• Lead data science and computational biology development efforts • Build data science group, recruit team members, and planning and managing budgets • Drive company strategy and execute plans to integrate different data modalities for disease/target prioritization and competition intelligence analysis • Manage AI and data science strategy for company and oversee construction and deployment of AI/ML models in multiple projects • Generate optimal UTR sequences and apply for patents • Analyze virus genomes by deep learnings to trace evolution trend and detect high-risk variants for mRNA vaccine development • Conduct epitope prediction and in-silico antibody affinity maturation based on sequence and structure-based futures • Set up computing infrastructures in AWS for cloud computing • Work with vendors to construct informatics platforms for automatic mRNA sequence design and mRNA production status tracking

• Led team to combine genetics analysis results from multiple Biobank (UKBB and FinnGen) and TCGA for immune-oncology target nomination • Develop machine learning models for multi-omics data for oncology targets related to DNA damaging pathway • Oversaw development of computation pipelines and databases for multi-omics data (different single cell omics data, RNA-Seq, ChIP-Seq and ATAC-Seq) and its migration to cloud environment • Worked with biology scientists and external collaborators for omics project design and data analysis

• Conducted integrative analysis of patient gene expression and clinical phenotype data from clinical trials to identify pharmacodynamics and response biomarkers • Designed machine learning models for patient stratification • Utilized machine learning analysis for integration and visualization of single-cell RNA-seq integration • Led teams to establish in-house sequencing data analysis production pipeline in both local cluster and Amazon Cloud environment and integrate and curate information from in-house sample database • Oversaw development of in-house visualization portal to integrate different data modalities (bulk RNA-Seq, scRNA-Seq), which has been used by several hundred scientists • Provided bioinformatics support for Oncology group to identify and validated drug targets via analysis of high throughput omics data (proteomics, peptidome, next-generation sequencing, flow cytometry and microarray) in different tumor models • Managed benchmark of different methods for immune repertoire (TCR) analysis from bulk and single cell RNAseq dataset, apply these methods in tumor model analysis • Analyzed large-scale cancer genome data from public TCGA and projects to generate hypothesis for new drug targets and MOAs, focusing on cancer related alternative splicing isoforms and gene fusions • Analyzed pre-clinical in-vivo/in-vitro profiling data in mouse and monkey to identify toxicity biomarkers of bi-specific antibodies

• Provide technical advice and guidance for the lab in bioinformatics and statistics• Analysis of gene expression data (RNA-Seq and microarray), discover biomarkers for prediction of organ transplantation result• Made a comprehensive benchmark test on different short-reads assembler on metagenome dataset, provided a guideline for usage of assembly software.• Analysis of metagenome sequences in different environments (human body, rumen)

• Development of bioinformatics analysis pipelines for the metagenome data, created an algorithm for identification of ribosomal genes in metagenomics sequences based on hidden Markov models (http://tools.camera.calit2.net/camera/meta_rna).• Developed a web-server (http://weizhong-lab.ucsd.edu/cdhit_suite/cgi-bin/index.cgi) for the clustering and comparing of biological sequences. Designed a cluster explorer based on tree structure, and a criterion to judge clustering quality based on statistical test.• Analysis of metegenome and metatranscriptome sequences from ocean sampling.

• Developed a new enzyme annotation algorithm called EFICAz2 (http://cssb.biology.gatech.edu/skolnick/webservice/EFICAz2/index.html) that combines the information from sequence alignment, protein family search and important residues detected by support vector machine• Using the metabolic networks assemble from our enzyme prediction and KEGG database, investigate its evolutionary and structure properties• Combining metabolic networks and gene expression information to detect new compounds with anti-cancer activity