A network-based framework to discover treatment-response-predicting biomarkers for complex diseases

EP4758617A1Pending Publication Date: 2026-06-17SCIPHER MEDICINE CORP
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
EP · EP
Patent Type
Applications
Current Assignee / Owner
SCIPHER MEDICINE CORP
Filing Date
2024-08-08
Publication Date
2026-06-17

AI Technical Summary

Technical Problem

Precision medicine for complex inflammatory and immunology diseases faces challenges due to limited data and inadequate sample sizes, making it difficult to predict treatment responses effectively.

Method used

The Predictive Response Biomarkers using Network medicine (PRoBeNet) framework operates with limited data and inadequate sample sizes by prioritizing biomarkers based on therapy-targeted proteins, disease-specific molecular signatures, and an underlying network of interactions among cellular components, using a dual PageRank score to rank nodes in the human interactome.

Benefits of technology

The PRoBeNet framework successfully identifies response-predicting biomarkers for both established and investigational therapies, outperforming other machine-learning models, especially when data is limited, and can be used to develop companion diagnostic tests to improve patient outcomes.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure US2024041461_13022025_PF_FP_ABST
    Figure US2024041461_13022025_PF_FP_ABST
Patent Text Reader

Abstract

Described are network-based frameworks to discover treatment-response-predicting biomarkers for complex diseases or disorders. In an aspect, described is a method of treating a subject suffering from an autoimmune disease or cancer. The method can include administering to the subject a therapy, in which the therapy has been predicted to generate a treatment response in the subject based at least in part on a trained machine learning (ML) classifier that classifies the subject as responsive or non-responsive to the therapy using treatment-response-predicting biomarkers.
Need to check novelty before this filing date? Find Prior Art