What challenges did Sonrai face before AI implementation?

Manual annotation of scRNA-seq cell clusters is time-consuming and error-prone. The workflow slows research and increases reliance on specialized immunologist expertise. The solution also needed strong governance and security for sensitive biological data.

What was the impact of the AI solution?

Sonrai cut annotation times by up to 50%. The solution achieved five times fewer errors in scaled annotation and interpretation. Sonrai saves clients up to $20,000 per experiment. Immunologists can focus more on higher-level analysis and strategy instead of manual tasks.

Rank#773of 2,978

Source

Sonrai Accelerates Single-Cell RNA-seq Data Analysis Using Amazon Bedrock

Use case typeLife sciences innovationUpdated Jun 13, 2026

Researchers in the biotech and pharmaceutical industries grapple daily with the complexity and volume of single-cell RNA sequencing (scRNA-seq) datasets, which are crucial for understanding diseases and developing targeted therapies. Sonrai sought to use generative AI to simplify and streamline interpretation of scRNA-seq data and reduce the manual burden on immunologists. Sonrai Discovery uses large language models through Amazon Bedrock to automate cluster annotation, generate consistent text reports, and support faster analysis on AWS.

Organization: Sonrai
Industry: Pharma
Location: United Kingdom
Published: May 2026

Reported outcomes

error reductionQuality & accuracy

−50%annotation time reduction20,000 USDcost savings per experiment

Strategic outcomes

New product / capabilityAutomated cluster annotation and report generationSpeed & agilityAccelerated scRNA-seq analysis workflowEmployee experienceReduced manual burden on immunologistsRisk & complianceBuilt with strong governance and security

Catalog median for quality & accuracy deployments: −40% across 42 reported metrics. Compare benchmarks →

Primary read

Use case focus

Showing 3 of 3

1Generative AI for Bioinformatics
2Drug Discovery Acceleration
3Data Annotation Automation

Manual annotation of scRNA-seq cell clusters is time-consuming and error-prone.
The workflow slows research and increases reliance on specialized immunologist expertise.
The solution also needed strong governance and security for sensitive biological data.

Sonrai built its scRNA-seq analysis technology stack entirely on AWS.
Amazon Bedrock powers large language model-based cluster annotation and text report generation.
Amazon SageMaker supports data processing and modeling workflows.
Amazon S3 is used to store FASTQ and other omics files.
AWS CDK is used to define and deploy infrastructure automatically.

Technologies

Amazon Bedrock Amazon SageMaker Amazon S3 AWS CDK

Sonrai cut annotation times by up to 50%.
The solution achieved five times fewer errors in scaled annotation and interpretation.
Sonrai saves clients up to $20,000 per experiment.
Immunologists can focus more on higher-level analysis and strategy instead of manual tasks.

Architecture

Sonrai Discovery is built on AWS with Amazon Bedrock for LLM-driven cluster annotation and report generation, Amazon SageMaker for ML workflows, Amazon S3 for omics data storage, and AWS CDK for automated infrastructure deployment.

Sources & evidence1

Groundedness: 5/5Type: Customer StoryPublished: May 27, 2026Publisher: AWSEvidence: VendorConfidence: High

Primary source

AI-generated summary. Verify important details with the linked sources before relying on this case.

Explore related AI use cases

Customer evidence