Origin

Roadmap & Position in Biotechnology

Designs regulatory DNA that outperforms DeepMind for safer, more precise gene therapies.

Company Overview

Builds the Axis AI platform, a transformer-based generative and predictive model that designs regulatory DNA elements (enhancers, promoters) to enable safer, more precise cell and gene therapies with programmable control over gene expression.

What They're Building

The company's public product roadmap & what they're committed to building.

Origin has publicly released the Axis model with free API access for researchers, announced plans to expand into multi-modal biological modeling (RNA, protein, cellular representations), and published benchmarks showing Axis outperforms Google DeepMind's AlphaGenome by 6.7% in regulatory element activity prediction. They've detailed a vision for a broad library of validated, cell-type-specific regulatory elements and positioned Axis as a foundational platform for programmable biology beyond gene therapy.

Latest Intelligence

Zeitgeist tracks private signals to determine where the company is heading strategically.

Competitors

AI-Native Genomics

Dyno Therapeutics (AAV capsid design), Profluent Bio (protein/gene editing AI), Basecamp Research (biodiversity-driven genomics).

Traditional Gene Therapy Tools

Genscript, Twist Bioscience (DNA synthesis).

Big Tech AI for Biology

Google DeepMind (AlphaGenome, AlphaFold), Microsoft Research (biological foundation models).

Academic Platforms

Broad Institute (Malinois model), UCSF gene therapy programs.

Origin

's Moat:

Axis model outperforms DeepMind's AlphaGenome by 6.7% on regulatory DNA activity prediction. Free API access for researchers builds a community moat while pharma partnerships monetize. Proprietary training data on enhancer and promoter sequences is the core barrier; Dr. Manolis Kellis (MIT, 85K+ citations) as advisor adds scientific credibility.

How They're Leveraging AI

AI Use Overview:

Using generative DNA sequence design with transformers, self-improving biological data loops, and predictive off-target risk modeling for safety.

More Similar Companies

10xScience

Turns weeks of manual protein analysis into minutes for drug development teams.

CellType

Simulates human biology with AI to predict drug effects and run virtual trials.

Google CEO Sundar Pichai highlighted their C2S-Scale 27B model for generating a novel cancer hypothesis that was later validated experimentally. CellType simulates human biology to predict drug effects using foundation models presented at ICML 2024, with all deals coming inbound from top-10 pharma. Yale professor turned down Google to build it.

Ditto Biosciences

Mines parasite genomes to discover protein therapeutics for autoimmune diseases.

Parasites evolved to suppress human immune responses over millions of years. Ditto mines their genomes for immunomodulatory proteins, and over 98% of those proteins remain uncharacterized. Three PhDs from Harvard, Berkeley, and UCSF with 40+ years of combined expertise in host-parasite biology.

Mango Medical

Automates surgical planning for orthopedic procedures from CT scans using agentic AI.

Surgical planning for shoulder replacements takes hours of manual CT scan interpretation. Mango automates it in seconds via API, already past $500K ARR before demo day, with an 8-figure LOI from a leading orthopedic company. Only company in YC W26 pursuing FDA 510(k) clearance.