Name: Menghao Guo
Email: menghao.guo.319@gmail.com
GitHub: https://github.com/JackKuo666
Huggingface: https://huggingface.co/jackkuo
Five years of AI experience: Currently a Research Specialist at Zhejiang Lab.
Expert in NLP, deep learning, and LLM applications: Led projects in text mining, knowledge graph construction, and multi-modal data integration, with a focus on leveraging LLM agents and AI for life sciences, including biocomputing, bioinformatics, and computational biology. Specialized in: Protein and genome foundation models, Multi-agent systems for life sciences data mining, Bioinformatics analysis and database construction, Drug repurposing, and Genomics-based personalized medicine.
Open-source contributor: Actively contributed to open-source projects such as AllenNLP and MindSpore by enhancing model performance and functionality.
Biocomputation projects: Involved in AMP-SEMiner, CRISPR-Cas Systems Discovery, Enzyme Kinetics Data Extraction (Enzyme Co-Scientist), and LLM Agent-based Chemical Literature Data Mining.
Diverse industry background: Extensive experience across Huawei (2012 Lab), Ant Group, Ping An Technology, China Tobacco Zhejiang Industrial, and the Research Center for Life Sciences Computing of Zhejiang Lab.
PhD goal: I am currently seeking a PhD position to expand my research on AI applications in life sciences, with a focus on developing data-driven solutions - integrating LLM agents with bioinformatics, causal inference, and reinforcement learning to advance precision medicine, enable drug repurposing, and optimize therapeutic strategies while delivering genotype-tailored recommendations.
Master’s Degree in Navigation, Guidance and Control
Northeastern University, China (Sep 2017 – Jan 2020)
Focused on unsupervised deep learning, multitask learning, and visual odometry.
Bachelor’s Degree in Electronic Information Science and Technology
Nanyang Normal University, China (Sep 2013 – Jun 2017)
Coursework in signal processing, software programming, and mathematical modeling.
Zhejiang Lab | Research Specialist
Mar 2022 – Present
Leading and collaborating on various AI and bioinformatics projects, with a focus on LLM applications and data-driven solutions.
China Tobacco Zhejiang Industrial Co., Ltd. | Algorithm Researcher
Aug 2020 – Mar 2022
Applied machine learning and spectral analysis techniques to optimize tobacco quality, integrating heterogeneous data sources to develop predictive models.
Huawei Communication Technology Co., Ltd. | Algorithm Engineer
May 2020 – Aug 2020
Optimized deep learning frameworks, including MindSpore, for NLP applications such as BERT, enhancing model training efficiency and scalability.
Zhejiang Ant Micro Financial Service Group | NLP Algorithm Engineer (Intern)
Jun 2019 – Sep 2019
Developed multi-task learning enhancements within the AllenNLP framework, improving model robustness in dialogue and data extraction tasks.
Ping An Technology (Shenzhen) Co., Ltd. | NLP Algorithm Engineer (Intern)
Oct 2018 – Jan 2019
Built an information extraction system for contract review using BERT and rule-based methods, advancing practical applications of NLP in structured data analysis.
LLM Literature Extraction: Led a project to develop prompt design and model fine-tuning techniques for automatic extraction of key scientific data from literature, enabling scalable biomedical data mining (A scientific paper published).
Knowledge Graph Construction: Integrated LLM-Agents with knowledge graphs in the KOSA project to fuse multi-source data into complex relational networks (A scientific paper published).
Enzyme Kinetics Extraction (Enzyme Co-Scientist): As co-first author, developed an LLM-based framework that extracted over 91,000 enzyme kinetics entries from ~3,500 papers with high accuracy (A manuscript has been preprinted and is under review).
AMP-SEMiner: As co-first author, created a framework using Protein Language Models to discover 1.6 million antimicrobial peptide candidates by integrating genomics, molecular dynamics, and LLM technology (A scientific paper published).
SLMP Platform: Proposed and implemented an LLM-powered platform for automated literature summarization, keyword extraction, and article analysis (A scientific paper published).
Chemical Literature Mining: Contributed to an LLM Agent system for extracting reaction predictions and molecular properties from chemical literature (A manuscript has been preprinted).
CRISPR-Cas Discovery: Participated in leveraging foundation models to identify novel Casλ homologs for advancing gene editing research (A scientific paper published).
Programming: Python, Java, C/C++, JavaScript
NLP & AI: Proficient with LLMs (e.g., GPT-4o, DeepSeek-R1, BioBERT), BERT variants, and classical NLP techniques (HMM/CRF, LDA, word2vec, FastText)
Frameworks & Tools: HuggingFace, TensorFlow, PyTorch, Docker, Git
Data & Graph Analysis: Pandas, NumPy, Matplotlib, Neo4j, RDF, SPARQL
Advanced Techniques: RL, Multi-Agent Coordination, Causal Inference, KG Construction
Menghao Guo, et al. “Investigations on scientific literature meta information extraction using large language models.” IEEE ICKG 2023.
Menghao Guo, et al. SLMP: A Scientific Literature Management Platform Based on Large Language Models. IEEE ICKG 2024.
Fei Huang, et al., Menghao Guo, et al., “KOSA: KO enhanced salary analytics based on knowledge graph and LLM capabilities.” IEEE ICDMW 2023.
Li, W., et al., Menghao Guo, et al.”Discovering CRISPR-Cas System with Self-processing Pre-crRNA Capability by Foundation Models.” Nature Communications (2024).
Wenhui LI†, Baicheng Huang†, Menghao Guo†, et al. “Unveiling the Evolution of Antimicrobial Peptides in Gut Microbes via Foundation Model-Powered Framework”. Cell Reports(2025).
[Preprints] Jinling Jiang†, Jie Hu†, Siwei Xie†, Menghao Guo†, et al. Enzyme Co-Scientist: Harnessing Large Language Models for Enzyme Kinetic Data Extraction from Literature. preprint and under review at Nature Computational Science.
[Preprints] Chen, K., et al., Menghao Guo, et al. “An Autonomous Large Language Model Agent for Chemical Literature Data Mining.” (arXiv)
[Master Thesis] Menghao Guo. Research on Visual Odometry Algorithm Based on Unsupervised Deep Learning [D]. 2020.
(†Co-first author)
Certifications: Advanced Information Systems Project Manager (2024)
Honors: Zhejiang E-Class Talent (2024)
Conferences: Oral presentations at IEEE ICKG, ICDM workshops
Patents: 11 related to tobacco quality optimization and biotech algorithms. [Search in Google Patents]