Big Data in Pharma - Overview and Use Cases
9 likes4,133 views
The document provides an overview of big data analyses in the pharmaceutical industry, focusing on its importance in drug discovery and development processes. It discusses various challenges, methodologies, and applications of data integration and analysis in understanding biochemical interactions and improving treatment outcomes. Key examples include the exploration of kinase inhibitors, genetic profiling, and the integration of social media data for pharmacovigilance.
![Example: Donepezil /
Acetylcholinesterase
• PDB 4EY7
Image extracted from Cheung et al.,
2012 [2]](https://image.slidesharecdn.com/biovariancebigdatainpharmajul2015-150803095711-lva1-app6891/85/Big-Data-in-Pharma-Overview-and-Use-Cases-46-320.jpg)
![Many birds tweet lots of noise …
BUT …
• [1] "Lipitor headache 0"
[1] "Lipitor rash 1"
[1] "Lipitor pain 27"
[1] "Lipitor bleeding 0"
[1] "Lipitor cough 0"
[1] "Lisinopril headache 0"
[1] "Lisinopril rash 0"
[1] "Lisinopril pain 8"
[1] "Lisinopril bleeding 0"
[1] "Lisinopril cough 7"
[1] "Simvastatin headache 0"
[1] "Simvastatin rash 0"
[1] "Simvastatin pain 0"
[1] "Simvastatin bleeding 0"
[1] "Simvastatin cough 0"
[1] "Plavix headache 0"
[1] "Plavix rash 0"
[1] "Plavix pain 0"
[1] "Plavix bleeding 1"
[1] "Plavix cough 0"
[1] "Crestor headache 0"
[1] "Crestor rash 0"
[1] "Crestor pain 0"
[1] "Crestor bleeding 0"
[1] "Crestor cough 0"](https://image.slidesharecdn.com/biovariancebigdatainpharmajul2015-150803095711-lva1-app6891/85/Big-Data-in-Pharma-Overview-and-Use-Cases-56-320.jpg)
Big Data in Pharma - Overview and Use Cases
- 1. Big Data Analyses in Pharma An Overview Josef Scheiber, PhD Managing Director July 2015
- 2. Geographie Startup Center in Waldsassen Main site Data Analyses and Software Development Westpark Center Garmischer Str. in Munich Scientific ActivitiesSince Jan 1, 2015 Basel/Switzerland Data Curation and customer- related activities Prag 150 km München 200 km Berlin 300 km Frankfurt 250 km
- 3. BioVariance at a Glance – Get most out of your complex data Curate.Integrate Analyze.Model Visualize.Explore DECIDE
- 4. Overview • Background • Strategy • Examples
- 5. Background
- 6. Courtesy: M. Zeinab, slideshare
- 7. What do we need out of Big Data? 1. What are the inhibitors of kinase X and the five most similar kinases with IC50 < 1 μM and with MW < 500 from all internal and external data sources? 2. What assay technologies have been used against my kinase? Which cell lines? 3. What other proteins are in the same kinase branch as target X, where there were validated chemical hits from external or internal sources? 4. If I hit a particular kinase, what would the potential side-effect profile look like? Which known inhibitor of this kinase has the best safety profile and the fewest known IC50s? 5. Have I identified other compounds with a bioactivity profile similar to compound X and with the same core substructure? 6. Can we create a phylochemical tree of kinases and for a new kinase target place it into the tree on the basis of activity against a reference panel of compounds? 7. Have I identified all kinases with an x-ray structure (in-house or external) that are in pathway X? Bridging Chemical and Biological Data: Implications for Pharmaceutical Drug Discovery JL Jenkins, J Scheiber, D Mikhailov, A Bender, A Schuffenhauer, B Cornett, V Chan, J Kondracki, B Rohde, JW Davies (2012) In: Computational Approaches in Cheminformatics and Bioinformatics Edited by:A Bender, R Guha. 25-56 John Wiley & Sons, Inc. ANSWERS
- 8. Context matters! metabolites drugs targets pathways diseases (phenotypes)
- 9. Context matters RNADNA It´s not that simple …
- 10. Descriptive: What happened? Diagnostic: Why did it happen? Predictive: What will happen? Prescriptive: How can we make it happen? Better data for better analytics Hindsight Insight Foresight
- 11. Need for interpretation 33,3 10 20 30 70 33,3 80 70 60 10 33,3 10 10 10 20 0% 10% 20% 30% 40% 50% 60% 70% 80% 90% 100% Before molecular biology Molecular biology golden age Genomics age Deep sequencing age Very soon Data Analysis Experiment Experimental Design
- 12. Big Data?
- 13. Volume
- 14. Genome Sequencing Slide adapted from George Church
- 15. Genome Sequencing Slide adapted from George Church
- 16. Cost Reduction - Example 458 Ferrari Spider - $398,000 in 2006 – 40 cents now!
- 17. Much more data for way less money
- 18. Challenges for Informatics? – 1 genome is roughly 500 GB/data 2011 – several 100 exomes
- 19. Drug Discovery Pipeline Target finding Lead Finding Lead Optimization … Phase 1 … Market Drug candidates Patients
- 20. Velocity
- 21. Velocity • Mutations in tumor • Resistance mechanisms in patients • long term/short term AE • compliance • Nutrition and microbiome • Data from wearables relevant for drugs
- 22. For each patient
- 23. Variety
- 24. Variety
- 25. Variety • Bioinformatics • Clinical • Social network • E-health • Also text/patents
- 26. A simplified overview – Molecules in Man Adapted from Gohlke JM, Portier CJ. Environ. Health Perspect. 115:1261-1263 (2007)
- 27. A question of complexity –They all interact … Biology Chemistry Physics
- 28. Dealing with a very complex environment – i.e. many opportunities DNA RNA Protein Interactions Clinical parameters Treatment History Tissue anatomy Surgical History Epigenetic Profiles from many patients at different timeponits Target Off-targets Metabolites Additional indications Unspecific effects Similar drugs Adapted from: J. Scheiber; How can we enable drug discovery informatics for personalized healthcare? Expert Opinion on Drug Discovery, 1-6; 2/2011
- 30. Sequences Expression Proteomics Biological networks (but also: Cells, Tissues, Organs) POPULATION
- 31. Veracity
- 32. Veracity • Chemogenomics data • Gene expression data Imputation?
- 33. Veracity - Chemogenomics Adapted from Tanrikulu et al. Missing Value Estimation for Compound- Target Activity Data, J. Mol. Inf
- 34. Veracity - Interactomics A Proteome-Scale Map of the Human Interactome Network Rolland, Thomas et al. Cell , Volume 159 , Issue 5 , 1212 - 1226
- 35. Veracity – Social Media
- 37. Strategy
- 39. Data integration strategy a) A central vocabulary/pointer server (information stored are preferred names and synonyms plus pointers to data servers, where to find what) b) semantic integration layer with domain-specific terminology and referential data c) A database for each datatype collected, storing only preferred names along with raw measurements d) Clearly defined APIs for further integration with public data sources and to enable large-scale analyses
- 40. Vocabularies needed • Genes, Drugs, Proteins • Diseases • Organisms • Microbiome species & genes • Localization & source • Phenotype • Metabolite common names
- 41. Answering workflow Vocabulary Vocabulary server acts as translator, aggregator and locator, i.e. knows where the respective facts can be found Firmicutes produce alpha-Linolein and thereby cause gut irritation species metabolite Further Data of each type is stored in a specific database to enhance performance of large-scale analyses Expert tools talk to data directly or via webservices API API API API Enduserinterfaceand visualization
- 42. Examples
- 43. Genome data at scale
- 44. Workflow Identify drug targets (primary and off-targets, from DrugBank) Call variations on a per- individuum basis
- 45. Workflow Analyse mutation rates in the targets and in particular drug binding pockets
- 46. Example: Donepezil / Acetylcholinesterase • PDB 4EY7 Image extracted from Cheung et al., 2012 [2]
- 49. Not very successful Alignment of the 3D structures of mutant number 52 (yellow) and PDB 4EY7 AChE protein (green). The only changed residue is the Y150 (magenta) to H150 (red). The white surface represents the molecular surface of donepezil.
- 50. Why is this a bad example? AChE a key enzyme in human biology these are the most highly conserved, even interspecies Learning: Look at that stuff before investing time
- 52. Vocabulary generation Extensive mapping of terms from various sources
- 53. Vocabulary generation 397211 preferred names 598532 synonyms 102086 identifiers The chevron diagram shows the number of samples annotated with names. Already by looking at the numbers you can see tha mapping everything is non-trivial. A Big Data exercise in itself …
- 54. Tweet mining
- 55. Mining Twitter for side effects Needed Drug Name and synonyms: Adalimumab Humira Exemptia 331731-18-1 L04AB04 MedDRA vocabulary
- 56. Many birds tweet lots of noise … BUT … • [1] "Lipitor headache 0" [1] "Lipitor rash 1" [1] "Lipitor pain 27" [1] "Lipitor bleeding 0" [1] "Lipitor cough 0" [1] "Lisinopril headache 0" [1] "Lisinopril rash 0" [1] "Lisinopril pain 8" [1] "Lisinopril bleeding 0" [1] "Lisinopril cough 7" [1] "Simvastatin headache 0" [1] "Simvastatin rash 0" [1] "Simvastatin pain 0" [1] "Simvastatin bleeding 0" [1] "Simvastatin cough 0" [1] "Plavix headache 0" [1] "Plavix rash 0" [1] "Plavix pain 0" [1] "Plavix bleeding 1" [1] "Plavix cough 0" [1] "Crestor headache 0" [1] "Crestor rash 0" [1] "Crestor pain 0" [1] "Crestor bleeding 0" [1] "Crestor cough 0"
- 57. Top 200 drugs - Cutoff is at 1500 tweets that a few drugs easily surpass (although it's mostly only pharmacies advertizing) - Others are not mentioned once (probably a synonym issue as I restricted to English as language). - - top drugs are tweeted more often, but e.g. Tarceva (in 2006) at the very bottom also reaches the top number of tweets (109 on list).
- 58. 089 – 189 6582 – 80 Garmischer Str. 4/V 80339 München josef.scheiber@biovariance.com: 09632 – 9248 325 Konnersreuther Str. 6g 95652 Waldsassen Questions?