Kewei Li
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Kewei Li has a total of 57 co-authors. Here are the top co-authors by number of shared publications:
- Fengfeng Zhou
College of Computer Science and Technology Jilin University 130012 Changchun China
9 shared publications Lan Huang
Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, Jilin University, Changchun, China
5 shared publications- Lan Huang
Jilin University
3 shared publications - Meiyu Duan
College of Information Science and Technology, Dalian Maritime University, Dalian, 116026, Liaoning, China
3 shared publications Qian Yang
Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, Jilin University , Changchun, Jilin 130012, China
2 shared publicationsYusi Fan
College of Computer Science and Technology Jilin University 130012 Changchun China
2 shared publications
Latest Publications
- Open Access
- 11 April 2026
- Published by Springer Nature in BioData Mining
- Vol. 19 (1)
SeqHIVE: a Python package to convert the biological sequences to informative vectors for sequence property predictions
Sequence-based analysis and prediction form a cornerstone of bioinformatics investigations of the sequence-structure-function paradigm across DNA, RNA, and
- 11 April 2026
- Published by Springer Nature in BioData Mining
- Vol. 19 (1)
Open AccessSeqHIVE: a Python package to convert the biological sequences to informative vectors for sequence property predictions
Sequence-based analysis and prediction form a cornerstone of bioinformatics investigations of the sequence-structure-function paradigm across DNA, RNA, and
- Open Access
GrifFinNet: A Graph-Relation Integrated Transformer for Financial Predictions
Predicting stock returns remains a central challenge in quantitative finance, transitioning from traditional statistical methods to contemporary deep learning techniques. However, many current models struggle with effectively capturing spatio-temporal dynamics and integrating multiple relational data sources. This study proposes GrifFinNet, a Graph-Relation Integrated Transformer for Financial Predictions, which combines multi-relational graph modeling with Transformer-based temporal encoding. GrifFinNet constructs inter-stock relation graphs based on industry sectors and institutional ownership, and incorporates an adaptive gating mechanism to dynamically integrate relational data in response to changing market conditions. This approach enables the model to jointly capture spatial dependencies and temporal patterns, offering a comprehensive representation of market dynamics. Extensive experiments on two Chinese A-share indices show that GrifFinNet consistently outperforms several baseline models and provides valuable, interpretable insights into financial market behavior. The code and data are available at: https://www.healthinformaticslab.org/supp/.
Open AccessGrifFinNet: A Graph-Relation Integrated Transformer for Financial Predictions
Predicting stock returns remains a central challenge in quantitative finance, transitioning from traditional statistical methods to contemporary deep learning techniques. However, many current models struggle with effectively capturing spatio-temporal dynamics and integrating multiple relational data sources. This study proposes GrifFinNet, a Graph-Relation Integrated Transformer for Financial Predictions, which combines multi-relational graph modeling with Transformer-based temporal encoding. GrifFinNet constructs inter-stock relation graphs based on industry sectors and institutional ownership, and incorporates an adaptive gating mechanism to dynamically integrate relational data in response to changing market conditions. This approach enables the model to jointly capture spatial dependencies and temporal patterns, offering a comprehensive representation of market dynamics. Extensive experiments on two Chinese A-share indices show that GrifFinNet consistently outperforms several baseline models and provides valuable, interpretable insights into financial market behavior. The code and data are available at: https://www.healthinformaticslab.org/supp/.
- 29 February 2024
- Published by Elsevier in Analytical Biochemistry
- Vol. 689, 115495
GANSamples-ac4C: Enhancing ac4C site prediction via generative adversarial networks and transfer learning
- 29 February 2024
- Published by Elsevier in Analytical Biochemistry
- Vol. 689, 115495
GANSamples-ac4C: Enhancing ac4C site prediction via generative adversarial networks and transfer learning
- Open Access
- 29 February 2024
- Published by Oxford University Press (OUP) in Bioinformatics
- Vol. 40 (4)
MolFeSCue: enhancing molecular property prediction in data-limited and imbalanced contexts using few-shot and contrastive learning
Motivation: Predicting molecular properties is a pivotal task in various scientific domains, including drug discovery, material science, and computational chemistry. This problem is often hindered by the lack of annotated data and imbalanced class distributions, which pose significant challenges in developing accurate and robust predictive models. Results: This study tackles these issues by employing pretrained molecular models within a few-shot learning framework. A novel dynamic contrastive loss function is utilized to further improve model performance in the situation of class imbalance. The proposed MolFeSCue framework not only facilitates rapid generalization from minimal samples, but also employs a contrastive loss function to extract meaningful molecular representations from imbalanced datasets. Extensive evaluations and comparisons of MolFeSCue and state-of-the-art algorithms have been conducted on multiple benchmark datasets, and the experimental data demonstrate our algorithm’s effectiveness in molecular representations and its broad applicability across various pretrained models. Our findings underscore MolFeSCues potential to accelerate advancements in drug discovery. Availability and implementation: We have made all the source code utilized in this study publicly accessible via GitHub at http://www.healthinformaticslab.org/supp/ or https://github.com/zhangruochi/MolFeSCue. The code (MolFeSCue-v1-00) is also available as the supplementary file of this paper.
- 29 February 2024
- Published by Oxford University Press (OUP) in Bioinformatics
- Vol. 40 (4)
Open AccessMolFeSCue: enhancing molecular property prediction in data-limited and imbalanced contexts using few-shot and contrastive learning
Motivation: Predicting molecular properties is a pivotal task in various scientific domains, including drug discovery, material science, and computational chemistry. This problem is often hindered by the lack of annotated data and imbalanced class distributions, which pose significant challenges in developing accurate and robust predictive models. Results: This study tackles these issues by employing pretrained molecular models within a few-shot learning framework. A novel dynamic contrastive loss function is utilized to further improve model performance in the situation of class imbalance. The proposed MolFeSCue framework not only facilitates rapid generalization from minimal samples, but also employs a contrastive loss function to extract meaningful molecular representations from imbalanced datasets. Extensive evaluations and comparisons of MolFeSCue and state-of-the-art algorithms have been conducted on multiple benchmark datasets, and the experimental data demonstrate our algorithm’s effectiveness in molecular representations and its broad applicability across various pretrained models. Our findings underscore MolFeSCues potential to accelerate advancements in drug discovery. Availability and implementation: We have made all the source code utilized in this study publicly accessible via GitHub at http://www.healthinformaticslab.org/supp/ or https://github.com/zhangruochi/MolFeSCue. The code (MolFeSCue-v1-00) is also available as the supplementary file of this paper.
- Open Access
- 18 November 2023
- Published by MDPI AG in Electronics
- Vol. 12 (22) , 4696
DanceTrend: An Integration Framework of Video-Based Body Action Recognition and Color Space Features for Dance Popularity Prediction
Background: With the rise of user-generated content (UGC) platforms, we are witnessing an unprecedented surge in data. Among various content types, dance videos have emerged as a potent medium for artistic and emotional expression in the Web 2.0 era. Such videos have increasingly become a significant means for users to captivate audiences and amplify their online influence. Given this, predicting the popularity of dance videos on UGC platforms has drawn significant attention. Methods: This study postulates that body movement features play a pivotal role in determining the future popularity of dance videos. To test this hypothesis, we design a robust prediction framework DanceTrend to integrate the body movement features with color space information for dance popularity prediction. We utilize the jazz dance videos from the comprehensive AIST++ street dance dataset and segment each dance routine video into individual movements. AlphaPose was chosen as the human posture detection algorithm to help us obtain human motion features from the videos. Then, the ST-GCN (Spatial Temporal Graph Convolutional Network) is harnessed to train the movement classification models. These pre-trained ST-GCN models are applied to extract body movement features from our curated Bilibili dance video dataset. Alongside these body movement features, we integrate color space attributes and user metadata for the final dance popularity prediction task. Results: The experimental results endorse our initial hypothesis that the body movement features significantly influence the future popularity of dance videos. A comprehensive evaluation of various feature fusion strategies and diverse classifiers discern that a pre–post fusion hybrid strategy coupled with the XGBoost classifier yields the most optimal outcomes for our dataset.
- 18 November 2023
- Published by MDPI AG in Electronics
- Vol. 12 (22) , 4696
Open AccessDanceTrend: An Integration Framework of Video-Based Body Action Recognition and Color Space Features for Dance Popularity Prediction
Background: With the rise of user-generated content (UGC) platforms, we are witnessing an unprecedented surge in data. Among various content types, dance videos have emerged as a potent medium for artistic and emotional expression in the Web 2.0 era. Such videos have increasingly become a significant means for users to captivate audiences and amplify their online influence. Given this, predicting the popularity of dance videos on UGC platforms has drawn significant attention. Methods: This study postulates that body movement features play a pivotal role in determining the future popularity of dance videos. To test this hypothesis, we design a robust prediction framework DanceTrend to integrate the body movement features with color space information for dance popularity prediction. We utilize the jazz dance videos from the comprehensive AIST++ street dance dataset and segment each dance routine video into individual movements. AlphaPose was chosen as the human posture detection algorithm to help us obtain human motion features from the videos. Then, the ST-GCN (Spatial Temporal Graph Convolutional Network) is harnessed to train the movement classification models. These pre-trained ST-GCN models are applied to extract body movement features from our curated Bilibili dance video dataset. Alongside these body movement features, we integrate color space attributes and user metadata for the final dance popularity prediction task. Results: The experimental results endorse our initial hypothesis that the body movement features significantly influence the future popularity of dance videos. A comprehensive evaluation of various feature fusion strategies and diverse classifiers discern that a pre–post fusion hybrid strategy coupled with the XGBoost classifier yields the most optimal outcomes for our dataset.
- 27 June 2023
- Published by Elsevier in Computers in Biology and Medicine
- Vol. 163, 107187
OCMR: A comprehensive framework for optical chemical molecular recognition
- 27 June 2023
- Published by Elsevier in Computers in Biology and Medicine
- Vol. 163, 107187
OCMR: A comprehensive framework for optical chemical molecular recognition
- Open Access
Transcriptional Dysregulations of Seven Non-Differentially Expressed Genes as Biomarkers of Metastatic Colon Cancer
Background: Colon cancer (CC) is common, and the mortality rate greatly increases as the disease progresses to the metastatic stage. Early detection of metastatic colon cancer (mCC) is crucial for reducing the mortality rate. Most previous studies have focused on the top-ranked differentially expressed transcriptomic biomarkers between mCC and primary CC while ignoring non-differentially expressed genes. Results: This study proposed that the complicated inter-feature correlations could be quantitatively formulated as a complementary transcriptomic view. We used a regression model to formulate the correlation between the expression levels of a messenger RNA (mRNA) and its regulatory transcription factors (TFs). The change between the predicted and real expression levels of a query mRNA was defined as the mqTrans value in the given sample, reflecting transcription regulatory changes compared with the model-training samples. A dark biomarker in mCC is defined as an mRNA gene that is non-differentially expressed in mCC but demonstrates mqTrans values significantly associated with mCC. This study detected seven dark biomarkers using 805 samples from three independent datasets. Evidence from the literature supports the role of some of these dark biomarkers. Conclusions: This study presented a complementary high-dimensional analysis procedure for transcriptome-based biomarker investigations with a case study on mCC.
Open AccessTranscriptional Dysregulations of Seven Non-Differentially Expressed Genes as Biomarkers of Metastatic Colon Cancer
Background: Colon cancer (CC) is common, and the mortality rate greatly increases as the disease progresses to the metastatic stage. Early detection of metastatic colon cancer (mCC) is crucial for reducing the mortality rate. Most previous studies have focused on the top-ranked differentially expressed transcriptomic biomarkers between mCC and primary CC while ignoring non-differentially expressed genes. Results: This study proposed that the complicated inter-feature correlations could be quantitatively formulated as a complementary transcriptomic view. We used a regression model to formulate the correlation between the expression levels of a messenger RNA (mRNA) and its regulatory transcription factors (TFs). The change between the predicted and real expression levels of a query mRNA was defined as the mqTrans value in the given sample, reflecting transcription regulatory changes compared with the model-training samples. A dark biomarker in mCC is defined as an mRNA gene that is non-differentially expressed in mCC but demonstrates mqTrans values significantly associated with mCC. This study detected seven dark biomarkers using 805 samples from three independent datasets. Evidence from the literature supports the role of some of these dark biomarkers. Conclusions: This study presented a complementary high-dimensional analysis procedure for transcriptome-based biomarker investigations with a case study on mCC.
- Open Access
Integration of lncRNAs, Protein-Coding Genes and Pathology Images for Detecting Metastatic Melanoma
Melanoma is a lethal skin disease that develops from moles. This study aimed to integrate multimodal data to predict metastatic melanoma, which is highly aggressive and difficult to treat. The proposed EnsembleSKCM method evaluated the prediction performances of long noncoding RNAs (lncRNAs), protein-coding messenger genes (mRNAs) and pathology images (images) for metastatic melanoma. Feature selection was used to screen for metastatic biomarkers in the lncRNA and mRNA datasets. The integrated EnsembleSKCM model was built based on the weighted results of the lncRNA-, mRNA- and image-based models. EnsembleSKCM achieved 0.9444 in the prediction accuracy of metastatic melanoma and outperformed the single-modal prediction models based on the lncRNA, mRNA and image data. The experimental data suggest the importance of integrating the complementary information from the three data modalities. WGCNA was used to analyze the relationship of molecular-level features and image features, and the results show connections between them. Another cohort was used to validate our prediction.
Open AccessIntegration of lncRNAs, Protein-Coding Genes and Pathology Images for Detecting Metastatic Melanoma
Melanoma is a lethal skin disease that develops from moles. This study aimed to integrate multimodal data to predict metastatic melanoma, which is highly aggressive and difficult to treat. The proposed EnsembleSKCM method evaluated the prediction performances of long noncoding RNAs (lncRNAs), protein-coding messenger genes (mRNAs) and pathology images (images) for metastatic melanoma. Feature selection was used to screen for metastatic biomarkers in the lncRNA and mRNA datasets. The integrated EnsembleSKCM model was built based on the weighted results of the lncRNA-, mRNA- and image-based models. EnsembleSKCM achieved 0.9444 in the prediction accuracy of metastatic melanoma and outperformed the single-modal prediction models based on the lncRNA, mRNA and image data. The experimental data suggest the importance of integrating the complementary information from the three data modalities. WGCNA was used to analyze the relationship of molecular-level features and image features, and the results show connections between them. Another cohort was used to validate our prediction.
- Open Access
- 5 May 2022
- Published by Oxford University Press (OUP) in Briefings in Bioinformatics
- Vol. 23 (5)
HLAB: learning the BiLSTM features from the ProtBert-encoded proteins for the class I HLA-peptide binding prediction
Human Leukocyte Antigen (HLA) is a type of molecule residing on the surfaces of most human cells and exerts an essential role in the immune system responding to the invasive items. The T cell antigen receptors may recognize the HLA-peptide complexes on the surfaces of cancer cells and destroy these cancer cells through toxic T lymphocytes. The computational determination of HLA-binding peptides will facilitate the rapid development of cancer immunotherapies. This study hypothesized that the natural language processing-encoded peptide features may be further enriched by another deep neural network. The hypothesis was tested with the Bi-directional Long Short-Term Memory-extracted features from the pretrained Protein Bidirectional Encoder Representations from Transformers-encoded features of the class I HLA (HLA-I)-binding peptides. The experimental data showed that our proposed HLAB feature engineering algorithm outperformed the existing ones in detecting the HLA-I-binding peptides. The extensive evaluation data show that the proposed HLAB algorithm outperforms all the seven existing studies on predicting the peptides binding to the HLA-A*01:01 allele in AUC and achieves the best average AUC values on the six out of the seven k-mers (k=8,9,...,14, respectively represent the prediction task of a polypeptide consisting of k amino acids) except for the 9-mer prediction tasks. The source code and the fine-tuned feature extraction models are available at http://www.healthinformaticslab.org/supp/resources.php.
- 5 May 2022
- Published by Oxford University Press (OUP) in Briefings in Bioinformatics
- Vol. 23 (5)
Open AccessHLAB: learning the BiLSTM features from the ProtBert-encoded proteins for the class I HLA-peptide binding prediction
Human Leukocyte Antigen (HLA) is a type of molecule residing on the surfaces of most human cells and exerts an essential role in the immune system responding to the invasive items. The T cell antigen receptors may recognize the HLA-peptide complexes on the surfaces of cancer cells and destroy these cancer cells through toxic T lymphocytes. The computational determination of HLA-binding peptides will facilitate the rapid development of cancer immunotherapies. This study hypothesized that the natural language processing-encoded peptide features may be further enriched by another deep neural network. The hypothesis was tested with the Bi-directional Long Short-Term Memory-extracted features from the pretrained Protein Bidirectional Encoder Representations from Transformers-encoded features of the class I HLA (HLA-I)-binding peptides. The experimental data showed that our proposed HLAB feature engineering algorithm outperformed the existing ones in detecting the HLA-I-binding peptides. The extensive evaluation data show that the proposed HLAB algorithm outperforms all the seven existing studies on predicting the peptides binding to the HLA-A*01:01 allele in AUC and achieves the best average AUC values on the six out of the seven k-mers (k=8,9,...,14, respectively represent the prediction task of a polypeptide consisting of k amino acids) except for the 9-mer prediction tasks. The source code and the fine-tuned feature extraction models are available at http://www.healthinformaticslab.org/supp/resources.php.