• No results found

Supercomputing. Medical big data

N/A
N/A
Protected

Academic year: 2021

Share "Supercomputing. Medical big data"

Copied!
19
0
0

Loading.... (view fulltext now)

Full text

(1)

Predictive medicine based on analysis and

simulation of time-series clinical data

Yasushi Okuno

Kyoto University, Graduate School of Medicine RIKEN Life Systems Research Center

RIKEN Advanced Institute for Computational Science Foundation for Biomedical Research and Innovation

(2)

KUHP Oncology Center

Time-series information acquisition

Time-series sample acquisition

(Blood, DNA, etc)

Collaborating

institutions Multi-omics

(Genome,Proteome)

Novel biomarkers and pharmaceutical targets Feedback to the clinical practice for

personalized medicine

Universities, Pharmas Feedback to the new targets for drug discovery

Medical simulation and optimal treatment prediction Data accumulation Patient reported outcome(PRO) Clinical information

Personalized medicine and drug discovery

from time-series accumulation of biomedical big data

Kyoto University Hospital:

Biobank & Informatics for Cancer (BIC) Project

(3)

Medical big data

More data than parseable by humans

Complex data correlations not resolvable 

by simple statistics.

Our Aim: Data-driven Predictive medicine and Personalized medicine

AI

Pattern extraction from data

Machine learning of complex patterns

Prediction of events from patterns

Supercomputing

Big

 

data

 

analysis

 

and

 

Simulation

 

for

 

medicine

Prediction of physical state, therapeutic efficiency, side effects, and outcomes.

Identification of markers for early discovery of conditions.

(4)

Criticality of medical big data

Learn from patients ⇒ Give back to patients

Clinical

 

trial

Standard

 

of

 

care

Clinical

 

practice

Target population for therapy evaluation

with restricted therapy conditions

Real

 

patients

Differences in distribution

Data‐driven EBM

More effective, safer care

Answering unmet medical needs

• Rare cases (hundreds, not thousands)

• Mainly adults; children, pregnant mothers excluded • Simultaneous drug/condition constraints reduce 

target population; potentially biased results • Long‐term treatment effect unclear

• Insufficient comparative treatment evaluation • Evaluation by specialists of a disease, objective?

Drug

 

development

Approval

Pharmacovigilence

(Post‐marketing tracking)

(5)

P atien t   number Examination date

Plots of rate of neutrophils for KUHP Oncology patient

Oncology prediction problem:

Prognosis prediction: tracking patient outcomes is critical due to possible metastasis 

and drug resistance.

Side effects prediction: monitoring patient symptom is critical because of active 

therapy with anti‐cancer drugs.

Medical big data and simulation

using real-world data from Kyoto Univ. Hospital

Data for analysisKyoto U. Hospital  chemotherapy recipients5285 patients2863 recorded deathsSurvival span after  initial exam / start of  therapy max 5930.0 days,  average 817.5 days

(6)

Time-series analysis using conventional clinical statistics

P atien t   number

Cox regression analysis

Survival following first exam (days)

Sur viv al   ra te

Computation using groups split at threshold of NLR = 4

5285 patients

2863 recorded deaths Survival span data

max 5930.0 days average 817.5

Examination date

Time‐course data of KUHP patient neutrophil‐to‐lymphocyte (NLR) ratio NLR is reported to be a predictor of  prognosis (low NLR: good outcome)

(7)

Reverse calculation: number of days prior to death P atien t   number 2863 deaths

Time-series analysis by heatmap plot

P atien t   number Examination date 5285 patients 2863 recorded deaths Survival span data

max 5930.0 days average 817.5

Selection of patients with recorded death and alignment using date of death

Time‐course data of KUHP patient neutrophil‐to‐lymphocyte (NLR) ratio NLR is reported to be a predictor of  prognosis (low NLR: good outcome)

(8)

NLR average

NLR changes dramatically rise 1 year 

prior to death

Reverse: #days prior to death

NLR likely better predictor of remaining life than prognosis

Time-series analysis by heatmap plot

Reverse: #days prior to death

P atien t   number 2863 deaths Time‐course data of KUHP patient neutrophil‐to‐lymphocyte (NLR) ratio NLR is reported to be a predictor of  prognosis (low NLR: good outcome)

(9)

NLR average

NLR changes dramatically rise 1 year 

prior to death

Reverse: #days prior to death

NLR likely better predictor of remaining life than prognosis

Time-series analysis by heatmap plot

Reverse: #days prior to death

P atien t   number 2863 deaths Time‐course data of KUHP patient neutrophil‐to‐lymphocyte (NLR) ratio NLR is reported to be a predictor of  prognosis (low NLR: good outcome)

Cases of long lifespan despite high CRP value

Cannot feed group statistics back to individuals

(10)

P atien t   number Examination date

Plots of rate of neutrophils for KUHP Oncology patient

Oncology prediction problem:

Prognosis prediction: tracking patient outcomes is critical due to possible metastasis 

and drug resistance.

Side effects prediction: monitoring patient symptom is critical because of active 

therapy with anti‐cancer drugs.

Medical big data and simulation

using real-world data from Kyoto Univ. Hospital

Data for analysisKyoto U. Hospital  chemotherapy recipients5285 patients2863 recorded deathsSurvival span after  initial exam / start of  therapy max 5930.0 days,  average 817.5 days

(11)

Distribution of prediction error

Example of 

large error Example of 

small error

Groups to individuals: neutrophil change simulations

Example of 

(12)

Cause

Ef

fe

ct

Impulse response method:

Estimate cause‐effect between 

variables by observing change in each 

variable after perturbation of a 

specific single variable

Monocytes strongly impact neutrophils.

RBC, ALB, CL, ALP are also effectors.

Cause-effect estimation

between lab data

(13)

KUHP Cancer Center

Personal Genome Data

Determination of

treatments and side-effects from individual genotypes. Genotype-driven therapy selection from existing guidelines and research literature.

Clinical sequence

Molecular Simulations for Personalized Medicine in Drug Therapy

Personalized Drug Therapy

In oncology, genome dynamical change due to drug resistance via mutation

Mechanisms for resistance acquisition not fully understood.

Mutation

(14)

Non-small cell lung cancer therapy and resistance

Crizotinib

Alectinib

Ceritinib

L1196 G1202 S1206

T1151

Crizotinib G1269

(15)

E1167 I/T1171

CH5424802

αC helix

Wild type vs I1171T mutant

V/L1180

CH5424802 Wild type vs V1180L mutant

(16)

6 6.2 6.4 6.6 6.8 7 7.2 7.4 7.6 7.8 8 8.2 ‐19 ‐18 ‐17 ‐16 ‐15 ‐14 ‐13 6 6.5 7 7.5 8 8.5 9 9.5 10 ‐18 ‐16 ‐14 ‐12 ‐10 6 6.2 6.4 6.6 6.8 7 7.2 7.4 7.6 7.8 8 ‐18 ‐16 ‐14 ‐12 ‐10 wt wt I1171T wt V1180L Alectinib Ceritinib Crizotinib wild I1171T F1174I F1174V V1180L V1185L L1196M L1198F G1202R G1269A F1174V Experimental pIC50 Experimental pIC50 Calculated ∆G (kcal/mol) Experimental pIC50 Calculated ∆G (kcal/mol) Calculated ∆G (kcal/mol)

Computed free energies vs.

(17)

Understanding mechanisms for reduction of Alectinib binding affinity

due to mutations in ALK

wild-CH5424802 (green)77.7460.4117.33 I1171T-CH5424802 (cyan)75.0658.0417.02 V1180L-CH5424802(magenta)74.5560.0114.54 coulomb vdw (kcal/mol) ∆G

Binding free energies using the MP-CAFEE method

E1167 I/T1171 Alectinib αC helix H.B. broken L1196 V/L1180 E1167 αC helix Alectinib

(18)

KUHP Cancer Center

Personal Genome Data

Determination of

treatments and side-effects from individual genotypes. Genotype-driven therapy selection from existing guidelines and research literature.

Clinical sequence

Molecular Simulations for Personalized Medicine in Drug Therapy

Personalized Drug Therapy

In oncology, genome dynamical change due to drug resistance via mutation

Mechanisms for resistance acquisition not fully understood.

Predicting response to drug therapy and side effects using simulation

Uncovering mechanisms explaining side effects and drug resistance

(19)

Acknowledgements

The KBDD Consortium

RIKEN Adv. Inst. Comput. Sci.

Res. Org. for Info. Sci. Tech (RIST)

Foundation Biomed. Res. Innov.

Osaka Univ. Cybermedia Center

Biogrid Center Kansai

Post-K, Priority issues program

CREST “Big Data Applications”

Mitsui Knowledge Industry Co. Ltd.

Chugai Pharmaceutical Co. Ltd.

COE program from Kobe and Hyogo

Kyoto University Grad. Sch. Medicine

Profs. Manabu Muto,

Assoc. Prof. Shigemi Matsumoto

Assoc. Prof. Masashi Kanai

All the members of Okuno Labo.

All the members of Priority Issue 1

All the members of KBDD Consortium

Special thanks

Japn. Foudation for Cancer Res.

Dr. Ryohei Katayama

RIKEN / AICS

Dr. Makoto Taiji

Dr. Mitsugu Araki

Kei Taneishi

Foundation Biomed. Res. Innov.

Dr. Tasuku Honjyo

Dr. Yoichi Nabeshima

Dr. Hiroaki Iwata

References

Related documents