Customer Stories
/
Accelerating Drug Discovery By AI-Driven Molecule Generation

Life Science

Accelerating Drug Discovery By AI-Driven Molecule Generation

AI molecule generation platform to speed up early-stage drug discovery in skin rejuvenation.

12x

Less drug candidates in HTS

Molecules confirmed active through wet lab validation

10x

Faster preclinical narrowing compared to baseline

Customer Stories

For a series B biotech company working on skin rejuvenation therapies.

Pharma & Biotech

Industry

USA

Location

Generative AI modeling, transcriptomic analysis, pathway prediction, model validation

Services

Challenge

Identifying and prioritizing novel small molecules for skin rejuvenation using transcriptomic data and pathway analysis — in a scalable, efficient way to support early-phase drug development.

See what we can do for you

Outcomes We Deliver

Solution

Blackthorn AI delivered a pipeline that combined generative AI, pathway graphs, and omics data ingestion to power molecule generation. The system enabled fast iteration, integration of biological constraints, and reduced reliance on trial-and-error lab synthesis.

Let’s talk about what’s possible

Tech Stack

To accelerate molecule discovery, Blackthorn AI used:

Python

FastAPI

OpenAI

PyTorch

Node.js

React

TypeScript

Neo4j

Airflow

PostgreSQL

AWS

Terraform

Docker

Python

FastAPI

OpenAI

PyTorch

Node.js

React

TypeScript

Neo4j

Airflow

PostgreSQL

AWS

Terraform

Docker

Roadmap

Project duration

1–2 Months

Initial Model & Analysis

Developed baseline predictive models from transcriptomics data and performed differential gene expression analysis.

3–4 Months

Pathway Mapping & Feature Design

Integrated pathway-level biological data to prioritize targets and refine compound features.

5–6 Months

Data Expansion & Model Training

Ingested additional RNASeq datasets and trained PerturbNet for more accurate compound activity prediction.

7–8 Months

Molecule Generation & Filtering

Generated thousands of novel compound candidates with skin rejuvenation potential using LLM-based tools.

9–10 Months

Handoff & Reporting

Finalized delivery, transferred documentation and results, and prepared for wet-lab validation phase.

1–2 Months

Initial Model & Analysis

Developed baseline predictive models from transcriptomics data and performed differential gene expression analysis.

3–4 Months

Pathway Mapping & Feature Design

Integrated pathway-level biological data to prioritize targets and refine compound features.

5–6 Months

Data Expansion & Model Training

Ingested additional RNASeq datasets and trained PerturbNet for more accurate compound activity prediction.

7–8 Months

Molecule Generation & Filtering

Generated thousands of novel compound candidates with skin rejuvenation potential using LLM-based tools.

9–10 Months

Handoff & Reporting

Finalized delivery, transferred documentation and results, and prepared for wet-lab validation phase.

Team Size

1 x Senior Bioinformatician

1 x AI Research Engineer

2 team members from Blackthorn.ai

1 x Senior Bioinformatician

1 x AI Research Engineer

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

37

Molecules

Confirmed active compounds in wet lab – significantly validating model accuracy and ROI.

9

Months

Saved in candidate discovery

10x

Faster

Preclinical narrowing compared to baseline

37

Molecules

Confirmed active compounds in wet lab – significantly validating model accuracy and ROI.

9

Months

Saved in candidate discovery

10x

Faster

Preclinical narrowing compared to baseline

Accelerating Drug Discovery By AI-Driven Molecule Generation

For a series B biotech company working on skin rejuvenation therapies.

Pharma & Biotech

USA

Generative AI modeling, transcriptomic analysis, pathway prediction, model validation

Identifying and prioritizing novel small molecules for skin rejuvenation using transcriptomic data and pathway analysis — in a scalable, efficient way to support early-phase drug development.

Solution

To accelerate molecule discovery, Blackthorn AI used:

Project duration

1–2 Months

3–4 Months

5–6 Months

7–8 Months

9–10 Months

1–2 Months

3–4 Months

5–6 Months

7–8 Months

9–10 Months

Team Size

Delivering Impact

37

9

10x

37

9

10x

Discover More Related Customer Stories

Discover More  Related Customer Stories