Mostlaboratoriesstudyingbiologicalprocessesandhumandiseaseusemicroscopestoimagesamples. Whetherinsmallorlargescalemicroscopyexperiments,biologistsincreasinglyneedsoftwaretoidentifyand measurecellsandotherbiologicalentitiesinimages,toimprovespeed,objectivity,and/orstatisticalpower. Theprincipalinvestigatorenvisionsbringingtransformativeimageanalysisandmachinelearningalgorithms andsoftwaretoawideswathofbiomedicalresearchers.Inadecade,researcherswilltacklefundamentally newproblemswithquantitativeimageanalysis,usingseamlessimagingworkflowsthathavedramaticnew capabilitiesgoingbeyondtheconstraintsofhumanvision. Tothisend,thePIwillcollaboratewithbiologistsonimportantquantitativeimagingprojectsthatalsoyield majoradvancementstotheiropensourceimageanalysissoftware,CellProfiler.Thisversatile,userfriendly softwareisindispensableforbiomedicalresearch.Launched125,000+times/yearworldwide,itiscitedin 3,400+papersfrom1,000+laboratories,impactingahugevarietyofbiomedicalfieldsviaassaysfromcounting cellstoscoringcomplexphenotypesbymachinelearning.CellProfilerevolvesinanintenselycollaborativeand interdisciplinaryresearchenvironmentthathasyieldeddozensofdiscoveriesandseveralpotentialdrugs. Still,manybiologistsaremissingoutonthequantitativebioimagingrevolutionduetolackofeffective algorithmsandusablesoftwarefortheirneeds.InadditiontomaintainingandsupportingCellProfiler,theteam willimplementbiologistrequestedfeatures,algorithms,andinteroperabilitytocopewiththechangingland scapeofmicroscopyexperiments.Challengesincludeincreasesinscale(sometimesmillionsofimages),size (20+GBimages),anddimensionality(timelapse,threedimensional,multispectral).Researchersalsoneedto accommodateavarietyofmodalities(superresolution,singlemolecule,andothers)andintegrateimage analysisintocomplexworkflowswithothersoftwareformicroscopecontrol,cloudcomputing,anddatamining. ThePIwillalsopioneernovelalgorithmsandapproacheschangingthewayimagesareusedinbiology, including:(1)afundamentalredesignoftheimageprocessingworkflowforbiologists,leveragingrevolutionary advancementsindeeplearning,(2)imageanalysisformorephysiologicallyrelevantsystems,suchasmodel organisms,humantissuesamples,andpatientderivedcultures,and(3)datavisualizationandinterpretation softwareforhighdimensionalsinglecellmorphologicalprofiling.Inprofiling,subtlepatternsofmorphological changesincellsaredetectedtoidentifycausesandtreatmentsforvariousdiseases.Wewillalso(4)integrate multipleprofilingdatatypes:morphologywithgeneexpression,epigenetics,andproteomics.Ultimately,we aimtomakeperturbationsincellmorphologyascomputableasotherlargescalefunctionalgenomicsdata. Overall,thelaboratory?sresearchwillyieldhighimpactdiscoveriesfrommicroscopyimages,andits softwarewillenablehundredsofotherNIHfundedlaboratoriestodothesame,acrossallbiologicaldisciplines.

Public Health Relevance

PublicHealthRelevance/Narrative Modernmicroscopyexperimentsareincreasinginscaleandscope?theresearchwillresultinpioneering computationaltechniquesandsoftwarethatwillchangethewaymicroscopyimagesareusedinbiology. Biologistswillusetheresultingsoftwaretotacklefundamentallynewproblemsusingquantitativeimage analysis,includingdetectingchangesintheappearanceofcellsthatareoverlookedbyhumanvisionand studyingintactorganismsandhumantissueratherthanisolatedcells.Themethodswillbedevelopedinthe contextofdozensofprojectsaddressingimportantfundamentalbiologicalquestionsandworldhealth problems,andtheresultingnewfunctionalitywillbeaddedtotheteam?spopular,userfriendly,opensource imageanalysissoftware,CellProfiler.

Agency
National Institute of Health (NIH)
Institute
National Institute of General Medical Sciences (NIGMS)
Type
Unknown (R35)
Project #
1R35GM122547-01
Application #
9276910
Study Section
Special Emphasis Panel (ZGM1)
Program Officer
Deatherage, James F
Project Start
2017-05-01
Project End
2022-04-30
Budget Start
2017-05-01
Budget End
2018-04-30
Support Year
1
Fiscal Year
2017
Total Cost
Indirect Cost
Name
Broad Institute, Inc.
Department
Type
DUNS #
623544785
City
Cambridge
State
MA
Country
United States
Zip Code
02142
Simm, Jaak; Klambauer, Günter; Arany, Adam et al. (2018) Repurposing High-Throughput Image Assays Enables Biological Activity Prediction for Drug Discovery. Cell Chem Biol 25:611-618.e3
Vasilevich, Aliaksei S; Mourcin, Frédéric; Mentink, Anouk et al. (2018) Designed Surface Topographies Control ICAM-1 Expression in Tonsil-Derived Human Stromal Cells. Front Bioeng Biotechnol 6:87
Bray, Mark-Anthony; Gustafsdottir, Sigrun M; Rohban, Mohammad H et al. (2017) A dataset of images and morphological profiles of 30 000 small-molecule treatments using the Cell Painting assay. Gigascience 6:1-5