The Algorithm for Precision Medicine
summary
Claims that data becomes the most powerful therapeutic agent and that precision medicine is best expressed declaratively. Uses the Translator/Medici Canon knowledge graph plus logical inference rules to connect genes, drugs and phenotypes. Concrete results: 40 predictions by March for COVID and 200,000 compounds screened in docking, yielding ~70 candidates, 14 FDA drugs and a lab-validated hit; a MAPK8IP3 case responds to high‑dose retinoids, ADNP autism shows ketamine‑linked biomarker and clinical benefit, cataplex drops from ~150 to 0 with amphetamines, and ENG1 deficiency improves with glucosamine and model organism validation.
AI-written summary · about
chapters (17)
- 0:00Precision medicine algorithm intro
- 2:13Data as medicine
- 7:07Two phases of precision medicine
- 11:45Drug screening process
- 13:28Patient case studies
- 16:57Biomedical data translator Oracle
- 18:40Declarative programming in knowledge graphs
- 21:48ADNP autism treatment discovery
- 24:18Cataplexy treatment insights
- 27:25COVID-19 therapy predictions
- 29:12Rare disease personal journey
- 37:27Epilepsy treatment success
- 38:31White House Precision Medicine Initiative
- 40:28Drug target docking simulations
- 44:37Algorithm parallel nature
- 47:46Patient-to-treatment expression
- 50:16Cyclic vomiting treatment
related talks
50mThe algorithm for precision medicine
20mTranslating a Trillion Pointo Diseases of Data into Therapies
30mLeveraging Molecular Data for Drug Discovery
30mMachine Learning: A New Approach to Drug Discovery
33mUnderstanding Molecular Complexity for Precision Medicine
33mNetwork Data Integration Enables Precision Medicine
35mUsing Large-Scale Clinico-Genomics Data for in silico Clinical Trials and Precision Oncology
36mFormatting Biological Big Data to Enable (Personalized) Systems Pharmacology
