Pheiron
AI-native tech-bio company that builds an AI-driven human evidence platform to integrate population-scale clinical and multi-omic data, derive causal biological insights, validate AI-derived biomarkers, and support target prioritization and patient stratification to de-risk drug development and inform trial design.
Industries
Nr. of Employees
small (1-50)
Products
PheironGPS
An AI-driven platform that uses population-scale human data to generate causal evidence for drug discovery and development decisions.
AI Biomarkers for Disease Phenotyping
AI algorithms that integrate multi-omic data to characterize disease phenotypes and progression, supporting clinical research and trial optimization.
PheironGPS
An AI-driven platform that uses population-scale human data to generate causal evidence for drug discovery and development decisions.
AI Biomarkers for Disease Phenotyping
AI algorithms that integrate multi-omic data to characterize disease phenotypes and progression, supporting clinical research and trial optimization.
Services
Platform service that integrates clinical and multi-omic cohort data, runs AI phenotyping and causal analyses to produce evidence for target, indication and population decisions.
Pre-packaged and customizable evidence reports that summarize integrated human genetic, phenotypic and outcome evidence to inform program decisions.
Construction, validation and application of AI-derived biomarkers (example: 12-lead ECG biomarker), including performance assessment in real-world datasets and use for trial emulation.
Collaborative pilot projects to profile targets, prioritize candidates, and emulate trial outcomes using partner data assets and pre-defined success criteria.
Platform service that integrates clinical and multi-omic cohort data, runs AI phenotyping and causal analyses to produce evidence for target, indication and population decisions.
Pre-packaged and customizable evidence reports that summarize integrated human genetic, phenotypic and outcome evidence to inform program decisions.
Construction, validation and application of AI-derived biomarkers (example: 12-lead ECG biomarker), including performance assessment in real-world datasets and use for trial emulation.
Collaborative pilot projects to profile targets, prioritize candidates, and emulate trial outcomes using partner data assets and pre-defined success criteria.
Expertise Areas
- AI-driven phenotyping and biomarker development
- Population-scale statistical genetics and causal inference
- Multi-omic data integration and analysis
- Real-world evidence and clinical trial emulation
Key Technologies
- Machine learning / neural networks for biomedical data
- Multi-omic data integration (metabolomics, proteomics, transcriptomics)
- Population-scale biobank analysis
- Real-world data analytics (RWD)
News & Updates
Presented integrated genetic and AI-driven phenotyping evidence suggesting additive ASCVD risk reduction from joint modulation of Lp(a) and PCSK9; work supports biomarker and patient-selection strategies for dual-pathway approaches.
Population-scale study linking medical history to phenome-wide disease onset and rapid response capabilities.
Real-world data study using AI-derived biomarkers to assess cardioprotective effects of GLP-1 receptor agonists.
Perspective on using population-scale human evidence to de-risk drug development and improve target and population selection.
Study linking metabolomic profiles to predictions of multiple disease outcomes.
Announcement of collaboration milestones using AI integration of multi-omic human data to profile candidate targets for RNA therapeutics.
Presented integrated genetic and AI-driven phenotyping evidence suggesting additive ASCVD risk reduction from joint modulation of Lp(a) and PCSK9; work supports biomarker and patient-selection strategies for dual-pathway approaches.
Population-scale study linking medical history to phenome-wide disease onset and rapid response capabilities.
Real-world data study using AI-derived biomarkers to assess cardioprotective effects of GLP-1 receptor agonists.
Perspective on using population-scale human evidence to de-risk drug development and improve target and population selection.
Study linking metabolomic profiles to predictions of multiple disease outcomes.
Announcement of collaboration milestones using AI integration of multi-omic human data to profile candidate targets for RNA therapeutics.