Pharma & Biotech

HTG Molecular Diagnostics

AI Drug Discovery Platform Using Multi-Omics Data

80%

Cost reduction in early-stage drug discovery

23

Validated candidates with confirmed biological activity

90%

Reduction in unnecessary synthesis of drug candidates

Case Studies

Multi-omics AI data platform for drug, indication, target discovery and repurposing

Check Testimonial

Biotech

Industry

USA

Location

AI Ops & MLOps, Cloud Architecture, UI/UX Design

Services

$200,000 to $999,999

Budget

The team surpassed expectations on timelines, provided much needed guidance and overall input on design, all while operating with a high degree of autonomy.

Carl Kaub

Vice President of Chemistry at HTG Molecular Diagnostic
Challenge

Efficient drug and target discovery and repurposing using genomic, transcriptomic, and proteomic data

See what we can do for you
Outcomes We Deliver

Solution

Our team developed a multi-omics AI data platform enabling the generation of drug candidates with desired physicochemical (logP, logS, pKa, BBBP, etc.) and biological (binding affinity, metabolic stability, toxicity, side effects, etc.) properties.

Tech Stack

To support high-throughput drug discovery and streamline multi-omics data processing across scientific teams, Blackthorn AI applied a production-grade tech stack including:

Python
Node.js
TypeScript
Docker
Angular
Roadmap

Project duration

01 Month

Discovery & Architecture Design

Collected project requirements, designed the scalable architecture for multi-omics processing, and defined key user flows for the web platform and molecule generation.

02 Month

Data Ingestion & Knowledge Graph Foundations

Built ingestion pipelines for omics data, launched the initial biomedical knowledge graph, and deployed secure GCP infrastructure with access control.

03 Month

Generative AI Model Development

Developed AI modules for drug-like molecule generation, added validation filters for key properties, and integrated a scoring system to assess quality and novelty.

04 Month

Multi-Omics Lakehouse & Workflow Automation

Deployed a unified multi-omics data lakehouse, connected AI outputs to the real-time knowledge graph, and automated workflows for ETL, descriptor computation, and annotation.

05 Month

Web Platform & Collaboration Tools

Delivered the researcher-facing web platform with molecule browser, query builder, analytics tools, and integrated front end with the AI engine and export features, along with admin controls.

06 Month

Testing Handoff & Lab-Ready Outputs

Conducted full QA and validation across all components, prepared candidate molecules for wet lab testing, and handed off documentation and onboarding materials to the HTG team.

Team Size

15 team members from Blackthorn.ai
1x Data Engineer
2x Frontend Engineers
2x Backend Engineers
2x QA
1x Sr Bioinformatician
2x AI Engineers
1x AI Architect
1x Sr. Software Solutions Architect
1x Project Manager
1x Chemist
1x Biologist

Delivering Impact

Beyond the values already highlighted, there’s even more to discover. Our commitment to innovation, client success, and impactful results sets us apart

Book a Meeting

23

Validated candidates with confirmed biological activity

Out of 300 molecules screened, 23 candidates demonstrated IC50 values lower than the reference compound

90%

Reduction in unnecessary synthesis of drug candidates

Advanced in silico screening and predictive modeling filtered out low-potential molecules prior to synthesis, minimizing chemical resource use and accelerating time-to-lead

80%

Cost reduction in early-stage drug discovery

By leveraging AI-driven multi-omics data integration and candidate prioritization, the platform significantly reduced experimental overhead and wet-lab costs in the hit-identification phase

Discover More Related Case Studies