Precision Medicine Data Modalities | Sonrai Analytics
Data modalities

Precision medicine
data modalities we can help you with

The precision medicine data modalities Sonrai can help you with span genomic, proteomic, imaging, and clinical datasets - all integrated inside a secure, reproducible environment to generate decision-ready evidence for drug development programmes.

Supporting discovery, translational and clinical programmes across precision medicine.

-4 -2 0 2 4 -4 -2 0 2 4 Factor 1 Factor 7 Overall Survival (months) MOFA+ · Multi-Omics Factor Analysis · Phase II Oncology Trial 40 20 0

Any pipeline.
On demand.

Sonrai supports the full NF-core library on demand - if your analysis requires a pipeline we have not run before, we scope and deploy it. Pipelines are driven by what your programme needs, not a fixed catalogue.

NF-coreFull library supported
98%Cost reduction vs DIY
70%Faster research timelines
Nextflow WDL CWL NF-core AWS HealthOmics BYOPipeline
Bring your own pipeline - upload your Docker container and Sonrai deploys it as a fully managed, auditable workflow inside the Discovery environment.
Powered by AWS HealthOmics - HIPAA and GDPR compliant, fully auditable. Read the AWS case study

Every pipeline runs inside a governed Trusted Research Environment. Outputs are versioned, traceable and reproducible - so the evidence your programme generates is defensible from day one.

PIPELINE EXECUTION INPUT NF-CORE PIPELINE OUTPUT FASTQ nf-core/rnaseq Expression BAM/CRAM nf-core/sarek Variants 10x FASTQ nf-core/scrnaseq Cell types Bisulfite nf-core/methylseq Methylation MZML nf-core/quantms Proteins NGS / FASTQ nf-core/airrflow Repertoire Your data Custom pipeline Insights All pipelines run inside Sonrai Discovery on AWS HealthOmics
Genomics

Identify variants and genetic drivers of disease and treatment response

Whole genome and exome sequencing data reveals the genetic architecture underlying disease biology. Sonrai integrates variant data with transcriptomic and clinical evidence to identify high-confidence drivers and support target selection decisions.

  • WGS (whole genome sequencing)
  • WES (whole exome sequencing)
  • Variant calling and annotation

Most relevant to Target ID and Validation · Patient Stratification

Pipelines we run
nf-core/sarek

All outputs versioned and reproducible inside Sonrai Discovery.

Manhattan plot - germline variants associated with CD8+ T cell infiltration across TCGA tumours

Germline variants associated with CD8+ T cell infiltration - GWAS analysis across TCGA tumours

Case study - Genomics

Precision Patient Stratification

WGS and digital pathology integrated with clinical trial outcomes to identify patient subgroups with distinct response profiles - enabling clearer trial design and patient selection strategy.

View case study
Also relevant Target ID and Validation - Variant data integrated with expression and proteomic evidence to identify and validate high-confidence therapeutic targets.
Transcriptomics

Discover biomarkers, mechanisms and patient subgroups from expression data

Transcriptomic data reveals what genes are actually doing across tissues, cell types and patient cohorts. Sonrai integrates bulk, single-cell and spatial expression data with clinical and imaging evidence to identify the biological signals that drive treatment response.

  • Bulk RNA-seq
  • Single-cell RNA-seq
  • Spatial transcriptomics

Most relevant to Translational Analysis · Target ID and Validation

Pipelines we run
nf-core/rnaseq nf-core/scrnaseq

All outputs versioned and reproducible inside Sonrai Discovery.

Gene expression heatmap

Gene expression heatmap - responder vs non-responder cohort analysis

Case study - Transcriptomics

Immunotherapy Development - From Bench to Bedside

Single-cell and bulk RNA-seq analysis used across preclinical and clinical stages to identify immune cell population changes and prognostic biomarkers of response.

View case study
Also relevant Multi-Modal Biomarker Discovery - RNA-seq integrated with methylation, proteomics, and imaging data to accelerate biomarker discovery in early-stage oncology diagnostics.
Epigenomics

Understand gene regulation and epigenetic drivers of disease

Epigenomic data captures the regulatory landscape that controls gene expression without changing the underlying sequence. Sonrai integrates methylation data with genomic and transcriptomic evidence to identify epigenetic biomarkers and regulatory mechanisms relevant to your programme.

  • DNA methylation (bisulfite sequencing)
  • WGBS / RRBS

Most relevant to Translational Analysis · Target ID and Validation

Pipelines we run
nf-core/methylseq nf-core/atacseq nf-core/chipseq

All outputs versioned and reproducible inside Sonrai Discovery.

Chromatin signatures of treatment response showing open chromatin, H3K4me1 and H3K27ac across healthy control, disease baseline, non-responder and responder patient groups

Chromatin signatures of treatment response - open chromatin, H3K4me1 and H3K27ac tracks across patient groups

Case study - Epigenomics

Multi-Modal Biomarker Discovery

Methylation data integrated with RNA-seq, proteomics, and imaging evidence to identify epigenetic biomarker signatures in early-stage oncology diagnostics.

View case study
Also relevant Target ID and Validation - Epigenomic signals combined with variant and expression data to identify regulatory mechanisms driving disease biology.
Proteomic

Validate biomarker signals and connect protein expression to clinical outcomes

Proteomic data captures what the genome is actually doing at the protein level. Sonrai integrates processed proteomic datasets with genomic and clinical evidence to validate biomarker hypotheses and build the multi-omic case for treatment response.

  • Olink proteomics
  • Mass spectrometry (via nf-core/quantms)

Most relevant to Translational Analysis · Target ID and Validation

Pipelines we run
nf-core/quantms

All outputs versioned and reproducible inside Sonrai Discovery.

Biomarker signal analysis

Protein biomarker signals - expression across patient cohorts

Case study - Proteomic

Multi-Omic Strategy for Optimising Oncology Clinical Trial Success

Olink proteomics integrated with clinical outcomes using MOFA to identify multi-omic biomarkers linked to survival in a Phase II NSCLC trial.

View case study
Also relevant Target ID and Validation - Proteomic signals used alongside genomic data to identify and validate high-confidence therapeutic targets.
Cytometry

Characterise immune cell populations and dynamics from cytometry data

Cytometry data profiles immune cell populations and their behaviour in response to treatment. Sonrai integrates processed cytometry datasets with molecular and clinical evidence to support mechanism of action studies, responder analysis and immune profiling.

  • Flow cytometry
  • CyTOF (processed datasets)

Most relevant to Translational Analysis · Patient Stratification

Tools we use
Pytometry

All outputs versioned and reproducible inside Sonrai Discovery.

Immune cell population analysis

Immune cell dynamics - responder vs non-responder population analysis

Case study - Cytometry

Multi-Omic Strategy for Optimising Oncology Clinical Trial Success

Flow cytometry and CyTOF data integrated with Olink proteomics and clinical outcomes using MOFA to distinguish high responder groups in a Phase II clinical trial.

View case study
Also relevant Immunotherapy Development - Single-cell RNA-seq used alongside cytometry data to characterise treatment-induced immune cell population changes over time.
Imaging

Identify patient subgroups and prognostic signals from tissue data

Imaging data adds spatial and phenotypic context that molecular data alone cannot provide. Sonrai integrates digital pathology and whole slide imaging with omics and clinical datasets to surface biologically meaningful patterns - and support patient selection and stratification decisions.

  • H&E
  • IHC
  • Whole slide imaging

Most relevant to Translational Analysis · Patient Stratification

Pipelines we run
Sonrai Imaging AI WSI foundation models

All outputs versioned and reproducible inside Sonrai Discovery.

Imaging and omics integration

Spatial and molecular signals - integrated tissue analysis

Case study - Imaging

Integrating Imaging and Omic Data

RNA-seq, IHC, and H&E imaging integrated with proteomic and clinical data to identify novel patient subgroups and support drug target discovery in oncology.

View case study
Also relevant Imaging-Derived Prognostic Biomarkers - Whole slide imaging and spatial data used to identify prognostic signals associated with disease progression and outcomes.
Clinical

Build the evidence base for trial design and patient selection

Clinical datasets are what connect biological findings to the decisions your programme needs to make. Sonrai integrates trial data, survival endpoints and response assessments with molecular and imaging evidence to generate the stratification and biomarker outputs teams need to move forward with confidence.

  • Clinical trial datasets
  • Survival and outcomes data
  • RECIST data

Most relevant to Patient Stratification · Translational Analysis

Pipelines we run
Sonrai Clinical Insights RECIST analysis Survival analysis

All outputs versioned and reproducible inside Sonrai Discovery.

Overall survival by treatment arm

Overall survival by treatment arm - patient stratification evidence

Case study - Clinical

Precision Patient Stratification

WGS and digital pathology integrated with clinical trial outcomes to identify patient subgroups with distinct response profiles - enabling clearer trial design and patient selection strategy.

View case study
Also relevant Multi-Omic Clinical Trial Insights - Clinical data from EDC systems and radiology imaging integrated with multi-omic biomarker data to map 12 distinct clinical outcomes.

Working with something
not listed here?

Many programmes involve data combinations that don't fit neatly into a single category. Talk to our team about your specific dataset and we will outline how we would approach it.

Talk to our team Explore all case studies

All analyses are performed within a secure Trusted Research Environment - protected, governed, and fully reproducible.