Big data in personalized medicine
summary
A Western Balkan genomic survey uses whole genome sequencing on regional cohorts to identify drug–pharmacogenomics marker pairs and to design a preemptive gene panel; pipeline moves FastQ → BAM → VCF, annotates variants with PharmGKB/CPIC evidence and runs FarmCAT to translate genotypes into phenotypes and dosing guidance. Infrastructure includes three Illumina machines, BGI long‑read, Nvidia GPU supercomputing and KAGO storage, trained staff, and a working prototype electronic PGX assistant (ePGA‑WB) for clinical decision support.
AI-written summary · about
chapters (13)
- 0:00Personalized medicine intro
- 1:10Institute research focus
- 2:58Precision medicine overview
- 4:27Pharmacogenomics variability
- 5:32EU pharmacogenomics project
- 6:58Sequencing and bioinformatics
- 8:50Illumina workflow
- 10:16Raw data to variants
- 12:06Interpreting variants
- 13:51Star allele challenges
- 14:57PharmCAT annotation
- 15:38Electronic assistant prototype
- 16:42Closing remarks
related talks
20mTranslating a Trillion Pointo Diseases of Data into Therapies
50mThe algorithm for precision medicine
29mDeveloping and Delivering Personalized Polygenic Scores at Scale
50mCancer Genomics - a biologist and a developer
35mUsing Large-Scale Clinico-Genomics Data for in silico Clinical Trials and Precision Oncology
20mDiagnostic Medical application of ML
12mHow data science can make your genome actionable
08mAnne Wojcicki interviewed at Web 2.0 Summit 2011