Related
Dr. Yu “Max” Qian is an associate professor specializing in single cell cytometry informatics. After PhD graduation, he joined the University of Texas Southwestern Medical Center at Dallas (UT Southwestern) as a postdoctoral senior research associate, where he was trained on immunology informatics, bioinformatics, and clinical informatics. He was appointed as an assistant professor of Department of Clinical Sciences and Department of Pathology of UT Southwestern in 2010. Before joining JCVI in 2013, he was leading the natural language processing project at the Parkland Center for Clinical Innovation (PCCI), Parkland Health and Hospital System at Dallas on real-time disease identification for re-admission reduction.
As an informatics researcher, Dr. Qian leads and co-develops a suite of standards, models, algorithms, and software systems for computational cytometry data analysis, including FLOCK/ImmPort FLOCK, FCSTrans, FuGEFlow, MIFlowCyt, and GenePattern FCM suite. These systems have been used by informatics researchers and immunologists to improve the management of experiment metadata, explore cellular phenotypic profiles, identify novel cell subsets, and quantify immune responses to clinical treatments. Collaborating with UC San Diego, Stanford, UC Irvine, and San Diego Supercomputer Center, he is leading the technical development of a computational infrastructure for improving precision diagnostics of certain types of blood cancers through identifying cell-based biomarkers from polychromatic flow cytometry (FCM) experiment data. He was one of the previous leading developers of the FCM component of ImmPort, the NIAID/DAIT-funded immunology database and analysis portal. He has been customizing analytical pipelines and performing computational analytics of big FCM data for multiple NIH-funded research projects, including the Respiratory Pathogens Research Center (RPRC) at University of Rochester and the Human Immunology Project Consortium (HIPC) center at La Jolla Institute for Allery and Immunology.
Dr. Qian had been a teaching assistant of UT Dallas for Computer Science classes on computer graphics, machine learning and natural language processing, software architecture, and computer architecture. He also taught classes at the Pathology Department of UT Southwestern on applied bioinformatics and DNA microarray data analysis.
Dr. Qian received his PhD degree in Computer Science from the University of Texas at Dallas (UT Dallas) in 2006, and an ME and a BS degree in Computer Science from Nanjing University, in 2001 and 1998, respectively.
Patents
- Patent US9147041 B2: Clinical dashboard user interface system and method, Parkland Center for Clinical Innovation, with Amarasingham R., et al., filed on 13 Sept 2012, granted on 29 Sept 2015.
- Patent US9536052 B2: Clinical predictive and monitoring system and method, Parkland Center for Clinical Innovation, with Amarasingham R., et al., filed on 13 Sept 2012, granted on 03 Jan 2017.
Research Priorities
- Computational methods for single cell flow, imaging, and mass cytometry data processing and analysis
- Design and implementation of cyberinfrastructures for immunology data management and analysis
- Integration of cytometry and RNA-seq data for cell type specific gene expression profiling
- Text mining and data classification methods for disease identification from clinical notes
- Computational methods to automatically scrub protected health information from clinical notes
- Graph-based management and exploration of cell type knowledge for biomarker discovery
Publications
Research Priorities
- Computational methods for single cell flow, imaging, and mass cytometry data processing and analysis
- Design and implementation of cyberinfrastructures for immunology data management and analysis
- Integration of cytometry and RNA-seq data for cell type specific gene expression profiling
- Text mining and data classification methods for disease identification from clinical notes
- Computational methods to automatically scrub protected health information from clinical notes
- Graph-based management and exploration of cell type knowledge for biomarker discovery
Discriminative Machine Learning for Blood Cancer Precision Diagnostics
Our goal is to improve and utilize machine intelligence for elucidating cancer heterogeneity and disease endotypes for supporting cancer precision medicine.