Deep learning is hot, making waves, delivering results, and is somewhat of a buzzword today. There is a desire to apply deep learning to anything that is digital. Unlike the brain, these artificial neural networks have a very strict predefined structure. The brain is made up of neurons that talk to each other via electrical and chemical signals. We do not differentiate between these two types of signals in artificial neural networks. They are essentially a series of advanced statistics based exercises that review the past to indicate the likely future. Another buzzword that was used for the last few years across all industries is “big data”. In biomedical and health sciences, both unstructured and structured information constitute "big data". On the one hand deep learning needs lot of data whereas “big data" has value only when it generates actionable insight. Given this, these two areas are destined to be married. The couple is made for each other. The time is ripe now for a synergistic association that will benefit the pharmaceutical companies. It may be only a short time before we have vice presidents of machine learning or deep learning in pharmaceutical and biotechnology companies. This presentation will review the prominent deep learning methods and discuss these techniques for their usefulness in biomedical and health informatics.
Call Girls In Sukhdev Vihar Delhi 💯Call Us 🔝8264348440🔝
II-SDV 2017: The Next Era: Deep Learning for Biomedical Research
1. The Next Era:
Deep Learning for Biomedical Research
II-SDV Conference
Nice, France
23 - 25 April 2017
Srinivasan Parthiban
Parthys Reverse Informatics
Chennai, Tamil Nadu, India
6. Big Data Availability
The World’s Technological Capacity to Store,
Communicate, and Compute Information
Hilbert, M., & Lopez, P (2011), Science, 332 (6025), 60-65
9. Machine Learning
Unsupervised learning Supervised learning
Reinforcement learning Optimization
"I know how to classify this data,
I just need you(the classifier) to sort it."
20. Recurrent Neural Networks (RNN)
𝒙 𝒕: the input at time step 𝑡
𝒔 𝒕: the hidden state at time 𝑡
𝒐 𝒕: the output state at time 𝑡
Prediction of next word:
the clouds are in the sky
I grew up in France …………
…..
I speak fluent French The issue :
Vanishing Gradient over time
21. LSTM and GRU
Long Short-Term Memory
i - input gate
f – forget gate
o – output gate
c – memory cell and
c˜ - new memory cell content
Gated Recurrent Unit
z – update gate
r – reset gate
h - hidden state
h˜ - new hidden state
LSTM
GRU
22. Design Patterns for RNN
Image
captioning
Sentiment
analysis
Machine
translation
Classify image
frame by frame
A man sitting in rooftop
restaurant with his laptop
Welcome to France
Bienvenue en France
II-SDV Conference
is absolutely a
great event
Image
Classification
Cat
23. A group of people
shopping at an
outdoor market.
There are many
vegetables at the
fruit stand.
Machine image recognition and descriptive captions generated
Language
Generating
RNN
Vision
Deep CNN
31. Dermatologist-level classification of skin
cancer with deep neural networks
Procedure for calculating inference class
probabilities from training class probabilities
Source: Nature 542, 115–118 (02 February 2017)
32. First FDA Approval For Clinical Cloud-Based Deep Learning In Healthcare
Arterys
Prostate MRI: An image is worth the 1000 blood tests.
MaxwellMRI
Deep Learning spots disease early using Chest-X rays
Enlitic
CT scans: Algorithms inform cardiovascular and metabolic state
of patients, and predicts the risk of heart attack and stroke
Zebra Medical Vision
33. AI heatmap: Deals Distribution by Category
Q1‘12-Q’17 (as of 3/23/17)
Source: CBinsights
Healthcare emerges as hottest area of investment
37. Data Repositories
Database Unique
Compounds
Experimental
facts
Main data types
ChEMBL v.21 1,592,191 13,968,617 PubChem HTS assays and data mined from
literature
BindingDB 529,618 1,207,821 Experimental protein-small molecule
interaction data
PubChem >60M >157M Bioactivity data from HTS assays
Reaxys >74M >500M Literature mined property, activity and
reaction data
SciFinder
(CAS)
>111M >80M Experimental properties 13C and 1H NMR
spectra, reaction data
GOSTAR >3M >24M Target-linked data from parents and articles
AZ IBIS - >150M AZ in-house SAR data points
OCHEM >600k >1.2M Mainly ADMET data collected from
literature
38. Architecture of Adversarial Autoencoder
(AAE) for New Molecule Development
Oncotarget, 2017, Vol. 8, (No. 7), pp: 10883-10890
40. Our Preliminary Model for ADMET
prediction
We have compiled a robust library of
over 155k records across 36 different ADMET properties to
facilitate 10-fold cross validation and confirm scalability
SMILES were used to represent the molecules in the database
Converted each molecule into Descriptors
856 2D/3D descriptors and 1024 unique “fingerprints”
We have implemented a process to identify the most
important descriptors upfront and focus resources on those
key data points
Our analysis yielded 27 descriptors that helps predict %GS
This subset is then fed into each of the 10 algorithms for
model fitting
Our initial results are promising.
Pred
Obs
41. Why Deep Learning?
How do data science techniques scale with amount of data?
Older learning
algorithms
Deep learning
42. Deep Learning Frameworks
% of papers mentioning the framework in March 2017
the fraction of papers that
mention the framework
somewhere in the full text
(anywhere — including
bibliography etc). For papers
uploaded on March 2017, we
get the numbers in this table.
% of papers framework
has been around
for (months)
9.1 tensorflow 16
7.1 caffe 37
4.6 theano 54
3.3 torch 37
2.5 keras 19
1.7 matconvnet 26
1.2 lasagne 23
0.5 chainer 16
0.3 mxnet 17
0.3 cntk 13
0.2 pytorch 1
0.1 deeplearning4j 14
43. The Rockstars of Deep Learning
Yoshua BengioYann Lecun Geoff Hinton Andrew Ng
IDSIA
Switzerland
Jürgen
Schmidhuber