Machine Learning Techniques for Omics Data Analysis

on YouTube ↗29m

" summary

Team uses ctrp portal gene-expression and drug-response data to predict cell-line sensitivity, starting from 686 samples and after cleaning using 516 (train 361 / val 77 / test 78). Pipeline switches from summary metrics to individual-dose responses, reduces ~19,000 genes via Spearman filtering plus forward/backward selection, compares Elastic Net and GAM but selects XGBoost with heavy hyperparameter tuning, and ends with ~20 gene features whose literature links many to cancer; one expected gene appears and another suggests a new liquid‑biopsy biomarker.

AI-written summary · about

" chapters (8)

1. 0:00Introduction
2. 1:08Omics technologies overview
3. 6:02Omics data generation
4. 10:45Processing omics data
5. 15:25Machine learning in omics
6. 19:23ML for tertiary analysis
7. 20:27Drug sensitivity case study
8. 28:57Q&A

" related talks

• 35mFrom cells to drug responses - machine learning in cancer researchJulian de Ruiter, Nanne Aben · PyData Amsterdam 2018
• 32mMulti-Omic Integration for Understanding DiseaseRon Shamir · Computational Challenges in Very Large-Scale 'Omics'
• 30mMachine Learning: A New Approach to Drug DiscoveryDaphne Koller · Women in Data Science (WiDS) Stanford 2020
• 33mUnderstanding Molecular Complexity for Precision MedicineNatasa Przulj · From Algorithms to Discovery in Genome-Scale Biology and Medicine 2022
• 30mLeveraging Molecular Data for Drug DiscoveryHaiyan Huang · Computational Challenges in Very Large-Scale 'Omics'
• 32mHow machine learning helps cancer researchEvelina Gabasova · Strange Loop 2015
• 28mHow ML can Help Tailor Immunotherapies to Cancer PatientsRaphael Gottardo · AWS re:Invent 2019 | AI & Machine Learning Summit
• 44mNetwork Propagation as a Tool for Deciphering Disease MechanismsRoded Sharan · Network Biology 2016