+ All Categories
Home > Health & Medicine > Accelerating Scientific Research Through Machine Learning and Graph

Accelerating Scientific Research Through Machine Learning and Graph

Date post: 16-Apr-2017
Category:
Upload: neo4j-the-fastest-and-most-scalable-native-graph-database
View: 128 times
Download: 1 times
Share this document with a friend
68
Accelerating scientific research through Machine Learning & Graph Jorge Soto CTO, Miroculus Antonio Molins VP Data Science, Miroculus SAN FRANCISCO 13-14 OCTOBER 2016
Transcript

Accelerating scientific research through Machine Learning & GraphJorge Soto CTO, Miroculus Antonio Molins VP Data Science, Miroculus

SAN FRANCISCO13-14 OCTOBER 2016

microRNAs

DNA

mRNA

DNA

mRNAPROTEIN

DNA

mRNAPROTEIN

DNA

microRNA

1993lin-4 in c. elegans

2000let-7 in h. sapiens

microRNA

microRNAs are tissue specific

1993lin-4 in c. elegans

2000let-7 in h. sapiens

microRNA expression across different cancer types

gastrointestinal tract samplesepithelial origin samples

Jun Lu et al. MicroRNA expression profiles classify human cancers. Nature 435, 834-838(9 June 2005)

1993lin-4 in c. elegans

2000let-7 in h. sapiens

20021st link to cancer

1993lin-4 in c. elegans

2000let-7 in h. sapiens

2008plasma

20021st link to cancer

microRNAs found cell-free in biofluids

Highly Stable

Organ/Tissue Specific

Detectable in blood

microRNA as an ideal biomarker

microRNAs reflect your physiology

Red blood cells

Liver

Muscle

Heart

Red blood cells

Liver

Muscle

Heart

microRNAs reflect your physiology

Red blood cells

Liver

Muscle

Heart

microRNAs reflect your physiology

Red blood cells

Liver

Muscle

Heart

microRNAs reflect your physiology

3 simple steps

Sample collection

20 mins

Assay sensitivity

3 simple steps

Sample collection Insert sample in a cartridge device

20 mins 60 mins

Digital microfluidics technology

3 simple steps

Sample collection Automated workflow and data analysis

real time

Insert sample in a cartridge device

20 mins 60 mins

Adaptated from Nair et al, Am J Epid, 2014

Tissue VS circulating microRNA related publications

2000let-7 in h. sapiens

2008plasma

BreastCancer

miR-34a

DADS

Retrieve Read LearnSearch Choose

Search Choose

Retrieve Read Learn

Retrieve Read Learn

Retrieve Read Learn

Retrieve Read Learn

Retrieve Read Learn

Retrieve Read Learn

Retrieved

1,000,000+articles

192,496,883 lines

199,639,090 sentences

111,382,775 concept mentions

What has the elephant learnt so far?

“As shown in Fig. 3, DADS inhibited breast cancer growth by up-regulating MiR-34A expression.”

What has the elephant learnt so far?

“As shown in Fig. 3, DADS inhibited breast cancer growth by up-regulating MiR-34A expression.”

What has the elephant learnt so far?

DADS

BreastCancer

DADS

“As shown in Fig. 3, DADS inhibited breast cancer growth by up-regulating MiR-34A expression.”

What has the elephant learnt so far?

BreastCancer

miR-34A

DADS

“As shown in Fig. 3, DADS inhibited breast cancer growth by up-regulating MiR-34A expression.”

What has the elephant learnt so far?

Distant supervision for relationship classification

Blog post in MSFT dev site

Distant supervision for relationship classification

Blog post in MSFT dev site

Distant supervision for relationship classification

Blog post in MSFT dev site

Distant supervision for relationship classification

Blog post in MSFT dev site

Distant supervision for relationship classification

Blog post in MSFT dev site

www.loom.bio

- connect to NCBI databases (pubmed and pmc) and fetch new publications

- identify when microRNAs are mentioned in relationship to genes or diseases- split the results into sentences

NLP

I can...Listener

I can...

Loom architectureScorer

I can...- score between 0 to 1 the accuracy of the relations between the entities using machine learning

Graph

I can...

- store the relationships and their score in a graph database- be queried about each node and their relationships

55

Weiland et al, RNA biology, 2012

When discovery > validation

“Most clinical research therefore fails to be useful not because of its findings but because of its design” - JPA Ioannidis, PLOS Medicine, 2016

Unmet clinical need for stomach cancer patients

In collaboration with:

Inclusion criteria Individuals suspected of stomach cancer eligible for endoscopies.

Collection All samples collected from 2010 to 2013.

Machine-learned model

Samples split 50/50 in two groups doubly balanced per country, gender, diagnosis, subtype and stage.

Cohort distribution 650 samples including the entire cascade of the disease.

Multi-center Samples collected in Chile, Lithuania and Latvia.

Clinical study design

Proprietary 7-microRNA diagnostic signature

Proprietary 7-microRNA diagnostic signatureDecision boundary set to maximize

accuracy for the observed prevalence

Robust regardless of stage Good performance across ethnicities

Decision boundary set to maximize accuracy for the observed prevalence

Proprietary 7-microRNA diagnostic signature

-+

Without Miroculus With Miroculus

NPV = 99.8%

Miroculus test compared to gold standard

Ideal biomarker

Cost effective, simple and accurate detection

Future of diagnostics

Enabling technology

Advanced data analysis

[email protected]@miroculus.com

http://loom.bio


Recommended