Main Page

Welcome to the U-M Big Data Summer Institute 2019 Wiki!

Reading Material

Machine Learning Group

Research Lecture Slides

• Introduction
• Explore MIMIC
• Getting x and y
• Some tips
• Sample Pipeline
• Training Pipleline
• CNN
• LSTM
• Structuring
• Dataset and DataLoader
• pytorch models
• Model Development
• Population
• Benchmark Features
• Inclusion Exclusion

Readings

• ARF Epidemiology
• CNN for Sentence Clarification
• Learning from Heterogenous Temporal Data
• MIMC 3
• MIMIC Benchmarks and Multitask RNN
• RNNs for Multivariate Time Series
• TREWScore for Septic Shock
• TREWScore Supplement

Genomics Group

Lectures

• BDSI Genomics Intro
• PopGen Intro

Intro Exercises

• Single Cell Exercise
• Single Cell R Code
• Intro Integrative

Papers

Population Genetics

• 1000 Genomes Project
• Cavalli SforzaHGDP 2005
• LiHGDP 2008
• NovembreNature 2008

Single Cell RNA

• Macosko_MouseRetinaDropSeq
• Single cell makes big data

Transcriptomics

• GamazonPrediXCan 2015
• GusevTWAS 2006

Online videos to better understand genetics and genomics

Genetics

• Introduction to Genetics by 23andMe (5 videos)
• TED-Ed : How Mendel's pea plants helped us understand genetics - Hortensia Jiménez Díaz
• Genetic Recombination and Gene Mapping by Bozeman Science
• Useful Genetics : A college-level comprehensive genetics course with 292 lectures offered by Rosie Redfield at UBC

Useful 3D Animations

• From DNA to protein - 3D Animation
• DNA Transcription - 3D Animation
• DNA splicing - 3D Animation
• mRNA Translation - 3D Animation
• How DNA is packaged - 3D Animation
• The Central Dogma - 3D Animation

Gene Regulation and Epigenetics

• Epigenetics Lecture by SciShow
• Hi-C Technique : A 3D map of the Human Genome
• The ENCODE Project
• RNAi by Nature Video

Sequencing Technologies

• TED-Ed : The race to sequence the human genome - Tien Nguyen
• DropSeq - Droplet-based Single Cell Sequencing by McCarroll Lab

2019 Presentations

Week 1

Day 1: June 17

• Al-Marzouki - The effect of scientific misconduct on the results of clinical trials: A Delphi survey
• Baggerly Coombes - Deriving Chemosensitivity from cell lines: forensic bioinformatics and reproducible research in high-throughput biology
• Benjamini - Redefine statistical significance
• Ethical guidelines - Ethical Guidelines for Statistical Practice article
• Ethics reviews - Ethical statistical practice review slides
• Moving to a World beyond - Moving to a World Beyond “p < 0.05”
• On being a scientist - On being a scientist article
• On being a scientist ppt - On being a scientist slides

Day 2: June 18

• Reproducible Research LeFaive
• Study design and Inference Little
• Linear regression Hector

Day 3: June 19

• Logistic regression - Hector
• Observational data and Bias - Little
• Probability - Hartman

Day 4: June 20

• Causal Inference - Wu
• Parameter estimation and Likelihood - Little
• Linear algebra - Hartman

Day 5: June 21

• Dplyr slides - Flickinger
• Dplyr flight practice - Flickinger
• Dplyr flight practice answers - Flickinger
• Dplyr and OCLS practice - Flickinger
• Dplyr and OCLS practice answers - Flickinger
• Dplyr code - Flickinger
• Journey lectures - Boehnke

Week 2

Day 6: Visualization Data in R with ggplot2 - Part I & II, June 24

• Ggplot2 slides - Flickinger
• Ggplot2 mpg exercise - Flickinger
• Ggplot2 mpg excercise answers - Flickinger
• Ggplot2 flights exercise - Flickinger
• Ggplot2 flights answers exercise - Flickinger

Day 7: Machine Learning I & Model Selection, June 25

• Model selection I & II slides - Beesley
• Machine Learning I slides - Wiens

Day 8: Machine Learning II & Unsupervised learning, Clustering I, June 26

• Machine Learning II slides - Wiens

Day 10: Python Workshop I and II, June 28

• Python Workshop I and II - Kamran

Week 3

Day 11: Data Mining I and Visualization I, July 1

• Visualization I slides - Kay

Day 12: Data Mining II and Precision Health, July 2

• Precision Health slides - Kheterpal

Day 13: Visualization II and Intro to Bayes I, July 3

• Visualization II slides - Kay
• Intro to Bayes I slides - Wen

Day 15: Intro to Bayes II, July 5

• Intro to Bayes II slides - Wen

Week 4

Day 16: From Genomics to Prevention of Cardiovascular Diseases and R Markdown, July 8

• From Genomics to Prevention of Cardiovascular Diseases slides - Surakka

Day 17: Bayes Computation I and II, July 9

• Bayes Computation I and II slides - Chen

Day 18: Reading Like a Scientific Writer and Social Network, July 10

• Reading Like a Scientific Writer slides - Griffiths

Day 19: Stroke Disparities and Human-Centered Computing: Using Speech to Understand Behavior, July 11

• Stroke Disparities slides - Lisabeth
• Human-Centered Computing slides - Provost

Day 20: Spatial Epidemiology, July 12

• Spatial Epidemiology slides - Zelner

Week 5

Day 22: Optimization I and II, July 16

• Optimization slides - Kang

Day 23: Writing from Point A to Point B and Bayesian Data Integration and Precision Medicine, July 17

• Writing from Point A to Point B slides - Griffiths
• Science of Writing paper - Griffiths

Day 24: Radiation Oncology and Imaging Analysis and Optimization in Health, July 18

• Radiation Oncology slides - Rao
• Optimization in Health slides - Denton
• Two Stage Biomarker Protocols paper
• Optimizing Active Surveillance Strategies paper
• Optimization of Prostate Biopsy Referral Decisions paper

Week 6

Day 26: Preparing for Graduate School and CVs and Resumes, July 22

• Preparing for Graduate School slides - Kidwell
• CVs and Resumes slides - Forbes
• Resume Rubric slides
• CV Guide handout
• Action Verb handout
• Resume Samples handout
• Word Tricks handout

Day 29: Symposium

2019 Professor Lectures Presentations

2019 Student Poster Presentations

2018 Student Poster Presentations

• Imaging Group Presentation
• Machine Learning Group Presentation
• Genetics Group Presentation
• Data Mining Presentation

2017 Student Poster Presentations

• Data Mining/ Machine Learning
• Electronic Health Records (EHR)
• Genomics
• Imaging

2017 Symposium Reference Files

• 2017 Symposium Program
• 2017 Symposium Flyer

2017 Symposium Projects

• A Time-to-Event Analysis of Heart Failure via Electronic Health Records
• Melanoma Detection by Classifying Skin Lesion Images
• Classifying Skin Lesions Images Using Adaptive Boosting
• Machine Learning Classification of Skin Lesion Images
• Genomics: Genome Storage and Assembly
• Predicting the Transcriptome from the Genome
• Classification of Cell Types from Peripheral Mononuclear Blood Cells
• EHR-Based Study of Long-Term Infectious Diseases
• Visualizing Lab and Phenotype Associations Using PheWAS and Electronic Health Records
• Data Mining: Microenvironment Microarray Spot Based Approach for Cell Prediction
• Estimating Cell Growth with Machine Learning and Data Mining

Additional Resources

• Daily Schedule - Last update June 4, 2019
• Social events Schedule - Last update June 6, 2019