Siwen Zhang
  • Projects
  • Skills
  • Bioinformatics
  • Publications
  • ResumĂ©

On this page

  • Precision Scientific · 2021–2024
  • GrandOmics Biosciences · 2019–2021
  • Geneis Beijing · 2017–2019

👩‍🏫 Professional Activities

I have spent 7+ years building bioinformatics and data science workflows for clinical genomics, translational research, rare disease diagnosis, and pathogen surveillance. My work focuses on turning high-dimensional biomedical data into validated, reproducible, and decision-ready analytical systems.

Precision Scientific · 2021–2024

R&D | Middle bioinformatics engineer

  • Delivered MRD/HRD analytics for oncology studies, including regulatory-ready reports and work presented at SGO 2024.
  • Built platelet RNA-seq machine learning classifiers for differential diagnosis and biomarker discovery.
  • Productionized WDL/Cromwell cloud workflows for cancer genomics, reducing both runtime and cost by 50%.
  • Supported bioinformatics analysis for 5 cell and gene therapy products.
Details

Cancer auxiliary diagnosis enablement

  • Designed and productionized circulating tumor DNA-based Minimal Residual Disease (MRD) pipelines, covering study design, feature engineering, data analysis, and statistical reporting.
  • Delivered 4 clinical MRD studies and translated results into regulatory-ready reports; one outcome was presented at SGO 2024; co-authored 2 manuscripts, one published.
  • Analyzed whole-genome doubling (WGD) using low-pass whole-genome sequencing at around 1x coverage; standardized WGD definitions across four studies.
  • Built machine learning classifiers using platelet RNA-seq data to differentiate uterine sarcoma from leiomyoma, covering preprocessing, feature engineering, model evaluation, and biomarker detection.
  • Contributed to the national HRD reference standard project led by China’s National Institutes for Food and Drug Control.

Cell and gene therapy bioinformatics

  • Built analysis workflows for viral integration site mapping, AAV mutation detection, and CRISPR off-target assessment.
  • Supported product development and clinical trials for 5 cell and gene therapy products.

Bioinformatics workflow automation

  • Designed and productionized an integrated bioinformatics pipeline for cancer genomics using WDL and Cromwell; automated data processing and analysis workflows on Alibaba Cloud.
  • Developed modular WDL components for each pipeline step and validated output consistency.
  • Reduced pipeline runtime by 50% and cost by 50%.

GrandOmics Biosciences · 2019–2021

R&D | Middle bioinformatics engineer

  • Led development of China’s first targeted capture panel for third-generation sequencing in Duchenne muscular dystrophy diagnosis.
  • Built COVID-19 pathogen surveillance workflows for mutation tracking, lineage analysis, metagenomic detection, reporting, and visualization.
  • Benchmarked Nanopore, PacBio, and Illumina sequencing platforms for SNV, InDel, and structural variant detection.
  • Contributed to 4 rare disease studies and 2 peer-reviewed publications.
Details

Rare disease diagnosis

  • Led development of China’s first targeted capture panel for third-generation sequencing for Duchenne muscular dystrophy (DMD).
  • Improved sensitivity and accuracy for SV, SNV, and InDel detection compared with gold-standard approaches.
  • Automated the workflow, conducted 4 studies, and published 2 papers.

Pathogen surveillance and diagnosis

  • Built a Galaxy-based pathogen surveillance system during COVID-19 for mutation tracking, lineage analysis, and visualization.
  • Designed targeted amplification kits covering 30 respiratory pathogens.
  • Implemented end-to-end pipelines for identification, automated reporting, and interactive dashboards.
  • Delivered analysis tools accessible to wet-lab and clinical users.

Sequencing technology benchmarking

  • Conducted systematic benchmarking of basecalling and variant accuracy across sequencing platforms.
  • Compared Nanopore R9 and R10 chemistry performance.
  • Evaluated Nanopore, PacBio, and Illumina for SNV, InDel, and structural variant detection.

Geneis Beijing · 2017–2019

R&D | Bioinformatics engineer

  • Developed oncology biomarker assays and reproducible analysis workflows for lung and gastric cancer studies.
  • Implemented CNV, MSI, TMB, survival, RNA-seq, and methylation analyses for translational research.
  • Supported clinical interpretation through validated thresholds, visualizations, and biological summaries.
  • Co-authored early work on gene fusion detection and liquid-biopsy MSI analysis.
Details

Oncology assay and biomarker panel development

  • Developed a targeted amplification panel for lung cancer biomarkers; established CNV baseline thresholds using MAD-based normalization.
  • Implemented MSI profiling and visualization for genomic instability assessment.
  • Delivered reproducible analysis workflows for clinical reporting.

Multi-omics analysis in developmental biology

  • Performed differential expression and methylation analysis of mouse oocytes; identified key transcription factors and maturation-associated pathways.
  • Integrated transcriptomic and epigenomic signals to characterize developmental regulation.
  • Generated interpretable visualizations and biological summaries for collaborators.

Clinical cancer genomics and survival analysis

  • Conducted retrospective gastric cancer genomics analysis across SNV, InDel, CNV, MSI, and TMB.
  • Evaluated clinical correlations and survival outcomes using Kaplan-Meier analysis.
  • Supported biomarker interpretation for translational research studies.