Chengxi Zang

Chengxi Zang (臧承熙), Ph.D.

Dr. Chengxi Zang currently is an Instructor in the Department of Population Health Sciences, Weill Medical College of Cornell University. He got his Ph.D. from Tsinghua University in January 2019 with an Excellent Ph.D. Dissertation Award in the Computer Science Department (top 3) and an Excellent Ph.D. Award in Tsinghua University. His current research focus is using AI, Machine Learning, and large-scale Real-World health Data to solve challenging healthcare problems, including drug repurposing for Alzheimer's Disease, suicide prevention, understanding Long Covid, and so on. His research has been published in the top venues of related areas such as Nature Medicine, Nature Communications, Journal of General Internal Medicine, Scientific Reports, Cell Patterns, Archives of Pathology & Laboratory Medicine, TKDE, KDD, AAAI, ICDM, and his papers have won ICDM'18 Best Paper Candidate and the Best Paper Award at AAAI'20 Workshop on Deep Learning on Graphs.

[PDF] C.V. (Updated in Sept. 2020)
[PDF] Research Statement
[PDF] Teaching Statement

Research

Research Interests

Health Data Science, AI for Healthcare, Drug Discovery and Development, Deep Learning, Machine Learning
Deep Generative Models, Causal Inference, High-throughput Trial Emulation
Real-World Data/Evidence Analysis (RWD/RWE), Electronic Health Records Mining
Long COVID, Post-Acute Sequelae of COVID-19 (PASC), Alzheimer's Disease, Mental Heath
Graph Mining, Graph Neural Networks, Complex Systems, Network Science, Social Media Analysis

Research Experiences

May 2022 - Present, Instructor in Population Health Sciences, Weill Medical College of Cornell University
February 2019 - Apirl 2022, Weill Cornell Medicine, Cornell University, working with Prof. Fei Wang
March 2020 - January 2021, Boehringer Ingelheim Pharmaceuticals, Inc., Postdoctoral Fellowship, Biostatistics & Data Science Americas
July 2018 - October 2018, WeChat, Tencent Rhino-Bird Elite Training Program
June 2017 - May 2018, Center for Complex Network Research, Visiting scholar, working with Prof. Albert-László Barabási
Summer 2015 & 2016, working with visiting Prof. Christos Faloutsos from Carnegie Mellon University
Summer 2014 & 2015, working with visiting Prof. Chaoming Song from Miami University
September 2013 - January 2019 , Department of Computer Science, Tsinghua University. Advisors Prof. Wenwu Zhu and Prof. Peng Cui
March 2011 - May 2012, Department of Computer Science, Sun Yat-sen University. Advisor: Prof. Jiwu Huang

Education

February 2019 - Apirl 2022, Postdoctoral Research Associate, Weill Cornell Medicine, Cornell University
August 2013 - January 2019 , Doctor of Engineering, Tsinghua University, Department of Computer Science and Technology (Excellent Ph.D. Award in Tsinghua University, and Excellent Ph.D. Dissertation Award in the Computer Science Department. Top 3 in CS, and top 70/2279=3% in THU.)
September 2009 - July 2013, Bachelor of Science, Sun Yat-Sen University, Department of Computer Science and Technology (GPA 4.1/5, Rank 1st/100)

Publications

Journal Papers

J10	Comparing the effects of four common drug classes on the progression of mild cognitive impairment to dementia using electronic health records Jie Xu, Fei Wang, Chengxi Zang, Hao Zhang, Kellyann Niotis, Ava L. Liberman, Cynthia M. Stonnington, Makoto Ishii, Prakash Adekkanattu, Yuan Luo, Chengsheng Mao, Luke V. Rasmussen, Zhenxing Xu, Pascal Brandt, Jennifer A. Pacheco, Yifan Peng, Guoqian Jiang, Richard Isaacson & Jyotishman Pathak Scientific reports (2023).	[PDF]
J9	Data-driven analysis to understand long COVID using electronic health records from the RECOVER initiative Chengxi Zang, Yongkang Zhang, Jie Xu, Jiang Bian, Dmitry Morozyuk, Edward J. Schenck, Dhruv Khullar, Anna S. Nordvig, Elizabeth A. Shenkman, Russell L. Rothman, Jason P. Block, Kristin Lyman, Mark G. Weiner, Thomas W. Carton, Fei Wang, Rainu Kaushal Nature Communications (2023).	[PDF]
J8	Data-driven identification of post-acute SARS-CoV-2 infection subphenotypes Hao Zhang, Chengxi Zang, Zhenxing Xu, Yongkang Zhang, Jie Xu, Jiang Bian, Dmitry Morozyuk, Dhruv Khullar, Yiye Zhang, Anna Nordvig, Edward Schenck, Elizabeth Shenkman, Russel Rothman, Jason Block, Kristin Lyman, Mark Weiner, Thomas Carton, Fei Wang, Rainu Kaushal Nature Medicine (2023).	[PDF]
J7	Racial/Ethnic Disparities in Post-acute Sequelae of SARS-CoV-2 Infection in New York: an EHR-Based Cohort Study from the RECOVER Program Dhruv Khullar, Yongkang Zhang, Chengxi Zang, Zhenxing Xu, Fei Wang, Mark G. Weiner, Thomas W. Carton, Russell L. Rothman, Jason P. Block, Rainu Kaushal Journal of General Internal Medicine (2023).	[PDF]
J6	Identifying environmental risk factors for post-acute sequelae of SARS-CoV-2 infection: An EHR-based cohort study from the recover program Yongkang Zhang, Hui Hu, Vasilios Fokaidis, Colby Lewis V, Jie Xu, Chengxi Zang, Zhenxing Xu, Fei Wang, Michael Koropsak, Jiang Bian, Jaclyn Hall, Russell L. Rothman, Elizabeth A. Shenkman, Wei-Qi Wei, Mark G. Weiner, Thomas W. Carton, Rainu Kaushal Environmental Advances (2023).	[PDF]
J5	Building the ModelChallenges and Considerations of Developing and Implementing Machine Learning Tools for Clinical Laboratory Medicine Practice Yang, He S., Daniel D. Rhoads, Jorge Sepulveda, Chengxi Zang, Amy Chadburn, and Fei Wang. Archives of Pathology & Laboratory Medicine (2022).	[PDF]
J4	Development of a screening algorithm for borderline personality disorder using electronic health records Chengxi Zang, Marianne Goodman, Zheng Zhu, Lulu Yang, Ziwei Yin, Zsuzsanna Tamas, Vikas Mohan Sharma, Fei Wang, and Nan Shao Scientific reports 12, no. 1 (2022): 1-12.	[PDF]
J3	Contrastive Learning Improves Critical Event Prediction in COVID-19 Patients Tingyi Wanyan, Hossein Honarvar, Suraj K. Jaladanki, Chengxi Zang, Nidhi Naik, Sulaiman Somani, Jessica K. De Freitas, Ishan Paranjpe, Akhil Vaid, Jing Zhang,Riccardo Miotto, Zhangyang Wang, Girish N. Nadkarni, Marinka Zitnik, Ariful Azad, Fei Wang, Ying Ding, Benjamin S. Glicksberg Cell Patterns, 2021.	[PDF]
J2	Exploring the collective human behavior in cascading systems: a comprehensive framework Yunfei Lu, Linyun Yu, Tianyang Zhang, Chengxi Zang, Peng Cui, Chaoming Song & Wenwu Zhu. Knowledge and Information Systems (KAIS), 2020.	[PDF]
J1	On Power Law Growth of Social Networks. Chengxi Zang, Peng Cui, Christos Faloutsos, Wenwu Zhu. IEEE Transactions on Knowledge and Data Engineering (TKDE), 2018	[PDF] [Code]

Conference Papers

C13	SCEHR: Supervised Contrastive Learning for Clinical Risk Prediction using Electronic Health Records Chengxi Zang and Fei Wang. 2021 IEEE International Conference on Data Mining (ICDM'21). (Acceptance Rate 98/990 =9.9%, Regular Paper)	[PDF] [Code]
C12	MoFlow: An Invertible Flow Model for Generating Molecular Graphs Chengxi Zang and Fei Wang. KDD '20: Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (Accept Rate 216/1279 = 16.89%, Full Paper)	[PDF] [Slides] [YouTube] [Code] [Demo!]
C11	Neural Dynamics on Complex Networks Chengxi Zang and Fei Wang. KDD '20: Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (Accept Rate 216/1279 = 16.89%, Full Paper)	[PDF] [Slides] [YouTube] [Code]
C10	Recent Advances on Graph Analytics and Its Applications in Healthcare Fei Wang , Peng Cui , Jian Pei , Yangqiu Song , Chengxi Zang KDD '20: Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining	[PDF] [Webpage]
C9	Dynamical Origins of Distribution Functions Chengxi Zang, Peng Cui, Wenwu Zhu, and Fei Wang. KDD '19: Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (Accept Rate (110 oral + 60 poster)/1200 = 14.2%, Oral)	[PDF]
C8	Uncovering Pattern Formation of Information Flow. Chengxi Zang, Peng Cui, Chaoming Song, Wenwu Zhu, and Fei Wang. KDD '19: Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (Accept Rate (110 oral + 60 poster)/1200 = 14.2%, Poster)	[PDF]
C7	Fates of Microscopic Social Ecosystems: Keep Alive or Dead? Haoyang Li, Peng Cui, Chengxi Zang, Tianyang Zhang, Wenwu Zhu, and Yishi Lin. KDD '19: Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (Accept Rate (110 oral + 60 poster)/1200 = 14.2%, Oral)	[PDF]
C6	Uncovering the Co-driven Mechanism of Social and Content Links in User Churn Phenomena Yunfei Lu, Lingyun Yu, Peng Cui, Chengxi Zang, Renzhe Xu, Yihao Liu, Lei Li, and Wenwu Zhu. KDD '19: Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (Accept Rate (45 oral + 100 poster)/700 = 20.7%, Poster, Applied Data Science Track)	[PDF]
C5	Learning and Interpreting Complex Distributions in Empirical Data Chengxi Zang, Peng Cui, Wenwu Zhu. KDD '18: Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (Accept Rate 181/983 = 18.4%, Oral)	[PDF] [PPT]
C4	Collective Human Behavior in Cascading System: Discovery, Modeling and Applications. Yunfei Lu, Linyun Yu, Tianyang Zhang, Chengxi Zang, Peng Cui, Chaoming Song, and Wenwu Zhu. 2018 IEEE International Conference on Data Mining (ICDM'18). (Acceptance Rate 84/948 =8.86%, Full Paper, Best Paper Candidate)	[PDF]
C3	Long Short Memory Process: Modeling Growth Dynamics of Microscopic Social Connectivity. Chengxi Zang, Peng Cui, Christos Faloutsos, Wenwu Zhu. KDD '17: Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (Accept Rate 131/748 = 17.5%, Oral)	[PDF] [PPT] [Poster] [Code] [Video 1 or 2]
C2	Quantifying Structural Patterns of Information Cascades. Chengxi Zang, Peng Cui, Chaoming Song, Christos Faloutsos, Wenwu Zhu. International World Wide Web Conference (WWW), Poster, 2017. (Accept Rate 67/166 = 40.4%)	[PDF] [PPT] [Poster]
C1	Beyond Sigmoids: the NetTide Model for Social Network Growth, and its Applications. Chengxi Zang, Peng Cui, Christos Faloutsos. KDD '16: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (Accept Rate 142/784 = 18.1%)	[PDF] [PPT] [Poster] [Code]

Workshop Papers & Others

W6	Visualizing Deep Graph Generative Models for Drug Discovery Karan Yang, Chengxi Zang, Fei Wang 2020 KDD Workshop on Applied Data Science for Healthcare	[PDF] [Webpage]
W5	MoFlow: An Invertible Flow Model for Molecular Graph Generation Chengxi Zang, Fei Wang 2020 ICML Workshop on Invertible Neural Networks, Normalizing Flows, and Explicit Likelihood Models (INNF+2020)	[PDF] [Webpage]
W4	Neural Dynamics on Complex Networks Chengxi Zang and Fei Wang. 2020 AAAI Deep Learning on Graphs: Methodologies and Applications (DLGMA’20) workshop (Best Paper Award)	[PDF] [Webpage]
W3	Causation-Driven Visualizations for Insurance Recommendation Zhixiu Liu, Chengxi Zang, Kun Kuang, Hao Zou, Hu Zheng, and Peng Cui IEEE International Conference on Multimedia & Expo (ICME), 2019, the Cross-media Analysis for Semantic Knowledge Reasoning and Transfer Workshop.	[PDF]
W2	Modeling the Dynamics of WeChat Social System. Chengxi Zang, Peng Cui, Linyun Yu, Tianyang Zhang, Wenwu Zhu, Hao Ye. Draft	[PDF]
W1	Structural Patterns of Information Cascades and their Implications for Dynamics and Semantics. Chengxi Zang, Peng Cui, Chaoming Song, Christos Faloutsos, Wenwu Zhu. arXiv Draft	[PDF]

Ph.D. Dissertation

D1	Data-Driven Dynamical Modeling of Complex Social Systems (复杂社交系统的数据驱动动力学建模研究) Chengxi Zang Defense Committee Members: Prof. Xindong Wu, Prof. Jianyong Wang, Prof. Jie Tang, Prof. Huawei Shen, Prof. Dan Li, and Prof. Wenwu Zhu	[PDF] [Webpage]

Tutorials

T2	Recent Advances on Graph Analytics and Its Applications in Healthcare Fei Wang (Cornell University); Peng Cui (Tsinghua University); Jian Pei (Simon Fraser University); Yangqiu Song (Hong Kong University of Science and Technology); Chengxi Zang (Cornell University). KDD 2020 Tutorial on August 23rd	[Webpage] [PDF]
T1	Differential Deep Learning on Graphs and its Applications Chengxi Zang (Cornell University) and Fei Wang (Cornell University). AAAI 2020 Tutorial on February 7, 2020, New York City, NY.	[Webpage] [PDF]

Media, News & Tweets

Media Coverage

May 2023. Our Data-driven analysis to understand long COVID using electronic health records from the RECOVER initiative was highlighted in Cornell Chronicle: Long COVID risk and symptoms vary across populations and in Weill Cornell Medicine Newsroom: Study Discovers Long COVID Risk and Symptoms Vary in Different Populations
May 2023. Our previous molecular generative AI paper MoFlow: An Invertible Flow Model for Generating Molecular Graphs was highlighted in Weill Cornell Medicine Population Health Sciences News
March 21st, 2023. Our Molecule Generative AI model - MoFlow was highlighted by NVIDIA CEO Jensen Huang @ NVIDIA GTC 2023 Keynote and being integrated into NVIDIA BioNeMo Service for AI-driven Drug Discovery! See the exciting moment and inspiring introduction at 48:00 mins at Youtube:GTC 2023 Keynote with NVIDIA CEO Jensen Huang. Also refer to the NVIDIA Developer Technical Blog: Build Generative AI Pipelines for Drug Discovery with NVIDIA BioNeMo Service for more details.
March 2023. Our Risk Factors and Predictive Modeling for Long Covid paper was highlighted in News Medical: What are the risk factors associated with post-acute SARS-CoV-2 infection?
March 2023. Our Racial/Ethnic Disparities in Long Covid paper was highlighted in BMJ News: Covid-19: US studies show racial and ethnic disparities in long covid.
March 2023. Our Environmental risk factors for Long Covid paper was highlighted in NIH Director's Blog: RECOVER: What Clinical Research Comes Next for Helping People with Long COVID.
February 2023. Our Racial/Ethnic Disparities in Long Covid paper was highlighted in NIH News Releases. NIH RECOVER research identifies potential long COVID disparities.
February 2023. Our Racial/Ethnic Disparities in Long Covid paper was highlighted in Cornell Chronicle and Weill Cornell Medicine Newsroom: Long COVID Symptoms Vary Among Racial and Ethnic Groups; Cancer Health: RECOVER Research Identifies Potential Long COVID Disparities; and Bet : Black, Hispanic Patients More Likely To Develop Lasting Symptoms After COVID.
February 2023. Our Long Covid subphenotyping paper was highlighted in NIH - News and Stories: Researchers Identify Four Long COVID Categories.
Janunary 2023. Our Long Covid subphenotyping paper was highlighted in Cornell Chronicle: Study identifies four major subtypes of long COVID; CN-HEALTHCARE 健康界: Nat Med：研究近3.5万名新冠患者数据，确定了长新冠存在四种主要的症状模式; Medical Xpress: Study identifies four major subtypes of long COVID; Verywellhealth: Long COVID May Manifest Itself in 4 Major Ways, Research Shows; Prevention: Study Finds There Are 4 Subtypes of Long COVID, New Atlas:Four distinct subtypes of long COVID defined in machine learning study; Miami Herald: There are 4 ‘major’ types of long COVID symptoms, study finds. How likely is each?; and BOSTON.com:New study categorizes long COVID symptoms, allowing for earlier detection, “They don’t have to suffer in silence.”
Janunary 2023. Our Long Covid subphenotyping paper was highlighted in Nature Medicine - Research Briefing: Machine learning identifies long COVID patterns from electronic health records.
December 2022. Our Long Covid subphenotyping paper was highlighted in Weill Cornell Medicine Newsroom. Study Identifies Four Major Subtypes of Long COVID, and MedPage Today. Are Subphenotypes for Long COVID Beneficial? — A new study can help physicians evaluate potential treatment approaches.
June 2022. Our Long Covid subphenotyping paper was highlighted in News Medical. Machine learning analysis suggests that there are four sub-phenotypes of long COVID
June 2022. Our Long Covid subphenotyping paper was highlighted in Fortune. Long COVID symptoms: What we know—and don’t know—about the mysterious illness that could affect up to 80% of COVID survivors
May 2022. Our Long Covid analysis paper was highlighted in News Medical.Largest study to date on long COVID identifies a broad list of diagnoses.

Tweets my own

Tweets by calvin_zcx

News

Upcoming KDD 2020 events of mine:

Our tutorial "Recent Advances on Graph Analytics and Its Applications in Healthcare" will start on August 23rd, 8:00 AM PDT (11:00 AM EDT). Click and find the materials and virtual location!
A spotlight presentation of our system on Visualizing Deep Graph Generative Models for Drug Discovery in KDD 2020 Workshop on Applied Data Science for Healthcare on August 24, 2020!
An oral presentaion of our full research paper MoFlow: An Invertible Flow Model for Generating Molecular Graphs will start on August 25th, 4:00 PM PDT (7:00 PM EDT)!
Another oral presentaion of our full research paper Neural Dynamics on Complex Networks will start on August 27th, 10:00 AM PDT (1:00 PM EDT)!

Two workshop papers on drug disocvery has been accepted by ICML 2020 Workshop on Invertible Neural Networks, Normalizing Flows, and Explicit Likelihood Models and KDD 2020 Workshop on Applied Data Science for Healthcare respectively. See our presentation there.

Two papers has been accepted by KDD 2020 as full papers! One is on continuous-time Graph Neural Networks (GNN), and the other is on de novo drug design by flow-based generative GNN model. 2020-05-15

Our tutorial "Recent Advances on Graph Analytics and Its Applications in Healthcare" has been accepted by KDD 2020, curated and presented by: Fei Wang (Cornell University); Peng Cui (Tsinghua University); Jian Pei (Simon Fraser University); Yangqiu Song (Hong Kong University of Science and Technology); Chengxi Zang (Cornell University). 2020-06-01

Our Paper Neural Dynamics on Complex Networks won the Best Paper Award in AAAI 2020 Deep Learning on Graphs: Methodologies and Applications (DLGMA’20) workshop (February 8, 2020, New York City, NY).

My tutorial on Differential Deep Learning on Graphs and its Applications. Held at AAAI-20 (February 7, 2020, New York City, NY).