Publications by authors named "Sungwon Kim"

123 Publications

Machine-enabled inverse design of inorganic solid materials: promises and challenges.

Chem Sci 2020 Apr 15;11(19):4871-4881. Epub 2020 Apr 15.

Department of Chemical and Biomolecular Engineering, Korea Advanced Institute of Science and Technology (KAIST) 291, Daehak-ro, Yuseong-gu Daejeon 34141 Republic of Korea

Developing high-performance advanced materials requires a deeper insight and search into the chemical space. Until recently, exploration of materials space using chemical intuitions built upon existing materials has been the general strategy, but this direct design approach is often time and resource consuming and poses a significant bottleneck to solve the materials challenges of future sustainability in a timely manner. To accelerate this conventional design process, inverse design, which outputs materials with pre-defined target properties, has emerged as a significant materials informatics platform in recent years by leveraging hidden knowledge obtained from materials data. Here, we summarize the latest progress in machine-enabled inverse materials design categorized into three strategies: high-throughput virtual screening, global optimization, and generative models. We analyze challenges for each approach and discuss gaps to be bridged for further accelerated and rational data-driven materials design.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1039/d0sc00594kDOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC8159218PMC
April 2020

Soccer, concussions, and safety: Perceptions of parents of youth soccer participants.

J Safety Res 2021 06 29;77:255-262. Epub 2021 Mar 29.

University of Florida, P.O. Box 118208, Gainesville, FL 32611, USA. Electronic address:

Introduction: The rate of concussions in youth soccer is among the highest of all youth sports. Parents play an important role in caring for their children and making decisions regarding whether they should participate in a sport, such as soccer, where concussions are well known. This study examined parental perceptions regarding: (a) coaches' role in concussion management, (b) heading restriction policies, and (c) overall concussion risk and participation issues.

Method: Online surveys were completed by 419 parents of youth soccer players who participated in the largest U.S. youth soccer programs nationwide.

Results: Findings indicated 44.5% of the respondents had considered keeping their children from playing organized soccer and 47.2% were concerned about a potential decline in youth soccer participation due to concussions. Nearly 69% of responding parents agreed that heading should be banned for participants 10 years old or younger, while 56.5% thought heading should not be limited for participants 13 or older. Only 35% of parents were very confident about their child's coach's ability to properly identify concussions and remove those suspected of a concussion from play. Parents' socioeconomic status (SES), soccer coaching and playing experience, and previous history of concussion(s) were key predictors of greater perceived risk about concussions.

Conclusions: Findings from this study shed light on parents' perceptions about concussions and related safety issues in youth soccer. Understanding what parents believe about concussions is vital to preserve youth soccer participation and can be used to strengthen education and policies that promote a safer environment for youth sport participants. Practical Applications: Youth soccer coaches can benefit from stronger, comprehensive educational efforts at the league/club level. Additionally, parents of youth athletes who are in the lower SES communities should be targeted to receive concussion safety information and/or interventions that would improve their knowledge, attitude, and practices regarding concussion safety.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.jsr.2021.03.008DOI Listing
June 2021

Deep Learning for the Detection of Breast Cancers on Chest Computed Tomography.

Clin Breast Cancer 2021 May 5. Epub 2021 May 5.

Department of Radiology, Research Institute of Radiological Science and Center for Clinical Image Data Science, Severance Hospital, Yonsei University College of Medicine, Seoul, Korea; Department of Radiology, Yongin Severance Hospital, Yonsei University College of Medicine, Yongin, Korea. Electronic address:

Background: Incidental breast cancers can be detected on chest computed tomography (CT) scans. With the use of deep learning, the sensitivity of incidental breast cancer detection on chest CT would improve. This study aimed to evaluate the performance of a deep learning algorithm to detect breast cancers on chest CT and to validate the results in the internal and external datasets.

Patients And Methods: This retrospective study collected 1170 preoperative chest CT scans after the diagnosis of breast cancer for algorithm development (n = 1070), internal test (n = 100), and external test (n = 100). A deep learning algorithm based on RetinaNet was developed and tested to detect breast cancer on chest CT.

Results: In the internal test set, the algorithm detected 96.5% of breast cancers with 13.5 false positives per case (FPs/case). In the external test set, the algorithm detected 96.1% of breast cancers with 15.6 FPs/case. When the candidate probability of 0.3 was used as the cutoff value, the sensitivities were 92.0% with 7.36 FPs/case for the internal test set and 93.0% with 8.85 FPs/case for the external test set. When the candidate probability of 0.4 was used as the cutoff value, the sensitivities were 88.5% with 5.24 FPs/case in the internal test set and 90.7% with 6.3 FPs/case in the external test set.

Conclusion: The deep learning algorithm could sensitively detect breast cancer on chest CT in both the internal and external test sets.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.clbc.2021.04.015DOI Listing
May 2021

Development of artificial intelligence models for well groundwater quality simulation: Different modeling scenarios.

PLoS One 2021 27;16(5):e0251510. Epub 2021 May 27.

Water Engineering Department, Shahid Bahonar University of Kerman, Kerman, Iran.

Groundwater is one of the most important freshwater resources, especially in arid and semi-arid regions where the annual amounts of precipitation are small with frequent drought durations. Information on qualitative parameters of these valuable resources is very crucial as it might affect its applicability from agricultural, drinking, and industrial aspects. Although geo-statistics methods can provide insight about spatial distribution of quality factors, applications of advanced artificial intelligence (AI) models can contribute to produce more accurate results as robust alternative for such a complex geo-science problem. The present research investigates the capacity of several types of AI models for modeling four key water quality variables namely electrical conductivity (EC), sodium adsorption ratio (SAR), total dissolved solid (TDS) and Sulfate (SO4) using dataset obtained from 90 wells in Tabriz Plain, Iran; assessed by k-fold testing. Two different modeling scenarios were established to make simulations using other quality parameters and the geographical information. The obtained results confirmed the capabilities of the AI models for modeling the well groundwater quality variables. Among all the applied AI models, the developed hybrid support vector machine-firefly algorithm (SVM-FFA) model achieved the best predictability performance for both investigated scenarios. The introduced computer aid methodology provided a reliable technology for groundwater monitoring and assessment.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://journals.plos.org/plosone/article?id=10.1371/journal.pone.0251510PLOS
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC8158946PMC
May 2021

CMOS-based cryogenic control of silicon quantum circuits.

Nature 2021 May 12;593(7858):205-210. Epub 2021 May 12.

QuTech, Delft University of Technology, Delft, The Netherlands.

The most promising quantum algorithms require quantum processors that host millions of quantum bits when targeting practical applications. A key challenge towards large-scale quantum computation is the interconnect complexity. In current solid-state qubit implementations, an important interconnect bottleneck appears between the quantum chip in a dilution refrigerator and the room-temperature electronics. Advanced lithography supports the fabrication of both control electronics and qubits in silicon using technology compatible with complementary metal oxide semiconductors (CMOS). When the electronics are designed to operate at cryogenic temperatures, they can ultimately be integrated with the qubits on the same die or package, overcoming the 'wiring bottleneck'. Here we report a cryogenic CMOS control chip operating at 3 kelvin, which outputs tailored microwave bursts to drive silicon quantum bits cooled to 20 millikelvin. We first benchmark the control chip and find an electrical performance consistent with qubit operations of 99.99 per cent fidelity, assuming ideal qubits. Next, we use it to coherently control actual qubits encoded in the spin of single electrons confined in silicon quantum dots and find that the cryogenic control chip achieves the same fidelity as commercial instruments at room temperature. Furthermore, we demonstrate the capabilities of the control chip by programming a number of benchmarking protocols, as well as the Deutsch-Josza algorithm, on a two-qubit quantum processor. These results open up the way towards a fully integrated, scalable silicon-based quantum computer.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1038/s41586-021-03469-4DOI Listing
May 2021

Radiomics analysis of contrast-enhanced CT for classification of hepatic focal lesions in colorectal cancer patients: its limitations compared to radiologists.

Eur Radiol 2021 May 10. Epub 2021 May 10.

Department of Radiology, Research Institute of Radiological Science, Severance Hospital, Yonsei University College of Medicine, 50-1 Yonsei-ro, Seodaemun-gu, Seoul, 03722, Republic of Korea.

Objective: To evaluate diagnostic performance of a radiomics model for classifying hepatic cyst, hemangioma, and metastasis in patients with colorectal cancer (CRC) from portal-phase abdominopelvic CT images.

Methods: This retrospective study included 502 CRC patients who underwent contrast-enhanced CT and contrast-enhanced liver MRI between January 2005 and December 2010. Portal-phase CT images of training (n = 386) and validation (n = 116) cohorts were used to develop a radiomics model for differentiating three classes of liver lesions. Among multiple handcrafted features, the feature selection was performed using ReliefF method, and random forest classifiers were used to train the selected features. Diagnostic performance of the developed model was compared with that of four radiologists. A subgroup analysis was conducted based on lesion size.

Results: The radiomics model demonstrated significantly lower overall and hemangioma- and metastasis-specific polytomous discrimination index (PDI) (overall, 0.8037; hemangioma-specific, 0.6653; metastasis-specific, 0.8027) than the radiologists (overall, 0.9622-0.9680; hemangioma-specific, 0.9452-0.9630; metastasis-specific, 0.9511-0.9869). For subgroup analysis, the PDI of the radiomics model was different according to the lesion size (< 10 mm, 0.6486; ≥ 10 mm, 0.8264) while that of the radiologists was relatively maintained. For classifying metastasis from benign lesions, the radiomics model showed excellent diagnostic performance, with an accuracy of 84.36% and an AUC of 0.9426.

Conclusion: Albeit inferior to the radiologists, the radiomics model achieved substantial diagnostic performance when differentiating hepatic lesions from portal-phase CT images of CRC patients. This model was limited particularly to classifying hemangiomas and subcentimeter lesions.

Key Points: • Albeit inferior to the radiologists, the radiomics model could differentiate cyst, hemangioma, and metastasis with substantial diagnostic performance using portal-phase CT images of colorectal cancer patients. • The radiomics model demonstrated limitations especially in classifying hemangiomas and subcentimeter liver lesions.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1007/s00330-021-07877-yDOI Listing
May 2021

Kinetics of the Cellular and Transcriptomic Response to in Relatively Resistant and Susceptible Chicken Lines.

Front Immunol 2021 25;12:653085. Epub 2021 Mar 25.

Division of Infection and Immunity, The Roslin Institute and R(D)SVS, University of Edinburgh, Roslin, United Kingdom.

is a common cause of coccidiosis in chickens, a disease that has a huge economic impact on poultry production. Knowledge of immunity to and the specific mechanisms that contribute to differing levels of resistance observed between chicken breeds and between congenic lines derived from a single breed of chickens is required. This study aimed to define differences in the kinetics of the immune response of two inbred lines of White Leghorn chickens that exhibit differential resistance (line C.B12) or susceptibility (line 15I) to infection by . Line C.B12 and 15I chickens were infected with and transcriptome analysis of jejunal tissue was performed at 2, 4, 6 and 8 days post-infection (dpi). RNA-Seq analysis revealed differences in the rapidity and magnitude of cytokine transcription responses post-infection between the two lines. In particular, IFN-γ and IL-10 transcript expression increased in the jejunum earlier in line C.B12 (at 4 dpi) compared to line 15I (at 6 dpi). Line C.B12 chickens exhibited increases of and mRNA in the jejunum at 4 dpi, whereas in line 15I transcription was delayed but increased to a greater extent. RT-qPCR and ELISAs confirmed the results of the transcriptomic study. Higher serum IL-10 correlated strongly with higher replication in line 15I compared to line C.B12 chickens. Overall, the findings suggest early induction of the IFN-γ and IL-10 responses, as well as immune-related genes including at 4 dpi identified by RNA-Seq, may be key to resistance to .
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.3389/fimmu.2021.653085DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC8027475PMC
March 2021

Autobifunctional Mechanism of Jagged Pt Nanowires for Hydrogen Evolution Kinetics via End-to-End Simulation.

J Am Chem Soc 2021 Apr 17;143(14):5355-5363. Epub 2021 Mar 17.

Department of Chemical and Biomolecular Engineering, Korea Advanced Institute of Science and Technology (KAIST), 291 Daehak-ro, Daejeon 34141, South Korea.

The extraordinary mass activity of jagged Pt nanowires can substantially improve the economics of the hydrogen evolution reaction (HER). However, it is a great challenge to fully unveil the HER kinetics driven by the jagged Pt nanowires with their multiscale morphology. Herein we present an end-to-end framework that combines experiment, machine learning, and multiscale advances of the past decade to elucidate the HER kinetics catalyzed by jagged Pt nanowires under alkaline conditions. The bifunctional catalysis conventionally refers to the synergistic increase in activity by the combination of two different catalysts. We report that monometals, such as jagged Pt nanowires, can exhibit bifunctional characteristics owing to its complex surface morphology, where one site prefers electrochemical proton adsorption and another is responsible for activation, resulting in a 4-fold increase in the activity. We find that the conventional design guideline that the sites with a 0 eV Gibbs free energy of adsorption are optimal for HER does not hold under alkaline conditions, and rather, an energy between -0.2 and 0.0 eV is shown to be optimal. At the reaction temperatures, the high activity arises from low-coordination-number (≤7) Pt atoms exposed by the jagged surface. Our current demonstration raises an emerging prospect to understand highly complex kinetic phenomena on the nanoscale in full by implementing end-to-end multiscale strategies.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1021/jacs.0c11261DOI Listing
April 2021

Impact of Oocyst Dose on Parasite Replication, Lesion Score and Cytokine Transcription in the Caeca in Three Breeds of Commercial Layer Chickens.

Front Vet Sci 2021 22;8:640041. Epub 2021 Feb 22.

Department of Pathobiology and Population Sciences, Royal Veterinary College, London, United Kingdom.

species parasites infect the gastrointestinal tract of chickens, causing disease and impacting on production. The poultry industry relies on anticoccidial drugs and live vaccines to control and there is a need for novel, scalable alternatives. Understanding the outcomes of experimental infection in commercial chickens is valuable for assessment of novel interventions. We examined the impact of different infectious doses of (one low dose, three high doses) in three commercial layer chicken lines, evaluating lesion score, parasite replication and cytokine response in the caeca. Groups of eight to ten chickens were housed together and infected with 250, 4,000, 8,000 or 12,000 sporulated oocysts at 21 days of age. Five days post-infection caeca were assessed for lesions and to quantify parasite replication by qPCR and cytokine transcription by RT-qPCR. Comparison of the three high doses revealed no significant variation between them in observed lesions or parasite replication with all being significantly higher than the low dose infection. Transcription of IFN-γ and IL-10 increased in all infected chickens relative to unchallenged controls, with no significant differences associated with dose magnitude ( > 0.05). No significant differences were detected in lesion score, parasite replication or caecal cytokine expression between the three lines of chickens. We therefore propose 4,000 oocysts is a sufficient dose to reliably induce lesions in commercial layer chickens, and that estimates of parasite replication can be derived by qPCR from these same birds. However, more accurate quantification of replication requires a separate low dose challenge group. Optimisation of challenge dose in an appropriate chicken line is essential to maximize the value of efficacy studies. For coccidiosis, this approach can reduce the numbers of chickens required for statistically significant studies and reduce experimental severity.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.3389/fvets.2021.640041DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7937735PMC
February 2021

Diagnostic Performance of Deep Learning-Based Lesion Detection Algorithm in CT for Detecting Hepatic Metastasis from Colorectal Cancer.

Korean J Radiol 2021 Jun 25;22(6):912-921. Epub 2021 Feb 25.

Department of Radiology, Research Institute of Radiological Science and Center for Clinical Image Data Science, Severance Hospital, Yonsei University College of Medicine, Seoul, Korea.

Objective: To compare the performance of the deep learning-based lesion detection algorithm (DLLD) in detecting liver metastasis with that of radiologists.

Materials And Methods: This clinical retrospective study used 4386-slice computed tomography (CT) images and labels from a training cohort (502 patients with colorectal cancer [CRC] from November 2005 to December 2010) to train the DLLD for detecting liver metastasis, and used CT images of a validation cohort (40 patients with 99 liver metastatic lesions and 45 patients without liver metastasis from January 2011 to December 2011) for comparing the performance of the DLLD with that of readers (three abdominal radiologists and three radiology residents). For per-lesion binary classification, the sensitivity and false positives per patient were measured.

Results: A total of 85 patients with CRC were included in the validation cohort. In the comparison based on per-lesion binary classification, the sensitivity of DLLD (81.82%, [81/99]) was comparable to that of abdominal radiologists (80.81%, = 0.80) and radiology residents (79.46%, = 0.57). However, the false positives per patient with DLLD (1.330) was higher than that of abdominal radiologists (0.357, < 0.001) and radiology residents (0.667, < 0.001).

Conclusion: DLLD showed a sensitivity comparable to that of radiologists when detecting liver metastasis in patients initially diagnosed with CRC. However, the false positives of DLLD were higher than those of radiologists. Therefore, DLLD could serve as an assistant tool for detecting liver metastasis instead of a standalone diagnostic tool.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.3348/kjr.2020.0447DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC8154788PMC
June 2021

Deep-learning system for real-time differentiation between Crohn's disease, intestinal Behçet's disease, and intestinal tuberculosis.

J Gastroenterol Hepatol 2021 Feb 7. Epub 2021 Feb 7.

Department of Internal Medicine and Institute of Gastroenterology, Yonsei University College of Medicine, Seoul, Republic of Korea.

Background And Aim: Pattern analysis of big data can provide a superior direction for the clinical differentiation of diseases with similar endoscopic findings. This study aimed to develop a deep-learning algorithm that performs differential diagnosis between intestinal Behçet's disease (BD), Crohn's disease (CD), and intestinal tuberculosis (ITB) using colonoscopy images.

Methods: The typical pattern for each disease was defined as a typical image. We implemented a convolutional neural network (CNN) using Pytorch and visualized a deep-learning model through Gradient-weighted Class Activation Mapping. The performance of the algorithm was evaluated using the area under the receiver operating characteristic curve (AUROC).

Results: A total of 6617 colonoscopy images of 211 CD, 299 intestinal BD, and 217 ITB patients were used. The accuracy of the algorithm for discriminating the three diseases (all-images: 65.15% vs typical images: 72.01%, P = 0.024) and discriminating between intestinal BD and CD (all-images: 78.15% vs typical images: 85.62%, P = 0.010) was significantly different between all-images and typical images. The CNN clearly differentiated colonoscopy images of the diseases (AUROC from 0.7846 to 0.8586). Algorithmic prediction AUROC for typical images ranged from 0.8211 to 0.9360.

Conclusion: This study found that a deep-learning model can discriminate between colonoscopy images of intestinal BD, CD, and ITB. In particular, the algorithm demonstrated superior discrimination ability for typical images. This approach presents a beneficial method for the differential diagnosis of the diseases.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1111/jgh.15433DOI Listing
February 2021

A radiomics-based model for predicting prognosis of locally advanced gastric cancer in the preoperative setting.

Sci Rep 2021 Jan 21;11(1):1879. Epub 2021 Jan 21.

Department of Radiology and Research Institute of Radiological Science, Severance Hospital, Yonsei University College of Medicine, 50-1 Yonsei-ro, Seodaemun-gu, Seoul, 03722, South Korea.

This study aims to evaluate the performance of a radiomic signature-based model for predicting recurrence-free survival (RFS) of locally advanced gastric cancer (LAGC) using preoperative contrast-enhanced CT. This retrospective study included a training cohort (349 patients) and an external validation cohort (61 patients) who underwent curative resection for LAGC in 2010 without neoadjuvant therapies. Available preoperative clinical factors, including conventional CT staging and endoscopic data, and 438 radiomic features from the preoperative CT were obtained. To predict RFS, a radiomic model was developed using penalized Cox regression with the least absolute shrinkage and selection operator with ten-fold cross-validation. Internal and external validations were performed using a bootstrapping method. With the final 410 patients (58.2 ± 13.0 years-old; 268 female), the radiomic model consisted of seven selected features. In both of the internal and the external validation, the integrated area under the receiver operating characteristic curve values of both the radiomic model (0.714, P < 0.001 [internal validation]; 0.652, P = 0.010 [external validation]) and the merged model (0.719, P < 0.001; 0.651, P = 0.014) were significantly higher than those of the clinical model (0.616; 0.594). The radiomics-based model on preoperative CT images may improve RFS prediction and high-risk stratification in the preoperative setting of LAGC.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1038/s41598-021-81408-zDOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7820605PMC
January 2021

Prediction of breast cancer molecular subtypes using radiomics signatures of synthetic mammography from digital breast tomosynthesis.

Sci Rep 2020 12 9;10(1):21566. Epub 2020 Dec 9.

Department of Radiology, Research Institute of Radiological Science and Center for Clinical Image Data Science, Severance Hospital, Yonsei University College of Medicine, 50-1 Yonsei-ro, Seodaemun-gu, Seoul, 03722, Republic of Korea.

We aimed to predict molecular subtypes of breast cancer using radiomics signatures extracted from synthetic mammography reconstructed from digital breast tomosynthesis (DBT). A total of 365 patients with invasive breast cancer with three different molecular subtypes (luminal A + B, luminal; HER2-positive, HER2; triple-negative, TN) were assigned to the training set and temporally independent validation cohort. A total of 129 radiomics features were extracted from synthetic mammograms. The radiomics signature was built using the elastic-net approach. Clinical features included patient age, lesion size and image features assessed by radiologists. In the validation cohort, the radiomics signature yielded an AUC of 0.838, 0.556, and 0.645 for the TN, HER2 and luminal subtypes, respectively. In a multivariate analysis, the radiomics signature was the only independent predictor of the molecular subtype. The combination of the radiomics signature and clinical features showed significantly higher AUC values than clinical features only for distinguishing the TN subtype. In conclusion, the radiomics signature showed high performance for distinguishing TN breast cancer. Radiomics signatures may serve as biomarkers for TN breast cancer and may help to determine the direction of treatment for these patients.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1038/s41598-020-78681-9DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7726048PMC
December 2020

In Situ Strain Evolution on Pt Nanoparticles during Hydrogen Peroxide Decomposition.

Nano Lett 2020 Dec 11;20(12):8541-8548. Epub 2020 Nov 11.

Department of Physics, Sogang University, Seoul 04107, Korea.

Fundamental understanding of structural changes during catalytic reactions is crucial to understanding the underlying mechanisms and optimizing efficiencies. Surface energy and related catalytic mechanisms are widely studied. However, the catalyst lattice deformation induced by catalytic processes is not well understood. Here, we study the strain in an individual platinum (Pt) nanoparticle (NP) using Bragg coherent diffraction imaging under in situ oxidation and reduction reactions. When Pt NPs are exposed to HO, a typical oxidizer and an intermediate during the oxygen reduction reaction process, alternating overall strain distribution near the surface and inside the NP is observed at the (111) Bragg reflection. In contrast, relatively insignificant changes appear in the (200) reflection. Density functional theory calculations are employed to rationalize the anisotropic lattice strain in terms of induced stress by HO adsorption and decomposition on the Pt NP surface. Our study provides deeper insight into the activity-structure relationship in this system.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1021/acs.nanolett.0c03005DOI Listing
December 2020

Statistical Image Restoration for Low-Dose CT using Convolutional Neural Networks

Annu Int Conf IEEE Eng Med Biol Soc 2020 07;2020:1303-1306

Deep learning has recently attracted widespread interest as a means of reducing noise in low-dose CT (LDCT) images. Deep convolutional neural networks (CNNs) are typically trained to transfer high-quality image features of normal-dose CT (NDCT) images to LDCT images. However, existing deep learning approaches for denoising LDCT images often overlook the statistical property of CT images. In this paper, we propose an approach to statistical image restoration for LDCT using deep learning (StatCNN). We introduce a loss function to incorporate the noise property in the image domain derived from the noise statistics in the sinogram domain. In order to capture the spatially-varying statistics of axial CT images, we increase the receptive fields of the proposed network to cover full-size CT slices. In addition, the proposed network utilizes z-directional correlation by taking multiple consecutive CT slices as input. For performance evaluation, the proposed network was thoroughly trained and tested by leave-one-out cross-validation with a dataset consisting of LDCT-NDCT image pairs. The experimental results showed that the denoising networks successfully reduced the noise level and restored the image details without adding artifacts. This study demonstrates that the statistical deep learning approach can transfer the image style from NDCT images to LDCT images without loss of anatomical information.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1109/EMBC44109.2020.9176265DOI Listing
July 2020

Diagnosis of thyroid nodules on ultrasonography by a deep convolutional neural network.

Sci Rep 2020 09 17;10(1):15245. Epub 2020 Sep 17.

Department of Radiology, Severance Hospital, Research Institute of Radiological Science, Yonsei University, College of Medicine, 50 Yonsei-ro, Seodaemun-gu, Seoul, 03722, Republic of Korea.

The purpose of this study was to evaluate and compare the diagnostic performances of the deep convolutional neural network (CNN) and expert radiologists for differentiating thyroid nodules on ultrasonography (US), and to validate the results in multicenter data sets. This multicenter retrospective study collected 15,375 US images of thyroid nodules for algorithm development (n = 13,560, Severance Hospital, SH training set), the internal test (n = 634, SH test set), and the external test (n = 781, Samsung Medical Center, SMC set; n = 200, CHA Bundang Medical Center, CBMC set; n = 200, Kyung Hee University Hospital, KUH set). Two individual CNNs and two classification ensembles (CNNE1 and CNNE2) were tested to differentiate malignant and benign thyroid nodules. CNNs demonstrated high area under the curves (AUCs) to diagnose malignant thyroid nodules (0.898-0.937 for the internal test set and 0.821-0.885 for the external test sets). AUC was significantly higher for CNNE2 than radiologists in the SH test set (0.932 vs. 0.840, P < 0.001). AUC was not significantly different between CNNE2 and radiologists in the external test sets (P = 0.113, 0.126, and 0.690). CNN showed diagnostic performances comparable to expert radiologists for differentiating thyroid nodules on US in both the internal and external test sets.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1038/s41598-020-72270-6DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7498581PMC
September 2020

Generative Adversarial Networks for Crystal Structure Prediction.

ACS Cent Sci 2020 Aug 10;6(8):1412-1420. Epub 2020 Jul 10.

Department of Chemical and Biomolecular Engineering, KAIST, 291 Daehak-ro, Daejeon 34141, South Korea.

The constant demand for novel functional materials calls for efficient strategies to accelerate the materials discovery, and crystal structure prediction is one of the most fundamental tasks along that direction. In addressing this challenge, generative models can offer new opportunities since they allow for the continuous navigation of chemical space via latent spaces. In this work, we employ a crystal representation that is inversion-free based on unit cell and fractional atomic coordinates and build a generative adversarial network for crystal structures. The proposed model is applied to generate the Mg-Mn-O ternary materials with the theoretical evaluation of their photoanode properties for high-throughput virtual screening (HTVS). The proposed generative HTVS framework predicts 23 new crystal structures with reasonable calculated stability and band gap. These findings suggest that the generative model can be an effective way to explore hidden portions of the chemical space, an area that is usually unreachable when conventional substitution-based discovery is employed.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1021/acscentsci.0c00426DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7453563PMC
August 2020

Combined Utility of 25 Disease and Risk Factor Polygenic Risk Scores for Stratifying Risk of All-Cause Mortality.

Am J Hum Genet 2020 09 5;107(3):418-431. Epub 2020 Aug 5.

Department of Biostatistics, Johns Hopkins Bloomberg School of Public Health, Baltimore, MD 21205, USA; Department of Oncology, Johns Hopkins University School of Medicine, Baltimore, MD 21205, USA. Electronic address:

While genome-wide association studies have identified susceptibility variants for numerous traits, their combined utility for predicting broad measures of health, such as mortality, remains poorly understood. We used data from the UK Biobank to combine polygenic risk scores (PRS) for 13 diseases and 12 mortality risk factors into sex-specific composite PRS (cPRS). These cPRS were moderately associated with all-cause mortality in independent data within the UK Biobank: the estimated hazard ratios per standard deviation were 1.10 (95% confidence interval: 1.05, 1.16) and 1.15 (1.10, 1.19) for women and men, respectively. Differences in life expectancy between the top and bottom 5% of the cPRS were estimated to be 4.79 (1.76, 7.81) years and 6.75 (4.16, 9.35) years for women and men, respectively. These associations were substantially attenuated after adjusting for non-genetic mortality risk factors measured at study entry (i.e., middle age for most participants). The cPRS may be useful in counseling younger individuals at higher genetic risk of mortality on modification of non-genetic factors.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.ajhg.2020.07.002DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7477009PMC
September 2020

Current State and Strategy for Establishing a Digitally Innovative Hospital: Memorial Review Article for Opening of Yongin Severance Hospital.

Yonsei Med J 2020 Aug;61(8):647-651

Yongin Severance Hospital, Yonsei University College of Medicine, Yongin, Korea.

The emergence of new technologies, especially digital transformation, influences the entire society, including the medical aspects. Therefore, the concept of digital hospital has been emerging. Here we present the Yongin Severance Hospital, which has developed various novel solutions to serve as foundations for the establishment of a digitally innovative hospital. Further strategies have also been provided to implement consistent and long-term planning.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.3349/ymj.2020.61.8.647DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7393291PMC
August 2020

Vaccination with transgenic Eimeria tenella expressing Eimeria maxima AMA1 and IMP1 confers partial protection against high-level E. maxima challenge in a broiler model of coccidiosis.

Parasit Vectors 2020 Jul 10;13(1):343. Epub 2020 Jul 10.

Department of Pathobiology and Population Sciences, Royal Veterinary College, Hawkshead Lane, Hatfield, Hertforshire, AL9 7TA, UK.

Background: Poultry coccidiosis is a parasitic enteric disease with a highly negative impact on chicken production. In-feed chemoprophylaxis remains the primary method of control, but the increasing ineffectiveness of anticoccidial drugs, and potential future restrictions on their use has encouraged the use of commercial live vaccines. Availability of such formulations is constrained by their production, which relies on the use of live chickens. Several experimental approaches have been taken to explore ways to reduce the complexity and cost of current anticoccidial vaccines including the use of live vectors expressing relevant Eimeria proteins. We and others have shown that vaccination with transgenic Eimeria tenella parasites expressing Eimeria maxima Apical Membrane Antigen-1 or Immune Mapped Protein-1 (EmAMA1 and EmIMP1) partially reduces parasite replication after challenge with a low dose of E. maxima oocysts. In the present study, we have reassessed the efficacy of these experimental vaccines using commercial birds reared at high stocking densities and challenged with both low and high doses of E. maxima to evaluate how well they protect chickens against the negative impacts of disease on production parameters.

Methods: Populations of E. tenella parasites expressing EmAMA1 and EmIMP1 were obtained by nucleofection and propagated in chickens. Cobb500 broilers were immunised with increasing doses of transgenic oocysts and challenged two weeks later with E. maxima to quantify the effect of vaccination on parasite replication, local IFN-γ and IL-10 responses (300 oocysts), as well as impacts on intestinal lesions and body weight gain (10,000 oocysts).

Results: Vaccination of chickens with E. tenella expressing EmAMA1, or admixtures of E. tenella expressing EmAMA1 or EmIMP1, was safe and induced partial protection against challenge as measured by E. maxima replication and severity of pathology. Higher levels of protection were observed when both antigens were delivered and was associated with a partial modification of local immune responses against E. maxima, which we hypothesise resulted in more rapid immune recognition of the challenge parasites.

Conclusions: This study offers prospects for future development of multivalent anticoccidial vaccines for commercial chickens. Efforts should now be focused on the discovery of additional antigens for incorporation into such vaccines.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1186/s13071-020-04210-2DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7350274PMC
July 2020

Diagnostic Models for Atopic Dermatitis Based on Serum Microbial Extracellular Vesicle Metagenomic Analysis: A Pilot Study.

Allergy Asthma Immunol Res 2020 Sep;12(5):792-805

Institute of MD Healthcare Inc., Seoul, Korea.

Purpose: Associations between a wide variety of diseases and the microbiome have been extensively verified. Recently, there has been a rising interest in the role the microbiome plays in atopic dermatitis (AD). Furthermore, metagenomic analysis of microbe-derived extracellular vesicles (EVs) has revealed the importance and relevance of microbial EVs in human health.

Methods: We compared the diversity and proportion of microbial EVs in the sera of 24 AD patients and 49 healthy controls, and developed a diagnostic model. After separating microbial EVs from serum, we specifically targeted the V3-V4 hypervariable regions of the gene for amplification and subsequent sequencing.

Results: Alpha and beta diversity between controls and AD patients both differed, but only the difference in beta diversity was significant. Proteobacteria, Firmicutes, and Bacteroidetes were the dominant phyla in healthy controls and AD patients, accounting for over 85% of the total serum bacterial EVs. Also, Proteobacteria, Firmicutes, Actinobacteria, Verrucomicrobia, and Cyanobacteria relative abundances were significantly different between the AD and control groups. At the genus level, the proportions of , , , and were drastically altered between the AD and control groups. AD diagnostic models developed using biomarkers selected on the basis of linear discriminant analysis effect size from the class to genus levels all yielded area under the receiver operating characteristic curve, sensitivity, specificity, and accuracy of value 1.00.

Conclusions: In summary, microbial EVs demonstrated the potential in their use as novel biomarkers for AD diagnosis. Therefore, future work should investigate larger case and control groups with cross-sectional or longitudinal clinical data to explore the utility and validity of serum microbiota EV-based AD diagnosis.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.4168/aair.2020.12.5.792DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7346989PMC
September 2020

Youth Soccer Parents' Attitudes and Perceptions About Concussions.

J Adolesc Health 2021 01 5;68(1):184-190. Epub 2020 Jul 5.

Department of Sport Management, University of Florida, Gainesville, Florida.

Purpose: Parents are important figures in properly managing youth sport concussions. Although media attention has predominantly centered on concussions in contact/collision sports, evidence suggests that the concussion rate in soccer is comparable to those found in contact/collision sports. Given the high rate of concussions in youth soccer, this study aimed to examine parents of youth soccer athletes' attitudes and perceptions about concussions and associated factors.

Methods: A cross-sectional study was conducted by surveying parents of youth soccer athletes from the five largest organized youth soccer programs across the U.S. The researchers developed a questionnaire after an extensive literature review and by modifying previously used instruments.

Results: Overall, 419 parents completed the survey. The vast majority (85%) agreed that a concussion is a serious injury, but only 27.9% believed that their child could suffer a concussion during the next season. Parents were most concerned about permanent brain damage when their child suffers a concussion. The vast majority (4.37 ± .89) perceived concussion reporting as an important injury prevention strategy. Greater appreciation and perceived risk about concussions was found particularly among parents who received concussion education and those who had witnessed or heard about a concussive incidence(s).

Conclusions: Findings suggest that youth soccer parents have high appreciation and perceived risk about concussions. However, the need for more targeted education was noted, as improvements to better manage and reduce concussions can be made. Future research should continue examining youth sport parents' belief and understanding about concussions as well as factors affecting them.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.jadohealth.2020.04.029DOI Listing
January 2021

Predictive performance of ultrasonography-based radiomics for axillary lymph node metastasis in the preoperative evaluation of breast cancer.

Ultrasonography 2021 Jan 1;40(1):93-102. Epub 2020 Apr 1.

Department of Radiology, Severance Hospital, Research Institute of Radiological Science and Center for Clinical Image Data Science, Yonsei University College of Medicine, Seoul, Korea.

Purpose: The purpose of this study was to evaluate the predictive performance of ultrasonography (US)-based radiomics for axillary lymph node metastasis and to compare it with that of a clinicopathologic model.

Methods: A total of 496 patients (mean age, 52.5±10.9 years) who underwent breast cancer surgery between January 2014 and December 2014 were included in this study. Among them, 306 patients who underwent surgery between January 2014 and August 2014 were enrolled as a training cohort, and 190 patients who underwent surgery between September 2014 and December 2014 were enrolled as a validation cohort. To predict axillary lymph node metastasis in breast cancer, we developed a preoperative clinicopathologic model using multivariable logistic regression and constructed a radiomics model using 23 radiomic features selected via least absolute shrinkage and selection operator regression.

Results: In the training cohort, the areas under the curve (AUC) were 0.760, 0.812, and 0.858 for the clinicopathologic, radiomics, and combined models, respectively. In the validation cohort, the AUCs were 0.708, 0.831, and 0.810, respectively. The combined model showed significantly better diagnostic performance than the clinicopathologic model.

Conclusion: A radiomics model based on the US features of primary breast cancers showed additional value when combined with a clinicopathologic model to predict axillary lymph node metastasis.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.14366/usg.20026DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7758097PMC
January 2021

Assessing the biochemical oxygen demand using neural networks and ensemble tree approaches in South Korea.

J Environ Manage 2020 Sep 5;270:110834. Epub 2020 Jun 5.

Distinguished Professor and Caroline & William N. Lehrer Distinguished Chair in Water Engineering, Department of Biological and Agricultural Engineering & Zachry Department of Civil Engineering, Texas A&M University, College Station, TX, 77843-2117, USA; National Water Center, UAE University, Al Ain, United Arab Emirates. Electronic address:

The biochemical oxygen demand (BOD), one of widely utilized variables for water quality assessment, is metric for the ecological division in rivers. Since the traditional approach to predict BOD is time-consuming and inaccurate due to inconstancies in microbial multiplicity, alternative methods have been recommended for more accurate prediction of BOD. This study investigated the capability of a novel deep learning-based model, Deep Echo State Network (Deep ESN), for predicting BOD, based on various water quality variables, at Gongreung and Gyeongan stations, South Korea. The model was compared with the Extreme Learning Machine (ELM) and two ensemble tree models comprising the Gradient Boosting Regression Tree (GBRT) and Random Forests (RF). Diverse water quality variables (i.e., BOD, potential of Hydrogen (pH), electrical conductivity (EC), dissolved oxygen (DO), water temperature (WT), chemical oxygen demand (COD), suspended solids (SS), total nitrogen (T-N), and total phosphorus (T-P)) were utilized for developing the Deep ESN, ELM, GBRT, and RF with five input combinations (i.e., Categories 1-5). These models were evaluated by root mean square error (RMSE), Nash-Sutcliffe efficiency (NSE), coefficient of determination (R), and correlation coefficient (R). Overall evaluations suggested that the Deep ESN5 model provided the most reliable predictions of BOD among all the models at both stations.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.jenvman.2020.110834DOI Listing
September 2020

Continuous monitoring of suspended sediment concentrations using image analytics and deriving inherent correlations by machine learning.

Sci Rep 2020 05 22;10(1):8589. Epub 2020 May 22.

Department of Civil Engineering, Tabriz Branch, Islamic Azad University, Tabriz, Iran.

The barriers for the development of continuous monitoring of Suspended Sediment Concentration (SSC) in channels/rivers include costs and technological gaps but this paper shows that a solution is feasible by: (i) using readily available high-resolution images; (ii) transforming the images into image analytics to form a modelling dataset; and (iii) constructing predictive models by learning inherent correlation between observed SSC values and their image analytics. High-resolution images were taken of water containing a series of SSC values using an exploratory flume. Machine learning is processed by dividing the dataset into training and testing sets and the paper uses the following models: Generalized Linear Machine (GLM) and Distributed Random Forest (DRF). Results show that each model is capable of reliable predictions but the errors at higher SSC are not fully explained by modelling alone. Here we offer sufficient evidence for the feasibility of a continuous SSC monitoring capability in channels before the next phase of the study with the goal of producing practice guidelines.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1038/s41598-020-64707-9DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7244478PMC
May 2020

Drought index prediction using advanced fuzzy logic model: Regional case study over Kumaon in India.

PLoS One 2020 21;15(5):e0233280. Epub 2020 May 21.

Department of Biological and Agricultural Engineering and Zachry Department of Civil Engineering, Texas A&M University, Austin, Texas, United States of America.

A new version of the fuzzy logic model, called the co-active neuro fuzzy inference system (CANFIS), is introduced for predicting standardized precipitation index (SPI). Multiple scales of drought information at six meteorological stations located in Uttarakhand State, India, are used. Different lead times of SPI were computed for prediction, including 1, 3, 6, 9, 12, and 24 months, with inputs abstracted by autocorrelation function (ACF) and partial-ACF (PACF) analysis at 5% significance level. The proposed CANFIS model was validated against two models: classical artificial intelligence model (e.g., multilayer perceptron neural network (MLPNN)) and regression model (e.g., multiple linear regression (MLR)). Several performance evaluation metrices (root mean square error, Nash-Sutcliffe efficiency, coefficient of correlation, and Willmott index), and graphical visualizations (scatter plot and Taylor diagram) were computed for the evaluation of model performance. Results indicated that the CANFIS model predicted the SPI better than the other models and prediction results were different for different meteorological stations. The proposed model can build a reliable expert intelligent system for predicting meteorological drought at multi-time scales and decision making for remedial schemes to cope with meteorological drought at the study stations and can help to maintain sustainable water resources management.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://journals.plos.org/plosone/article?id=10.1371/journal.pone.0233280PLOS
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7241731PMC
August 2020

Lung Disease Diagnostic Model Through IgG Sensitization to Microbial Extracellular Vesicles.

Allergy Asthma Immunol Res 2020 Jul;12(4):669-683

Institute of MD Healthcare Inc., Seoul, Korea.

Purpose: Recently, there has been a rise in the interest to understand the composition of indoor dust due to its association with lung diseases such as asthma, chronic obstructive pulmonary disease (COPD) and lung cancer. Furthermore, it has been found that bacterial extracellular vesicles (EVs) within indoor dust particles can induce pulmonary inflammation, suggesting that these might play a role in lung disease.

Methods: We performed microbiome analysis of indoor dust EVs isolated from mattresses in apartments and hospitals. We developed diagnostic models based on the bacterial EVs antibodies detected in serum samples via enzyme-linked immunosorbent assay (ELISA) in this analysis.

Results: Proteobacteria was the most abundant bacterial EV taxa observed at the phylum level while , and were the most prominent organisms at the genus level, followed by . Based on the microbiome analysis, serum anti-bacterial EV immunoglobulin G (IgG), IgG1 and IgG4 were analyzed using ELISA with EV antibodies that targeted , , and . The levels of anti-bacterial EV antibodies were found to be significantly higher in patients with asthma, COPD and lung cancer compared to the healthy control group. We then developed a diagnostic model through logistic regression of antibodies that showed significant differences between groups with smoking history as a covariate. Four different variable selection methods were compared to construct an optimal diagnostic model with area under the curves ranging from 0.72 to 0.81.

Conclusions: The results of this study suggest that ELISA-based analysis of anti-bacterial EV antibodies titers can be used as a diagnostic tool for lung disease. The present findings provide insights into the pathogenesis of lung disease as well as a foundation for developing a novel diagnostic methodology that synergizes microbial EV metagenomics and immune assays.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.4168/aair.2020.12.4.669DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7224999PMC
July 2020

Advanced machine learning model for better prediction accuracy of soil temperature at different depths.

PLoS One 2020 14;15(4):e0231055. Epub 2020 Apr 14.

Department of Civil Engineering, Faculty of Engineering, University Malaya, Kuala Lumpur, Malaysia.

Soil temperature has a vital importance in biological, physical and chemical processes of terrestrial ecosystem and its modeling at different depths is very important for land-atmosphere interactions. The study compares four machine learning techniques, extreme learning machine (ELM), artificial neural networks (ANN), classification and regression trees (CART) and group method of data handling (GMDH) in estimating monthly soil temperatures at four different depths. Various combinations of climatic variables are utilized as input to the developed models. The models' outcomes are also compared with multi-linear regression based on Nash-Sutcliffe efficiency, root mean square error, and coefficient of determination statistics. ELM is found to be generally performs better than the other four alternatives in estimating soil temperatures. A decrease in performance of the models is observed by an increase in soil depth. It is found that soil temperatures at three depths (5, 10 and 50 cm) could be mapped utilizing only air temperature data as input while solar radiation and wind speed information are also required for estimating soil temperature at the depth of 100 cm.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://journals.plos.org/plosone/article?id=10.1371/journal.pone.0231055PLOS
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7156082PMC
July 2020

Uncertainty-Quantified Hybrid Machine Learning/Density Functional Theory High Throughput Screening Method for Crystals.

J Chem Inf Model 2020 04 6;60(4):1996-2003. Epub 2020 Apr 6.

Department of Chemical and Biomolecular Engineering, Korea Advanced Institute of Science and Technology (KAIST), 291 Daehak-ro, Daejeon 34141, Republic of Korea.

Computational high throughput screening (HTS) has emerged as a significant tool in material science to accelerate the discovery of new materials with target properties in recent years. However, despite many successful cases in which HTS led to the novel discovery, currently, the major bottleneck in HTS is a large computational cost of density functional theory (DFT) calculations that scale cubically with system size, limiting the chemical space that can be explored. The present work aims at addressing this computational burden of HTS by presenting a machine learning (ML) framework that can efficiently explore the chemical space. Our model is built upon an existing crystal graph convolutional neural network (CGCNN) to obtain formation energy of a crystal structure but is modified to allow uncertainty quantification for each prediction using the hyperbolic tangent activation function and dropout algorithm (CGCNN-HD). The uncertainty quantification is particularly important since typical usage of CGCNN (due to the lack of gradient implementation) does not involve structural relaxation which could cause substantial prediction errors. The proposed method is benchmarked against an existing application that identified promising photoanode material among the >7,000 hypothetical Mg-Mn-O ternary compounds using all DFT-HTS. In our approach, we perform the approximate HTS using CGCNN-HD and refine the results using full DFT for those selected (denoted as ML/DFT-HTS). The proposed hybrid model reduces the required DFT calculations by a factor of >50 compared to the previous DFT-HTS in making the same discovery of MgMnO, experimentally validated new photoanode material. Further analysis demonstrates that the addition of HD components with uncertainty measures in the CGCNN-HD model increased the of promising materials relative to all DFT-HTS from 30% (CGCNN) to 68% (CGCNN-HD). The present ML/DFT-HTS with uncertainty quantification can thus be a fast alternative to DFT-HTS for efficient exploration of the vast chemical space.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1021/acs.jcim.0c00003DOI Listing
April 2020