De Novo molecular design with Deep Reinforcement Learning

Size: px
Start display at page:

Download "De Novo molecular design with Deep Reinforcement Learning"

Transcription

1 De Novo molecular design with Deep Reinforcement Olexandr Isayev, Ph.D. University of North Carolina at Chapel Hill

2 About me Ph.D. in Chemistry (computational) Minor in CS/ML Worked in Federal research lab on HPC & GPU computing to solve chemical problems Now I am faculty at the University of North Carolina, Chapel Hill We use ML & AI to solve challenging problems in chemistry olexandr@unc.edu

3 A public-private partnership that supports the discovery of new medicines through open access research

4 The Long and Winding Road to Drug Discovery Data Science approaches useful across the pipeline, but very different techniques aim for success, but if not: fail early, fail cheap

5 internal rate of return (IRR) Source: Endpoints News

6 Drowning in Data but starving for Knowledge

7 The growing appreciation of molecular modeling and informatics 7

8 Behold the rise of the machines

9 Summary of recent AI-based studies on chemical library design Molecular representations Generative models Method of biasing generated compounds Fingerprints SMILES Graphs Autoencoders Generative adversarial models (GANs) Recurrent neural networks (RNNs) Convolutional neural networks (CNNs) None Latent space optimization Fine-tuning on small subset of molecules with the desired property Reinforcement Learning

10 De Novo molecular design with Deep Reinforcement Learning General Approach Application to Molecular design Tm; LogP; pic50; etc Predictive Deep Network Molecules Generative Deep Network Patent pending arxiv:

11 Drug discovery pipeline CHEMICAL STRUCTURES CHEMICAL DESCRIPTORS PREDICTIVE QSAR MODELS PROPERTY/ ACTIVITY CHEMICAL DATABASE QSAR MAGIC VIRTUAL SCREENING HITS (confirmed actives) ~ molecules INACTIVES (confirmed inactives)

12 Design of the ReLeaSE* method Challenges: Generate chemically feasible SMILES Develop SMILESbased QSAR model Employ Predictive ML model to bias library generation *Popova, Mariya, Olexandr Isayev, and Alexander Tropsha. "Deep reinforcement learning for de-novo drug design." arxiv preprint arxiv: (2017).

13 Language of SMILEs

14 Generative model 1.5M molecules from ChEMBL <START>c1ccc(O)cc1<END> c1cc) ( F) cc1<end> c1ccc(o)cc1 NO <START> c1ccc( O) cc1 + loss YES Did the training converge? Softmax loss

15 Reinforcement learning for chemical design Generative model Predictive model FC(F)COc1ccc2c(Nc3ccc(Cl)c(Cl)c3)ncnc2c1 M. Popova, O. Isayev, A. Tropsha. "Deep reinforcement learning for de-novo drug design." arxiv preprint arxiv: (2017).

16 Reinforcement learning for chemical design Generative model Predictive model FC(F)COc1ccc2c(Nc3ccc(Cl)c(Cl)c3)ncnc2c1 M. Popova, O. Isayev, A. Tropsha. "Deep reinforcement learning for de-novo drug design." arxiv preprint arxiv: (2017).

17 Reinforcement learning for chemical design Generative model INACTIVE! Predictive model M. Popova, O. Isayev, A. Tropsha. "Deep reinforcement learning for de-novo drug design." arxiv preprint arxiv: (2017).

18 Reinforcement learning for chemical design Generative model INACTIVE! Predictive model M. Popova, O. Isayev, A. Tropsha. "Deep reinforcement learning for de-novo drug design." arxiv preprint arxiv: (2017).

19 Reinforcement learning for chemical design Generative model INACTIVE! Predictive model M. Popova, O. Isayev, A. Tropsha. "Deep reinforcement learning for de-novo drug design." arxiv preprint arxiv: (2017).

20 Reinforcement learning for chemical design Generative model Predictive model M. Popova, O. Isayev, A. Tropsha. "Deep reinforcement learning for de-novo drug design." arxiv preprint arxiv: (2017).

21 Reinforcement learning for chemical design Generative model Predictive model Fc1ccc2c(Nc3ccc(F)c(F)c3)ncnc2c1 M. Popova, O. Isayev, A. Tropsha. "Deep reinforcement learning for de-novo drug design." arxiv preprint arxiv: (2017).

22 Reinforcement learning for chemical design Generative model Predictive model Fc1ccc2c(Nc3ccc(F)c(F)c3)ncnc2c1 M. Popova, O. Isayev, A. Tropsha. "Deep reinforcement learning for de-novo drug design." arxiv preprint arxiv: (2017).

23 Reinforcement learning for chemical design Generative model ACTIVE! Predictive model M. Popova, O. Isayev, A. Tropsha. "Deep reinforcement learning for de-novo drug design." arxiv preprint arxiv: (2017).

24 Reinforcement learning for chemical design Generative model ACTIVE! Predictive model M. Popova, O. Isayev, A. Tropsha. "Deep reinforcement learning for de-novo drug design." arxiv preprint arxiv: (2017).

25 Reinforcement learning for chemical design Generative model ACTIVE! Predictive model M. Popova, O. Isayev, A. Tropsha. "Deep reinforcement learning for de-novo drug design." arxiv preprint arxiv: (2017).

26 Reinforcement learning for chemical design Generative model Predictive model M. Popova, O. Isayev, A. Tropsha. "Deep reinforcement learning for de-novo drug design." arxiv preprint arxiv: (2017).

27 Technical details Models were trained on Nvidia Titan X and Titan V GPUs Training generative model on ChEMBL took ~ 25 days Training predictive models took ~ 2 hours Biasing generative model with reinforcement learning for one property ~ 1 day Generative model produces 1000s compounds per minute

28 Results: Biasing target properties in the designed libraries Optimized Baseline * JAK2 Inhibition (pic50) Melting temperature (T m ), o C 400 Partition coefficient (logp) M. Popova, O. Isayev, A. Tropsha. "Deep reinforcement learning for de-novo drug design." arxiv preprint arxiv: (2017).

29 JAK2 (Kinase) inhibition Train data distribution Maximized property distribution Minimized property distribution NEW CHEMOTYPE CAS (buffer reagent) ZINC SIMILAR SCAFFOLDS New molecule arxiv:

30 Results: analysis of similarity Distribution of Tanimoto similarity to the nearest neighbor in training dataset for compounds predicted to be active for EGFR by consensus of QSAR models: Similarity= 0.69 Similarity= 0.57 Similarity = Tanimoto similarity 1.0

31 Results: Synthetic accessibility score* of the designed libraries *Ertl, Peter, and Ansgar Schuffenhauer. "Estimation of synthetic accessibility score of drug-like molecules based on molecular complexity and fragment contributions." Journal of cheminformatics 1.1 (2009): 8.

32 Target predictions for generated compounds using SEA* *Keiser MJ, Roth BL, Armbruster BN, Ernsberger P, Irwin JJ, Shoichet BK. Relating protein pharmacology by ligand chemistry. Nat Biotech 25 (2), (2007).

33 Target predictions for generated compounds using SEA* *Keiser MJ, Roth BL, Armbruster BN, Ernsberger P, Irwin JJ, Shoichet BK. Relating protein pharmacology by ligand chemistry. Nat Biotech 25 (2), (2007).

34 Model visualization for JAK2 (projection using t-sne) ZINC pic50 = 8.64 ZINC pic50 = 3.31 ZINC pic50 = 8.23 ZINC pic50 = 3.76 ZINC pic50 = 8.39 pic50 = pic50 = M. Popova, O. Isayev, A. Tropsha. "Deep reinforcement learning for de-novo drug design." arxiv preprint arxiv: (2017).

35 Examples of Stack-RNN cells with interpretable gate activations M. Popova, O. Isayev, A. Tropsha. "Deep reinforcement learning for de-novo drug design." arxiv preprint arxiv: (2017).

36 Summary AI methods coupled with SMILES representation afford biased libraries generation The system naturally embeds reinforcement to produce novel structure with the desired property The system can be tuned to bias libraries towards specific property ranges Next phase is experimental validation of hits by UNC SGC team

Deep Reinforcement Learning for de-novo Drug Design

Deep Reinforcement Learning for de-novo Drug Design Deep Reinforcement Learning for de-novo Drug Design Mariya Popova 1,2,3, Olexandr Isayev 1*, Alexander Tropsha 1* 1 Laboratory for Molecular Modeling, Division of Chemical Biology and Medicinal Chemistry,

More information

In silico generation of novel, drug-like chemical matter using the LSTM deep neural network

In silico generation of novel, drug-like chemical matter using the LSTM deep neural network In silico generation of novel, drug-like chemical matter using the LSTM deep neural network Peter Ertl Novartis Institutes for BioMedical Research, Basel, CH September 2018 Neural networks in cheminformatics

More information

In silico generation of novel, drug-like chemical matter using the LSTM neural network

In silico generation of novel, drug-like chemical matter using the LSTM neural network In silico generation of novel, drug-like chemical matter using the LSTM neural network Peter Ertl 1, Richard Lewis 1, Eric Martin 2, Valery Polyakov 2 1 Novartis Institutes for BioMedical Research, Novartis

More information

Deep Learning: What Makes Neural Networks Great Again?

Deep Learning: What Makes Neural Networks Great Again? 6 th Strasbourg Summer School in Chemoinformatics (CS3-2018) Deep Learning: What Makes Neural Networks Great Again? Igor I. Baskin M. V. Lomonosov Moscow State University The First Neural Network (Perceptron)

More information

Deep Generative Models for Graph Generation. Jian Tang HEC Montreal CIFAR AI Chair, Mila

Deep Generative Models for Graph Generation. Jian Tang HEC Montreal CIFAR AI Chair, Mila Deep Generative Models for Graph Generation Jian Tang HEC Montreal CIFAR AI Chair, Mila Email: jian.tang@hec.ca Deep Generative Models Goal: model data distribution p(x) explicitly or implicitly, where

More information

Virtual screening in drug discovery

Virtual screening in drug discovery Virtual screening in drug discovery Pavel Polishchuk Institute of Molecular and Translational Medicine Palacky University pavlo.polishchuk@upol.cz Drug development workflow Vistoli G., et al., Drug Discovery

More information

Introduction. OntoChem

Introduction. OntoChem Introduction ntochem Providing drug discovery knowledge & small molecules... Supporting the task of medicinal chemistry Allows selecting best possible small molecule starting point From target to leads

More information

Development of a Structure Generator to Explore Target Areas on Chemical Space

Development of a Structure Generator to Explore Target Areas on Chemical Space Development of a Structure Generator to Explore Target Areas on Chemical Space Kimito Funatsu Department of Chemical System Engineering, This materials will be published on Molecular Informatics Drug Development

More information

Machine learning for ligand-based virtual screening and chemogenomics!

Machine learning for ligand-based virtual screening and chemogenomics! Machine learning for ligand-based virtual screening and chemogenomics! Jean-Philippe Vert Institut Curie - INSERM U900 - Mines ParisTech In silico discovery of molecular probes and drug-like compounds:

More information

Molecular Dynamics Graphical Visualization 3-D QSAR Pharmacophore QSAR, COMBINE, Scoring Functions, Homology Modeling,..

Molecular Dynamics Graphical Visualization 3-D QSAR Pharmacophore QSAR, COMBINE, Scoring Functions, Homology Modeling,.. 3 Conformational Search Molecular Docking Simulate Annealing Ab Initio QM Molecular Dynamics Graphical Visualization 3-D QSAR Pharmacophore QSAR, COMBINE, Scoring Functions, Homology Modeling,.. Rino Ragno:

More information

Structure-Activity Modeling - QSAR. Uwe Koch

Structure-Activity Modeling - QSAR. Uwe Koch Structure-Activity Modeling - QSAR Uwe Koch QSAR Assumption: QSAR attempts to quantify the relationship between activity and molecular strcucture by correlating descriptors with properties Biological activity

More information

bcl::cheminfo Suite Enables Machine Learning-Based Drug Discovery Using GPUs Edward W. Lowe, Jr. Nils Woetzel May 17, 2012

bcl::cheminfo Suite Enables Machine Learning-Based Drug Discovery Using GPUs Edward W. Lowe, Jr. Nils Woetzel May 17, 2012 bcl::cheminfo Suite Enables Machine Learning-Based Drug Discovery Using GPUs Edward W. Lowe, Jr. Nils Woetzel May 17, 2012 Outline Machine Learning Cheminformatics Framework QSPR logp QSAR mglur 5 CYP

More information

Computational chemical biology to address non-traditional drug targets. John Karanicolas

Computational chemical biology to address non-traditional drug targets. John Karanicolas Computational chemical biology to address non-traditional drug targets John Karanicolas Our computational toolbox Structure-based approaches Ligand-based approaches Detailed MD simulations 2D fingerprints

More information

Navigation in Chemical Space Towards Biological Activity. Peter Ertl Novartis Institutes for BioMedical Research Basel, Switzerland

Navigation in Chemical Space Towards Biological Activity. Peter Ertl Novartis Institutes for BioMedical Research Basel, Switzerland Navigation in Chemical Space Towards Biological Activity Peter Ertl Novartis Institutes for BioMedical Research Basel, Switzerland Data Explosion in Chemistry CAS 65 million molecules CCDC 600 000 structures

More information

Multi objective de novo drug design with conditional graph generative model

Multi objective de novo drug design with conditional graph generative model https://doi.org/10.1186/s13321-018-0287-6 RESEARCH ARTICLE Open Access Multi objective de novo drug design with conditional graph generative model Yibo Li, Liangren Zhang * and Zhenming Liu * Abstract

More information

Introduction to Chemoinformatics and Drug Discovery

Introduction to Chemoinformatics and Drug Discovery Introduction to Chemoinformatics and Drug Discovery Irene Kouskoumvekaki Associate Professor February 15 th, 2013 The Chemical Space There are atoms and space. Everything else is opinion. Democritus (ca.

More information

PREDICTION OF HETERODIMERIC PROTEIN COMPLEXES FROM PROTEIN-PROTEIN INTERACTION NETWORKS USING DEEP LEARNING

PREDICTION OF HETERODIMERIC PROTEIN COMPLEXES FROM PROTEIN-PROTEIN INTERACTION NETWORKS USING DEEP LEARNING PREDICTION OF HETERODIMERIC PROTEIN COMPLEXES FROM PROTEIN-PROTEIN INTERACTION NETWORKS USING DEEP LEARNING Peiying (Colleen) Ruan, PhD, Deep Learning Solution Architect 3/26/2018 Background OUTLINE Method

More information

October 6 University Faculty of pharmacy Computer Aided Drug Design Unit

October 6 University Faculty of pharmacy Computer Aided Drug Design Unit October 6 University Faculty of pharmacy Computer Aided Drug Design Unit CADD@O6U.edu.eg CADD Computer-Aided Drug Design Unit The development of new drugs is no longer a process of trial and error or strokes

More information

Chemical Data Retrieval and Management

Chemical Data Retrieval and Management Chemical Data Retrieval and Management ChEMBL, ChEBI, and the Chemistry Development Kit Stephan A. Beisken What is EMBL-EBI? Part of the European Molecular Biology Laboratory International, non-profit

More information

Introducing a Bioinformatics Similarity Search Solution

Introducing a Bioinformatics Similarity Search Solution Introducing a Bioinformatics Similarity Search Solution 1 Page About the APU 3 The APU as a Driver of Similarity Search 3 Similarity Search in Bioinformatics 3 POC: GSI Joins Forces with the Weizmann Institute

More information

A Deep Convolutional Neural Network for Bioactivity Prediction in Structure-based Drug Discovery

A Deep Convolutional Neural Network for Bioactivity Prediction in Structure-based Drug Discovery AtomNet A Deep Convolutional Neural Network for Bioactivity Prediction in Structure-based Drug Discovery Izhar Wallach, Michael Dzamba, Abraham Heifets Victor Storchan, Institute for Computational and

More information

Xia Ning,*, Huzefa Rangwala, and George Karypis

Xia Ning,*, Huzefa Rangwala, and George Karypis J. Chem. Inf. Model. XXXX, xxx, 000 A Multi-Assay-Based Structure-Activity Relationship Models: Improving Structure-Activity Relationship Models by Incorporating Activity Information from Related Targets

More information

QSAR Modeling of ErbB1 Inhibitors Using Genetic Algorithm-Based Regression

QSAR Modeling of ErbB1 Inhibitors Using Genetic Algorithm-Based Regression APPLICATION NOTE QSAR Modeling of ErbB1 Inhibitors Using Genetic Algorithm-Based Regression GAINING EFFICIENCY IN QUANTITATIVE STRUCTURE ACTIVITY RELATIONSHIPS ErbB1 kinase is the cell-surface receptor

More information

Machine Learning Concepts in Chemoinformatics

Machine Learning Concepts in Chemoinformatics Machine Learning Concepts in Chemoinformatics Martin Vogt B-IT Life Science Informatics Rheinische Friedrich-Wilhelms-Universität Bonn BigChem Winter School 2017 25. October Data Mining in Chemoinformatics

More information

arxiv: v1 [physics.chem-ph] 6 Apr 2018

arxiv: v1 [physics.chem-ph] 6 Apr 2018 Population-based de novo molecule generation, using grammatical evolution arxiv:1804.02134v1 [physics.chem-ph] 6 Apr 2018 Naruki Yoshikawa a, Kei Terayama a, Teruki Honma b, Kenta Oono c, Koji Tsuda a,d,e,

More information

Hit Finding and Optimization Using BLAZE & FORGE

Hit Finding and Optimization Using BLAZE & FORGE Hit Finding and Optimization Using BLAZE & FORGE Kevin Cusack,* Maria Argiriadi, Eric Breinlinger, Jeremy Edmunds, Michael Hoemann, Michael Friedman, Sami Osman, Raymond Huntley, Thomas Vargo AbbVie, Immunology

More information

Development and application of ligand-based computational methods for de-novo drug. design and virtual screening. Alexander Richard Geanes.

Development and application of ligand-based computational methods for de-novo drug. design and virtual screening. Alexander Richard Geanes. Development and application of ligand-based computational methods for de-novo drug design and virtual screening By Alexander Richard Geanes Thesis Submitted to the Faculty of the Graduate School of Vanderbilt

More information

Progress of Compound Library Design Using In-silico Approach for Collaborative Drug Discovery

Progress of Compound Library Design Using In-silico Approach for Collaborative Drug Discovery 21 th /June/2018@CUGM Progress of Compound Library Design Using In-silico Approach for Collaborative Drug Discovery Kaz Ikeda, Ph.D. Keio University Self Introduction Keio University, Tokyo, Japan (Established

More information

MSc Drug Design. Module Structure: (15 credits each) Lectures and Tutorials Assessment: 50% coursework, 50% unseen examination.

MSc Drug Design. Module Structure: (15 credits each) Lectures and Tutorials Assessment: 50% coursework, 50% unseen examination. Module Structure: (15 credits each) Lectures and Assessment: 50% coursework, 50% unseen examination. Module Title Module 1: Bioinformatics and structural biology as applied to drug design MEDC0075 In the

More information

Capturing Chemistry. What you see is what you get In the world of mechanism and chemical transformations

Capturing Chemistry. What you see is what you get In the world of mechanism and chemical transformations Capturing Chemistry What you see is what you get In the world of mechanism and chemical transformations Dr. Stephan Schürer ead of Intl. Sci. Content Libraria, Inc. sschurer@libraria.com Distribution of

More information

An Integrated Approach to in-silico

An Integrated Approach to in-silico An Integrated Approach to in-silico Screening Joseph L. Durant Jr., Douglas. R. Henry, Maurizio Bronzetti, and David. A. Evans MDL Information Systems, Inc. 14600 Catalina St., San Leandro, CA 94577 Goals

More information

Chemical Space. Space, Diversity, and Synthesis. Jeremy Henle, 4/23/2013

Chemical Space. Space, Diversity, and Synthesis. Jeremy Henle, 4/23/2013 Chemical Space Space, Diversity, and Synthesis Jeremy Henle, 4/23/2013 Computational Modeling Chemical Space As a diversity construct Outline Quantifying Diversity Diversity Oriented Synthesis Wolf and

More information

Raed Saeed Khashan. Chapel Hill Approved by: Dr. Alexander Tropsha. Dr. Weifan Zheng. Dr. Alexander Golbraikh. Dr. Wei Wang. Dr.

Raed Saeed Khashan. Chapel Hill Approved by: Dr. Alexander Tropsha. Dr. Weifan Zheng. Dr. Alexander Golbraikh. Dr. Wei Wang. Dr. DEVELOPMENT AND APPLICATION OF LIGAND-BASED AND STRUCTURE- BASED COMPUTATIONAL DRUG DISCOVERY TOOLS BASED ON FREQUENT SUBGRAPH MINING OF CHEMICAL STRUCTURES Raed Saeed Khashan A dissertation submitted

More information

The use of Design of Experiments to develop Efficient Arrays for SAR and Property Exploration

The use of Design of Experiments to develop Efficient Arrays for SAR and Property Exploration The use of Design of Experiments to develop Efficient Arrays for SAR and Property Exploration Chris Luscombe, Computational Chemistry GlaxoSmithKline Summary of Talk Traditional approaches SAR Free-Wilson

More information

CHEMINFORMATICS MODELING OF DIVERSE AND DISPARATE BIOLOGICAL DATA AND THE USE OF MODELS TO DISCOVER NOVEL BIOACTIVE MOLECULES

CHEMINFORMATICS MODELING OF DIVERSE AND DISPARATE BIOLOGICAL DATA AND THE USE OF MODELS TO DISCOVER NOVEL BIOACTIVE MOLECULES CHEMINFORMATICS MODELING OF DIVERSE AND DISPARATE BIOLOGICAL DATA AND THE USE OF MODELS TO DISCOVER NOVEL BIOACTIVE MOLECULES Man Luo A dissertation submitted to the faculty of the University of North

More information

Virtual Libraries and Virtual Screening in Drug Discovery Processes using KNIME

Virtual Libraries and Virtual Screening in Drug Discovery Processes using KNIME Virtual Libraries and Virtual Screening in Drug Discovery Processes using KNIME Iván Solt Solutions for Cheminformatics Drug Discovery Strategies for known targets High-Throughput Screening (HTS) Cells

More information

Building innovative drug discovery alliances. Just in KNIME: Successful Process Driven Drug Discovery

Building innovative drug discovery alliances. Just in KNIME: Successful Process Driven Drug Discovery Building innovative drug discovery alliances Just in KIME: Successful Process Driven Drug Discovery Berlin KIME Spring Summit, Feb 2016 Research Informatics @ Evotec Evotec s worldwide operations 2 Pharmaceuticals

More information

Cheminformatics analysis and learning in a data pipelining environment

Cheminformatics analysis and learning in a data pipelining environment Molecular Diversity (2006) 10: 283 299 DOI: 10.1007/s11030-006-9041-5 c Springer 2006 Review Cheminformatics analysis and learning in a data pipelining environment Moises Hassan 1,, Robert D. Brown 1,

More information

Few-shot learning with KRR

Few-shot learning with KRR Few-shot learning with KRR Prudencio Tossou Groupe de Recherche en Apprentissage Automatique Départment d informatique et de génie logiciel Université Laval April 6, 2018 Prudencio Tossou (UL) Few-shot

More information

How IJC is Adding Value to a Molecular Design Business

How IJC is Adding Value to a Molecular Design Business How IJC is Adding Value to a Molecular Design Business James Mills Sexis LLP ChemAxon TechTalk Stevenage, ov 2012 james.mills@sexis.co.uk Overview Introduction to Sexis Sexis IJC use cases Data visualisation

More information

Integrated Cheminformatics to Guide Drug Discovery

Integrated Cheminformatics to Guide Drug Discovery Integrated Cheminformatics to Guide Drug Discovery Matthew Segall, Ed Champness, Peter Hunt, Tamsin Mansley CINF Drug Discovery Cheminformatics Approaches August 23 rd 2017 Optibrium, StarDrop, Auto-Modeller,

More information

CSC321 Lecture 20: Reversible and Autoregressive Models

CSC321 Lecture 20: Reversible and Autoregressive Models CSC321 Lecture 20: Reversible and Autoregressive Models Roger Grosse Roger Grosse CSC321 Lecture 20: Reversible and Autoregressive Models 1 / 23 Overview Four modern approaches to generative modeling:

More information

Using AutoDock for Virtual Screening

Using AutoDock for Virtual Screening Using AutoDock for Virtual Screening CUHK Croucher ASI Workshop 2011 Stefano Forli, PhD Prof. Arthur J. Olson, Ph.D Molecular Graphics Lab Screening and Virtual Screening The ultimate tool for identifying

More information

Chemoinformatics and information management. Peter Willett, University of Sheffield, UK

Chemoinformatics and information management. Peter Willett, University of Sheffield, UK Chemoinformatics and information management Peter Willett, University of Sheffield, UK verview What is chemoinformatics and why is it necessary Managing structural information Typical facilities in chemoinformatics

More information

A Study of Complex Deep Learning Networks on High Performance, Neuromorphic, and Quantum Computers

A Study of Complex Deep Learning Networks on High Performance, Neuromorphic, and Quantum Computers A Study of Complex Deep Learning Networks on High Performance, Neuromorphic, and Quantum Computers Thomas E. Potok, Ph.D. Computational Data Analytics Group Oak Ridge National Laboratory ORNL is managed

More information

Cross Discipline Analysis made possible with Data Pipelining. J.R. Tozer SciTegic

Cross Discipline Analysis made possible with Data Pipelining. J.R. Tozer SciTegic Cross Discipline Analysis made possible with Data Pipelining J.R. Tozer SciTegic System Genesis Pipelining tool created to automate data processing in cheminformatics Modular system built with generic

More information

Cheminformatics Role in Pharmaceutical Industry. Randal Chen Ph.D. Abbott Laboratories Aug. 23, 2004 ACS

Cheminformatics Role in Pharmaceutical Industry. Randal Chen Ph.D. Abbott Laboratories Aug. 23, 2004 ACS Cheminformatics Role in Pharmaceutical Industry Randal Chen Ph.D. Abbott Laboratories Aug. 23, 2004 ACS Agenda The big picture for pharmaceutical industry Current technological/scientific issues Types

More information

Similarity methods for ligandbased virtual screening

Similarity methods for ligandbased virtual screening Similarity methods for ligandbased virtual screening Peter Willett, University of Sheffield Computers in Scientific Discovery 5, 22 nd July 2010 Overview Molecular similarity and its use in virtual screening

More information

Chemogenomic: Approaches to Rational Drug Design. Jonas Skjødt Møller

Chemogenomic: Approaches to Rational Drug Design. Jonas Skjødt Møller Chemogenomic: Approaches to Rational Drug Design Jonas Skjødt Møller Chemogenomic Chemistry Biology Chemical biology Medical chemistry Chemical genetics Chemoinformatics Bioinformatics Chemoproteomics

More information

Pose and affinity prediction by ICM in D3R GC3. Max Totrov Molsoft

Pose and affinity prediction by ICM in D3R GC3. Max Totrov Molsoft Pose and affinity prediction by ICM in D3R GC3 Max Totrov Molsoft Pose prediction method: ICM-dock ICM-dock: - pre-sampling of ligand conformers - multiple trajectory Monte-Carlo with gradient minimization

More information

Supporting Information

Supporting Information Supporting Information Convolutional Embedding of Attributed Molecular Graphs for Physical Property Prediction Connor W. Coley a, Regina Barzilay b, William H. Green a, Tommi S. Jaakkola b, Klavs F. Jensen

More information

Contents 1 Open-Source Tools, Techniques, and Data in Chemoinformatics

Contents 1 Open-Source Tools, Techniques, and Data in Chemoinformatics Contents 1 Open-Source Tools, Techniques, and Data in Chemoinformatics... 1 1.1 Chemoinformatics... 2 1.1.1 Open-Source Tools... 2 1.1.2 Introduction to Programming Languages... 3 1.2 Chemical Structure

More information

Deep Learning Srihari. Deep Belief Nets. Sargur N. Srihari

Deep Learning Srihari. Deep Belief Nets. Sargur N. Srihari Deep Belief Nets Sargur N. Srihari srihari@cedar.buffalo.edu Topics 1. Boltzmann machines 2. Restricted Boltzmann machines 3. Deep Belief Networks 4. Deep Boltzmann machines 5. Boltzmann machines for continuous

More information

Patent Searching using Bayesian Statistics

Patent Searching using Bayesian Statistics Patent Searching using Bayesian Statistics Willem van Hoorn, Exscientia Ltd Biovia European Forum, London, June 2017 Contents Who are we? Searching molecules in patents What can Pipeline Pilot do for you?

More information

Memory-Augmented Attention Model for Scene Text Recognition

Memory-Augmented Attention Model for Scene Text Recognition Memory-Augmented Attention Model for Scene Text Recognition Cong Wang 1,2, Fei Yin 1,2, Cheng-Lin Liu 1,2,3 1 National Laboratory of Pattern Recognition Institute of Automation, Chinese Academy of Sciences

More information

Studying the effect of noise on Laplacian-modified Bayesian Analysis and Tanimoto Similarity

Studying the effect of noise on Laplacian-modified Bayesian Analysis and Tanimoto Similarity Studying the effect of noise on Laplacian-modified Bayesian nalysis and Tanimoto Similarity David Rogers, Ph.D. SciTegic, Inc. (Division of ccelrys, Inc.) drogers@scitegic.com Description of: nalysis methods

More information

AMRI COMPOUND LIBRARY CONSORTIUM: A NOVEL WAY TO FILL YOUR DRUG PIPELINE

AMRI COMPOUND LIBRARY CONSORTIUM: A NOVEL WAY TO FILL YOUR DRUG PIPELINE AMRI COMPOUD LIBRARY COSORTIUM: A OVEL WAY TO FILL YOUR DRUG PIPELIE Muralikrishna Valluri, PhD & Douglas B. Kitchen, PhD Summary The creation of high-quality, innovative small molecule leads is a continual

More information

A Tiered Screen Protocol for the Discovery of Structurally Diverse HIV Integrase Inhibitors

A Tiered Screen Protocol for the Discovery of Structurally Diverse HIV Integrase Inhibitors A Tiered Screen Protocol for the Discovery of Structurally Diverse HIV Integrase Inhibitors Rajarshi Guha, Debojyoti Dutta, Ting Chen and David J. Wild School of Informatics Indiana University and Dept.

More information

Ignasi Belda, PhD CEO. HPC Advisory Council Spain Conference 2015

Ignasi Belda, PhD CEO. HPC Advisory Council Spain Conference 2015 Ignasi Belda, PhD CEO HPC Advisory Council Spain Conference 2015 Business lines Molecular Modeling Services We carry out computational chemistry projects using our selfdeveloped and third party technologies

More information

The Molecule Cloud - compact visualization of large collections of molecules

The Molecule Cloud - compact visualization of large collections of molecules Ertl and Rohde Journal of Cheminformatics 2012, 4:12 METHODOLOGY Open Access The Molecule Cloud - compact visualization of large collections of molecules Peter Ertl * and Bernhard Rohde Abstract Background:

More information

Deep Learning for Gravitational Wave Analysis Results with LIGO Data

Deep Learning for Gravitational Wave Analysis Results with LIGO Data Link to these slides: http://tiny.cc/nips arxiv:1711.03121 Deep Learning for Gravitational Wave Analysis Results with LIGO Data Daniel George & E. A. Huerta NCSA Gravity Group - http://gravity.ncsa.illinois.edu/

More information

Artificial Intelligence Methods for Molecular Property Prediction. Evan N. Feinberg Pande Lab

Artificial Intelligence Methods for Molecular Property Prediction. Evan N. Feinberg Pande Lab Artificial Intelligence Methods for Molecular Property Prediction Evan N. Feinberg Pande Lab AI Drug Discovery trends.google.com https://g.co/trends/3y4uf MNIST Performance over Time https://srconstantin.wordpress.com/2017/01/28/performance-trends-in-ai/

More information

Structure based drug design and LIE models for GPCRs

Structure based drug design and LIE models for GPCRs Structure based drug design and LIE models for GPCRs Peter Kolb kolb@docking.org Shoichet Lab ACS 237 th National Meeting, March 24, 2009 p.1/26 [Acknowledgements] Brian Shoichet John Irwin Mike Keiser

More information

Deep learning / Ian Goodfellow, Yoshua Bengio and Aaron Courville. - Cambridge, MA ; London, Spis treści

Deep learning / Ian Goodfellow, Yoshua Bengio and Aaron Courville. - Cambridge, MA ; London, Spis treści Deep learning / Ian Goodfellow, Yoshua Bengio and Aaron Courville. - Cambridge, MA ; London, 2017 Spis treści Website Acknowledgments Notation xiii xv xix 1 Introduction 1 1.1 Who Should Read This Book?

More information

DATA FUSION APPROACHES IN LIGAND-BASED VIRTUAL SCREENING: RECENT DEVELOPMENTS OVERVIEW

DATA FUSION APPROACHES IN LIGAND-BASED VIRTUAL SCREENING: RECENT DEVELOPMENTS OVERVIEW DATA FUSION APPROACHES IN LIGAND-BASED VIRTUAL SCREENING: RECENT DEVELOPMENTS OVERVIEW Mubarak Himmat 1, Naomie Salim 1, Ali Ahmed 1, 2, and Mohammed Mumtaz Al-Dabbagh 1 1 Faculty of Computing, University

More information

Similarity Search. Uwe Koch

Similarity Search. Uwe Koch Similarity Search Uwe Koch Similarity Search The similar property principle: strurally similar molecules tend to have similar properties. However, structure property discontinuities occur frequently. Relevance

More information

Increasing the Coverage of Medicinal Chemistry-Relevant Space in Commercial Fragments Screening

Increasing the Coverage of Medicinal Chemistry-Relevant Space in Commercial Fragments Screening pubs.acs.org/jcim Increasing the Coverage of Medicinal Chemistry-Relevant Space in Commercial Fragments Screening N. Yi Mok,, Ruth Brenk,*,,# and Nathan Brown*, Cancer Research UK Cancer Therapeutics Unit,

More information

A reliable computational workflow for the selection of optimal screening libraries

A reliable computational workflow for the selection of optimal screening libraries DOI 10.1186/s13321-015-0108-0 RESEARCH ARTICLE Open Access A reliable computational workflow for the selection of optimal screening libraries Yocheved Gilad 1, Katalin Nadassy 2 and Hanoch Senderowitz

More information

Juergen Gall. Analyzing Human Behavior in Video Sequences

Juergen Gall. Analyzing Human Behavior in Video Sequences Juergen Gall Analyzing Human Behavior in Video Sequences 09. 10. 2 01 7 Juer gen Gall Instit u t e of Com puter Science III Com puter Vision Gr oup 2 Analyzing Human Behavior Analyzing Human Behavior Human

More information

Introduction to Chemoinformatics

Introduction to Chemoinformatics Introduction to Chemoinformatics Dr. Igor V. Tetko Helmholtz Zentrum München - German Research Center for Environmental Health (GmbH) Institute of Bioinformatics & Systems Biology (HMGU) Kyiv, 10 August

More information

Deep Learning Autoencoder Models

Deep Learning Autoencoder Models Deep Learning Autoencoder Models Davide Bacciu Dipartimento di Informatica Università di Pisa Intelligent Systems for Pattern Recognition (ISPR) Generative Models Wrap-up Deep Learning Module Lecture Generative

More information

Targeting protein-protein interactions: A hot topic in drug discovery

Targeting protein-protein interactions: A hot topic in drug discovery Michal Kamenicky; Maria Bräuer; Katrin Volk; Kamil Ödner; Christian Klein; Norbert Müller Targeting protein-protein interactions: A hot topic in drug discovery 104 Biomedizin Innovativ patientinnenfokussierte,

More information

Topology based deep learning for biomolecular data

Topology based deep learning for biomolecular data Topology based deep learning for biomolecular data Guowei Wei Departments of Mathematics Michigan State University http://www.math.msu.edu/~wei American Institute of Mathematics July 23-28, 2017 Grant

More information

Prototype-Based Compound Discovery using. Deep Generative Models

Prototype-Based Compound Discovery using. Deep Generative Models Prototype-Based Compound Discovery using Deep Generative Models Shahar Harel and Kira Radinsky Department of Computer Science, Technion - Israel Institute of Technology E-mail: sshahar@cs.technion.ac.il;

More information

est Drive K20 GPUs! Experience The Acceleration Run Computational Chemistry Codes on Tesla K20 GPU today

est Drive K20 GPUs! Experience The Acceleration Run Computational Chemistry Codes on Tesla K20 GPU today est Drive K20 GPUs! Experience The Acceleration Run Computational Chemistry Codes on Tesla K20 GPU today Sign up for FREE GPU Test Drive on remotely hosted clusters www.nvidia.com/gputestd rive Shape Searching

More information

Structural biology and drug design: An overview

Structural biology and drug design: An overview Structural biology and drug design: An overview livier Taboureau Assitant professor Chemoinformatics group-cbs-dtu otab@cbs.dtu.dk Drug discovery Drug and drug design A drug is a key molecule involved

More information

JCICS Major Research Areas

JCICS Major Research Areas JCICS Major Research Areas Chemical Information Text Searching Structure and Substructure Searching Databases Patents George W.A. Milne C571 Lecture Fall 2002 1 JCICS Major Research Areas Chemical Computation

More information

Docking. GBCB 5874: Problem Solving in GBCB

Docking. GBCB 5874: Problem Solving in GBCB Docking Benzamidine Docking to Trypsin Relationship to Drug Design Ligand-based design QSAR Pharmacophore modeling Can be done without 3-D structure of protein Receptor/Structure-based design Molecular

More information

Next Generation Computational Chemistry Tools to Predict Toxicity of CWAs

Next Generation Computational Chemistry Tools to Predict Toxicity of CWAs Next Generation Computational Chemistry Tools to Predict Toxicity of CWAs William (Bill) Welsh welshwj@umdnj.edu Prospective Funding by DTRA/JSTO-CBD CBIS Conference 1 A State-wide, Regional and National

More information

LIBRARY DESIGN FOR COLLABORATIVE DRUG DISCOVERY: EXPANDING DRUGGABLE CHEMOGENOMIC SPACE

LIBRARY DESIGN FOR COLLABORATIVE DRUG DISCOVERY: EXPANDING DRUGGABLE CHEMOGENOMIC SPACE 5 th /June/2018@British Embassy in Tokyo LIBRARY DESIGN FOR COLLABORATIVE DRUG DISCOVERY: EXPANDING DRUGGABLE CHEMOGENOMIC SPACE Kazuyoshi Ikeda, Ph.D. Keio University SELF-INTRODUCTION Keio University,

More information

PROVIDING CHEMINFORMATICS SOLUTIONS TO SUPPORT DRUG DISCOVERY DECISIONS

PROVIDING CHEMINFORMATICS SOLUTIONS TO SUPPORT DRUG DISCOVERY DECISIONS 179 Molecular Informatics: Confronting Complexity, May 13 th - 16 th 2002, Bozen, Italy PROVIDING CHEMINFORMATICS SOLUTIONS TO SUPPORT DRUG DISCOVERY DECISIONS CARLETON R. SAGE, KEVIN R. HOLME, NIANISH

More information

Introduction to Machine Learning Midterm Exam

Introduction to Machine Learning Midterm Exam 10-701 Introduction to Machine Learning Midterm Exam Instructors: Eric Xing, Ziv Bar-Joseph 17 November, 2015 There are 11 questions, for a total of 100 points. This exam is open book, open notes, but

More information

Practical QSAR and Library Design: Advanced tools for research teams

Practical QSAR and Library Design: Advanced tools for research teams DS QSAR and Library Design Webinar Practical QSAR and Library Design: Advanced tools for research teams Reservationless-Plus Dial-In Number (US): (866) 519-8942 Reservationless-Plus International Dial-In

More information

Translating Methods from Pharma to Flavours & Fragrances

Translating Methods from Pharma to Flavours & Fragrances Translating Methods from Pharma to Flavours & Fragrances CINF 27: ACS National Meeting, New Orleans, LA - 18 th March 2018 Peter Hunt, Edmund Champness, Nicholas Foster, Tamsin Mansley & Matthew Segall

More information

DivCalc: A Utility for Diversity Analysis and Compound Sampling

DivCalc: A Utility for Diversity Analysis and Compound Sampling Molecules 2002, 7, 657-661 molecules ISSN 1420-3049 http://www.mdpi.org DivCalc: A Utility for Diversity Analysis and Compound Sampling Rajeev Gangal* SciNova Informatics, 161 Madhumanjiri Apartments,

More information

Exploring the chemical space of screening results

Exploring the chemical space of screening results Exploring the chemical space of screening results Edmund Champness, Matthew Segall, Chris Leeding, James Chisholm, Iskander Yusof, Nick Foster, Hector Martinez ACS Spring 2013, 7 th April 2013 Optibrium,

More information

Design and Synthesis of the Comprehensive Fragment Library

Design and Synthesis of the Comprehensive Fragment Library YOUR INNOVATIVE CHEMISTRY PARTNER IN DRUG DISCOVERY Design and Synthesis of the Comprehensive Fragment Library A 3D Enabled Library for Medicinal Chemistry Discovery Warren S Wade 1, Kuei-Lin Chang 1,

More information

What I Did Last Summer

What I Did Last Summer What I Did Last Summer LINGOs, GPUs, and Monitoring Vertex Imran Haque Department of Computer Science Pande Lab, Stanford University http://cs.stanford.edu/people/ihaque http://folding.stanford.edu ihaque@cs.stanford.edu

More information

Deep learning on 3D geometries. Hope Yao Design Informatics Lab Department of Mechanical and Aerospace Engineering

Deep learning on 3D geometries. Hope Yao Design Informatics Lab Department of Mechanical and Aerospace Engineering Deep learning on 3D geometries Hope Yao Design Informatics Lab Department of Mechanical and Aerospace Engineering Overview Background Methods Numerical Result Future improvements Conclusion Background

More information

Tutorials on Library Design E. Lounkine and J. Bajorath (University of Bonn) C. Muller and A. Varnek (University of Strasbourg)

Tutorials on Library Design E. Lounkine and J. Bajorath (University of Bonn) C. Muller and A. Varnek (University of Strasbourg) Tutorials on Library Design E. Lounkine and J. Bajorath (University of Bonn) C. Muller and A. Varnek (University of Strasbourg) The purpose of this tutorial is to generate a library of potential inhibitors

More information

Tasks ADAS. Self Driving. Non-machine Learning. Traditional MLP. Machine-Learning based method. Supervised CNN. Methods. Deep-Learning based

Tasks ADAS. Self Driving. Non-machine Learning. Traditional MLP. Machine-Learning based method. Supervised CNN. Methods. Deep-Learning based UNDERSTANDING CNN ADAS Tasks Self Driving Localizati on Perception Planning/ Control Driver state Vehicle Diagnosis Smart factory Methods Traditional Deep-Learning based Non-machine Learning Machine-Learning

More information

Unsupervised Learning

Unsupervised Learning CS 3750 Advanced Machine Learning hkc6@pitt.edu Unsupervised Learning Data: Just data, no labels Goal: Learn some underlying hidden structure of the data P(, ) P( ) Principle Component Analysis (Dimensionality

More information

Artificial Neural Networks. Introduction to Computational Neuroscience Tambet Matiisen

Artificial Neural Networks. Introduction to Computational Neuroscience Tambet Matiisen Artificial Neural Networks Introduction to Computational Neuroscience Tambet Matiisen 2.04.2018 Artificial neural network NB! Inspired by biology, not based on biology! Applications Automatic speech recognition

More information

CHAPTER 6 QUANTITATIVE STRUCTURE ACTIVITY RELATIONSHIP (QSAR) ANALYSIS

CHAPTER 6 QUANTITATIVE STRUCTURE ACTIVITY RELATIONSHIP (QSAR) ANALYSIS 159 CHAPTER 6 QUANTITATIVE STRUCTURE ACTIVITY RELATIONSHIP (QSAR) ANALYSIS 6.1 INTRODUCTION The purpose of this study is to gain on insight into structural features related the anticancer, antioxidant

More information

Dr. Sander B. Nabuurs. Computational Drug Discovery group Center for Molecular and Biomolecular Informatics Radboud University Medical Centre

Dr. Sander B. Nabuurs. Computational Drug Discovery group Center for Molecular and Biomolecular Informatics Radboud University Medical Centre Dr. Sander B. Nabuurs Computational Drug Discovery group Center for Molecular and Biomolecular Informatics Radboud University Medical Centre The road to new drugs. How to find new hits? High Throughput

More information

Interactive Feature Selection with

Interactive Feature Selection with Chapter 6 Interactive Feature Selection with TotalBoost g ν We saw in the experimental section that the generalization performance of the corrective and totally corrective boosting algorithms is comparable.

More information

Data Mining. CS57300 Purdue University. March 22, 2018

Data Mining. CS57300 Purdue University. March 22, 2018 Data Mining CS57300 Purdue University March 22, 2018 1 Hypothesis Testing Select 50% users to see headline A Unlimited Clean Energy: Cold Fusion has Arrived Select 50% users to see headline B Wedding War

More information

QSAR/QSPR modeling. Quantitative Structure-Activity Relationships Quantitative Structure-Property-Relationships

QSAR/QSPR modeling. Quantitative Structure-Activity Relationships Quantitative Structure-Property-Relationships Quantitative Structure-Activity Relationships Quantitative Structure-Property-Relationships QSAR/QSPR modeling Alexandre Varnek Faculté de Chimie, ULP, Strasbourg, FRANCE QSAR/QSPR models Development Validation

More information

Development of Pharmacophore Model for Indeno[1,2-b]indoles as Human Protein Kinase CK2 Inhibitors and Database Mining

Development of Pharmacophore Model for Indeno[1,2-b]indoles as Human Protein Kinase CK2 Inhibitors and Database Mining Development of Pharmacophore Model for Indeno[1,2-b]indoles as Human Protein Kinase CK2 Inhibitors and Database Mining Samer Haidar 1, Zouhair Bouaziz 2, Christelle Marminon 2, Tiomo Laitinen 3, Anti Poso

More information

BioSolveIT. A Combinatorial Approach for Handling of Protonation and Tautomer Ambiguities in Docking Experiments

BioSolveIT. A Combinatorial Approach for Handling of Protonation and Tautomer Ambiguities in Docking Experiments BioSolveIT Biology Problems Solved using Information Technology A Combinatorial Approach for andling of Protonation and Tautomer Ambiguities in Docking Experiments Ingo Dramburg BioSolve IT Gmb An der

More information