VIB-KU Leuven Center for Cancer Biology (CCB)

Bioinformatics & AI

Our story

Every discovery in modern cancer biology begins with data; mountains of it. 

Sequencing reads that fill servers overnight. Long‑read single‑cell assays with thousands of tiny barcodes. Gigabytes of microscopy and mass spectrometry images. It’s exciting. It’s powerful … But it can also be overwhelming.

Most labs simply don’t have the time, or specialized experience to process all of this into something meaningful. And that’s exactly why the Bioinformatics & AI Expertise Center was created.

At the VIB‑KU Leuven Center for Cancer Biology, we exist to make advanced data analysis accessible, reliable, and reproducible for every CCB group; not just for experts, but for everyone who wants to push their research further.

 

 

Contact: masoomeh.rahimpour@kuleuven.be 

ORCID: 0000-0003-1713-9394 

 

How we help - Our services

Training and workshops

Practical, hands‑on sessions that help you get started quickly on HPC onboarding, containerization (docker/singularity), generative AI for biologists, and more.

HPC assistance

Guidance on running large‑scale analyses efficiently and reproducibly on HPC.

AI‑enabled analysis

We help researchers use AI models in ways that genuinely support scientific discovery. These include automated tissue or ROI, detection/segmenation, ML‑based clustering, denoising, or classification, and more.

AI agent–based analysis

Beyond individual models, we also support AI agents; small, task‑focused systems that can automate multi‑step workflows.

Pipeline development and maintenance

We design, build, and maintain pipelines that scale smoothly and are easy to reuse.

Analysis guidance

  • Single‑cell and long‑read technologies
  • Spatial transcriptomics
  • Image analysis and computer vision
  • Multi‑modal data integration
 

Projects and pipelines (selected portfolio)

  • scdnalong: Long‑read single‑cell DNA preprocessing: Nextflow pipeline to run quality control, barcode detection and correction, alignment, and deduplication for single‑cell long‑read DNA libraries.
  • Roadmap: Planned coupling with nf‑core/scnanoseq to support simultaneous processing of single‑cell long‑read transcriptomic and genomic data (e.g., SPLONGGET).
  • lrsomatic: Long‑read somatic variant calling (WGS): Nextflow pipeline to run quality control, alignment, phasing, short‑variant calling, structural variant calling, and copy‑number calling for PacBio/ONT WGS data.
  • Spatial Metabolomics Shiny App: Preprocess and reorganize spatial metabolomics data exported from SCiLS; perform basic analysis and statistical testing between user‑defined annotations
  • AI enabled image analysis: Automated whole slide image anslysis, and tissue segmentation.
  • Trainings and workshops: We design and deliver training sessions covering the fundamentals of LLMs, practical applications in biological research, and best practices for integrating LLMs into scientific workflows (i.e. Generative AI: Introduction to Large Language Models (LLMs) and Their Applications in Research)
     
 

Roadmap and planned projects

  • Multi‑omics integration pipelines
  • Visium (HD) + Mass Spectrometry Images: Co‑registration, region annotation, cross‑modal quantification, and joint statistical models for spatial transcriptomics and spatial metabolomics.