Chemical Informatics & Cyberinfrastructure Collaboratory
This presentation is the property of its rightful owner.
Sponsored Links
1 / 44

David J. Wild Visiting Assistant Professor Indiana University School of Informatics PowerPoint PPT Presentation


  • 110 Views
  • Uploaded on
  • Presentation posted in: General

Chemical Informatics & Cyberinfrastructure Collaboratory Cheminformatics Aspects: HTS Data Analysis & Virtual Screening. David J. Wild Visiting Assistant Professor Indiana University School of Informatics [email protected] http://www.informatics.indiana.edu/djwild/. About Me.

Download Presentation

David J. Wild Visiting Assistant Professor Indiana University School of Informatics

An Image/Link below is provided (as is) to download presentation

Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author.While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server.


- - - - - - - - - - - - - - - - - - - - - - - - - - E N D - - - - - - - - - - - - - - - - - - - - - - - - - -

Presentation Transcript


David j wild visiting assistant professor indiana university school of informatics

Chemical Informatics & Cyberinfrastructure CollaboratoryCheminformatics Aspects:HTS Data Analysis & Virtual Screening

David J. Wild

Visiting Assistant Professor

Indiana University School of Informatics

[email protected]

http://www.informatics.indiana.edu/djwild/

David Wild – ECCR Meeting, October 2005. Page 1


About me

About Me

  • Ph.D. and postdoc in Peter Willett’s Lab (Sheffield) – parallel 2D and 3D similarity algorithms.

  • Postdoc then Senior Scientist at Parke-Davis, Ann Arbor (now Pfizer), researching and developing chemoinformatics tools for bench chemists & modelers. Led collaborations with Tripos and Bioreason for development of HTS analysis software (SAR Navigator, ClassPharmer)

  • Left in 2002 to form Wild Ideas Consulting and take up adjunct position at University of Michigan

  • Visiting Assistant Professor at Indiana since August 2004. Permanent position starting fall 2006.

  • Now run research group focused on handling large and diverse sources of chemical information.More at http://www.informatics.indiana.edu/djwild

David Wild – ECCR Meeting, October 2005. Page 2


Cheminformatics contect of cicc proposal

“Cheminformatics” contect ofCICC proposal

  • Development of user-centered tools for query, organization, navigation and analysis of large chemical HTS datasets (specifically Pubchem and its subsets), including:

    • Rapid organization of large datasets (cluster analysis)

    • Intuitive interfaces for navigation and analysis

    • Virtual screening

    • Standardization of data exchange formats

    • Data mining of SAR across multiple screens

  • Or allowing scientists to ask the right questions and have them answered effectively

David Wild – ECCR Meeting, October 2005. Page 3


Thoughts relating to pubchem hts analysis and more widely applicable

Thoughts relating to Pubchem HTS analysis(and more widely applicable)

  • Scientists’ questions are probably not going to be conceptually complex, but finding the answers can currently be very time consuming and/or complex (for a human)

    • “which of the 10,000 hits from this screen are most promising for follow-up?”

    • “who else is working on similar chemical structures to these?”

    • “are there any compounds in Pubchem (or elsewhere) that might bind to the active site of this protein I just resolved?”

    • “do any compounds related to this one exhibit toxic side effects?”

  • We need to figure out just what the questions are!(Contextual Inquiry, Use cases)

  • Answers are often “stale” after a short period of time – questions need to be re-answered as new information is generated

  • Almost all current systems are passive, and follow the(web) browsing model

  • Existing approaches do not scale up well

David Wild – ECCR Meeting, October 2005. Page 4


Use case which of these hits should i follow up

Use CaseWhich of these hits should I follow up?

  • An HTS experiment has produced 10,000 possible hits out of a screening set of 2m compounds. A chemist on the project wants to know what the most promising series of compounds for follow-up are, based on:

    • Series selection  BCI cluster analysis

    • Structure-activity relationships lots of methods

    • Chemical and pharmacokinetic propertiesmitools, chemaxon

    • Compound history gNova / PostgreSQL / Pubchem search

    • Patentability  BCI Markush handling software

    • Toxicity

    • Synthetic feasibility

    • + requires visualization tools!

David Wild – ECCR Meeting, October 2005. Page 5


Use case are there any good ligands for my target

Use CaseAre there any good ligands for my target?

  • A chemist is working on a project involving a particular protein target, and wants to know:

    • Any newly published compounds which might fit the protein receptor site  gNova / PostgreSQL, PubChem search, FRED Docking

    • Any published 3D structures of the protein or of protein-ligand complexes  PDB search

    • Any interactions of compounds with other proteins  gNova / PostgreSQL, PubChem search

    • Any information published on the protein target  Journal text search

David Wild – ECCR Meeting, October 2005. Page 6


David j wild visiting assistant professor indiana university school of informatics

Wild, D.J., Strategies for Using Information Effectively in Early-stage Drug Discovery, in Ekins, S. (ed), Computer Applications in Pharmaceutical Research and Development, submitted July 2005

David Wild – ECCR Meeting, October 2005. Page 7


David j wild visiting assistant professor indiana university school of informatics

interfaces / grid portal

knowledge mgt.

atomic web services

databases & tools

Wild, D.J., Strategies for Using Information Effectively in Early-stage Drug Discovery, in Ekins, S. (ed), Computer Applications in Pharmaceutical Research and Development, submitted July 2005

David Wild – ECCR Meeting, October 2005. Page 8


David j wild visiting assistant professor indiana university school of informatics

Request from Human Interface

USE-CASE SCRIPT

Invoke New Structure Service

Convert structures to 3D

Dock results & protein file

Extract any hits

Return links for visualization

AGENT / SMART CLIENT

Parse request

Select appropriate use cases

and/or web service(s)

Schedule as necessary

“find me all the

structures that fit the

enclosed protein for

The next three months”

UDDI

WSDL

SOAP

New Structure Service

Search online databases

for recent structures

Search local databases

for recent structures

Merge Results

Online

database

(e.g. PubChem)

Local

database

3D Docking

Tool

2D-3D

converter

3D

visualizer

atomic services

aggregate services

David Wild – ECCR Meeting, October 2005. Page 9


Visualization interface level tools

Visualization & interface level tools

  • No matter how clever the smarts underneath, the overriding factor in usefulness will be the quality of scientists’ interaction with the system

  • Several metaphors in existence for looking at large amounts of 2D structural information: 2D plot (SAR Navigator), “spreadsheet” views (Accord, etc), enhanced spreadsheets (Classpharmer, ChemTK), Kohonen maps, TreeMaps

  • Contextual Design, Interaction Design (Cooper) and Usability Studies have proven effective in designing the right interfaces for the right peoplein chemical informatics, and deserve investigation for future use in this project (in collaboration with HCI colleagues on the project)

  • Possibility of multiple interfaces for different people groups(Cooper’s “primary personas”)

  • Don’t assume the browser interface – email / nat. lang. proc ?

  • Start with the basics

    • 2D chemical structure drawing (input)

    • Visualization of large numbers of chemical structures in 2D

    • 3D chemical structure visualization

  • Planning on evaluation of NLP, email, RSS, etc. as well asbrowser-based interfaces

  • Interface tools will be developed in a grid portal environment usingportlet technology

David Wild – ECCR Meeting, October 2005. Page 10


Visualization methods for datasets clusters

Visualization methods for datasets & clusters

  • Partitions

    • Spreadsheets

    • Enhanced Spreadsheets

    • 2D or 3D plots

  • Hierarchies

    • Dendograms

    • Tree Maps

    • Hyperbolic Maps

David Wild – ECCR Meeting, October 2005. Page 11


Usability of 2d structure drawing tools

Usability of 2D structure drawing tools

  • Key difference between “sequential” and “random” drawers

  • Huge difference in intuitiveness

  • Key factor how badly you can mess things up

  • Marvin Sketch ≈ JME > ChemDraw >> ISIS Draw

David Wild – ECCR Meeting, October 2005. Page 12


Next steps

Next Steps

  • Develop realistic use-cases based on as much information about potential users as we can muster

  • Work with other members of CICC to define Grid architecture (services required and their interfaces) by integrating requirements of different aspects of Cheminformatics

  • Implement some web services that are likely to be employed in use cases

    • Rapid dataset search and organization

      • Search of PubChem (SOAP interface already exists)

      • Search of local gNova / PostgreSQL database

      • Clustering using BCI (Digital Chemistry) Divisive K-Means

      • BCI Markush searching

    • Interface tools for navigation and analysis

      • Integration with Spotfire

      • ChemTK (or other spreadsheet-metaphor product)

      • Develop entirely new interface tools (usability studies)

    • Virtual Screening

      • Molecular docking with OpenEye FRED

      • Property calculation with Molinspiration / Chemaxon

      • PDB Search (EMBL)

      • Activity prediction modules (Molinspiration / RP / SVMs etc)

David Wild – ECCR Meeting, October 2005. Page 13


Supplemental slides

Supplemental Slides

David Wild – ECCR Meeting, October 2005. Page 14


David j wild visiting assistant professor indiana university school of informatics

David Wild – ECCR Meeting, October 2005. Page 15


David j wild visiting assistant professor indiana university school of informatics

David Wild – ECCR Meeting, October 2005. Page 16


Use case 1 are there any good ligands for my target

Use Case #1Are there any good ligands for my target?

  • A chemist is working on a project involving a particular protein target, and wants to know:

    • Any newly published compounds which might fit the protein receptor site

    • Any published 3D structures of the protein or of protein-ligand complexes

    • Any interactions of compounds with other proteins

    • Any information published on the protein target

David Wild – ECCR Meeting, October 2005. Page 17


Use case 1 are there any good ligands for my target1

Use Case #1Are there any good ligands for my target?

  • A chemist is working on a project involving a particular protein target, and wants to know:

    • Any newly published compounds which might fit the protein receptor site  gNova / PostgreSQL, PubChem search, FRED Docking

    • Any published 3D structures of the protein or of protein-ligand complexes  PDB search

    • Any interactions of compounds with other proteins  gNova / PostgreSQL, PubChem search

    • Any information published on the protein target  Journal text search

David Wild – ECCR Meeting, October 2005. Page 18


Use case 2 who else is working on these structures

Use Case #2Who else is working on these structures?

  • A chemist is working on a chemical series for a particular project and wants to know:

    • If anyone publishes anything using the same or related compounds

    • Any new compounds added to the corporate collection which are similar or related

    • If any patents are submitted that might overlap the compounds he is working on

    • Any pharmacological or toxicological results for those or related compounds

    • The results for any other projects for which those compounds were screened

David Wild – ECCR Meeting, October 2005. Page 19


Use case 2 who else is working on these structures1

Use Case #2Who else is working on these structures?

  • A chemist is working on a chemical series for a particular project and wants to know:

    • If anyone publishes anything using the same or related compounds ~ PubChem search

    • Any new compounds added to the corporate collection which are similar or related  gNova CHORD / PostgreSQL

    • If any patents are submitted that might overlap the compounds he is working on~ BCI Markush handling software

    • Any pharmacological or toxicological results for those or related compounds  gNova CHORD / PostgreSQL, MiToolkit

    • The results for any other projects for which those compounds were screened  gNova CHORD / PostgreSQL, PubChem search

David Wild – ECCR Meeting, October 2005. Page 20


Use case pubchem which of these hits should i follow up

Use Case - PubchemWhich of these hits should I follow up?

  • An MLI HTS experiment has produced 10,000 possible hits out of a screening set of 2m compounds. A chemist at another laboratory wants to know if there are any interesting active series she might want to pursue, based on:

    • Structure-activity relationships

    • Chemical and pharmacokinetic properties

    • Compound history

    • Patentability

    • Toxicity

    • Synthetic feasibility

David Wild – ECCR Meeting, October 2005. Page 21


Use case pubchem which of these hits should i follow up1

Use Case – PubChemWhich of these hits should I follow up?

  • An HTS experiment has produced 10,000 possible hits out of a screening set of 2m compounds. A chemist on the project wants to know what the most promising series of compounds for follow-up are, based on:

    • Series selection  BCI cluster analysis

    • Structure-activity relationships lots of methods

    • Chemical and pharmacokinetic propertiesmitools, chemaxon

    • Compound history gNova / PostgreSQL / Pubchem search

    • Patentability  BCI Markush handling software

    • Toxicity

    • Synthetic feasibility

    • + requires visualization tools!

David Wild – ECCR Meeting, October 2005. Page 22


Cluster analysis and chemical informatics

Cluster Analysis and Chemical Informatics

  • Used for organizing datasets into chemical series, to build predictive models, or to select representative compounds

  • Organizational usage has not been as well studies as the other two, but see

    • Wild, D.J., Blankley, C.J. Comparison of 2D Fingerprint Types and Hierarchy Level Selection Methods for Structural Grouping using Wards Clustering, Journal of Chemical Information and Computer Sciences., 2000, 40, 155-162.

  • Essentially helping large datasets become manageable

  • Methods used:

    • Jarvis-Patrick and variants

      • O(N2), single partition

    • Ward’s method

      • Hierarchical, regarded as best, but at least O(N2)

    • K-means

      • < O(N2), requires set no of clusters, a little “messy”

    • Sphere-exclusion (Butina)

      • Fast, simple, similar to JP

    • Kohonen network

      • Clusters arranged in 2D grid, ideal for visualization

David Wild – ECCR Meeting, October 2005. Page 23


Limitations of ward s method for large datasets 1m

Limitations of Ward’s method forlarge datasets (>1m)

  • Best algorithms have O(N2) time requirement (RNN)

  • Requires random access to fingerprints

    • hence substantial memory requirements (O(N))

  • Problem of selection of best partition

    • can select desired number of clusters

  • Easily hit 4GB memory addressing limit on 32 bit machines

    • Approximately 2m compounds

David Wild – ECCR Meeting, October 2005. Page 24


Scaling up clustering methods

Scaling up clustering methods

  • Parallelisation

    • Clustering algorithms can be adapted for multiple processors

    • Some algorithms more appropriate than others for particular architectures

    • Ward’s has been parallelized for shared memory machines, but overhead considerable

  • New methods and algorithms

    • Divisive (“bisecting”) K-means method

    • Hierarchical Divisive

    • Approx. O(NlogN)

David Wild – ECCR Meeting, October 2005. Page 25


Divisive k means clustering

Divisive K-means Clustering

  • New hierarchical divisive method

    • Hierarchy built from top down, instead of bottom up

    • Divide complete dataset into two clusters

    • Continue dividing until all items are singletons

    • Each binary division done using K-means method

    • Originally proposed for document clustering

  • “Bisecting K-means”

    • Steinbach, Karypis and Kumar (Univ. Minnesota)http://www-users.cs.umn.edu/~karypis/publications/Papers/PDF/doccluster.pdf

    • Found to be more effective than agglomerative methods

    • Forms more uniformly-sized clusters at given level

David Wild – ECCR Meeting, October 2005. Page 26


Bci divkmeans

BCI Divkmeans

  • Several options for detailed operation

    • Selection of next cluster for division

    • size, variance, diameter

    • affects selection of partitions from hierarchy, not shape of hierarchy

  • Options within each K-means division step

    • distance measure

    • choice of seeds

    • batch-mode or continuous update of centroids

    • termination criterion

  • Have developed parallel version for Linux clusters / grids in conjunction with BCI

  • For more information, see Barnard and Engels talks at: http://cisrg.shef.ac.uk/shef2004/conference.htm

David Wild – ECCR Meeting, October 2005. Page 27


Comparative execution times nci subsets 2 2 ghz intel celeron processor

Comparative execution timesNCI subsets, 2.2 GHz Intel Celeron processor

7h 27m

3h 06m

2h 25m

44m

David Wild – ECCR Meeting, October 2005. Page 28


Clustering a 1 million compound dataset on a 2 2 ghz celeron desktop machine

Clustering a 1 million compound dataseton a 2.2 GHz Celeron Desktop Machine

Results from AVIDD clusters & Teragrid coming soon….

* Time for a single run may vary due to different selection of seeds. Runtimes can be shortened e.g. by using a max. number of iterations or a % relocation cutoff.

David Wild – ECCR Meeting, October 2005. Page 29


Divisive kmeans conclusions

Divisive Kmeans: Conclusions

  • Much faster than Ward’s, speed comparable to K-means, suitable for very large datasets (millions)

    • Time requirements approximately O(N log N)

    • Current implementation can cluster 1m compounds in under a week on a low-power desktop PC

    • Cluster 1m compounds in a few hours with a 4-node parallel Linux cluster

  • Better balance of cluster sizes than Wards or Kmeans

  • Visual inspection of clusters suggests better assembly of compound series than other methods

  • Better clustering of actives together than previously-studied methods

  • Memory requirements minimal

  • Experiments using AVIDD cluster and Teragrid forthcoming(50+ nodes)

David Wild – ECCR Meeting, October 2005. Page 30


Visualization interface level tools1

Visualization & interface level tools

  • No matter how clever the smarts underneath, the overriding factor in usefulness will be the quality of scientists’ interaction with the system

  • Contextual Design, Interaction Design (Cooper) and Usability Studies have proven effective in designing the right interfaces for the right peoplein chemical informatics [collaboration with HCI?]

  • Possibility of multiple interfaces for different people groups(Cooper’s “primary personas”)

  • Don’t assume the browser interface – email / NLP ?

  • Start with the basics

    • 2D chemical structure drawing (input)

    • Visualization of large numbers of chemical structures in 2D

    • 3D chemical structure visualization

  • Planning on evaluation of NLP, email, RSS, etc. as well asbrowser-based interfaces

David Wild – ECCR Meeting, October 2005. Page 31


Usability of 2d structure drawing tools1

Usability of 2D structure drawing tools

  • Key difference between “sequential” and “random” drawers

  • Huge difference in intuitiveness

  • Key factor how badly you can mess things up

  • Marvin Sketch ≈ JME > ChemDraw >> ISIS Draw

David Wild – ECCR Meeting, October 2005. Page 32


Visualization methods for datasets clusters1

Visualization methods for datasets & clusters

  • Partitions

    • Spreadsheets

    • Enhanced Spreadsheets

    • 2D or 3D plots

  • Hierarchies

    • Dendograms

    • Tree Maps

    • Hyperbolic Maps

David Wild – ECCR Meeting, October 2005. Page 33


David j wild visiting assistant professor indiana university school of informatics

David Wild – ECCR Meeting, October 2005. Page 34


David j wild visiting assistant professor indiana university school of informatics

David Wild – ECCR Meeting, October 2005. Page 35


David j wild visiting assistant professor indiana university school of informatics

VisualiSAR – with a nod to Edward Tufte.

See http://www.daylight.com/meetings/mug99/Wild/Mug99.html

David Wild – ECCR Meeting, October 2005. Page 36


David j wild visiting assistant professor indiana university school of informatics

Tree Maps – very Tufte-esque

David Wild – ECCR Meeting, October 2005. Page 37


External support

External support

  • ECCR grant ($500,000)

    • 20% Co-PI with Fox for development of web services for HTS data organization and visualization

    • May lead to $5m/5 years grant for full center

  • Applied for Microsoft Smart Clients for eScience grant ($50,000)

    • Including Marlon Pierce in the Community Grids lab

  • Peter Murray-Rust group, Cambridge – offering expertise and assistance with web services

  • IO-Informatics – provision of Sentient software and consulting

  • BCI – clustering, structure enumeration & toolkit, consulting

  • OpenEye – a range of calculation tools, FRED docking

  • Molinspiration – MiTools Toolkit

  • gNova – CHORD chemical database system

  • Possible financial support from company in the UK

David Wild – ECCR Meeting, October 2005. Page 38


Technology

Technology

  • Perl SOAP::Lite

    • Will be used for initial web service development

    • Doesn’t really implement WSDL & UDDI

  • Apache Axis & Tomcat

    • Deploy WSDL for web services

  • BPEL4WS – Business Process Execution Language

    • For aggregation of web services

    • http://www-128.ibm.com/developerworks/library/specification/ws-bpel/

  • Microsoft .NET & C#

David Wild – ECCR Meeting, October 2005. Page 39


Current activities

Current activities

  • Core activities

    • Development of use-cases

    • Development of initial web services (Perl SOAP::Lite)

    • Use of Taverna to prototype use-case scripts

  • Basic research on future components

    • Organizing large amounts of chemical informationfor human consumption

      • Development of very fast parallel clustering techniques – to be exposed as web services

    • Selection of interface-level tools for basic interaction

      • Chemical structure drawing, display

      • Investigation of email, NLP, RSS, and browser interfaces

    • Interface-level tools for visualization, navigation and analysis

      • Cluster and dataset visualization, natural language interfaces)

David Wild – ECCR Meeting, October 2005. Page 40


Sentient an alternative approach to managing heterogenous data sources

Sentient - an alternative approachto managing heterogenous data sources

  • Collaboration with IO-Informatics (along with Cornell, and UCSD) for the investigation of service-oriented architectures in life sciences research using Sentient software

  • Aim to integrate several sources of information relating to Alzheimer’s Disease (brain imaging, morphology, gene expression) so that cross-dataset biomarkers can be identified

  • Sentient usies Intelligent Multidimensional Objects (IMOs) to define and query data sources and the tools used toaccess them

  • Still a browsing approach, but with a layer of coherenceand “intelligence”

  • Hope to expand to include chemistry data

  • Can also be used as an interface-level tool

David Wild – ECCR Meeting, October 2005. Page 41


David j wild visiting assistant professor indiana university school of informatics

David Wild – ECCR Meeting, October 2005. Page 42


David j wild visiting assistant professor indiana university school of informatics

David Wild – ECCR Meeting, October 2005. Page 43


Conclusions so far

Conclusions so far

  • Effective exploitation of large volumes and diverse sources of chemical information is a critical problem to solve, with a potential huge impact on the drug discovery process

  • Most information needs of chemists and drug discovery scientists are conceptually straightforward, but complex (for them) to implement

  • All of the technology is now in place to implement may of these information need “use-cases”: the four level model using service-oriented architectures together with smart clients look like a neat way of doing this

  • The aggregation and interface levels offer the most challenges

  • In conjunction with grid computing, rapid and effective organization and visualization of large chemical datasets is feasible in a web service environment

  • Some pieces are missing:

    • Chemical structure search of journals (wait for InChI)

    • Automated patent searching

    • Effective dataset organization

    • Effective interfaces, especially visualization of large numbers of 2D structures(we’re working on it!)

David Wild – ECCR Meeting, October 2005. Page 44


  • Login