Transcription
Integratinggg CambridgeSoftgChemOffice Enterprise andTIBCO SpotfireTo make a best-in-breed Life Science datavisualization and analysis platformconfidential
Overview Aqquick review of the scientific data visualization andanalysis problem. CambridgeSoft informatics infrastructure as the dataaccess component. Spotfire as the data visualization and analysis component. Integrating to yield a best-in-class solution. Democonfidential
Problem Present drug discovery data to the scientists such that theycan easily develop and compare hypotheses.– Lots of data from multiple assays.– The key hypotheses change during the lifespan of a project. View the problem through 2 lenses at Array:– Drug discovery and development– Translational Medicineconfidential
The structure of scientific data Data visualization and analysisyis not a new pproblem and isnot unique to life sciences. BUT, there are some aspects of scientific data that render itmore challenging than other fields.– Diversity of data types and end points.– Diversity of units.– Highly multivariate space. Conceptually, the data space is a large, hierarchicallyorganized sparse matrixorganized,matrix.confidential
Data shape There are 2 traditional “shapes”pto data:– Tall and 3AKT5etc.– Short and WideCompoundMEKBRAFAKTAR12320105confidential
Shape of drug discovery data is hierarchicalCompoundCompound average(e.g. Avg. IC50)BatchBatch average (e.g.Average IC50)(sample)confidentialAssay Run (e.g.IC50)
Or more accuratelyaccurately CompoundBatch(sample)confidential
Shape of translational medicine data – 2 DemogTreatment“Omics”InventoryMed HXconfidential
The ideal solution The ideal solution– Keeps track of the Compounds of interest or Subjects ofinterest.– Allows the user to transition between levels of the datahierarchy easily and elegantly.– Integrates form, grid (spreadsheet), and visualrepresentations of the data.– Respects and employs the hierarchical nature of the datadomain.confidential
Why is data visualization important? Napoleon'spmarch on Moscow 1812-1813 in a 1/15/1812 Troop /181302/17/1813 53203473923202017203Position120 12' 15",120 30' 15",121 02' 14",121 23' 41",37 23' 43"37 44' 13"38 45' 20"38 57' 21"121 23' 41", 38 57' 21"121 02'02 1414", 38 45'45 2020"120 30' 15", 37 23' 43"120 12' 15", 37 23' 43"confidentialDirection RetreatingRetreatingRetreating0-1515-10-18
As a visualizationvisualization confidential
So visual scanning important because of:So, Densityy of data. Humans are (usually) visual creatures.– Specifically, humans are good at spatial visual scanning vs.temporal visual scanning.– Thus, put the data side-by-side. Read Tufte’s books– The Visual Display of Quantitative Information– Envisioning Information– Visual Explanations: Images and Quantities, Evidence andNarrativeconfidential
Overview Aqquick review of the scientific data visualization andanalysis problem. CambridgeSoft informatics infrastructure as the dataaccess component. Spotfire as the data visualization and analysis component. Integrating to yield a best-in-class solution. Democonfidential
CambridgeSoftgInfrastructure for DruggDiscovery dataADMETManual FeedBioAssayDesktop AppOracle DBAssaySubmissionWeb AppADMETAutomated FeedServer AppData MiningO l DBOracleRegistrationBiology Data MartPhysicalPropertiesOracle DBOracle DBChemDrawFor ExcelBioSARDesktop AppWeb AppServer AppChemBioVIZ.NETDesktop AppconfidentialSpotfireDesktop and Web App
What we have today: All Efficacy,y, Bioavailability,y, and Toxicityy data is fielded to acentralized Oracle data mart. A meta-data database (BioSAR) and a variety of reportingtools sitting on this data mart and is used for data extraction– Research Assay History– ChemBioViz for Excel– BioSARconfidential
Developing Translational Medicine infrastructureMedidataRAVEValidated eCRFSASfilfilesNightly outputWinNonLinSASPK data processingCSVfilesTranslational Med.D t MartDataM tClinical Data MartWe’re not here yet, but mostof the pieces are in place – wehhavetto stitchtit h ththem ttogether.thSpotfireChemBioVIZ.NETDesktop and Web AppDesktop AppconfidentialBioAssayPD dataSampleinventoryinfoChemDrawFor ExcelDesktop App
Spotfire Well-established best-in-breed ggeneral data visualizationand analysis tool. Widely used in the pharmaceutical industry. Includes very robust data modeling features and a fantasticAPI.confidential
TIBCO Spotfire Enterprise Analyticsy–Platform OverviewManagers, Consumers,ExecutivesCLIEENTSSpotfireWeb PlayerAnalystsIndependentsConfiguratorsManagers, Consumers,Executives(*) SpotfireEnterprise PlayerZero install web rofessionalSpotfirepMinerVisual, Analytic & Dynamic In-Memory EnginesInformaticiansStatisticiansSpotfirepS (*) Advanced Computational EnginesSpotfireDeveloperDlSpotfire ServerSERVERRSSpotfire Web Player Server(*) SpotfireStatisticsServicesAdministration & Integration((*)) Spotfire Automation Services(*) EventProcessingServices - OA(*) SpotfireApplication DataServicesReal-Time ConnectivityApp Data ConnectivityComputation EngineIn-Memory EnginesSDKsIT / BMSSpreadsheetsFlatFilesCustomEvent DataStreamsSAP R/3SAP BW(*) Optional essWebServices
Overview Aqquick review of the scientific data visualization andanalysis problem. CambridgeSoft informatics infrastructure as the dataaccess component. Spotfire as the data visualization and analysis component. Integrating to yield a best-in-class solution. Democonfidential
Timeline and approach In the springp g and summer of 2010,, we reviewed the state ofthe art in life science data visualization and analysis tools. Nothing was a great fit for our needs and budget. Array approached CambridgeSoft and Spotfire andproposed a new integrated solution .– Both the new ChemOffice Enterprise and the new SpotfireDecisionSite are .NET applications.– TheyTh eachh bringb i strongtexpertiseti tto ththe ttable.bl– Array has a long history of working with best-of-breed solutionproviders to create novel integrated solutionssolutions.confidential
Process First pproposalpmade in August/Sept.gp of 2010. First proof-of-concept completed at the end of October. The last 5 months have focused on convertingg the pproofof-concept into productized code. The full system is installed and operational on adevelopment infrastructure at Array We plan to go to production at the end of Q2.confidential
Conceptual architectureconfidential
Demo – example workflow Focus on Drugg Discoveryy example.p User:1.2.3.4.5.6.7.Builds a form in ChemBioVIZ.Net.Queries for Batches of interest.pPulls the data into Spotfire.Identifies a key comparison of interest.gg gthe keyy assayy data upp to the Batches level.AggregatesBuilds the key plot.Identifies the lead compounds to advance.confidential
ChemBioVIZ Net - Form viewChemBioVIZ.NetAny number of Forms, Tables,and query interfaces.Queries permitspfor tracking listsof compoundsof interest andlist logic.gSend to Spotfire.SpotfireconfidentialAssemble datafrom assays andaggregate to anylevel of the datahierarchy
ChemBioVIZ Net – Dataview treeChemBioVIZ.Net Allows for administrative control of how the users accessdata. Organized by project, therapeutic area, etc. as needed.confidential
Clicking “SendSend to SpotfireSpotfire” for its robust capabilities Example, enzymatic assay vs. cell assay, color by Rule of 5 violations.Mouse-over to getdetails.Select to populatedrill-down chart.Details-ondemand showingstructuret tconfidential
Spotfire – SAR table With rich qualitative and quantitative coloring (structures hidden in this examle).confidential
From within the Spotfire workflow – modifyythe data in the analysis Results criteria editor permits application-independent authoring of thedata to view.confidential
Results Criteria Editor features Fast access to all tablesin the dataview. Fast form building. AggregateAt betweenb thierarchy levels. Drag-and-drop columnorganization. Quick filtering of availableco u scolumns. Column renaming.confidential
Features of the integrated solution.solution ChemBioVIZ.Net and the Spotfirepview are in sync.ySelecting a point in Spotfire places that Compound in viewin the Form viewer. The Results Criteria will allow for a user to transition fromChemBioVIZ.Net to CBV for Excel to Spotfire easily. The Spotfire analysis file “remembers” it’s Results Criteriaand thus can be launched independently. Loosely coupled,coupled but tightly integrated solution.solutionconfidential
CambridgeSoft and Spotfire – current status The pproof-of-conceptp was veryy successful – qquickimplementation and the integration works well. Work is ongoing to productize the solution - Array plans tohave a first implementation in production at the end of Q2. Spotfire deployed at Array.– Training ongoing– Value being generated even with flat-file and SD filei tintegrations.ti Combined solution promises to proved Drug Discovery andTranslational Medicine solutions to Array.confidential
Questions? Thank you!yconfidential
Spotfire confidential Desktop App Web App Desktop App Desktop and Web App. What we have today:What we have today: All Efficacy,y, y, y Bioavailability, and Toxicity data is fielded to a centralized Oracle data mart.