Kiin Bio

About Kiin Bio

Kiin Bio is building KiinOS, an AI-native platform designed to accelerate drug discovery by enabling researchers to generate and test therapeutic hypotheses faster and more reliably. At its core, KiinOS integrates multi-modal biomedical data—including genomic, chemical, clinical, and literature-derived sources—through a knowledge graph architecture optimized for AI reasoning.

The platform functions as a virtual scientist, equipped with curated biomedical context and optimized for real-time interaction. It leverages large language models (LLMs), domain-specific ontologies, and automated reasoning tools to support users in surfacing non-obvious relationships, predicting biological targets, and validating compound-disease interactions. The system is designed to reduce the time and cost of early-stage R&D by guiding scientists through complex biological questions with structured, explainable outputs.

KiinOS is aimed at pharmaceutical companies, biotech startups, and academic labs that seek to enhance their in silico discovery capabilities. The platform can be used to explore novel drug mechanisms, identify repositioning opportunities, and prioritize assets for further experimental validation. Its knowledge engine continuously ingests public and proprietary data and harmonizes it into a machine-readable biomedical graph, enabling context-aware hypothesis generation and cross-domain discovery.

The company was founded in 2024 by Filippo Abbondanza (CEO), Mark Davies (Chief Data & Scientific Officer), and Bogdan Urse (CTO), combining deep experience in computational biology, AI infrastructure, and pharmaceutical informatics. Their shared mission is to make drug discovery more intelligent, transparent, and data-driven.

In 2025, Kiin Bio secured a 1.9€ million seed round to further develop its platform and expand collaborations with pharma and biotech partners. With its hybrid approach to knowledge representation and scalable AI pipelines, KiinOS is positioned to become a core layer in the modern biomedical R&D stack.

Tags /