Curriculum Vitae

Flavio C. Lombardo, PhD

Computational Cancer Biologist/Embedded Bioinformatician (Postdoctoral Researcher) Generating real-world evidence from clinical multi-omics datasets and leading observational health data analytics projects for precision medicine applications. Collaborating with clinical teams across Switzerland.🎓🧬💻
University Hospital Basel
📍 Switzerland
✉️ fl@flaviolombardo.site

Professional Experience

2021 - Present
Computational Cancer Biologist/Embedded Bioinformatician (Postdoctoral Researcher)
Department of Biomedicine, University of Basel & Universitätsspital Basel

Leveraging clinical multi-omics data (bulk and single cell) to identify biomarkers in gynecological cancer cohorts. Deploying advanced machine learning and modeling techniques to drive discovery and enhance precision medicine approaches.

Key Achievements:

  • Successfully applied feature engineering to multi-omics datasets, generating biological insights on novel biomarkers
  • Developed machine learning models for patient stratification and outcome prediction
  • Published CRAN package drugsens for imaging data analysis
  • Mentoring BSc/MSc students
  • Teaching R and variant annotation analysis
2020
Intern in scientific computing and consulting (Data Science)
Novartis, Basel

Developed R-Shiny applications for data science and statistical analysis to support Phase III clinical trials.

Key Contributions:

  • Created tailored applications for analyzing Phase III clinical trial data
  • Enhanced and optimized existing R-Shiny packages within Novartis
  • Streamlined deployment of R packages through containerization
2016 - 2019
PhD Research Scientist - Drug Development
University of Basel

Applied PK/PD mathematical modeling to evaluate novel compounds, leading to the development of an innovative drug screening platform.

Research Highlights:

  • Developed and validated PK/PD models for lead compounds
  • Designed automated analysis pipelines for PK/PD data
  • Created web-scraping and data mining tools for multi-source data integration or drugs
  • Structure activity relationship analysis (SAR)
  • Developed with Biosystems Engineering Department at ETH (DBSSE) a novel drug screening platform

Education

2019
PhD in Microbiology and Drug Development
University of Basel, Switzerland
  • Thesis: “Development of novel strategies to fill the empty drug pipeline for schistosomiasis: from drug sensitivity assay development to preclinical studies”
  • Created analytical pipelines for PK/PD modeling
2014
MSc in Industrial and Molecular Biotechnology
University of Bologna (Italy) & Karolinska Institute (Sweden)
  • Thesis: “Methods for IL-10 detection in NF-κB deficient mouse model”
  • Gained proficiency in flow cytometry data analytics
2011
BSc in Molecular Biology
University of Catania, Italy
  • Developed molecular assays for colon carcinoma (CRC) antibody evaluation

Technical Expertise

Production Programming & Development

Core Languages (8+ years production experience)

  • R: Expert - Published CRAN author, production pipelines processing patients genomics data, Bioconductor contributor
  • Python: Advanced - ML pipelines (scikit-learn, PyTorch), clinical data ETL
  • Bash/Linux: Advanced - HPC environments, SLURM scheduling, automated deployments across compute nodes
  • SQL: Proficient - Clinical database integration, GDPR-compliant queries, multi-omic data warehousing

Expanding Expertise

  • Julia: Scientific computing, high-performance numerical analysis
  • Rust: Currently developing next-gen bioinformatics tools for 100x performance gains

Machine Learning & Analytics

Production ML Applications

  • Biomarker Discovery: Random Forest models achieving >90% accuracy in 300+ patient cohorts in patients stratification
  • Clinical Decision Support: Logistic regression for treatment response prediction, deployed in clinical workflows
  • Feature Engineering: Multi-omic integration, dimensionality reduction, clinical outcome modeling
  • Deep Learning: Expanding PyTorch expertise for potential usage in omics data
  • LLMs: Fine tuning for clinical data

Statistical Methods

  • Survival Analysis: Time-to-event modeling for clinical outcomes
  • Bayesian Methods: Clinical trial design, treatment effect estimation
  • PK/PD Modeling: Population pharmacokinetics for drug development
  • Causal Inference: Treatment effect estimation from observational clinical data

Industry-Grade Infrastructure

Cloud & Scalability

  • AWS/Google Cloud and Terra: Genomic analysis pipelines, auto-scaling compute clusters processing many samples
  • Docker/Singularity: Containerized deployments ensuring reproducibility across regulatory environments
  • Nextflow: Production workflows with automated QC, error handling, and clinical reporting
  • Git/CI-CD: Collaborative development, automated testing, deployment pipelines

Specialized Bioinformatics Applications

Multi-omics Integration (5+ years)

  • Genomics, proteomics, transcriptomics, imaging data for precision medicine applications
  • Successfully integrated datasets from several different platforms for biomarker discovery
  • Developed standardized workflows

Single-cell Analysis (3+ years)

  • Seurat, Scanpy, spatial transcriptomics for tumor microenvironment characterization
  • Processed single-cell samples for biomarker identification and study of responses to drugs
  • Taught SIB course on variant calling and annotation in cancer genomics (2024)

Cancer Genomics (4+ years)

  • Somatic variant calling, mutation signature analysis, driver gene identification
  • GATK4/Mutect2 pipelines processing clinical samples for precision oncology
  • Deconvolution analysis with custom signature matrices

Drug Development (PhD and Industry)

  • PK/PD modeling, drug sensitivity screening, mechanism of action studies
  • Novartis experience with Phase III clinical trial analytics and regulatory submissions
Continuous Learning & Innovation

Currently expanding expertise in:

  • Foundation Models: PyTorch and JAX for protein sequence analysis and drug discovery applications
  • Causal Inference: Advanced statistical methods for treatment effect estimation
  • High-Performance Computing: Rust development for next-generation bioinformatics algorithms

Last updated: January 2025

Bioinformatics Tools

  • Single-cell: Seurat, Scanpy, scVI-tools, CellRanger
  • Genomics: Bioconductor, GATK, samtools, bcftools
  • Proteomics: MaxQuant, Perseus, MSstats
  • Workflow: Nextflow, Snakemake
  • Visualization: tidyverse, ComplexHeatmap, plotly, matplotlib, seaborn, altair
  • Data Protection: GDPR compliance for clinical research data
  • Cloud Computing: AWS, GCC
  • LLMs: ollama

Selected Achievements

  • 📦 CRAN Package Author: Published drugsens package for drug sensitivity analysis
  • 🏆 Research Innovation: Developed novel drug screening platform combining electrical impedance and microfluidics
  • 📊 Machine Learning Publication: First author on paper using Random Forest for ATR-FTIR spectroscopic data analysis (in press)
  • 👨‍🏫 Teaching: SIB instructor for cancer genomic variants courses
  • 🤝 Industry Collaboration: Successfully completed projects at Novartis improving clinical trial analysis

Professional Development

Currently expanding expertise in:

  • 🧠 PyTorch and JAX for deep learning applications
  • 🧬 Foundation models for protein sequence analysis
  • 📈 Causal inference statistics
  • 🦀 Rust programming for high-performance bioinformatics tools