- 1. Collaborative Database and Computational Models for
Tuberculosis Drug Discovery Sean Ekins Collaborations in Chemistry,
Fuquay Varina, NC. Collaborative Drug Discovery, Burlingame, CA.
Department of Pharmacology, University of Medicine & Dentistry
of New Jersey-Robert Wood Johnson Medical School, Piscataway, NJ.
School of Pharmacy, Department of Pharmaceutical Sciences,
University of Maryland, Baltimore, MD.
2. In the long history of human kind (and animal kind, too)
those who have learned to collaborate and improvise most
effectively have prevailed. Charles Darwin 3. Outline
- Collaborative Drug Discovery
- TB Collaborations and Drug Discovery Research
- Repurposing FDA approved drugs
- The Future Mobile Apps for Drug Discovery
4. Open Innovation Open innovation is a paradigm that assumes
that firms can and should use external ideas as well as internal
ideas, and internal and external paths to market, as the firms look
toadvance their technologyChesbrough, H.W. (2003).Open Innovation:
The new imperative for creating and profiting from
technology.Boston: Harvard Business School Press, p.
xxivCollaborative Innovation A strategy in which groups partner to
create a product - drive the efficient allocation of
R&Dresources. Collaborating with outsiders-including customers,
vendors and even competitors-acompany is able to import lower-cost,
higher-quality ideas from the best sources in the world.Open Source
Whileopen sourceand open innovation might conflict on patent
issues,they are not mutually exclusive, as participating companies
can donate their patentsto an independent organization, put them in
a common pool or grantunlimited license use to anybody. Hence some
open source initiativescan merge the two conceptsSome Definitions
5. How to do it better?What can we do with software to facilitate
it ? The future is more collaborative We have tools but need
integration
- Groups involved traverse the spectrum from pharma, academia,
not for profit and government
- More free, open technologies to enable biomedical research
- Precompetitive organizations, consortia..
A starting point for collaboration A core root of the current
inefficiencies in drug discovery are due to organizations and
individuals barriers to collaborate effectively Bunin & Ekins
DDT 16: 643-645, 2011 6. Major collaborative grants in EU:
Framework, IMI NIH moving in same direction? Cross continent
collaboration CROs in China, India etc Pharmas in US / Europe More
industry academia collaboration not invented here a thing of the
past More effort to go after rare and neglected diseases
-Globalization and connectivity of scientists will be key Current
pace of change in pharma may not be enough. Need to rethink how we
use all technologies & resources Collaboration is everywhere 7.
Hardware is getting smaller 1930s 1980s 1990s Room size Desktop
size Not to scale and not equivalent computing power illustrates
mobility Laptop Netbook Phone Watch 2000s 8. Models and software
becoming more accessible- free, precompetitive efforts -
collaboration Free tools are proliferating 9. Typical Lab:The Data
Explosion Problem & Collaborations DDTFeb 2009 10.
Collaborative Drug Discovery Platform
-
- CDD Vault Secure web-based place for private data private by
default
-
- CDD Collaborate Selectively share subsets of data
-
- CDD Public public data sets - Over 3 Million compounds, with
molecular properties, similarity and substructure searching, data
plotting etc
-
-
- will host datasets from companies, foundations etc
-
-
- vendor libraries (Asinex, TimTec, ChemBridge)
-
- Unique to CDD simultaneously query your private data,
collaborators data, & public data,Easy GUI
www.collaborativedrug.com 11. 12. CDD:Single Click to Key
Functionality 13. CDD:Mining across projects and datasets 14.
- Tuberculosis Kills 1.6-1.7m/yr (~1 every 8 seconds)
- 1/3 rdof worlds population infected!!!!
- Multi drug resistance in 4.3% of cases
- Extensively drug resistant increasing incidence
- No new drugs in over 40 yrs
- Drug-drug interactions and Co-morbidity with HIV
- Collaboration between groups is rare
- These groups may work on existing or new targets
- Use of computational methods with TB is rare
- Literature TB data is not well collated (SAR)
- Funded by Bill and Melinda Gates Foundation
Applying CDD to Build a disease community for TB 15. ~ 20 public
datasetsfor TB Including Novartis data on TB hits >300,000 cpds
Patents, Papers Annotated by CDD Open to browse by
anyonehttp://www.collaborativedrug.com/register Molecules with
activityagainst 16. CDD is a partner on a 5 year project supporting
>20 labs and proving cheminformatics supportwww.mm4tb.org More
Medicines for Tuberculosis 17. Ekins et al, Trends in
Microbiology19: 65-74, 2011 Fitting into the drug discovery process
18. Searching for TB molecular mimics; collaboration Lamichhane G,
et al Mbio, 2: e00301-10, 2011Modeling CDD Biology Johns Hopkins
Chemistry Texas A&M 19. Simple descriptor analysis on >
300,000 compounds tested vs TB4.72 (1.99) 77.75 (30.17)** 42.43
(8.94)* 0.12 (0.34)** 4.24 (1.58) 1.11 (0.82)** 3.38 (1.36)**
352.59 (70.87) Inactive< 90% inhibition at 10uM(N =100,931) 4.76
(1.99) 70.28 (29.55) 41.88 (9.44) 0.19 (0.40) 4.18 (1.66) 0.98
(0.84) 4.04 (1.02) 349.58 (63.82) Active 90% inhibition at 10uM(N
=1702) TAACF-NIAID CB2 4.91 (2.35) 85.06 (32.08)* 43.38 (10.73)
0.09 (0.31)** 4.86 (1.77) 1.14 (0.88) 2.82 (1.44)** 350.15
(77.98)** Inactive< 90% inhibition at 10uM(N = 216367) 4.85
(2.43) 83.46 (34.31) 42.99 (12.70) 0.20 (0.48) 4.89 (1.94) 1.16
(0.93) 3.58 (1.39) 357.10 (84.70) Active 90% inhibition at 10uM(N =
4096) MLSMRRBN PSA Atom count RO 5 HBA HBD logP MWT Dataset 20.
Bayesian Classification Models for TB Good Bad active compounds
with MIC < 5uM Laplacian-corrected Bayesian classifier models
were generated using FCFP-6 and simple descriptors. 2 models
220,000 and >2000 compoundsEkins et al., Mol BioSyst, 6:
840-851, 2010 21. Bayesian Classification Dose response Good Bad
Ekins et al., Mol BioSyst, 6: 840-851, 2010 22. Bayesian machine
learning Ekins, Williams and Xu, Drug Metab Dispos 38: 2302-2308,
2010 Bayesian classification is a simple probabilistic
classification model. It is based on Bayes theorem his the
hypothesis or model dis the observed data p ( h ) is the prior
belief (probability of hypothesishbefore observing any data) p ( d
) is the data evidence (marginal probability of the data) p ( d|h )
is the likelihood (probability of datadif hypothesishis true)p (
h|d ) is the posterior probability (probability of hypothesishbeing
true given the observed datad )A weight is calculated for each
feature using a Laplacian-adjusted probability estimate to account
for the different sampling frequencies of different features.The
weights are summed to provide a probability estimate 23. Bayesian
Classification TB Models Leave out 50% x 100 Ekins et al., Mol
BioSyst, 6: 840-851, 201065.477.96 67.217.05 66.854.06 0.750.01
0.730.01 MLSMRdose response set (N = 2273)77.132.26 78.591.94
78.561.86 0.860 0.860 MLSMRAll single point screen(N =
220463)Sensitivity Specificity Concordance Internal ROC Score
External ROC Score Dateset(number of molecules) 24. 100K
libraryNovartis Data FDA drugsAdditional test sets Suggests models
can predict data from the same and independent labs Initial
enrichment enables screening few compounds to find actives 21 hits
in 2108 cpds 34 hits in 248 cpds 1702 hits in >100K cpds Ekins
and Freundlich,Pharm Res, 28, 1859-1869, 2011. Ekins et al., Mol
BioSyst, 6: 840-851, 2010 25.
- Generated with kinase data [1] - - (blind testing of previous
models showed 3-4 fold
- Models were built as described previously [2]
- Data for single point screening (cut off for activity %
inhibition at 10uM >or equal to
- 2.IC 50data Cut off for active = or equal to 5uM
- 3.IC 90data Cut off for active = or equal to 10uM andvero cell
selectivity index greater or
- [1] Reynolds RC, et al. Tuberculosis (Edinburgh, Scotland) 2011
In Press.
- [2] Ekins S, et al.,Mol BioSystems 2010;6:840-51.
Models with SRI kinase library data 26. Models with SRI kinase
library data; refining data with cytotoxicity Model 1 ROC XV AUC(N
23797)= 0.89 Model 2 (N 1248) = 0.72 Model 3(N 1248)= 0.77 Leave
out 50% x 100 Adding cytotoxicity data improves models
Dateset(number of molecules) External ROC Score Internal ROC Score
Concordance Specificity Sensitivity Model 1 (N = 23797)0.870 0.880
76.772.14 76.492.41 81.72.96 Model 2 (N = 1248)0.650.01 0.700.01
61.581.56 61.858.45 61.308.24 Model 3 (N=1248) 0.740.02 0.750.02
68.676.88 69.289.84 64.8412.11 27. Original TB Models : refining
data with cytotoxicity Ekins et al., Mol BioSyst, 6: 840-851,
2010Single ptROC XV AUC= 0.88 Dose resp = 0.78 Dose resp + cyto=
0.86 Leave out 50% x 100 Dateset(number of molecules) External ROC
Score Internal ROC Score Concordance Specificity Sensitivity
MLSMRAll single point screen(N = 220463)0.860 0.860 78.561.86
78.591.94 77.132.26 MLSMRdose response set (N = 2273)0.730.01
0.750.01 66.854.06 67.217.05 65.477.96 NEW Dose resp and
cytotoxicity(N = 2273) 0.820.02 0.840.02 82.614.68 83.915.48
65.997.47 28.
- Combining cheminformatics methods and pathway analysis
- Identified essential TB targets that had not been
exploited
- Used resources available to both to identify targets and
molecules that mimic substrates
- Computationally searched >80,000 molecules - tested 23
compoundsin vitro (3 picked as inactives),lead to 2 proposed as
mimics of D-fructose 1,6 bisphosphate, (MIC of 20 and 40
ug/ml)
- POC took < 6mths - - Submitted phase II STTR, Submitted
manuscript
- Still need to test vs target- verify it hits suggested
target
Ekins et al, Trends in Microbiology Feb 2011 Phase I STTR-NIAID
funded collaboration with Stanford Research International 29.
http://www.slideshare.net/ekinssean Ekins S and Williams AJ,
MedChemComm,1: 325-330, 2010. Analysis of malaria and TB data 30.
TB Compound libraries and filter failures Filtering using SMARTs
filters to remove thiol reactives, false positives etcat University
of New Mexico
(http://pasilla.health.unm.edu/tomcat/biocomp/smartsfilter) Ekins
et al., Mol Biosyst, 6: 2316-2324, 2010 31. Antimalarial Compound
libraries and filter failures Ekins and Williams Drug Disc Today
15; 812-815, 2010% Failure 32. Correlation between the number of
SMARTS filter failures and the number of Lipinski violations for
different types of rules sets with FDA drug set from CDD (N = 2804)
Suggests # of Lipinski violations may also be an indicator of
undesirable chemical features that result in reactivityFilter
Correlations with Rule of 5 Ekins and Freundlich,Pharm Res, 28,
1859-1869, 2011. 33. Summary Computational models based on Whole
cell TB data could improve efficiency of screening Collaborations
get us to interesting compounds quickly Availability of datasets
enable analysis that could suggest simple rules A high proportion
of compounds fail the Abbott filters for reactivity when compared
to drugs and antimalarialsUnderstanding the chemical properties and
characteristics of compounds=better compounds for lead
optimization. 34. Could all pharmas share their data as models with
each other? Increasing Data & Model Access Ekins and Williams,
Lab On A Chip, 10: 13-22, 2010. 35. Bridging the Gap
- Challenge..There is limited access to ADME/Tox data and models
needed for R&D
- How could a company share data but keep the structures
proprietary?
- Sharing models means both parties use costly software
- What about open source tools?
- Pfizr had never considered this - So we proposed a study and
Rishi Gupta generated models
36.
- What can be developed with very large training and test
sets?
- HLM training 50,000 testing 25,000 molecules
- training 194,000 and testing 39,000
- MDCK training 25,000 testing 25,000
- MDR training 25,000 testing 18,400
- Open molecular descriptors / models vs commercial
descriptors
Gupta RR, et al., Drug Metab Dispos, 38: 2083-2090, 2010Open
source tools for modeling 37. Massive Human liver microsomal
stability model PCA of training (red) and test (blue) compounds
Overlap in Chemistry space Gupta RR, et al., Drug Metab Dispos, 38:
2083-2090, 2010
- # Descriptors: 818 Descriptors
- # Training Set compounds:193,930
- Cross Validation Results:38,786compounds
- Blind Data Set (2310 compounds):
- Time (sec/compound): 0.303
- # Descriptors: 578 Descriptors
- # Training Set compounds:193,650
- Cross Validation Results:38,730compounds
- Blind Data Set (2310 compounds):
- Time (sec/compound): 0.252
HLM Model with MOE2D and SMARTS Keys HLM Model with CDK and
SMARTS Keys: 38. RRCK Permeability and MDR Open descriptors results
almost identical to commercial descriptors Across many datasets and
quantitative and qualitative data Smaller solubility datasets give
similar results Provides confidence that open models could be
viable MDCK training 25,000 testing 25,000 MDR training 25,000
testing 18,400 Gupta RR, et al., Drug Metab Dispos, 38: 2083-2090,
2010Kappa = 0.50 Sensitivity = 0.62 Specificity = 0.94 PPV = 0.68
Kappa = 0.53 Sensitivity = 0.64 Specificity = 0.94 PPV = 0.72
(Baseline) Kappa = 0.47 Sensitivity = 0.59 Specificity = 0.93 PPV =
0.67 C5.0 RRCK Permeability Kappa = 0.65 Sensitivity = 0.86
Specificity = 0.78 PPV = 0.84 CDK and SMARTS Keys Kappa = 0.67
Sensitivity = 0.86 Specificity = 0.80 PPV = 0.85 (Baseline) MOE2D
and SMARTS Keys Kappa = 0.62 Sensitivity = 0.85 Specificity = 0.77
PPV = 0.83 CDK descriptors C5.0 MDR 39. Merck KGaACombining models
may give greater coverage of ADME/ Tox chemistry space and improve
predictions? Model coverageof chemistry space Lundbeck Pfizer Merck
GSK Novartis Lilly BMS Allergan Bayer AZ Roche BI Merk KGaA 40.
Next steps
- ADME/Tox Data crosses diseases
- Potential to share models selectively with collaborators e.g.
academics, neglected disease researchers
- We used the proof of concept to submit an SBIR Biocomputation
across distributed private datasets to enhance drug discovery
- Develop prototype for sharing models securely- collaborate to
show how combining data for TB etc could improve models
- Phase II- develop a commercial product that leverages CDD
41. Bunin & Ekins DDT 16: 643-645, 2011A complex ecosystem
of collaborations: A new business model Inside Company
Collaborators Inside Academia Collaborators Molecules, Models, Data
Molecules, Models, Data Inside Foundation Collaborators Molecules,
Models, Data Inside Government Collaborators Molecules, Models,
Data IP IP IP IP Shared IP Collaborative platform/s 42. Finding
Promiscuous Old Drugs for New Uses
- Research published in the last six years - 34 studies -
Screened libraries of FDA approved drugs against various whole cell
or target assays.
- 1 or more compounds with a suggested new bioactivity
- 13 drugs were active against more than one additional disease
in vitro
43. Finding Promiscuous Old Drugs for New Uses
- 109 molecules were identified by screening in vitro
- Statistically more hydrophobic (log P) and higher MWT than
orphan-designated products with at least one marketing approval for
a common disease indication or one marketing approval for a rare
disease from the FDAs rare disease research database.
- Created structure searchable databases in CDD
44. 2D Similarity search with hit from screeningExport database
and use for 3D searching with a pharmacophore or other model
Suggest approveddrugs for testing -may also indicate other uses if
it is present in more than one databaseSuggestin silicohits forin
vitroscreening Key databases of structures and bioactivity data FDA
drugs database Repurpose FDA drugs in silico Ekins S, Williams AJ,
Krasowski MD and Freundlich JS, Drug Disc Today,16: 298-310, 2011
45. Crowdsourcing Project Off the Shelf R&D All pharmas have
assets on shelf that reached clinic Off the Shelf R&DGet the
crowd to help in repurposing / repositioning these assets How can
software help? - Create communities to test - Provide informatics
tools that are accessible to the crowd- enlarge user base - Data
storage on cloud integration with public data - Crowd becomes
virtual pharma-CROs and the customer for enabling services 46.
Tools for Open Science
- What about Twitter, Facebook, could these be used for social
collaboration, science?
47. 2020: A Drug Discovery Odyssey Could our Pharma R&D look
like this Massive collaboration networks software enabled. We are
in Generation App. Crowdsourcing will have a role in R&D. Drug
discovery possible by anyone with app access Ekins & Williams,
Pharm Res, 27: 393-395, 2010. 48.
- Make science more accessible = >communication
- Mobile take a phone into field /lab and do science more readily
than on a laptop
- GREEN energy efficient computing
- MolSync + DropBox + MMDS = Share molecules as SDF files on the
cloud = collaborate
Mobile Apps for Drug Discovery Williams et al DDT16:928-939,
2011 49. www.scimobileapps.com How do you find scientific mobile
Apps ? Development of Wikis to track developments in tools.. 50.
Acknowledgments
- Rishi Gupta , Eric Gifford, Ted Liston, Chris Waller
(Pfizer)
- Joel Freundlich (Texas A&M), Gyanu Lamichhane (Johns
Hopkins)
- Carolyn Talcott,Malabika Sarker , Peter Madrid, Sidharth Chopra
(SRI International)
- Takushi Kaneko (TB Alliance)
- Nicko Goncharoff (SureChem)
- Matthew D. Krasowski (University of Iowa)
- Alex Clark (Molecular Materials Informatics, Inc)
- Slideshare: http://www.slideshare.net/ekinssean
- Blog: http://www.collabchem.com/
- Website: http://www.collaborations.com/CHEMISTRY.HTM
51. Novartis aerobic and anaerobic TB hits Anaerobic compounds
showed statistically different and higher mean descriptor property
values compared with the aerobic hits(e.g. molecular weight, logP,
hydrogen bond donor, hydrogen bond acceptor, polar surface area and
rotatable bond number) The mean molecular properties for the
Novartis compounds are in a similar range to the MLSMR and
TAACF-NIAID CB2 hits Ekins and Freundlich,Pharm Res, 28, 1859-1869,
2011.
