Cloud Accelerated Genomics by Allen Day of Google

Oxford Nanopore SmidgION
DNA-IoT Interdiction:
● Epidemics
● Poaching/Smuggling
● Acute Lethal
Infections

DeepDream (wikipedia)
is a computer vision program
created by Google which uses a
convolutional neural network to
find and enhance patterns in
images via algorithmic
pareidolia[1], thus creating a
dream-like hallucinogenic
appearance in the deliberately
over-processed images.
A late-stage DeepDream processed photograph of three men in a pool.
[1]Pareidolia is a psychological phenomenon in which the mind responds to a stimulus (an image or a sound) by
perceiving a familiar pattern where none exists.

Allen Day, PhD // Science Advocate // @allenday // #genomics #ml #datascience

GOOGLE CONFIDENTIAL
Google Cloud
Run your apps on the same system as Google

Table of Contents
Introduction Precision Medicine: an Informed Opinion
Section 1 Deep Learning Concepts
Section 2 Deep Learning @ Genomic Analysis
Section 3 Deep Learning @ Precision Agriculture

Cloud Accelerated Genomics by Allen Day of Google

Genetic
Optimization
(Breeding)
Organism Context
(Environment)
Optimization
Today’s Focus: Learn these Functions

Deep Neural Networks: Algorithms that Learn
● Modernization of artificial neural networks
● Made of of simple mathematical units,
organized in layers, that together can
compute some (arbitrary) function
● more layers = deeper = more general
● Learn from raw, heterogeneous data

* Human Performance
based on analysis done
by Andrej Karpathy.
More details here.
Image understanding is (getting) better than human level
ImageNet Challenge: Given
an image, predict one of
1000+ of classes
%errors

“Given an image,
predict one of
1000+ of classes”
Image credit:
360phot0.blogspot.com
ImageNet
Challenge

Transfer Learning
Quickly able to Learn New Concepts
“t-rex”“quidditch”
Learning like a Child: Fast Novel Visual Concept Learning from Sentence Descriptions of Images 2015

Style Transfer
Learn features from one dataset, apply them to another
Can be done within domain:
Image Labels => New Image Classes
And between domains:
Image Features => Image Filters
Image Labels + Language Model => Image Captions
Show and Tell: A
Neural Image Caption
Generator 2015

Style Transfer
https://magenta.tensorflow.org/

Released in Nov. 2015
#1
repository
for “machine learning”
category on GitHub
TensorFlow

Genetic
Optimization
(Breeding)
Marker Assisted Breeding

Google Cloud Platform
Marker-Assisted Breeding Rapidly Increases Frequency of
Favorable Genes
https://www.slideshare.net/finance28/monsanto-082305a

Yield needs to increase by
3% per year
to match GDP growth

Marker-assisted selection for quantitative traits
https://www.sec.gov/Archives/edgar/data/1110783/0000950134
02011773/c71992exv99w2.htm

Select & Recombine
Identify
desirable individuals
Grow

Select & Recombine
Grow
Generate Marker Fingerprint
Sample tissue
Extract DNAModel Data & Identify
desirable carriers
Favorable Genes

Genomics & Genetics Problems:
How to Start Applying DNNs?
Must-haves for deep learning:
● Lots of data: >50k examples, >1M examples ideal
● High-quality input and labels for training
● Label ~ F(data) unknown but certainly function exists
● High-quality prev. efforts so we know that DNNs are key
○ i.e. hard to solve with classical statistical
approaches
SNP and indel calling from NGS data

Verily | Confidential & Proprietary
Calling genetic variation may seem easy...

... but lots of places in the genome are difficult

Creating a universal SNP and small indel
variant caller with deep neural networks
Ryan Poplin, Cory McLean, Dan Newburger, Jojo Dijamco, Nam Nguyen, Dion Loy,
Sam Gross, Madeleine Cule, Peyton Greenside, Justin Zook, Marc Salit, Mark
DePristo, Verily Life Sciences, October 2016

DNN (Inception V3) Predicts True Genotype from Pileup Images
{ 0.001, 0.994, 0.005 }
{ 0.001, 0.990, 0.009 }
{ 0.000, 0.001, 0.999 }
{ 0.600, 0.399, 0.001 }
Output:
Probability of diploid
genotype states
{ HOM_REF, HET, HOM_VAR }
Raw pixels
Input:
Millions of labeled pileup
images from gold standard
samples

Using deep learning for ultra-accurate mutation detection
Input:
Millions of labeled
pileup image
stacks from gold
standard sample
Raw pixels
{ 0.001, 0.994, 0.005 }
{ 0.001, 0.990, 0.009 }
{ 0.000, 0.001, 0.999 }
{ 0.600, 0.399, 0.001 }
Output:
Probability distribution
over the three diploid
genotype states
{ HOM_REF, HET, HOM_VAR }
31

Example DNA read pileup “images”
true snps true indels false variants
red = {A,C,G,T}. green = {quality score}. blue = {read strand}.
alpha = {matches ref genome}.

PrecisionFDA: unique opportunity with blinded truth sample
NA12878

t
log($-1
)
reads writes edits

Select & Recombine
Grow
Sample tissue
desirable carriers
Favorable Genes
DNA sequencing is no
longer the bottleneck...

Select & Recombine
Grow
Sample tissue
desirable carriers
Favorable Genes
Leading to increased
investment in
machine learning DNA sequencing is no
longer the bottleneck...

Select & Recombine
Grow
Sample tissue
desirable carriers
Favorable Genes
Increased investment
in machine
learning…
...requires more data and other data types

Organism Context
(Environment)
Optimization
Gene/Environment Harmonization

anezconsulting.com/precision-agronomy/
Agronometric Integration
● Satellite & UAV
Images
● Geological Data
● Meteorological
& Sensor Data
● Cultivar Data
● Other GIS Data
● Yield Data

TensorFlow
https://cloudplatform.googleblog.com/2015/11/startup-spotlight-Descartes-Labs-monitors-planet-Earths-resources-with-Google-Compute-Engine.html

Open Source Software
&
Open Access Data

Bootstrapping a Virtuous Cycle
● Increased profit (from risk modeling) leads to increased investment
and risk reduction in the form of:
● More accurate forecasting / engineering of climate
○ Collect & model more meteorological data
● Development of crop varieties to complement future terrestrial /
climate conditions
● High-precision placement and monitoring of individual plants
○ Autonomous planting
○ remote sensing

+
Tractors are
Geospatial Printers

+
Tractors are
Geospatial Printers
Micro-environment optimized cultivars

Mapping the Diversity of Maize Races in Mexico
http://journals.plos.org/plosone/article?id=10.1371/journal.pone.0114657

Why Cannabis?
● Intellectual Property - No patented genes or strains… yet
● Update Mar 18, 2017: US PTO issues trademark for Gorilla Glue #4
● Production - Breeding is highly fragmented… for now
● However, unclear that breeding will centralize due to cheap DNA
sequencing and digital phenotyping
● Distribution (Growing) - Most likely to centralize due to economies of
scale (e.g. multi-tenant greenhouses), and already crowded, wtf?
● Market Access - Unclear that this is a viable segment of supply chain
(see GG#4 above). Also self-replication property of plants...

Why Cannabis?
● Intellectual Property - No patented genes or strains… yet
● Update Mar 18, 2017: US PTO issues trademark for Gorilla Glue #4
● Production - Breeding is highly fragmented… for now
● However, unclear that breeding will centralize due to cheap DNA
sequencing and digital phenotyping
● Distribution (Growing) - Most likely to centralize due to economies of
scale (e.g. multi-tenant greenhouses), and already crowded, wtf?
● Market Access - Unclear that this is a viable segment of supply chain
(see GG#4 above). Also self-replication property of plants...
● Threat: does Cannabis become like Yogurt starter kits?

Cannabis Genomics @ Google Cloud
https://cloud.google.com/bigquery/public-data/1000-cannabis

Build What’s Next
Thank You!
Allen Day, PhD // Science Advocate // @allenday // #genomics #ml #datascience

Cloud Accelerated Genomics by Allen Day of Google

More Related Content

Similar to Cloud Accelerated Genomics by Allen Day of Google (20)

More from Data Con LA (20)

Recently uploaded (20)

Cloud Accelerated Genomics by Allen Day of Google