (LI; 70 patients) and without intervention (non-LI; 71 patients) groups. The osteoporosis treatment rate, osteoporosis treatment persistence rate, fall rate, fracture incidence rate, and bone density measurement rate 3 months, 6 months, 1 year, and 2 years after registration were compared between the two groups. Non-parametric tests were used to analyze data at each inspection period.

RESULTS

The osteoporosis treatment initiation rate was significantly higher in the LI group than in the non-LI group (85.7% vs. 71.8%; p = 0.04). The LI group had significantly higher bone density assessment implementation rates than the non-LI group at the time of registration (90.0% vs. 69.0%; p = 0.00) and 6 months after registration (50.0% vs. 29.6%; p = 0.01), but not 1 or 2 years after registration. In addition, no significant differences in fall or fracture incidence rates were found between the two groups.

CONCLUSION

The coordinator-based interventions for fragility fractures improved bone density assessment implementation and treatment rates and enhanced treatment persistence rates in the early stages following bone fractures. The findings suggest that liaison intervention may help both fracture and osteoporosis physicians for the evaluation of osteoporosis and initiation and continuation of osteoporosis medication.

Generating Ampicillin-Level Antimicrobial Peptides with Activity-Aware Generative Adversarial Networks

Antimicrobial peptides are a potential solution to the threat of multidrug-resistant bacterial pathogens. Recently, deep generative models including generative adversarial networks (GANs) have been shown to be capable of designing new antimicrobial peptides. Intuitively, a GAN controls the probability distribution of generated sequences to cover active peptides as much as possible. This paper presents a peptide-specialized model called PepGAN that takes the balance between covering active peptides and dodging nonactive peptides. As a result, PepGAN has superior statistical fidelity with respect to physicochemical descriptors including charge, hydrophobicity, and weight. Top six peptides were synthesized, and one of them was confirmed to be highly antimicrobial. The minimum inhibitory concentration was 3.1 μg/mL, indicating that the peptide is twice as strong as ampicillin.

Visualization of ferroaxial domains in an order-disorder type ferroaxial crystal

Ferroaxial materials that exhibit spontaneous ordering of a rotational structural distortion with an axial vector symmetry have gained growing interest, motivated by recent extensive studies on ferroic materials. As in conventional ferroics (e.g., ferroelectrics and ferromagnetics), domain states will be present in the ferroaxial materials. However, the observation of ferroaxial domains is non-trivial due to the nature of the order parameter, which is invariant under both time-reversal and space-inversion operations. Here we propose that NiTiO₃ is an order-disorder type ferroaxial material, and spatially resolve its ferroaxial domains by using linear electrogyration effect: optical rotation in proportion to an applied electric field. To detect small signals of electrogyration (order of 10⁻⁵ deg V⁻¹), we adopt a recently developed difference image-sensing technique. Furthermore, the ferroaxial domains are confirmed on nano-scale spatial resolution with a combined use of scanning transmission electron microscopy and convergent-beam electron diffraction. Our success of the domain visualization will promote the study of ferroaxial materials as a new ferroic state of matter.

The presence of ferroaxial domain states is recently experimentally demonstrated by a nonlinear optical technique, which lacks high spatial resolution to visualize ferroaxial domains. Here, the authors visualize spatial distributions of ferroaxial domains in NiTiO₃ showing an order-disorder type ferroaxial transition.

CompRet: a comprehensive recommendation framework for chemical synthesis planning with algorithmic enumeration

In computer-assisted synthesis planning (CASP) programs, providing as many chemical synthetic routes as possible is essential for considering optimal and alternative routes in a chemical reaction network. As the majority of CASP programs have been designed to provide one or a few optimal routes, it is likely that the desired one will not be included. To avoid this, an exact algorithm that lists possible synthetic routes within the chemical reaction network is required, alongside a recommendation of synthetic routes that meet specified criteria based on the chemist’s objectives. Herein, we propose a chemical-reaction-network-based synthetic route recommendation framework called “CompRet” with a mathematically guaranteed enumeration algorithm. In a preliminary experiment, CompRet was shown to successfully provide alternative routes for a known antihistaminic drug, cetirizine. CompRet is expected to promote desirable enumeration-based chemical synthesis searches and aid the development of an interactive CASP framework for chemists.

NMR-TS: de novo molecule identification from NMR spectra

Nuclear magnetic resonance (NMR) spectroscopy is an effective tool for identifying molecules in a sample. Although many previously observed NMR spectra are accumulated in public databases, they cover only a tiny fraction of the chemical space, and molecule identification is typically accomplished manually based on expert knowledge. Herein, we propose NMR-TS, a machine-learning-based python library, to automatically identify a molecule from its NMR spectrum. NMR-TS discovers candidate molecules whose NMR spectra match the target spectrum by using deep learning and density functional theory (DFT)-computed spectra. As a proof-of-concept, we identify prototypical metabolites from their computed spectra. After an average 5451 DFT runs for each spectrum, six of the nine molecules are identified correctly, and proximal molecules are obtained in the other cases. This encouraging result implies that de novo molecule generation can contribute to the fully automated identification of chemical structures. NMR-TS is available at https://github.com/tsudalab/NMR-TS.

Artificial Neural Networks Applied as Molecular Wave Function Solvers

We use artificial neural networks (ANNs) based on the Boltzmann machine (BM) architectures as an encoder of ab initio molecular many-electron wave functions represented with the complete active space configuration interaction (CAS-CI) model. As first introduced by the work of Carleo and Troyer for physical systems, the coefficients of the electronic configurations in the CI expansion are parametrized with the BMs as a function of their occupancies that act as descriptors. This ANN-based wave function ansatz is referred to as the neural-network quantum state (NQS). The machine learning is used for training the BMs in terms of finding a variationally optimal form of the ground-state wave function on the basis of the energy minimization. It is relevant to reinforcement learning and does not use any reference data nor prior knowledge of the wave function, while the Hamiltonian is given based on a user-specified chemical structure in the first-principles manner. Carleo and Troyer used the restricted Boltzmann machine (RBM), which has hidden units, for the neural network architecture of NQS, while, in this study, we further introduce its replacement with the BM that has only visible units but with different orders of connectivity. For this hidden-node free BM, the second- and third-order BMs based on quadratic and cubic energy functions, respectively, were implemented. We denote these second- and third-order BMs as BM2 and BM3, respectively. The pilot implementation of the NQS solver into an exact diagonalization module of the quantum chemistry program was made to assess the capability of variants of the BM-based NQS. The test calculations were performed by determining the CAS-CI wave functions of illustrative molecular systems, indocyanine green, and dinitrogen dissociation. The simulated energies have been shown to converge to CAS-CI energy in most cases by improving RBM with an increasing number of hidden nodes. BM3 systematically yields lower energies than BM2, reproducing the CAS-CI energies of dinitrogen across potential energy curves within an error of 50 μE_h.

Pushing property limits in materials discovery via boundless objective-free exploration

Our developed algorithm, BLOX (BoundLess Objective-free eXploration), successfully found “out-of-trend” molecules potentially useful for photofunctional materials from a drug database.

Materials chemists develop chemical compounds to meet often conflicting demands of industrial applications. This process may not be properly modeled by black-box optimization because the target property is not well defined in some cases. Herein, we propose a new algorithm for automated materials discovery called BoundLess Objective-free eXploration (BLOX) that uses a novel criterion based on kernel-based Stein discrepancy in the property space. Unlike other objective-free exploration methods, a boundary for the materials properties is not needed; hence, BLOX is suitable for open-ended scientific endeavors. We demonstrate the effectiveness of BLOX by finding light-absorbing molecules from a drug database. Our goal is to minimize the number of density functional theory calculations required to discover out-of-trend compounds in the intensity–wavelength property space. Using absorption spectroscopy, we experimentally verified that eight compounds identified as outstanding exhibit the expected optical properties. Our results show that BLOX is useful for chemical repurposing, and we expect this search method to have numerous applications in various scientific disciplines.

Computer Vision-Based Approach for Quantifying Occupational Therapists' Qualitative Evaluations of Postural Control

This study aimed to leverage computer vision (CV) technology to develop a technique for quantifying postural control. A conventional quantitative index, occupational therapists' qualitative clinical evaluations, and CV-based quantitative indices using an image analysis algorithm were applied to evaluate the postural control of 34 typically developed preschoolers. The effectiveness of the CV-based indices was investigated relative to current methods to explore the clinical applicability of the proposed method. The capacity of the CV-based indices to reflect therapists' qualitative evaluations was confirmed. Furthermore, compared to the conventional quantitative index, the CV-based indices provided more detailed quantitative information with lower costs. CV-based evaluations enable therapists to quantify details of motor performance that are currently observed qualitatively. The development of such precise quantification methods will improve the science and practice of occupational therapy and allow therapists to perform to their full potential.

P938Extensive formation of atherosclerotic cardiovascular disease in subjects with severe familial hypercholesterolemia defined by the international atherosclerosis society criteria

Introduction

The International Atherosclerosis Society (IAS) has proposed “severe familial hypercholesterolemia (FH)” as a FH phenotype with the highest cardiovascular risk. Coronary artery disease (CAD) represents a major atherosclerotic change in FH patients. Given their higher LDL-C level and atherogenic clinical features, more extensive formation of atherosclerosis cardiovascular disease including not only CAD but stroke/peripheral artery disease (PAD) may more frequently occur in severe FH.

Methods

481 clinically-diagnosed heterozygous FH subjects were analyzed. Severe FH was defined as untreated LDL-C>10.3 mmol/l, LDL-C>8.0 mmol/l+ 1 high-risk feature, LDL-C>4.9 mmol/l + 2 high-risk features or presence of clinical ASCVD according to IAS proposed statement. Cardiac (cardiac death and ACS) and non-cardiac (stroke and peripheral artery disease) events were compared in severe and non-severe FH subjects.

Results

Severe FH was identified in 50.1% of study subjects. They exhibit increased levels of LDL-C and Lipoprotein (a) with a higher frequency of LDLR mutation. Furthermore, a proportion of %LDL-C reduction>50% was greater in severe FH under more lipid-lowering therapy (Table). However, during the observational period (median=6.3 years), severe FH was associated with a 5.9-fold (95% CI, 2.05–25.2; p=0.004) and 5.8-fold (95% CI, 2.02–24.7; p=0.004) greater likelihood of experiencing cardiac-death/ACS and stroke/PAD, respectively (picture). Multivariate analysis demonstrated severe FH as an independent predictor of both cardiac-death/ACS (hazard ratio=3.39, 95% CI=1.12–14.7, p=0.02) and stroke/PAD (hazard ratio=3.38, 95% CI=1.16–14.3, p=0.02) events.

Clinical characteristics of severe FH Non-severe FH Severe FH P-value Baseline LDL-C (mmol/l) 5.3±1.5 6.6±2.0 <0.0001 Lp(a) (mg/dl) 15 [8–28] 21 [10–49] <0.0001 LDLR mutation (%) 49.6% 58.9% 0.00398 On-treatment LDL-C (mmol) 133 [106–165] 135 [103–169] 0.9856 %LDL-C reduction>50% 21.3% 49.8% <0.0001 High-intensity statin (%) 13.3% 42.3% <0.0001 PCSK9 inhibitor (%) 6.3% 21.2% <0.0001

Clinical outcome

Conclusions

Severe FH subjects exhibit substantial atherosclerotic risks for coronary, carotid and peripheral arteries despite lipid lowering therapy. Our finding underscore the screening of systemic arteries and the adoption of further stringent lipid management in severe FH patients.

P1561An elevated risk of heart failure and stroke events in octogenarian Japanese patients with acute myocardial infarction who received percutaneous coronary intervention

Background

The proportion of the octogenarian population is expanding especially in Eastern society. Due to the clustering of risk factors, acute myocardial infarction (AMI) represents a major cardiovascular complication in octogenarian subjects. This suggests the need to further optimize their therapeutic management to prevent future cardiac events after AMI. However, analysis of clinical characteristics and cardiovascular outcomes in octogenarian subjects with AMI who received the current established medical therapies is limited.

Purpose

To investigate clinical features and prognosis in octogenarian AMI subjects treated with percutaneous coronary intervention (PCI).

Methods

We analyzed 1547 AMI subjects underwent PCI between 2007 and 2017. Baseline characteristics and the occurrence of composite major adverse cardiovascular events (cardiac death, non-fatal MI, revascularization, heart failure and stroke) were compared in octogenarian and non-octogenarian subjects.

Results

22.0% (340/1547) of study subjects was octogenarian. They were more likely to have chronic kidney disease (CKD) and a lower level of LDL-C on admission (Table). Moreover, a higher prevalence of severer Killip class and LVEF <30% were observed in octogenarians (Table). However, they were not optimally treated with the established medical therapies at discharge (Table). During the observational period (median=3.1 years), the composite of cardiovascular events more frequently occurred in octogenarian subjects. Of note, they exhibited a 2.15-fold and 3.01-fold increased risk for heart failure and stroke events, respectively (Figure).

Table 1 Non-Octogenarian (n=1207) Octogenarian (n=340) P-value CKD* (%) 33.8 63.2 <0.0001 LVEF <30% (%) 5.7 10.3 0.02 Killip class 1.33±0.03 1.55±0.05 <0.0001 LDL-C (mmol/L) 3.20±0.03 2.80±0.05 <0.0001 Statin (%) 86.3 78.2 0.0006 Beta-blocker (%) 74.0 65.8 0.005 ACE-I/ARB (%) 87.3 76.6 <0.0001 DAPT (%) 86.0 88.6 0.42 *CKD is defined as estimated glomerular filtration rate (eGFR) <60 ml/min/1.73 m2.

Figure 1

Conclusions

Octogenarian subjects with AMI were high-risk group associated with heart failure and stroke events. Their distinct clinical backgrounds may affect the adoption of optimal medical therapies, potentially resulting in worse cardiovascular outcomes. Further intensified management should be applied to octogenarian subjects with AMI.

P6257Low systolic blood pressure on admission as a predictor of outcome in octogenarian patients with heart failure and preserved ejection fraction

Background

Heart failure (HF) is an epidemic in healthcare worldwide including Asia. It appears that HF will become more serious with aging of the population. The patients with heart failure and preserved ejection fraction (HFpEF) were older, more often female, and frequently have comorbidities including hypertension. However, lower systolic blood pressure (SBP) on admission is associated with poor outcomes in patients with HF. It remains unclear whether this association is similar in very elderly patients with HFpEF.

Purpose

To investigate clinical features and prognosis in octogenarian HFpEF subjects.

Methods

We analyzed 87 consecutive subjects aged 80 years or older who were hospitalized for acute decompensated HF with left ventricular ejection fraction (LVEF) ≥50% between 2015 and 2017. Clinical characteristics and a composite event of cardiac death and HF hospitalization were compared in two groups according to SBP cut-off of 140 mmHg on admission.

Results

The prevalence of lower SBP subjects (mean BP = 118 mmHg) and higher SBP (mean BP = 166 mmHg) subjects were 41.4% and 58.6%, respectively. Lower SBP subjects were more comorbid with atrial fibrillation (72.2 vs. 45.1%, p=0.01). In the lower SBP group, diuretics, mineralocorticoid receptor antagonists (MRA), beta-blockers and ACE inhibitors/ARBs were more commonly used than higher SBP group (Table). During the observational period (median = 1.0 year), lower SBP on admission was associated with a 2.65-fold [95% confidence interval (CI): 1.29–5.55, p=0.009] greater likelihood of experiencing the composite events of cardiac death and rehospitalization for HF (Figure). This observation was still consistent even after adjusting clinical demographics and comorbidity [hazard ratio = 2.95, 95% CI: 1.30–6.87, p=0.01].

Table 1 Lower SBP group (n=36) Higher SBP group (n=51) P-value Atrial fibrillation (%) 72.2 0.01 0.01 Loop diuretic (%) 97.1 83.7 0.08 MRA (%) 47.1 24.5 0.04 Beta-blocker (%) 52.9 44.9 0.51 ACE inhibitor/ARB (%) 59.2 29.4 0.01

Figure 1

Conclusions

In octogenarian patients with acute decompensated HF and preserved LVEF, SBP on admission less than 140 mmHg is significantly associated with poor outcomes. Future studies need to prospectively evaluate optimal SBP treatment goals in very elderly patients with HFpEF.

MP-LAMP: parallel detection of statistically significant multi-loci markers on cloud platforms

Summary

Exhaustive detection of multi-loci markers from genome-wide association study datasets is a computationally challenging problem. This paper presents a massively parallel algorithm for finding all significant combinations of alleles and introduces a software tool termed MP-LAMP that can be easily deployed in a cloud platform, such as Amazon Web Service, as well as in an in-house computer cluster. Multi-loci marker detection is an unbalanced tree search problem that cannot be parallelized by simple tree-splitting using generic parallel programming frameworks, such as Map-Reduce. We employ work stealing and periodic reduce-broadcast to decrease the running time almost linearly to the number of cores.

Availability and implementation

MP-LAMP is available at https://github.com/tsudalab/mp-lamp.

Supplementary information

Supplementary data are available at Bioinformatics online.

Enhancing Biomolecular Sampling with Reinforcement Learning: A Tree Search Molecular Dynamics Simulation Method

This paper proposes a novel molecular simulation method, called tree search molecular dynamics (TS-MD), to accelerate the sampling of conformational transition pathways, which require considerable computation. In TS-MD, a tree search algorithm, called upper confidence bounds for trees, which is a type of reinforcement learning algorithm, is applied to sample the transition pathway. By learning from the results of the previous simulations, TS-MD efficiently searches conformational space and avoids being trapped in local stable structures. TS-MD exhibits better performance than parallel cascade selection molecular dynamics, which is one of the state-of-the-art methods, for the folding of miniproteins, Chignolin and Trp-cage, in explicit water.

Machine-Learning-Assisted Development and Theoretical Consideration for the Al2Fe3Si3 Thermoelectric Material

Chemical composition alteration is a general strategy to optimize the thermoelectric properties of a thermoelectric material to achieve high-efficiency conversion of waste heat into electricity. Recent studies show that the Al₂Fe₃Si₃ intermetallic compound with a relatively high power factor of ∼700 μW m^-1 K^-2 at 400 K is promising for applications in low-cost and nontoxic thermoelectric devices. To accelerate the exploration of the thermoelectric properties of this material in a mid-temperature range and to enhance its power factor, a machine-learning method was employed herein to assist the synthesis of off-stoichiometric samples (namely, Al_{23.5+ x}Fe_36.5Si_{40- x}) of the Al₂Fe₃Si₃ compound by tuning the Al/Si ratio. The optimal Al/Si ratio for a high power factor in the mid-temperature range was found rapidly and efficiently, and the optimal ratio of the sample at x = 0.9 was found to increase the power factor at ∼510 K by about 40% with respect to that of the initial sample at x = 0.0. The possible mechanism for the enhanced power factor is discussed in terms of the precipitations of the metallic secondary phases in the Al_{23.5+ x}Fe_36.5Si_{40- x} samples. Furthermore, the maximum achievable thermal conductivity of Al₂Fe₃Si₃ estimated by the Slack model is ∼10 W m^-1 K^-1 at the Debye temperature. An avoided-crossing behavior of the acoustic and the low-lying optical modes along several crystallographic directions is found in the phonon dispersion of Al₂Fe₃Si₃ calculated by ab initio density functional theory method. These preliminary results suggest that Al₂Fe₃Si₃ can have a low thermal conductivity. The calculated formation energies of point defects suggest that the antisite defects between Al and Si are likely to cause the Al and Si off-stoichiometries in Al₂Fe₃Si₃. The theoretically obtained insight provides additional information for the further understanding of Al₂Fe₃Si₃.

An interpretable machine learning model for diagnosis of Alzheimer's disease

We present an interpretable machine learning model for medical diagnosis called sparse high-order interaction model with rejection option (SHIMR). A decision tree explains to a patient the diagnosis with a long rule (i.e., conjunction of many intervals), while SHIMR employs a weighted sum of short rules. Using proteomics data of 151 subjects in the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset, SHIMR is shown to be as accurate as other non-interpretable methods (Sensitivity, SN = 0.84 ± 0.1, Specificity, SP = 0.69 ± 0.15 and Area Under the Curve, AUC = 0.86 ± 0.09). For clinical usage, SHIMR has a function to abstain from making any diagnosis when it is not confident enough, so that a medical doctor can choose more accurate but invasive and/or more costly pathologies. The incorporation of a rejection option complements SHIMR in designing a multistage cost-effective diagnosis framework. Using a baseline concentration of cerebrospinal fluid (CSF) and plasma proteins from a common cohort of 141 subjects, SHIMR is shown to be effective in designing a patient-specific cost-effective Alzheimer's disease (AD) pathology. Thus, interpretability, reliability and having the potential to design a patient-specific multistage cost-effective diagnosis framework can make SHIMR serve as an indispensable tool in the era of precision medicine that can cater to the demand of both doctors and patients, and reduce the overwhelming financial burden of medical diagnosis.

Ultranarrow-Band Wavelength-Selective Thermal Emission with Aperiodic Multilayered Metamaterials Designed by Bayesian Optimization

We computationally designed an ultranarrow-band wavelength-selective thermal radiator via a materials informatics method alternating between Bayesian optimization and thermal electromagnetic field calculation. For a given target infrared wavelength, the optimal structure was efficiently identified from over 8 billion candidates of multilayers consisting of multiple components (Si, Ge, and SiO₂). The resulting optimized structure is an aperiodic multilayered metamaterial exhibiting high and sharp emissivity with a Q-factor of 273. The designed metamaterials were then fabricated, and reasonable experimental realization of the optimal performance was achieved with a Q-factor of 188, which is significantly higher than those of structures empirically designed and fabricated in the past. This is the first demonstration of the experimental realization of metamaterials designed by Bayesian optimization. The results facilitate the machine-learning-based design of metamaterials and advance our understanding of the narrow-band thermal emission mechanism of aperiodic multilayered metamaterials.