Incoming PhD Student in Computational Biology Department of Computational Biology, Mohamed bin Zayed University of Artificial Intelligence (MBZUAI) PAI Lab, advised by Dr. Jun Wen Research: Graph Machine Learning for Contextualized Drug Response and Drug Repurposing tel: +44 7432 164777 / +86 195 2048 2118 email: keqin.peng@mbzuai.ac.ae [CV] [GitHub] [中文页面]

About Me

I am an incoming PhD student in Computational Biology at Mohamed bin Zayed University of Artificial Intelligence (MBZUAI), where I will join PAI Lab under the supervision of Dr. Jun Wen. My research focuses on graph machine learning for contextualized drug response prediction and drug repurposing.

My current research direction is Contextualized High-Order Biomedical Relation Learning (CHORL). The goal is to construct comprehensive biomedical knowledge graphs that integrate multi-source prior knowledge from genomic, transcriptomic, proteomic, pharmacological, perturbational, and clinical domains. By learning context-aware and high-order biomedical relations, I aim to support complex biomedical tasks such as drug synergy prediction, drug-disease association prediction, side effect modeling, drug discovery and repurposing, and gene mutation-to-disease mapping.

Before moving into AI-enabled drug discovery, I worked on natural language processing, document-level relation extraction, biomedical experimental text mining, and knowledge graph construction. This background motivates my interest in building literature-aware and biologically interpretable graph learning systems for computational biology and precision cancer therapy.

Research Direction

My PhD research centers on Contextualized High-Order Biomedical Relation Learning (CHORL). CHORL aims to build a unified graph learning framework that injects heterogeneous biomedical priors into knowledge graphs and learns context-specific relations among drugs, genes, proteins, diseases, perturbations, cellular states, and clinical phenotypes.

• Contextualized Drug Response Prediction: modeling drug responses under different cellular, disease, molecular, and perturbational contexts.

• Drug Combination and Synergy Prediction: predicting drug-drug synergy by integrating drug targets, pathways, cell-line contexts, and high-order biomedical relations.

• Drug-Disease Association and Drug Repurposing: learning latent associations among drugs, diseases, genes, and phenotypes to support indication expansion and therapeutic repositioning.

• Perturbation-aware Biomedical Graph Learning: incorporating resources such as LINCS L1000 and Tahoe-100M to model transcriptional and cellular responses after drug perturbations.

• Interpretable Biomedical Relation Learning: identifying target-pathway evidence, context-specific PPI patterns, and knowledge graph evidence paths for precision cancer therapy.

Education

Mohamed bin Zayed University of Artificial Intelligence (MBZUAI) (2026.08 ~ 2030.07 expected) Degree: PhD in Computational Biology Department: Department of Computational Biology Advisor: Dr. Jun Wen Lab: PAI Lab Research: Graph Machine Learning for Contextualized Drug Response and Drug Repurposing

University of Glasgow (2024.09 ~ 2025.09) Degree: MSc in Robotics and Artificial Intelligence School: James Watt School of Engineering Key Course Grade: Intro to AI (Grade A2)

Beijing Normal University (2018.09 ~ 2022.07) Degree: BSc in Computer Science and Technology School: School of Artificial Intelligence GPA: 3.3/4.0 [GPA Proof] [Chinese Transcript] [English Transcript] Awards and Honors: Jing Shi Scholarship (2020.10), First-Class Academic Scholarship (2021.09), Outstanding Student of Summer School (2020.09)

Biomedical Data and Knowledge Graphs

My research focuses on integrating heterogeneous biomedical data into graph-structured representations, including drugs, diseases, genes, protein-protein interactions, perturbation profiles, drug combinations, and cellular contexts.

• Drug / Compound Resources: DrugBank, ChEMBL, PubChem, LINCS perturbagens, Tahoe-100M perturbagens.

• Disease / Target / Gene Resources: CTD, NCBI Gene.

• Drug Response and Combination Resources: DrugComb, DrugCombDB, NCI-ALMANAC, DepMap.

• Omics and Perturbation Resources: LINCS L1000 and Tahoe-100M.

• Network and Knowledge Graph Resources: STRING, PrimeKG, and self-constructed biomedical knowledge graphs.

Research Keywords

• Graph Machine Learning

• Biomedical Knowledge Graphs

• Contextualized High-Order Relation Learning

• Drug Combination Prediction

• Drug-Disease Association Prediction

• Drug Repurposing

• Drug Perturbation Response Modeling

• Precision Cancer Therapy

• Pharmacogenomics

• Interpretable AI for Drug Discovery

Publications

Publications

• U-Net with depthwise separable convolutions and big kernels for document-level relation extraction
  Rongen Yan, Keqin Peng and Depeng Dang
  2023 11th Transactions of the Association for Computational Linguistics. [Reviewing]
  destails

  The article will be presented to you when it is published


• Document-level relation extraction with less redundant image-style feature
  Rongen Yan, Keqin Peng and Depeng Dang
  2023 11th Transactions of the Association for Computational Linguistics. [Reviewing]
  destails

  The article will be presented to you when it is published
  
  
• Research on Multi-Document Summary Generation Method Based on Event Structure
  Keqin Peng and Xuesong Wang
  Beijing Normal University Graduation Thesis[PDF]
  details

  1. Traditional multi-text summarization methods often suffer from the problem of losing information between text segments, which limits the output of traditional automatic summarization neural network models This limits the output effect of traditional automatic summarization neural network models. We introduce a hierarchical Transformer model to connect and encode the sorted and filtered paragraphs hierarchically, which improves the quality of the output summary. The quality of the output summary is improved.
  2. The sorting algorithm based on LSTM model can calculate the correlation between paragraphs and input headings, which can be used as the basis for sorting and filtering to improve the model's capacity for input size. The model's capacity for input size is improved.
  3. The hierarchical Transformer structure learns contextual information about the characters within and between paragraphs separately and portrays the event structure.
  4. Use Beam Search and length normalization methods to improve the length and fluency of output sentences.

Work Experience

Hunan Changsha Bank Digital Technology Co., Ltd.
2024.01 ~ 2024.09
Position: Backend Development Engineer, Development Division 1

• Project Development

  • Intelligent Financial and Taxation System
    • Developed an automated accounting bot module using the Python and Selenium tech stack, enabling web automation and local file processing.
    • Participated in requirements discussions to help define functionality scope and technical choices.
    • Designed and implemented the logic of the automated preprocessing bot module, utilizing PyPDF2 and Pandas to process document data, improving automation and data accuracy.
  • Data Butler System
    • Developed modules such as Configuration Center, Project Workspace, Homepage, and Business Management using Java and the Spring Boot framework, ensuring high system performance and maintainability.
    • Contributed to the logic design of the Project Center module, applying RESTful API design principles to enable efficient management of project lists and assigned tasks.
    • Designed the database schema, optimized query performance, and used the MySQL database management system to support fast access to large amounts of data, achieving efficient ORM (Object-Relational Mapping) with MyBatis.

• Research on Enterprise AI Transformation

  • Designed theoretical knowledge and practical assessment processes for large model application capabilities.
  • Drafted an AI development recommendation report for the company: analyzed the current situation and competitive landscape, selected suitable technical routes and development paths; provided detailed analysis of AI development strategies, investment scale, product output models, and cash flow cycles; and drafted basic development processes and standards for the company's AI development team.

Institute for AI Industry Research, Tsinghua University
2022.07 ~ 2023.07
Position: NLP Research and Development Engineer

• NLP Technology R&D and Applications

  • Created a medical experiment text dataset: collected 200,000 operation texts from laboratories in various fields of global medical experiments; used a combination of NER + RE + keylist methods to clean and organize data, ensuring uniform formatting and valid content; and generated a high-quality dataset at low cost using a combination of few-shot pre-training and automated labeling models.
  • Conducted technical validation and pipeline development: validated existing technologies such as NER, RE, SRL, and KG to provide feasible technical solutions for tasks.
  • Proposed new tasks and designed models: introduced the task of extracting key step flowcharts from natural language texts and designed corresponding models.
  • Redesigned end-to-end models: optimized model design based on task requirements to address issues of error accumulation and error propagation.
  • Deployed new technologies and collaborated with medical laboratories.

Patent

• A document-level relationship extraction method, system, device and storage medium
  Rongen Yan, Keqin Peng
  National Invention Patent, Under Review

Other Projects

• Research task publishing platform
  Database leader; 2021.3~2021.5
  Independent Exploration Project for Undergraduates of Beijing Normal University
  

• American College Mathematical Modeling Competition
  Programmer; 2021.01-2021.03