Shuqi Li

Dr. Shuqi Li

orcid

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 July 2025 in Nature Communications
Verified
Journal Article
Open access
PDF file
FXFanglei Xue
Fanglei Xue
MZMeihan Zhang
Meihan Zhang
SLShuqi Li
Shuqi Li
XGXinyu Gao
Xinyu Gao
JWJames Wohlschlegel
James Wohlschlegel
WDWeixian Deng
Weixian Deng
Targeted protein degradation (TPD) has rapidly emerged as a powerful modality for drugging previously “undruggable” proteins. TPD employs small molecules like PROTACs and molecular glue degraders (MGD) to induce target protein degradation via the formation of a ternary complex with an E3 ligase. However, the rational design of these degraders is severely hindered by the difficulty of obtaining these ternary structures. Here we introduce DeepTernary, a novel end-to-end deep learning approach using an SE(3)-equivariant encoder and a query-based decoder to accurately and rapidly predict these critical structures. Trained on carefully curated TernaryDB, DeepTernary achieves state-of-the-art performance on PROTAC benchmarks without prior exposure to known PROTACs and shows notable prediction capability on the more challenging MGD benchmark with a blind docking protocol. Remarkably, the buried surface areas calculated from predicted structures correlate with experimental degradation potency metrics. Overall, DeepTernary offers a powerful tool for the development of targeted protein degraders.

26 June 2023 in Proceedings of the AAAI Conference on Artificial Intelligence
Verified
Journal Article
Open access
PDF file
SLShuqi Li
Shuqi Li
WLWeiheng Liao
Weiheng Liao
YCYuhan Chen
Yuhan Chen
RYRui Yan
Rui Yan
Nowadays explainability in stock price movement prediction is attracting increasing attention in banks, hedge funds and asset managers, primarily due to audit or regulatory reasons. Text data such as financial news and social media posts can be part of the reasons for stock price movement. To this end, we propose a novel framework of Prediction-Explanation Network (PEN) jointly modeling text streams and price streams with alignment. The key component of the PEN model is an shared representation learning module that learns which texts are possibly associated with the stock price movement by modeling the interaction between the text data and stock price data with a salient vector characterizing their correlation. In this way, the PEN model is able to predict the stock price movement by identifying and utilizing abundant messages while on the other hand, the selected text messages also explain the stock price movement. Experiments on real-world datasets demonstrate that we are able to kill two birds with one stone: in terms of accuracy, the proposed PEN model outperforms the state-of-art baseline; on explainability, the PEN model are demonstrated to be far superior to attention mechanism, capable of picking out the crucial texts with a very high confidence.

8 January 2025 in IEEE Transactions on Knowledge and Data Engineering
Verified
Journal Article
Closed access
DLDi Luo
Di Luo
SLShuqi Li
Shuqi Li
WLWeiheng Liao
Weiheng Liao
RYRui Yan
Rui Yan
Quantitative trading is a prominent field that employs time series analysis today, attracting researchers who apply machine intelligence to real-world issues like stock price movement prediction. In recent literature, various types of auxiliary data have been integrated alongside stock prices to improve prediction accuracy, such as textual news and correlational information. However, they typically rely on directly related documents or symmetric price correlations to make predictions for a particular stock (we refer to as “self-influence”). In this paper, we propose a Memory-Aware Graph Interactive Causal Network (MagicNet) that considers both temporal and spatial dependencies in financial documents and introduces causality-based correlations between multivariate stocks in a hierarchical fashion. MagicNet involves a text memory slot for each stock to retain the most influential texts over time and contains a dynamic interaction graph based on causal relationships to aggregate interactive influences asymmetrically. We believe that MagicNet leverages influential texts across stocks and explores their interrelationships through a logical structure, improving predictions on multiple stocks (we refer to as “interactive-influence”). The effectiveness of MagicNet is demonstrated through experiments on three real-world datasets, where MagicNet outperforms existing state-of-the-art models, offering an intuitive framework for understanding how texts and correlations affect future stock prices.

Verified
Journal Article
Open access
PDF file
TZTianju Zheng
Tianju Zheng
LSLiping Sun
Liping Sun
JCJifeng Chen
Jifeng Chen
XCXinyuan Cui
Xinyuan Cui
SLShuqi Li
Shuqi Li
The construction of artificial islands is a complex engineering challenge requiring precise scheduling to optimize resource utilization, manage costs, ensure safety, and minimize environmental impacts in dynamic marine settings. In this paper, we present a multi-objective artificial island construction scheduling optimization model. This model considers many crucial factors that influence artificial island construction from 5 aspects: construction time, construction cost, project quality, resource utilization efficiency, and environmental impact. To optimize the proposed model, we propose an algorithm called Multi-objective Cooperative Differential Evolution (MOCDE). MOCDE integrates Cooperative Co-evolutionary Algorithms, and Differential Evolution to efficiently obtain the optimal schedules. To explore the performance of this model and the algorithm, extensive experiments are conducted based on real-world project data. Comparing MOCDE with established algorithms, results indicate that MOCDE improvements over previous SOTA models, achieving a reduction of 0.56% in Total Time, a decrease of 0.43% in Total Cost, and an enhancement of 7.38% in Total Quality. Besides, it also could adhere to ensure the environmental requirements.

10 March 2025 in IEEE Transactions on Computational Biology and Bioinformatics
Verified
Journal Article
Closed access
SLShuqi Li
Shuqi Li
SXShufang Xie
Shufang Xie
HSHongda Sun
Hongda Sun
YCYuhan Chen
Yuhan Chen
TQTao Qin
Tao Qin
RYRui Yan
Rui Yan
Traditional drug discovery processes are both time-consuming and require extensive professional expertise. With the accumulation of drug-target interaction (DTI) data from experimental studies, leveraging modern machine-learning techniques to discern patterns between drugs and target proteins has become increasingly feasible. In this paper, we introduce the Multi-channel Interaction Network (MIN), a novel framework designed to predict DTIs through two primary components: a representation learning module and a multi-channel interaction module. The representation learning module features a C-Score Predictor-assisted screening mechanism, which selects critical residues to enhance prediction accuracy and reduce noise. The multi-channel interaction module incorporates a structure-agnostic channel, a structure-aware channel, and an extended-mixture channel, facilitating the identification of interaction patterns at various levels for optimal complementarity. Additionally, contrastive learning is utilized to harmonize the representations of diverse data types. Our experimental evaluations on public datasets demonstrate that MIN surpasses other strong DTI prediction methods. Furthermore, the case study reveals a high overlap between the residues selected by the C-Score Predictor and those in actual binding pockets, underscoring MIN's explainability capability. These findings affirm that MIN is not only a potent tool for DTI prediction but also offers fresh insights into the prediction of protein binding sites.

Verified
Journal Article
Open access
PDF file
TZTianju Zheng
Tianju Zheng
LSLiping Sun
Liping Sun
MLMing-Wei Li
Ming-Wei Li
GYGuangyao Yuan
Guangyao Yuan
SLShuqi Li
Shuqi Li
Artificial island construction is a multifaceted engineering endeavor that demands precise scheduling to optimize resource allocation, control costs, ensure safety, and minimize environmental impact within dynamic marine environments. This study introduces a comprehensive multi-objective optimization model that integrates critical factors such as resource limitations, task dependencies, environmental variability, safety risks, and regulatory compliance. To effectively address the complexities of this model, we develop and employ the Multi-Objective Adaptive Cooperative Evolutionary Marine Genetic Algorithm (MACEMGA). MACEMGA combines cooperative coevolution, adaptive dynamic weighting, dynamic penalty functions, and advanced genetic operators to navigate the solution space efficiently and identify Pareto optimal schedules. Through extensive computational experiments using data from the Dalian Bay Cross-Sea Traffic Engineering project, MACEMGA is benchmarked against algorithms such as NSGA-II, SPEA2, and MOEA/D. The results demonstrate that MACEMGA achieves a reduction in construction time from 32.8 to 23.5 months and cost savings from CNY 4105.3 million to CNY 3650.0 million while maintaining high-quality outcomes and compliance with environmental standards. Additionally, MACEMGA shows improvements in hypervolume by up to 15% over existing methods and a Convergence Rate that is 8% faster than MOEA/D.