Ryan Yang

Ryan Y. Yang
PhD, MSc


Personal Profile

Multi-disciplinary research data scientist with 10+ years experience in research data analysis, data management, molecular modeling, predictive modeling and machine-learning on supporting cancer drug discovery, cancer genomics and personalized medicine with data-driven decision making. A self-motivated professional with excellent interdisciplinary communication skills and a creative approach to problem solving.

Professional Experience
Research Data Scientist, Bioinformatics
Stanford University, USA

2016 - Present

Leading the design, development of analytics platform and solutions to consolidate and analyze unstructured, diverse "big data" that generated by Circulating Tumor DNA (ctDNA) based liquid biopsy technology for personalized cancer treatment.

Head of Product Development
Virtual Reach Technology Ltd, Canada/USA

2015 - Present

Spearheaded the design and implementation of an automated protocol, which utilizes diverse analytics tools leading to more reliable predictive model generation, in order to help patients and doctors to make better decisions on treatment options.

Research Program Lead, Bioinformatician
University of British Columbia / BC Cancer Agency, Canada

2013 - 2015

Led bioinformatics, data analysis and project management activities across multiple collaborative research projects, in interpreting next-generation sequence data for defining mutational landscapes in various rare cancer diseases. Focused on characterization of cancer genomes for determination of pathogenic driver mutations, and gene expression analyses in cancer subtypes.

Senior Scientist
Crown Bioscience Inc. China

2011 - 2013

Led Computational Chemistry effort and applied structure-based molecular design techniques to support multiple cancer drug discovery projects in collaboration with leading pharmaceutical companies. liaised with internal project teams and outsourcing partners for project management and resource allocation

Senior Research Scientist
AstraZeneca R&D, Sweden

2008 - 2011

Initiated on the investigation of a novel molecular topology concept with the discovery of several new molecular descriptors, that enable a better understanding of drug-likeness, and has made a significant impact on the study of structure-property relationships in medicinal chemistry and drug design through several publications. Designed and implemented automated workflows for large-scale drug discovery data management, data mining, visualization and interpretations, ranges from the analysis of high-throughput screening data, to the prediction of adverse drug reactions to support research decision-making.

Research Assistant / PhD Candidate
Trinity College Dublin, Ireland

2003 - 2008

Developed, published and commercialized a novel tiered Structure-Based Virtual Screening software platform for computer-aided drug discovery, that started with a proof of concept, and throughout development, implementation and validation phases.

Areas of Expertise
  • Bioinformatics
  • Cheminformatics
  • Molecular Modelling
  • Drug Discovery
  • Data Management
  • Data Mining
  • Full-stack development
  • Project Management
Education
Trinity College, University of Dublin

PhD in Computational Chemistry

Research focused on the methodological developments of novel virtual screening workflow, and application of virtual library synthesis for hit-to-lead optimization in early drug discovery, that has comprised proof of concept, technology development and computational implementation.

University of Leeds

MSc in Bioinformatics

Developed and implemented machine-learning algorithm for geometric classification of protein structure, and prediction from its amino acid sequence using Artificial Neural Networks.

Research Projects

For more information on some of my research projects, see my Publications page.