Yiquan Wang(王一权)

Personal Profile

Yiquan Wang is an undergraduate student at Xinjiang University and a joint-training scholar in the Tsien Excellence in Engineering Program at Tsinghua University & X-Institute. His research focuses on AI for Science, at the intersection of deep learning, computational biology, and bioinformatics. He is dedicated to developing advanced computational models to investigate complex biological systems, with research topics spanning protein function prediction, biological sequence representation, protein design optimization, and protein dynamics. His work has been published in journals like the Journal of Chemical Information and Modeling and at top-tier conferences in artificial intelligence and bioinformatics, including ICLR, ICML, AAAI, and BIBM.

Education

Undergraduate： Xinjiang University School of Mathematics and System Sciences--National Base for Research and Teaching Talents in Basic Sciences "Mathematics"--Major in Mathematics and Applied Mathematics , 2023.09-2027.06

• Main Courses: Mathematical Analysis, Advanced Algebra, Analytical Geometry, Partial Differential Equations, Functional Analysis, etc. See Mathematics Base Introduction

Joint Training： Tsinghua University Tsien Excellence in Engineering Program - Shenzhen X-Institute , 2024.06-2027.06

• Main Research: ESRT, ORIC, SURF See Qian Class Step-by-Step Training Program

Visiting Student： Shenzhen Bay Laboratory-Institute of Neurological and Psychiatric Disorders-Wen Yuan Research Group, 2025.07-2025.09

• Research Interests: Neuroscience, Biochemistry, Computational Biology

Research Experience

Selected Papers

1. Wang, Y., Cai, M., Dong, Y., et al. (2025). From Signal to Symphony: Exploring 2D Sequence Representations for Protein Function Prediction. Journal of Chemical Information and Modeling (JCR Q1, CAS Q2 Top).

2. Wang, Y., Ma, Y., Chang, Y., et al. (2025). Diffusion Models at the Drug Discovery Frontier: A Review on Generating Small Molecules versus Therapeutic Peptides. biology (JCR Q1, CAS Q2).

3. Wang, Y., Zai, J., Liu, Z., et al. (2025). Resilient AI Infrastructure by Design: A Spatially-Aware Framework for Tolerating Clustered Failures. In 4th Annual AAAI Workshop on AI to Accelerate Science and Engineering (AI2ASE).

4. Wang, Y., Cai, M., Zhang, J., et al. (2025). Adaptive Decision-Making in Multi-Stage Production: A Framework for Cost Optimization under Sampling Uncertainty. Applied Operations and Analytics.

5. Wang, Y.*, Cai, M., & Huang, T. Y. (2025). AI for disease prediction: Performance insights and key limitations. Journal of Clinical Neuroscience, 138, 111360. (letter, JCR Q3, CAS Q4)

6. Wang, Y.*, Huang, T. Y., Gao, Q., & Zhang, J. (2025). HeDA: An Intelligent Agent System for Heatwave Risk Discovery through Automated Knowledge Graph Construction and Multi-layer Risk Propagation Analysis. arXiv preprint arXiv:2509.25112.

7. Wang, X., Wang, Y., & Huang, T. Y. (2025). Crypto-ncRNA: Non-coding RNA (ncRNA) Based Encryption Algorithm. ICLR 2025 Workshop. (Co-first author).

8. Wang, X., Wang, Y.*, Huang, T. Y., et al. (2025). Octopus Inspired Optimization (OIO): A Hierarchical Framework for Navigating Protein Fitness Landscapes. In 2025 IEEE International Conference on Bioinformatics and Biomedicine (BIBM). IEEE. (CCF-B, Co-first author).

9. Wang, X., Wang, Y.*, & Pan, J. (2025). Digital Art Creation and Copyright Protection in Pollock Style Using GANs, Fractal Analysis, and NFT Generation. ICLR 2025 Workshop. (Co-first author).

10. Wang, Y.*, Zhang, J., & Chang, Y. (2024, November). A probability prediction model for flood disasters based on Multi-layer Perceptron. In Journal of Physics: Conference Series (Vol. 2905, No. 1, p. 012003). IOP Publishing.

Note: *Corresponding author

All articles on Google Scholar.

Academic Participation

Reviewer

• NeurIPS 2025 AI for Science Workshop link

• NeurIPS 2025 MATH-AI Workshop link

• ICML 2025 Workshop on AI for Math link

• ICLR 2025 Workshop on AI for Nucleic Acids link

• ICLR 2025 Workshop: The 1st Workshop on GenAI Watermarking link

• Mini-Reviews in Medicinal Chemistry link

• Current Science link

• F1000 Research link

Research Projects

1. Tsinghua University Qian Xuesen Class ESRT: From Signal to Symphony: Exploring 2D Sequence Representations for Protein Function Prediction, 2024.8-2025.10

   • Abstract: Predicting protein function from its primary sequence is a fundamental challenge in computational biology. While deep learning has excelled, the optimal representation of sequence data remains an open question. This study explores protein sonification---the conversion of amino acid sequences into 2D spectrograms---as a representation for this task. To facilitate this investigation, we developed a benchmark dataset of 18,000 sequences spanning 12 functionally diverse protein classes. Our systematic evaluation suggests that the structural transformation from a 1D sequence to a 2D spectrogram may be a key contributor to the model's predictive performance. This observation is supported by ablation studies where models using either purely visual or acoustic features from the spectrogram demonstrated effective standalone performance, suggesting that the representation itself is a key source of this capability. For instance, a model using a sonification map without explicit biophysical meaning achieved 81.08% accuracy, while our biophysically-informed model reached 84.00%, indicating that such domain knowledge may offer a modest performance benefit. When trained from scratch on our dataset, our fusion model achieved performance comparable to or slightly exceeding that of standard transformer architectures like ESM-2 and ProtBERT, suggesting its potential for data efficiency in this specific context. The model's potential for generalizability was further supported by its performance on the external CARE enzyme classification benchmark, where it achieved 90.44% accuracy. Finally, as a proof-of-concept, we explore the utility of our encoding to guide a diffusion model in generating novel GFP variants, which were assessed for structural viability using computational methods. Our work provides evidence suggesting that the utility of sonification in this context may stem largely from its representational structure, offering a perspective on feature engineering for biological sequences.

   • Keywords: Protein Function Prediction, Sonification, Biological Signal Processing, Sequence Representation, Generative Protein Design

   • Project Address:GitHub/Symphony_of_Fate      Supervised by Prof. Kai Wei.

2. 2025 College Student Innovation Training Project (National Level Project; Student Advisor): Copy Number Variation Conditional Diffusion Model: For Alzheimer's Disease Risk Assessment, 2025.4-2026.4

   • Abstract: This project aims to integrate copy number variation (CNV) features from whole-genome sequencing data with multi-dimensional clinical data such as metabolic indicators. Leveraging the success of diffusion models in processing high-dimensional simulation data and protein phenotype prediction, we will construct a comprehensive framework consisting of CNV feature encoding, genomic region attention, and conditional U-Net diffusion modules. This will simulate CNV distribution changes and evolutionary processes in the genome, analyze the specific role of CNV in regulating Alzheimer's disease pathways, and ultimately improve disease risk assessment and early intervention accuracy.

   • Keywords: Diffusion; Copy Number Variation; WGS; Alzheimer's disease

   • Project Address:      Supervised by Prof. Kai Wei.

3. 2024 Chinese Academy of Sciences Undergraduate Innovation Practice Training Program (National Level Project; First Responsible Person): HeDA: An Intelligent Agent System for Heatwave Risk Discovery through Automated Knowledge Graph Construction and Multi-layer Risk Propagation Analysis, 2024.11-2025.9

   • Abstract: Heatwaves pose complex cascading risks across interconnected climate, social, and economic systems, but knowledge fragmentation in scientific literature hinders comprehensive understanding of these risk pathways. We introduce HeDA (Heatwave Discovery Agent), an intelligent multi-agent system designed for automated scientific discovery through knowledge graph construction and multi-layer risk propagation analysis. HeDA processes over 10,247 academic papers to construct a comprehensive knowledge graph with 23,156 nodes and 89,472 relationships, employing novel multi-layer risk propagation analysis to systematically identify overlooked risk transmission pathways. Our system achieves 78.9% accuracy on complex question-answering tasks, outperforming state-of-the-art baselines including GPT-4 by 13.7%. Critically, HeDA successfully discovered five previously unidentified high-impact risk chains, such as "heatwave → water demand surge → industrial water restrictions → small business disruption," which were validated through historical case studies and domain expert review. This work presents a new paradigm for AI-driven scientific discovery, providing actionable insights for developing more resilient climate adaptation strategies.

   • Keywords: Knowledge Graph, Intelligent Agents, Heatwave Risk Analysis, Scientific Discovery, Climate Adaptation, Multi-layer Risk Propagation

   • Project Address:      Supervised by Researcher Yong Ge.

4. 2024 College Student Innovation Training Project (Autonomous Region Level Project; First Responsible Person): Research on the Generation Cyclability of Cartesian Product Graphs and Related Problems, 2024.03-2025.6

   • Abstract: The $k$-ary $n$-cube ($Q_n^k$) is a critical topology for large-scale computing systems powering modern AI and HPC workloads, where fault tolerance is paramount. Traditional fault models, which assume faults are independent and random, yield unrealistic resilience estimates because real-world failures are spatially correlated, manifesting as topological clusters. This paper introduces the Region-Based Fault (RBF) model, a new paradigm that addresses this gap by directly modeling this spatial correlation. Our primary contribution is a proof that for odd $k \geq 3$ and $n \geq 2$, the $Q_n^k$ remains Hamiltonian-connected—a property vital for deadlock-free routing and efficient task scheduling—under a sufficient set of RBF conditions. We present a constructive algorithm that finds a Hamiltonian path by leveraging an adaptive decomposition strategy. Experimental analysis demonstrates that our approach significantly enhances fault tolerance and remains robust far beyond its conservative theoretical guarantees. This work provides a practical, high-performance solution for maintaining connectivity in systems where fault clustering is prevalent.

   • Keywords: $k$-ary $n$-cubes, fault-tolerant embedding, Hamiltonian-connected, clustered faults, interconnection networks.

   • Project Address:GitHub/Region-Based Fault Model      Supervised by Prof. Eminjan Sabir.

5. Research on Elderly Companionship Solutions Based on Artificial Intelligence Digital Twin Technology, 2024.12-2026.9

   • Abstract: This project, centered on artificial intelligence digital twin technology, aims to alleviate the lack of family companionship for the elderly in China's aging society, bridge the digital divide for older adults, and enhance primary and secondary school students' artificial intelligence practical capabilities. Implemented by Shenzhen X - Institute in collaboration with ByteDance and other organizations, the project is divided into preparation, implementation, and promotion phases. It plans to facilitate students in customizing personalized digital twins for the elderly, enhancing intergenerational communication, and exploring application scenarios of AI large models in social welfare. The project not only provides companionship and psychological support for the elderly at a spiritual level but also opens up a new path for Chinese-style elderly care while promoting artificial intelligence education and social innovation development. Through multi-party collaboration, risk management, and media promotion, the project will achieve the goal of progressing from pilot programs to nationwide promotion, with significant social, educational, and technological implications.

   • Keywords: Artificial Intelligence; Social Innovation

   • Project Address:      Supervised by Min Tang (Former Counselor of the State Council).

Learning Experience

1. Tsinghua University-Peking University Center for Life Sciences (Tsinghua) 2025 Summer Camp 2025.07 See Link

2. Shenzhen Academy of Medical Sciences / Shenzhen Bay Laboratory Summer Research 2025.07-2025.09

3. Tsinghua University Qian Xuesen Mechanics Class and Shenzhen X - Institute — Zero One Scholar (Long-term Training) 2024.06-2027.06

4. AI Winter School 2025 - CFPU/Brown University Department of Physics 2025.1

5. CAAI Artificial Intelligence and Technology Ethics Training Course by China Association for Artificial Intelligence 2024.9-2024.12

6. 2024 Fudan University Summer School of Mathematical Logic 2024.08 See Link

7. Jinan University 2024 Guangdong Thousand Villages Survey Project 2024.08 See Link

8. Wuhan University National Tianyuan Mathematics Central Center - "Mathematics and Algorithms Triggered by Irrational Numbers" Discussion Class 2024.03-2024.6 See Link

9. Xinjiang University Innovation Laboratory/"Want to Put Memories Together for You" CTF Team Member 2024.03-2024.6 See Link

Internship Experience

1. Beijing Frontier Research Center for Biological Structure, Tsinghua University 2025.06-present: I developed the Polypeptide Structure Database and have been engaged in work on protein and polypeptide design.

2. Huawei Mindspore Community & Chinese Academy of Sciences Institute of Software Open Source Internship 2024.09-2025.3: I utilized machine learning, artificial intelligence, and other technologies to implement VGG19-based Pollock style transfer paintings with fractal and turbulence feature extraction and NFT tag generation. Currently reported by Huawei Official Account

3. Bose Quantum "Spark People" Community Intern 2024.09-present

Competition Honors

1. Contemporary Undergraduate Mathematical Contest in Modeling (CUMCM) National Second Prize, 2025.11

2. SynBio Challenges Silver Award, 2025 See Link

3. The Mathematical Contest in Modeling (MCM) Honorable Mention, 2025.5

4. 2024 Alibaba Cloud Tianchi University Student Competition National Finals 17th Place, 2024.10See Link

5. 2024 14th APMCM Asia-Pacific Mathematical Modeling Competition National Third Prize, 2024.08

6. "Alpha Egg Cup" 2024 National Amateur Go King Championship and "Commercial Travel Grand Canal Cup" City Go Competition 15th Place, 2024.07

7. Xinjiang Youth Amateur Go Dan Level Competition 53rd Place, 2024.05

8. Hunan Province Spring Cup Go Competition 7th Place, 2024.02

9. National Youth Intellectual Sports Meeting Go Competition 9th Place, 2024.02

10. Xinjiang University Vulnerability Reporting Honor, 2023.10

11. 2023 Xinjiang "Tianshan Fixed Network Cup" Network Security Skills Competition 7th Place, 2023.10

Website Development

1. Shenzhen X-Institute Course Website: https://lingyi.wyqmath.cn/

2. Polypeptide Structure Database: https://www.frcbs.tsinghua.edu.cn/cpdb/

3. Tong Wang Research Group: https://tongwang.vercel.app/

About Tsinghua University Tsien Excellence in Engineering Program - Shenzhen X-Institute:

Shenzhen X-Institute originated from the Tsinghua University "Xuetang Plan" Qian Xuesen Mechanics Class (abbreviated as "Tsinghua Qian Class"). Founded in 2009, Tsinghua Qian Class is one of the 66 pilot projects of the National "Outstanding Student Training Experimental Program for Basic Disciplines" and the "Tsinghua Xuetang Talent Training Plan". It is the only experimental class not positioned in a single discipline, but focused on engineering foundations (or interdisciplinary innovation across mechanics and all engineering technology disciplines). Its mission is to discover and cultivate innovative talents who aspire to change the world and benefit humanity through technology, explore future innovative talent training models, and answer "Qian Xuesen's Question".

Curriculum Vitae Download.