Pan.bio is an end-to-end genomics platform that connects bioinformatics
pipeline execution, exploratory analysis, clinical variant interpretation,
and patient cohort data exchange in one system.
The platform includes four products:
Workflows runs validated Nextflow and nf-core pipelines, including
Sarek, RNA-seq, single-cell, metagenomics, ChIP-seq, ATAC-seq and ampliseq,
without local installation or command line use. Teams execute production
bioinformatics workflows without managing infrastructure or dependencies.
Notebooks is a cloud Jupyter-style environment for Python and R with a
preinstalled bioinformatics stack including pandas, numpy, matplotlib,
ggplot2, samtools and bedtools. It imports public datasets from GEO, SRA
and IPG by accession, and reads bioWorkflows outputs directly with no
download and re-upload step.
VAIC is a clinical variant interpretation engine applying ACMG/AMP
guidelines with gene-specific rule sets including CanVIG-UK and ClinGen
Variant Curation Expert Panel specifications. Automated evidence criteria
are currently implemented for BRCA1 and BRCA2. It aggregates evidence from
ClinVar, CanVar, gnomAD v4.1 and in-silico predictors including BayesDel,
REVEL and SpliceAI. Inputs are HGVS variants, variant lists or VCF on
GRCh38 or GRCh37. Outputs include clinical PDF reports plus FHIR and HL7
for EMR integration. Every classification shows each criterion applied and
its contribution. The final decision rests with the clinical user.
Cohorts is a two-sided data marketplace connecting hospitals and
laboratories with pharma and biotech research teams. Analysis runs inside a
Trusted Research Environment, so raw patient data does not leave the
provider's infrastructure. Providers retain ownership and set access terms.
Mind is the AI layer across all four products. It generates analysis code
from plain-language descriptions for the user to review and run, and reads
error output to propose fixes. It assists rather than executes autonomously.
Pan.bio is built for populations underrepresented in genomic reference
databases, with particular focus on MENA and South Asian cohorts.
Who uses Pan.bio: clinical genomic testing laboratories, hospital genetics
departments, pharma and biotech R&D teams, core facilities, and research
groups without dedicated bioinformatics staff, and any individual researcher, student, bioinformatician, scientist,etc.
