Gordion Bioscience | LinkedIn

Overview

MOTIVATED TO MAKE BETTER DRUGS -POWERED WITH TUMOR DATA -DELIVERED BY MACHINE LEARNING

Today is one of those goose‑bump moments at Gordion Bioscience !We’ve officially licensed out our MTAP‑deleted‑tumour programme to the brilliant minds at Kohde Pharma .This licensing deal proves and underscores our firm believe that patient data+AI outshine cell‑line models. Why? Because our platform can uncover cancer vulnerabilities that just aren’t visible in cell lines. This opens the doors to uncovering entirely new targets and, ultimately, better treatment outcomes.

Why this milestone matters : MTAP deletions appear in ~15% of all cancers, yet patients still lack targeted options. Kohde Pharma has full access to Gordion’s AI‑powered platform. Gordion mined real patient data and uncovered new synthetic‑lethal targets.

Huge congratulations to Thomas Wirth , Pawel Zawadzki , and the entire teams at Kohde Pharma and Gordion Bioscience for making this happen! One program licensed. Many more to come. The future of drug discovery is data‑native, AI enabled, patient‑powered and boldly collaborative. #DrugDiscovery #MTAP #OncologyInnovation #DataDrivenScience #AIDrugDiscovery #PrecisionMedicine #Collaboration #TeamingUpForPatients

Leadership and Team Updates

Welcome Thomas Wirth to Gordion Bioscience as our Interim Chief Business Officer!Could there be better news than having Thomas join us to help shape the future with his expertise, leadership, and vision?

With over 20 years in biotech, Thomas has been instrumental in bringing groundbreaking science to the clinic—leading Phase I trials, securing major investments, and driving innovation in oncology and regenerative medicine. His experience spans early-stage venture development, strategic growth, and navigating complex regulatory landscapes.Thomas has held key leadership roles, including Chief Business Officer at Nodus Oncology, Strategic Advisor at GIO Therapeutics, and Executive in Residence at Cumulus Oncology, where he scouted oncology investment opportunities and drove fundraising initiatives. As the founder of Aurealis Therapeutics, he built a novel gene and cell therapy platform, secured major industry partnerships, and played a pivotal role in advancing innovative treatments. It’s so good to have you on board, Thomas!

#Oncology #Teamwork #Collaboration #DrugDevelopment #MakingAnImpact

CEO at Gordion Bio, pioneering patient-derived drug program designs

Industry Perspective

Another reason why DeepSeek is such a 'Sputnik moment'—not just for AI but also for drug discovery—is that it demonstrated a systemic approach to engineering breakthroughs by questioning key assumptions one by one (e.g., do you need so much data and compute?). Ask your startup : what underlying principle or belief—has your team chosen to challenge? Questioning these foundational assumptions is what separates teams engineering breakthroughs from those relying on luck.

At Gordion, we’ve embraced this principle to build our model. Two years ago, most people told us it was impossible to create a cancer genomics model for novel target identification using 10,000 datasets, each with 3.2 billion variables. By challenging this assumption and applying the approach described by Jon Turow below, we’ve developed a model capable of identifying novel drug targets invisible to other methods.

Jon Turow

Builder. Madrona Partner. Ex Amazon AWS.

7mo

DeepSeek R1's performance and cost numbers have the industry's attention, but its approach to model building might be the bigger breakthrough. Yes, it's a gift to app developers who get powerful new open-source models to build on. And yes, major labs will use these efficiency innovations to build even bigger models.But there's a deeper story here : DeepSeek shows how domain expertise might matter more than raw compute in building specialized AI models. Their approach - using verifiable data and efficient reward functions - creates a new path for teams with deep domain knowledge to build their own models at a fraction of the usual cost.Consider that DeepSeek emerged from a hedge fund, where the reward function is crystal clear. This hints at how other domain experts might leverage similar techniques - whether in finance, medicine, law, or industrial operations.We're entering an era where smart training may matter more than raw compute. The future of AI may not just belong to those with the biggest GPU clusters, but to those who can most effectively combine domain expertise with clever training techniques.I explore this shift in depth here :

Statements from Leadership

CEO at Gordion Bio, pioneering patient-derived drug program designs

Pawel Zawadzki

CEO at Gordion Bio, pioneering patient-derived drug program designs

Upcoming Activities

10mo Edited

Excited to be back at BIO-Europe! Looking forward to talking about In-Patient CRISPR screening for novel target ID.

Incredible to be here at the 36th EORTC-NCI-AACR Symposium in Barcelona, surrounded by so many brilliant minds advancing cancer research and drug development! It’s inspiring to engage in meaningful discussions, gain insights, and observe the latest innovations in oncology.Being part of this vibrant community reinforces our commitment Gordion Bioscience to integrating real patient tumor data into drug development, helping improve trial success and drive impactful treatments. Thank you to everyone who has shared their expertise and vision with us so far—we’re excited to see what’s next!If you’re here, come say hello to Pawel Zawadzki and the team #ENA2024 #CancerResearch #OncologyInnovation

• Find people you know at Gordion Bioscience

#J-18808-Ljbffr