Yue Wan
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
Research Subjects
Yue Wan has a total of 18 co-authors. Here are the top co-authors by number of shared publications:
- Xiaowei Jia
Rutgers University, New Brunswick, NJ, USA
4 shared publications - Chang-Yu Hsieh
Zhejiang University
2 shared publications Jialu Wu
Innovation Institute for Artificial Intelligence in Medicine of Zhejiang University, College of Pharmaceutical Sciences, Zhejiang University, Hangzhou, China
2 shared publications- Na Du
School of Computing and Information, University of Pittsburgh, Pittsburgh, Pennsylvania, USA
2 shared publications Shengyu Zhang
Tencent Quantum Laboratory, Tencent, Shenzhen 518057, China
2 shared publications- Shihong Ling
Department of Informatics and Networked Systems, School of Computing and Information, University of Pittsburgh, Pittsburgh, Pennsylvania, USA
2 shared publications
Latest Publications
- Open Access
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 9882-9893
Accelerating MHC-II Epitope Discovery via Multi-Scale Prediction in Antigen Presentation
Antigenic epitopes presented by major histocompatibility complex II (MHC-II) proteins plays an essential role in immunotherapy. However, compared to the more widely studied MHC-I in computational immunotherapy, the study of MHC-II antigenic epitope poses significantly more challenges due to its complex binding specificity and ambiguous motif patterns. Consequently, existing datasets for MHC-II interactions are smaller and less standardized than those available for MHC-I. To address these challenges, we present a well-curated dataset derived from the Immune Epitope Database (IEDB) and other public sources. It not only extends and standardizes existing peptide–MHC-II datasets, but also introduces a novel antigen–MHC-II dataset with richer biological context. Leveraging this dataset, we formulate three major machine learning (ML) tasks of peptide binding, peptide presentation, and antigen presentation, which progressively capture the broader biological processes within the MHC-II antigen presentation pathway. We further employ a multi-scale evaluation framework to benchmark existing models, along with a comprehensive analysis over various modeling designs to this problem with a modular framework. Overall, this work serves as a valuable resource for advancing computational immunotherapy, providing a foundation for future research in ML guided epitope discovery and predictive modeling of immune responses.
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 9882-9893
Open AccessAccelerating MHC-II Epitope Discovery via Multi-Scale Prediction in Antigen Presentation
Antigenic epitopes presented by major histocompatibility complex II (MHC-II) proteins plays an essential role in immunotherapy. However, compared to the more widely studied MHC-I in computational immunotherapy, the study of MHC-II antigenic epitope poses significantly more challenges due to its complex binding specificity and ambiguous motif patterns. Consequently, existing datasets for MHC-II interactions are smaller and less standardized than those available for MHC-I. To address these challenges, we present a well-curated dataset derived from the Immune Epitope Database (IEDB) and other public sources. It not only extends and standardizes existing peptide–MHC-II datasets, but also introduces a novel antigen–MHC-II dataset with richer biological context. Leveraging this dataset, we formulate three major machine learning (ML) tasks of peptide binding, peptide presentation, and antigen presentation, which progressively capture the broader biological processes within the MHC-II antigen presentation pathway. We further employ a multi-scale evaluation framework to benchmark existing models, along with a comprehensive analysis over various modeling designs to this problem with a modular framework. Overall, this work serves as a valuable resource for advancing computational immunotherapy, providing a foundation for future research in ML guided epitope discovery and predictive modeling of immune responses.
- Open Access
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-20
When to Explain: Modeling User Need for Explanations in Real-World Autonomous Driving
The integration of artificial intelligence into autonomous vehicles (AVs) raises transparency challenges that can hinder user acceptance and experience. To address when users need AV explanations, we created a large-scale dataset of 3327 diverse driving scenarios, each paired with a user-friendly explanation, and conducted an online study to survey when users need explanations. Using both scenario and user-related factors, our best-performing tree-ensemble models predicted explanation need with great performance (F1=0.72, AUC=0.82). SHAP analyses revealed that while both user- and scenario-related factors matter, factors directly related to driving (AV driving style, AV action, event cause, annual mileage, human driving style) were more contributive than general demographics and environmental factors. Our study delivers a comprehensively annotated dataset that underpins future human-AV interaction research, an explainable model that reliably predicts explanation needs, and valuable insights to inform the design of adaptive AV interfaces for superior user experiences.
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-20
Open AccessWhen to Explain: Modeling User Need for Explanations in Real-World Autonomous Driving
The integration of artificial intelligence into autonomous vehicles (AVs) raises transparency challenges that can hinder user acceptance and experience. To address when users need AV explanations, we created a large-scale dataset of 3327 diverse driving scenarios, each paired with a user-friendly explanation, and conducted an online study to survey when users need explanations. Using both scenario and user-related factors, our best-performing tree-ensemble models predicted explanation need with great performance (F1=0.72, AUC=0.82). SHAP analyses revealed that while both user- and scenario-related factors matter, factors directly related to driving (AV driving style, AV action, event cause, annual mileage, human driving style) were more contributive than general demographics and environmental factors. Our study delivers a comprehensively annotated dataset that underpins future human-AV interaction research, an explainable model that reliably predicts explanation needs, and valuable insights to inform the design of adaptive AV interfaces for superior user experiences.
- Open Access
- 6 January 2025
- Published by Springer Nature in Nature Communications
- Vol. 16 (1) , 1-13
Multi-channel learning for integrating structural hierarchies into context-dependent molecular representation
Reliable molecular property prediction is essential for various scientific endeavors and industrial applications, such as drug discovery. However, the data scarcity, combined with the highly non-linear causal relationships between physicochemical and biological properties and conventional molecular featurization schemes, complicates the development of robust molecular machine learning models. Self-supervised learning (SSL) has emerged as a popular solution, utilizing large-scale, unannotated molecular data to learn a foundational representation of chemical space that might be advantageous for downstream tasks. Yet, existing molecular SSL methods largely overlook chemical knowledge, including molecular structure similarity, scaffold composition, and the context-dependent aspects of molecular properties when operating over the chemical space. They also struggle to learn the subtle variations in structure-activity relationship. This paper introduces a multi-channel pre-training framework that learns robust and generalizable chemical knowledge. It leverages the structural hierarchy within the molecule, embeds them through distinct pre-training tasks across channels, and aggregates channel information in a task-specific manner during fine-tuning. Our approach demonstrates competitive performance across various molecular property benchmarks and offers strong advantages in particularly challenging yet ubiquitous scenarios like activity cliffs.
- 6 January 2025
- Published by Springer Nature in Nature Communications
- Vol. 16 (1) , 1-13
Open AccessMulti-channel learning for integrating structural hierarchies into context-dependent molecular representation
Reliable molecular property prediction is essential for various scientific endeavors and industrial applications, such as drug discovery. However, the data scarcity, combined with the highly non-linear causal relationships between physicochemical and biological properties and conventional molecular featurization schemes, complicates the development of robust molecular machine learning models. Self-supervised learning (SSL) has emerged as a popular solution, utilizing large-scale, unannotated molecular data to learn a foundational representation of chemical space that might be advantageous for downstream tasks. Yet, existing molecular SSL methods largely overlook chemical knowledge, including molecular structure similarity, scaffold composition, and the context-dependent aspects of molecular properties when operating over the chemical space. They also struggle to learn the subtle variations in structure-activity relationship. This paper introduces a multi-channel pre-training framework that learns robust and generalizable chemical knowledge. It leverages the structural hierarchy within the molecule, embeds them through distinct pre-training tasks across channels, and aggregates channel information in a task-specific manner during fine-tuning. Our approach demonstrates competitive performance across various molecular property benchmarks and offers strong advantages in particularly challenging yet ubiquitous scenarios like activity cliffs.
- Open Access
- 11 March 2024
- Published by Association for Computing Machinery (ACM)
- p. 443-451
Improving Explainable Object-induced Model through Uncertainty for Automated Vehicles
The rapid evolution of automated vehicles (AVs) has the potential to provide safer, more efficient, and comfortable travel options. However, these systems face challenges regarding reliability in complex driving scenarios. Recent explainable AV architectures neglect crucial information related to inherent uncertainties while providing explanations for actions. To overcome such challenges, our study builds upon the "object-induced" model approach that prioritizes the role of objects in scenes for decision-making and integrates uncertainty assessment into the decision-making process using an evidential deep learning paradigm with a Beta prior. Additionally, we explore several advanced training strategies guided by uncertainty, including uncertainty-guided data reweighting and augmentation. Leveraging the BDD-OIA dataset, our findings underscore that the model, through these enhancements, not only offers a clearer comprehension of AV decisions and their underlying reasoning but also surpasses existing baselines across a broad range of scenarios.
- 11 March 2024
- Published by Association for Computing Machinery (ACM)
- p. 443-451
Open AccessImproving Explainable Object-induced Model through Uncertainty for Automated Vehicles
The rapid evolution of automated vehicles (AVs) has the potential to provide safer, more efficient, and comfortable travel options. However, these systems face challenges regarding reliability in complex driving scenarios. Recent explainable AV architectures neglect crucial information related to inherent uncertainties while providing explanations for actions. To overcome such challenges, our study builds upon the "object-induced" model approach that prioritizes the role of objects in scenes for decision-making and integrates uncertainty assessment into the decision-making process using an evidential deep learning paradigm with a Beta prior. Additionally, we explore several advanced training strategies guided by uncertainty, including uncertainty-guided data reweighting and augmentation. Leveraging the BDD-OIA dataset, our findings underscore that the model, through these enhancements, not only offers a clearer comprehension of AV decisions and their underlying reasoning but also surpasses existing baselines across a broad range of scenarios.
- Open Access
- 11 November 2022
- Published by Elsevier in Acta Pharmaceutica Sinica B
- Vol. 13 (6) , 2572-2584
MF-SuP-pKa: Multi-fidelity modeling with subgraph pooling mechanism for pKa prediction
- 11 November 2022
- Published by Elsevier in Acta Pharmaceutica Sinica B
- Vol. 13 (6) , 2572-2584
Open AccessMF-SuP-pKa: Multi-fidelity modeling with subgraph pooling mechanism for pKa prediction
- Open Access
- 7 December 2021
- Published by American Chemical Society (ACS) in ChemRxiv
NeuralTPL: a deep learning approach for efficient reactionspace exploration
Computer-aided synthesis planning (CASP) has been helping chemists to synthesize novel molecules at an accelerated pace. The recent integration of deep learning with CASP has opened up new avenues for digitizing and exploring the vastly unknown chemical space, and has led to high expectations for fully automated synthesis plannings using machine-discovered novel reactions in the "future". Despite many progresses in the past few years, most deep-learning methods only focus on improving few aspects of CASP (e.g., top-k accuracy). In this work, we target specifically the efficiency of reaction space exploration and its impact on CASP. We propose NeuralTPL, a template-oriented generative approach, that performs impressively across a range of evaluation metrics including chemical validity, diversity, and novelty for various tasks in CASP. In addition, our Transformer-based model bears the potential to learn the core reaction transformation as it can efficiently explore the reaction space. We then perform several experiments and conduct a thorough analysis regarding the three metrics and demonstrate its chemical value for improving the existing deep-learning-driven CASP algorithms.
- 7 December 2021
- Published by American Chemical Society (ACS) in ChemRxiv
Open AccessNeuralTPL: a deep learning approach for efficient reactionspace exploration
Computer-aided synthesis planning (CASP) has been helping chemists to synthesize novel molecules at an accelerated pace. The recent integration of deep learning with CASP has opened up new avenues for digitizing and exploring the vastly unknown chemical space, and has led to high expectations for fully automated synthesis plannings using machine-discovered novel reactions in the "future". Despite many progresses in the past few years, most deep-learning methods only focus on improving few aspects of CASP (e.g., top-k accuracy). In this work, we target specifically the efficiency of reaction space exploration and its impact on CASP. We propose NeuralTPL, a template-oriented generative approach, that performs impressively across a range of evaluation metrics including chemical validity, diversity, and novelty for various tasks in CASP. In addition, our Transformer-based model bears the potential to learn the core reaction transformation as it can efficiently explore the reaction space. We then perform several experiments and conduct a thorough analysis regarding the three metrics and demonstrate its chemical value for improving the existing deep-learning-driven CASP algorithms.