Python’s role in accelerating biomedical science
summary
Project sequences 4,000 single cells and faces a matrix only 2.2–2.6% filled, so code trains a random forest iterative imputation on simulated mutation trees to infer pairwise SNV ordering, then computes a custom probability‑weighted distance for sparse binary profiles. Python libraries used: pandas, seaborn, scikit‑learn, NetworkX and matplotlib patches. Output is a mutation tree with pie‑chart nodes showing copy‑number mixes and cell counts; methods produce coherent trees and visualizations that match expected biological patterns.
AI-written summary · about
chapters (9)
- 0:00Start
- 4:03OUTLINE
- 4:30GENOME IS THE CODE OF LIFE
- 7:23Cost per Genome 2nd
- 20:08PYTHON CODE INPLEMENTATION
- 22:44ROW COLORS FOR SEABORN CLUSTERMAP
- 24:26ITERATIVE RANDOM FOREST TRAINING
- 26:32PLOTTING MULTIPLE LAYERS OF DATA
- 28:08ADD PIE CHART TO EACH NODE
related talks
44mNetwork Propagation as a Tool for Deciphering Disease Mechanisms
57mBig Data and New Models Needed to Study DNA Variation in Evolution and Cancer
01h 03mIntroduction to Cancer Bioinformatics II: Tumor Phylogeny
31mFrom Genes to Grids How Python Brings Sequence Alignment to Life
35mFrom cells to drug responses - machine learning in cancer research
01h 31mIntroduction to Cancer Bioinformatics I: Inferring Genomic Variation from Tumor Sequencing Data
30mBig data biology for pythonistas: getting in on the genomics revolution
30m23, Python and Me: Using Machine Learning in Python to Analyze Consumer Genomics Data