Changyong Lee
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Changyong Lee has a total of 103 co-authors. Here are the top co-authors by number of shared publications:
Yongtae Park
12 shared publicationsSunhee Kim
Affiliation Department of Industrial and Systems Engineering, Kongju National University, Cheonan, Republic of Korea
8 shared publications- Byungun Yoon
Department of Industrial & Systems Engineering, Dongguk University, Seoul, South Korea
7 shared publications - Juram Kim
Graduate School of Management of Technology, Sogang University, Seoul, Republic of Korea
7 shared publications Bomi Song
Korea Inst Ind Technol, Innovat Strategy Div, 89 Yangdaegiro Gil, Cheonan Si 31056, Chungcheongnam, South Korea
6 shared publicationsHakyeon Lee
6 shared publications
Latest Publications
- Open Access
- 20 August 2026
- Published by Public Library of Science (PLoS) in PLOS Computational Biology
- Vol. 22  (8) , e1014603
A portable recalibration workflow for reference-based variant calling in non-human genomes
A key computational step in reference-based variant calling is distinguishing true genetic variants from sequencing errors. Advanced tools and workflows have been developed to handle this by computational modelling of technical errors from the sequencing machines. However, these recalibration workflows have largely been evaluated for human data only and its exact applicability for non-human data remains unknown. Here, we conducted a systematic evaluation of variant calling on human, rice, sheep, and chickpea data, and found that existing workflows introduce unexpected statistical bias, thus leading to suboptimal variant calls for non-human data. To address this problem, we present simple guidelines for constructing a âpseudo-âdatabase (pseudoDB) of genetic variants as a scalable and portable solution for recalibration and variant calling. With human data, our pseudoDB-based workflow performs comparably to existing dbSNP-based GATK3 workflows and those using DeepVariant, Strelka2, and FreeBayes. We extend this to other non-human genomes, namely cattle, brown bear, swan goose, African oil palm, Komodo dragon, and stevia, altogether resulting in the identification of up to 242.0% unique genetic variants. The majority of newly identified variants are within the non-coding regions, hinting at the rich diversity of genome regulation in the non-human population. Our pseudoDB-based workflow is agnostic to reference genomes and modular for easy integration with other computational workflows for human and non-human resequencing data.
- 20 August 2026
- Published by Public Library of Science (PLoS) in PLOS Computational Biology
- Vol. 22  (8) , e1014603
Open AccessA portable recalibration workflow for reference-based variant calling in non-human genomes
A key computational step in reference-based variant calling is distinguishing true genetic variants from sequencing errors. Advanced tools and workflows have been developed to handle this by computational modelling of technical errors from the sequencing machines. However, these recalibration workflows have largely been evaluated for human data only and its exact applicability for non-human data remains unknown. Here, we conducted a systematic evaluation of variant calling on human, rice, sheep, and chickpea data, and found that existing workflows introduce unexpected statistical bias, thus leading to suboptimal variant calls for non-human data. To address this problem, we present simple guidelines for constructing a âpseudo-âdatabase (pseudoDB) of genetic variants as a scalable and portable solution for recalibration and variant calling. With human data, our pseudoDB-based workflow performs comparably to existing dbSNP-based GATK3 workflows and those using DeepVariant, Strelka2, and FreeBayes. We extend this to other non-human genomes, namely cattle, brown bear, swan goose, African oil palm, Komodo dragon, and stevia, altogether resulting in the identification of up to 242.0% unique genetic variants. The majority of newly identified variants are within the non-coding regions, hinting at the rich diversity of genome regulation in the non-human population. Our pseudoDB-based workflow is agnostic to reference genomes and modular for easy integration with other computational workflows for human and non-human resequencing data.
- 6 December 2025
- Published by Springer Nature in Scientometrics
- Vol. 131  (4) , 2439-2469
Technological impact-guided technology opportunity analysis using a generative-predictive machine learning model
- 6 December 2025
- Published by Springer Nature in Scientometrics
- Vol. 131  (4) , 2439-2469
Technological impact-guided technology opportunity analysis using a generative-predictive machine learning model
- Open Access
- 5 November 2024
- Published by Springer Nature in Scientific Reports
- Vol. 14  (1) , 1-18
A tied-weight autoencoder for the linear dimensionality reduction of sample data
Dimensionality reduction is a method used in machine learning and data science to reduce the dimensions in a dataset. While linear methods are generally less effective at dimensionality reduction than nonlinear methods, they can provide a linear relationship between the original data and the dimensionality-reduced representation, leading to better interpretability. In this research, we present a tied-weight autoencoder as a dimensionality reduction model with the merit of both linear and nonlinear methods. Although the tied-weight autoencoder is a nonlinear dimensionality reduction model, we approximate it to function as a linear model. This is achieved by removing the hidden layer units that are largely inactivated by the input data, while preserving the modelâs effectiveness. We evaluate the proposed model by comparing its performance with other linear and nonlinear models using benchmark datasets. Our results show that the proposed model performs comparably to the nonlinear model of a similar autoencoder structure to the proposed model. More importantly, we show that the proposed model outperforms the linear models in various metrics, including the mean square error, data reconstruction, and the classification of low-dimensional projections of the input data. Thus, our study provides general recommendations for best practices in dimensionality reduction.
- 5 November 2024
- Published by Springer Nature in Scientific Reports
- Vol. 14  (1) , 1-18
Open AccessA tied-weight autoencoder for the linear dimensionality reduction of sample data
Dimensionality reduction is a method used in machine learning and data science to reduce the dimensions in a dataset. While linear methods are generally less effective at dimensionality reduction than nonlinear methods, they can provide a linear relationship between the original data and the dimensionality-reduced representation, leading to better interpretability. In this research, we present a tied-weight autoencoder as a dimensionality reduction model with the merit of both linear and nonlinear methods. Although the tied-weight autoencoder is a nonlinear dimensionality reduction model, we approximate it to function as a linear model. This is achieved by removing the hidden layer units that are largely inactivated by the input data, while preserving the modelâs effectiveness. We evaluate the proposed model by comparing its performance with other linear and nonlinear models using benchmark datasets. Our results show that the proposed model performs comparably to the nonlinear model of a similar autoencoder structure to the proposed model. More importantly, we show that the proposed model outperforms the linear models in various metrics, including the mean square error, data reconstruction, and the classification of low-dimensional projections of the input data. Thus, our study provides general recommendations for best practices in dimensionality reduction.
- Open Access
- 3 October 2024
- Published by Springer Nature in Research Square
A method of identifying false positives in the variety-specific variant calling of rice
This study investigated the effect of variety (or subspecies) specificity on genetic variant calling using next-generation sequencing data from rice. Specifically, we used two major rice genome varieties, Indica and Japonica, to construct different variant calling models with varying compositions of samples from these two varieties. Our investigation revealed that divergence of samples from the reference sequence corresponded to increased variant prediction. Specifically, including samples that differed in variety from the reference sequence significantly increased the number of variants predicted. We used machine learning techniques to understand this phenomenon and evaluated the performance of different variant calling models based on the predicted variants. Our results indicated that a significant proportion of the additional predicted variants represented potential false positives, which was particularly accentuated when phylogenetically distinct accessions from the reference were included in the samples. To improve the accuracy of the predicted variants, we proposed a method to identify false positives and allow their exclusion if necessary. This proposed approach involved calling true variants from purebred (or typical) samples. We validated the effectiveness of this method across different variant calling models and demonstrated a significant reduction in false-positive predicted variants. As a practical application, we implemented the method on dbSNP of rice, a database of known rice variants, and demonstrated a means to identify false positives within dbSNP. Our study provides general recommendations for best practices in variety-specific variants calling for rice.
- 3 October 2024
- Published by Springer Nature in Research Square
Open AccessA method of identifying false positives in the variety-specific variant calling of rice
This study investigated the effect of variety (or subspecies) specificity on genetic variant calling using next-generation sequencing data from rice. Specifically, we used two major rice genome varieties, Indica and Japonica, to construct different variant calling models with varying compositions of samples from these two varieties. Our investigation revealed that divergence of samples from the reference sequence corresponded to increased variant prediction. Specifically, including samples that differed in variety from the reference sequence significantly increased the number of variants predicted. We used machine learning techniques to understand this phenomenon and evaluated the performance of different variant calling models based on the predicted variants. Our results indicated that a significant proportion of the additional predicted variants represented potential false positives, which was particularly accentuated when phylogenetically distinct accessions from the reference were included in the samples. To improve the accuracy of the predicted variants, we proposed a method to identify false positives and allow their exclusion if necessary. This proposed approach involved calling true variants from purebred (or typical) samples. We validated the effectiveness of this method across different variant calling models and demonstrated a significant reduction in false-positive predicted variants. As a practical application, we implemented the method on dbSNP of rice, a database of known rice variants, and demonstrated a means to identify false positives within dbSNP. Our study provides general recommendations for best practices in variety-specific variants calling for rice.
- Open Access
Early screening of potential breakthrough technologies with enhanced interpretability: A patent-specific hierarchical attention network model
Despite the usefulness of machine learning approaches for the early screening of potential breakthrough technologies, their practicality is often hindered by opaque models. To address this, we propose an interpretable machine learning approach to predicting future citation counts from patent texts using a patent-specific hierarchical attention network (PatentHAN) model. Central to this approach are (1) a patent-specific pre-trained language model, capturing the meanings of technical words in patent claims, (2) a hierarchical network structure, enabling detailed analysis at the claim level, and (3) a claim-wise self-attention mechanism, revealing pivotal claims during the screening process. A case study of 35,376 pharmaceutical patents demonstrates the effectiveness of our approach in early screening of potential breakthrough technologies while ensuring interpretability. Furthermore, we conduct additional analyses using different language models and claim types to examine the robustness of the approach. It is expected that the proposed approach will enhance expert-machine collaboration in identifying breakthrough technologies, providing new insight derived from text mining into technological value.
Open AccessEarly screening of potential breakthrough technologies with enhanced interpretability: A patent-specific hierarchical attention network model
Despite the usefulness of machine learning approaches for the early screening of potential breakthrough technologies, their practicality is often hindered by opaque models. To address this, we propose an interpretable machine learning approach to predicting future citation counts from patent texts using a patent-specific hierarchical attention network (PatentHAN) model. Central to this approach are (1) a patent-specific pre-trained language model, capturing the meanings of technical words in patent claims, (2) a hierarchical network structure, enabling detailed analysis at the claim level, and (3) a claim-wise self-attention mechanism, revealing pivotal claims during the screening process. A case study of 35,376 pharmaceutical patents demonstrates the effectiveness of our approach in early screening of potential breakthrough technologies while ensuring interpretability. Furthermore, we conduct additional analyses using different language models and claim types to examine the robustness of the approach. It is expected that the proposed approach will enhance expert-machine collaboration in identifying breakthrough technologies, providing new insight derived from text mining into technological value.
- Open Access
- 10 July 2024
- Published by Frontiers Media SA in Frontiers in Genetics
- Vol. 15, 1401470
Stacked generalization as a computational method for the genomic selection
As genomic selection emerges as a promising breeding method for both plants and animals, numerous methods have been introduced and applied to various real and simulated data sets. Research suggests that no single method is universally better than others; rather, performance is highly dependent on the characteristics of the data and the nature of the prediction task. This implies that each method has its strengths and weaknesses. In this study, we exploit this notion and propose a different approach. Rather than comparing multiple methods to determine the best one for a particular study, we advocate combining multiple methods to achieve better performance than each method in isolation. In pursuit of this goal, we introduce and develop a computational method of the stacked generalization within ensemble methods. In this method, the meta-model merges predictions from multiple base models to achieve improved performance. We applied this method to plant and animal data and compared its performance with currently available methods using standard performance metrics. We found that the proposed method yielded a lower or comparable mean squared error in predicting phenotypes compared to the current methods. In addition, the proposed method showed greater resistance to overfitting compared to the current methods. Further analysis included statistical hypothesis testing, which showed that the proposed method outperformed or matched the current methods. In summary, the proposed stacked generalization integrates currently available methods to achieve stable and better performance. In this context, our study provides general recommendations for effective practices in genomic selection.
- 10 July 2024
- Published by Frontiers Media SA in Frontiers in Genetics
- Vol. 15, 1401470
Open AccessStacked generalization as a computational method for the genomic selection
As genomic selection emerges as a promising breeding method for both plants and animals, numerous methods have been introduced and applied to various real and simulated data sets. Research suggests that no single method is universally better than others; rather, performance is highly dependent on the characteristics of the data and the nature of the prediction task. This implies that each method has its strengths and weaknesses. In this study, we exploit this notion and propose a different approach. Rather than comparing multiple methods to determine the best one for a particular study, we advocate combining multiple methods to achieve better performance than each method in isolation. In pursuit of this goal, we introduce and develop a computational method of the stacked generalization within ensemble methods. In this method, the meta-model merges predictions from multiple base models to achieve improved performance. We applied this method to plant and animal data and compared its performance with currently available methods using standard performance metrics. We found that the proposed method yielded a lower or comparable mean squared error in predicting phenotypes compared to the current methods. In addition, the proposed method showed greater resistance to overfitting compared to the current methods. Further analysis included statistical hypothesis testing, which showed that the proposed method outperformed or matched the current methods. In summary, the proposed stacked generalization integrates currently available methods to achieve stable and better performance. In this context, our study provides general recommendations for effective practices in genomic selection.
- 30 May 2024
- Published by Springer Nature in Journal of the Korean Physical Society
- Vol. 85  (2) , 201-211
A computational model for sample dependence in hypothesis testing of genome data
- 30 May 2024
- Published by Springer Nature in Journal of the Korean Physical Society
- Vol. 85  (2) , 201-211
A computational model for sample dependence in hypothesis testing of genome data