Presentation is loading. Please wait.

Presentation is loading. Please wait.

ProSanos Corporation Confidential and Proprietary Modeling and clustering disease progression for correlation with genetic and demographic factors Robert.

Similar presentations


Presentation on theme: "ProSanos Corporation Confidential and Proprietary Modeling and clustering disease progression for correlation with genetic and demographic factors Robert."— Presentation transcript:

1 ProSanos Corporation Confidential and Proprietary Modeling and clustering disease progression for correlation with genetic and demographic factors Robert Kingan

2 ProSanos Corporation Confidential and Proprietary What is SSIFT?  “To address […] common diseases, which include schizophrenia, depression, and breast cancer, it is essential to incorporate observations of the clinical progression of the disease to refine the definition of phenotype.” – Michael N. Liebman, U. Penn.  Yes, but what is SSIFT? –SSIFT = Stratification and Synchronization Inference Technology

3 ProSanos Corporation Confidential and Proprietary What is SSIFT?  Stratification: Dividing a patient population into groups which are meaningful for diagnosis, prognosis, treatment selection, or genotype- phenotype correlation.  Synchronization: Recognizing a pattern of disease progression, regardless of disease stage for a particular patient.

4 ProSanos Corporation Confidential and Proprietary SSIFT overview  Assumptions—what is SSIFT-able  Other constraints on data selection  Outline of technique –Identifying variables –Modeling disease progression –Parameterizing different models –Clustering patients by progression patterns –Interpreting the results

5 ProSanos Corporation Confidential and Proprietary Pattern of disease progression Time Disease marker initial value final value period of change

6 ProSanos Corporation Confidential and Proprietary SSIFT workflow Survey the data Select useful variables Fit disease progression models Construct feature vectors Assign feature weights Cluster weighted feature vectors Evaluate the clustering results Complete? No Yes

7 ProSanos Corporation Confidential and Proprietary SSIFT workflow SSIFT

8 ProSanos Corporation Confidential and Proprietary SSIFT curve types

9 ProSanos Corporation Confidential and Proprietary Converting parameters Logistic Constant Linear Early stable Late stable y* = population mean, t 1 =first time point, t n =last time point

10 ProSanos Corporation Confidential and Proprietary Modified Mahalanobis distance

11 ProSanos Corporation Confidential and Proprietary SSIFT workflow Survey the data Select useful variables Fit disease progression models Construct feature vectors Assign feature weights Cluster weighted feature vectors Evaluate the clustering results Complete? No Yes

12 ProSanos Corporation Confidential and Proprietary SSIFT workflow Survey the data Select useful variables Fit disease progression models Construct feature vectors Assign feature weights Cluster weighted feature vectors Evaluate the clustering results Complete? No Yes Correlate results with: demographic data genetic data

13 ProSanos Corporation Confidential and Proprietary Application of SSIFT to NIDDK  About NIDDK  SSIFT and transplant data  Variable selection  Modeling  Results

14 ProSanos Corporation Confidential and Proprietary Candidate variables   -Fetoprotein  Albumin  Alkaline phosphatase (AP)  Bicarbonate  Blood urea nitrogen (BUN)  Calcium  Creatinine clearance  Cholesterol  Chlorine  Corrected PT control  Creatinine  Direct bilirubin  FK506 level  Glomerular filtration rate  Gamma GTP  Glucose  Hematocrit (HCT)  Hemoglobin  CSA HPLC level  Potassium  CSA monoclonal level  Sodium  Platelet count  Prothrombin time  Part. thromboplastin CT  Part. thromboplastin PT  CSA RIA level  SGOT (AST)  SGPT (ALT)  Total bilirubin  CSA TDX level  Total protein  White blood cells (WBC)  Weight in KG

15 ProSanos Corporation Confidential and Proprietary Selected variables VariableLog? ŜuŜu Weights ŜwŜw abm  ASTYes0.1901100.32 APYes0.1801100.28 HemoglobinNo0.1301010.24 Total bilirubinYes0.1501010.21 PotassiumNo0.201111 HematocritNo0.191111 WBCYes0.171111 BUNYes0.141111 CreatinineYes0.121111 SodiumNo0.111111

16 ProSanos Corporation Confidential and Proprietary Evaluating Kaplan-Meier curves ŜŜ

17 ProSanos Corporation Confidential and Proprietary Final selected variables  Best pair: AST + AP,  Ŝ=0.34  Best triple: AST + AP + hematocrit,  Ŝ=0.42  No set of four variables exceeded  Ŝ=0.42

18 ProSanos Corporation Confidential and Proprietary Survival by clustered SSIFT AST, AP and HCT parameters  Ŝ = 0.42

19 ProSanos Corporation Confidential and Proprietary Cluster mean curves Best cluster Worst cluster

20 ProSanos Corporation Confidential and Proprietary SSIFT in Gene Discovery: Simulation Time Markers SSIFT™ Disease Genes Disease Progression Pattern Determine Analyze Discover

21 ProSanos Corporation Confidential and Proprietary Simulated data Marker Value (relative scale) Time (years)

22 ProSanos Corporation Confidential and Proprietary Clustering Results

23 ProSanos Corporation Confidential and Proprietary Nearest-Neighbor Analysis GeneGenotype for Nearest Neighbors, based on SSIFT Pattern 123456789012345678901234567890123456789012345678901234567890123456789 C9254352131423364133346331543231331365461513311265564413451642314514456463 D7562323136554461643162336542432246213615526446315262641541251463645444165 J1789122552224555422461565335314552346323516442534343355552444332245543456 A2109451422556633426215561542335632532551544111436664632366416662551652621 J2602261323412652652223665466252216452111435542263542444161536324633341322 W4147321143532244464333634436443621115464641422635644662235654536525633252 C2353 L9800336242634156534231126616432343525335453144614443526334516552645522411 P3336134335463316364241553225312351666146252445354642364643361143152565441 R2489333645353163166613452462363523625226142335415145144513456124654144534 K805125622234521326136152541524635445125324132524235224536261424613321411 K8420121246521534522166135433555544321611651615366165466361564321116551155 D7336656426432634424564226153331645113553652653122613653166613412212454536 S4207336631132522113543146663466524336526152322153355236454211112421554435 S9560612133524211556321334441342343121422445113565223663146264256263231422 B3833111451165325313114512436245536622531545565455124463645111525655366466 B1192641336314611531121361246426232236435651132226313322353452353441515446 S939235312511132633313662343516122256413432554515433213166261326465216115 T3285441652143434363443164114445154263532135434413455513346363354553424142 555555566666666666645526566351142222222222224412114442333333333344344 C2353 is related to SSIFT pattern of disease progression (p<10 -41 ).

24 ProSanos Corporation Confidential and Proprietary SSIFT: Stratification and Synchronization Inference Technology Discussion


Download ppt "ProSanos Corporation Confidential and Proprietary Modeling and clustering disease progression for correlation with genetic and demographic factors Robert."

Similar presentations


Ads by Google