SlideShare a Scribd company logo
1 of 27
Academia Sinica
Taiwan
Gul Muneer
INSTITUTE OF CHEMISTRY
Coach Professor: Dr. Hwang Ming-Jing
Sit-in Professor: Dr. Carmay Lim
Class Coordinator: Dr. Takashi Angata
ANALYSIS _computational
BIOLOGY
1
ANALYSIS _computational
BIOLOGY
2
Predicting patient survival― How do clinicians predict?
How do oncologists know how long you have left to live?
 Prognostics ─ relating to “prediction”
How long have I got, Doc?
 Doctors can’t accurately predict the survival time (prognosis)
 Survival prediction ─ task of predicting the remaining life
 Prognosis─ guide doctors on planning future and selecting
therapies
3
Traditional prognosis
Tumor stage
Luminal A
Luminal B
ERB2+
Basal-like
Luminal BBasal-like ERB2+ Luminal A
ER + ER -
Proliferation
Differentiation
70-Gene
signature
76-Gene
signature
Wound
signature
Recurrence
score
Genomic
grade
Invasiveness
Gene
signature
Molecular classification
Luminal BBasal ERB2+ Luminal A
Good
Prognosis
Poor
PrognosisS3
S2
S1
Traditional and recent prediction approaches for Prognosis
Molecular Classification
Molecular prognosis Genomic prognosis
These studies have used “single-platform data” and have been limited to a “single cancer type”
4
Aims and motivations of the study
Kidney
Glioblastoma
Lung
Ovarian
Deletion Normal Amplif.
Cytosine 5-Methyl
Cytosine
AAAA
AAA
AA
Survival Clinical
variables
Somatic copy no. alteration
DNA methylation
mRNA expression
miRNA expression
Protein expression
How and to what extent
molecular profiling
affect oncology practice?
Prognostic utility
(Survival prediction)?
Therapeutic utility
(Clinically actionable genes)?
 Target selection for drug
development
 Clinical trail design
 Identify patient populations
for targeted therapies
5
Data
Training
Data
Test
Data
Feeds into
Machine Learning
Algorithm
Model
Schematic diagram of machine learning process
Accuracy
Test the Model
Determine AccuracyProduce
Model
Produce
Model
Machine Learning is about using data to train a model
6
Overview of TCGA samples
kidney renal clear cell carcinoma (KIRC); glioblastoma multiforme (GBM)
ovarian serous cystadenocarcinoma (OV); lung squamous cell carcinoma (LUSC)
(i) SCNA: ~100 arm or focal alterations
(ii) DNA methylation: ~20,000 genes
(iii) mRNA expression: ~20,000 genes
(iv) microRNA expression: >500
microRNAs
(v) protein expression: ~170 proteins
7
Overview of the computational approach
Cox regression-builds a predictive model for time-to-event data
LASSO-to identify good features and reduce feature redundancy
Random survival forest-an algorithm for analysis of survival data
C-Index-quantifies power of predictive model.
C-index = 1 indicates perfect prediction accuracy
C-index = 0.5 is as good as a random guess. 8
Prognostic power of molecular and clinical data
Integrated data showed higher predictive power for both cancers
Kidney cancer
Ovarian cancer
9
Prognostic power of molecular and clinical data
Lung cancer protein expression had predictive power comparable to clinical data
Glioblastoma
Lung cancer
10
Predictive power of clinical, molecular and integrated data
 Integrated models showed significant predictive
power in 3 cancer types.
 LUSC protein expression is only molecular data
alone showed performance similar to clinical data
 Similar trends in Cox and RSF models.
11
Biological insights from prognostic models
Building classifiers
By 5-fold cross-validation
NMF subtypes reveal
Distinct survival patterns
Predicted NMF subtypes
show expected survival
NMF subtypes (derived from miRNA expression) showed distinct survival patterns 12
Survival pattern of NMF subtypes matches the survival correlation of individual protein markers.
Molecular subtypes defined by LUSC protein expression
13
KIRC miRNAs correlated with survival
Higher or lower signature miRNAs are correlated with survival
Better prognosis
Worse prognosis
Better prognosis
14
KIRC mRNA-expression NMF subtypes
15
KIRC protein-expression correlated with NMF subtypes
KIRC protein expression data matches the distinct survival pattern
16
C-index
calculation
Patient survival prediction using cross-tumor models
Cross-tumor models could be used to predict patient survival.
17
Common feature for cross-tumor predictive power
“12q” crucial for cross-tumor
predictive power
Shared biological features provide insights into mechanistic connections b/w two cancer types
18
Modeling factors affecting prediction of survival data
Predictive power of molecular data strongly depend on the cancer type
19
Variation by modeling factors and their interactions
cancer type, data type, and their interactions are dominant sources of variability
35.7%
17.4% 11.8%
20
Other
(n = 623,096)
Noalterations
Nonsynonymous in
121 actionable genes
(n=10,281)
Somatic alterations in clinically relevant genes
10,281 somatic alterations across 12 tumor types
in 2,928 of 3,277 patients (89.4%)
ERBB2-
Neratinib
AKT1-
AKT inhibitors
FGFR1-
FGFR inhibitors
MAP2K1 & MAP2K2
MEK/ERK inhibitors
21
Expanding genome profiling to exome sequencing
↑ % of Patients with clinically actionable alterations
22
Alterations in clinically relevant genes
Global surveys of mutational patterns may stratify patients resistant to certain therapies 23
Conclusion
Deletion Normal Amplif.
Cytosine 5-Methyl
Cytosine
AAAA
AAA
AA
Survival Clinical
variables
Somatic copy no. alteration
DNA methylation
mRNA expression
miRNA expression
Protein expression
How and to what extent
molecular profiling
affect oncology practice?
Prognostic utility
(Survival prediction)?
Therapeutic utility
(Clinically actionable genes)?
Survival prediction significantly
improved for 3 cancer types
(2.2 % to 23.9%, FDR < 0.05)
10,281 somatic mutations in 2,928
patients (89.4%) out of 3,277
patients across 12 cancer types
This information could be helpful
in setting treatment targets.
24
Discussion and future perspective
 No obvious improvement with addition of “OMICS” to clinical. Difference is unlikely predictive.
 Predictive power of molecular data depended on cancer type but still cross-tumor models were used.
 Upgrading from hotspot profiling to exome sequencing will yield a more complete and clinically
useful patient tumor profile.
 Genes rarely mutated in any given tumor type are more regularly altered when considering aggregate
studies.
25
Non-thesis?
Manuscript?Revisions
Reviewer?
Thank you very much
For
Your Patience!
Would you survive the Ph.D.?
Machine learning has the answer!
Study more at www.sinica.edu.tw
26
27

More Related Content

What's hot

Alternative lengthening of telomeres is enriched in, and impacts survival of ...
Alternative lengthening of telomeres is enriched in, and impacts survival of ...Alternative lengthening of telomeres is enriched in, and impacts survival of ...
Alternative lengthening of telomeres is enriched in, and impacts survival of ...Joshua Mangerel
 
Alain Toledano : Test and genomic profile : what future in breast cancer trea...
Alain Toledano : Test and genomic profile : what future in breast cancer trea...Alain Toledano : Test and genomic profile : what future in breast cancer trea...
Alain Toledano : Test and genomic profile : what future in breast cancer trea...breastcancerupdatecongress
 
NY Prostate Cancer Conference - S. Stone - Session 1: Cell cycle progression ...
NY Prostate Cancer Conference - S. Stone - Session 1: Cell cycle progression ...NY Prostate Cancer Conference - S. Stone - Session 1: Cell cycle progression ...
NY Prostate Cancer Conference - S. Stone - Session 1: Cell cycle progression ...European School of Oncology
 
A review of micro rn as related to the occurrence, diagnosis, and prognosis o...
A review of micro rn as related to the occurrence, diagnosis, and prognosis o...A review of micro rn as related to the occurrence, diagnosis, and prognosis o...
A review of micro rn as related to the occurrence, diagnosis, and prognosis o...Clinical Surgery Research Communications
 
Liangqun ms defense.pptx
Liangqun ms defense.pptxLiangqun ms defense.pptx
Liangqun ms defense.pptxLiangqun Lu
 
BiPday 2014 -- Santorsola Mariangela
BiPday 2014 -- Santorsola MariangelaBiPday 2014 -- Santorsola Mariangela
BiPday 2014 -- Santorsola Mariangelaeventi-ITBbari
 
Ovarian_Cancer_Presentation-Tritz_VanLith_WareJoncas_Elwell
Ovarian_Cancer_Presentation-Tritz_VanLith_WareJoncas_ElwellOvarian_Cancer_Presentation-Tritz_VanLith_WareJoncas_Elwell
Ovarian_Cancer_Presentation-Tritz_VanLith_WareJoncas_ElwellZachary WareJoncas
 
Exploring chemo-resistance in NSCLC - Dr Martin Barr
Exploring chemo-resistance in NSCLC - Dr Martin BarrExploring chemo-resistance in NSCLC - Dr Martin Barr
Exploring chemo-resistance in NSCLC - Dr Martin BarrHannahMcCarthy31
 
Ultrasound reverses adriamycin resistance in non-small cell lung cancer via p...
Ultrasound reverses adriamycin resistance in non-small cell lung cancer via p...Ultrasound reverses adriamycin resistance in non-small cell lung cancer via p...
Ultrasound reverses adriamycin resistance in non-small cell lung cancer via p...Clinical Surgery Research Communications
 
Personalizing Oncology with Genomics
Personalizing Oncology with GenomicsPersonalizing Oncology with Genomics
Personalizing Oncology with GenomicsJeff Fitzgerald
 
Resveratrol induces apoptosis, autophagy and endoplasmic reticulum stress in ...
Resveratrol induces apoptosis, autophagy and endoplasmic reticulum stress in ...Resveratrol induces apoptosis, autophagy and endoplasmic reticulum stress in ...
Resveratrol induces apoptosis, autophagy and endoplasmic reticulum stress in ...Clinical Surgery Research Communications
 
Solitary cerebral metastasis from undiagnosed prostate cancer. potential role...
Solitary cerebral metastasis from undiagnosed prostate cancer. potential role...Solitary cerebral metastasis from undiagnosed prostate cancer. potential role...
Solitary cerebral metastasis from undiagnosed prostate cancer. potential role...Clinical Surgery Research Communications
 
Mi r 449b inhibits the migration and invasion of colorectal cancer cells thro...
Mi r 449b inhibits the migration and invasion of colorectal cancer cells thro...Mi r 449b inhibits the migration and invasion of colorectal cancer cells thro...
Mi r 449b inhibits the migration and invasion of colorectal cancer cells thro...Clinical Surgery Research Communications
 
Lnc rna nnt as1 affect progesterone resistance by regulating mir-542-3p or su...
Lnc rna nnt as1 affect progesterone resistance by regulating mir-542-3p or su...Lnc rna nnt as1 affect progesterone resistance by regulating mir-542-3p or su...
Lnc rna nnt as1 affect progesterone resistance by regulating mir-542-3p or su...Clinical Surgery Research Communications
 
Integrative Analysis of Gene Expression and Promoter Methylation during Repro...
Integrative Analysis of Gene Expression and Promoter Methylation during Repro...Integrative Analysis of Gene Expression and Promoter Methylation during Repro...
Integrative Analysis of Gene Expression and Promoter Methylation during Repro...Y-h Taguchi
 

What's hot (19)

Alternative lengthening of telomeres is enriched in, and impacts survival of ...
Alternative lengthening of telomeres is enriched in, and impacts survival of ...Alternative lengthening of telomeres is enriched in, and impacts survival of ...
Alternative lengthening of telomeres is enriched in, and impacts survival of ...
 
Alain Toledano : Test and genomic profile : what future in breast cancer trea...
Alain Toledano : Test and genomic profile : what future in breast cancer trea...Alain Toledano : Test and genomic profile : what future in breast cancer trea...
Alain Toledano : Test and genomic profile : what future in breast cancer trea...
 
NY Prostate Cancer Conference - S. Stone - Session 1: Cell cycle progression ...
NY Prostate Cancer Conference - S. Stone - Session 1: Cell cycle progression ...NY Prostate Cancer Conference - S. Stone - Session 1: Cell cycle progression ...
NY Prostate Cancer Conference - S. Stone - Session 1: Cell cycle progression ...
 
A review of micro rn as related to the occurrence, diagnosis, and prognosis o...
A review of micro rn as related to the occurrence, diagnosis, and prognosis o...A review of micro rn as related to the occurrence, diagnosis, and prognosis o...
A review of micro rn as related to the occurrence, diagnosis, and prognosis o...
 
Gtc presentation
Gtc presentationGtc presentation
Gtc presentation
 
Liangqun ms defense.pptx
Liangqun ms defense.pptxLiangqun ms defense.pptx
Liangqun ms defense.pptx
 
BiPday 2014 -- Santorsola Mariangela
BiPday 2014 -- Santorsola MariangelaBiPday 2014 -- Santorsola Mariangela
BiPday 2014 -- Santorsola Mariangela
 
Ovarian_Cancer_Presentation-Tritz_VanLith_WareJoncas_Elwell
Ovarian_Cancer_Presentation-Tritz_VanLith_WareJoncas_ElwellOvarian_Cancer_Presentation-Tritz_VanLith_WareJoncas_Elwell
Ovarian_Cancer_Presentation-Tritz_VanLith_WareJoncas_Elwell
 
Exploring chemo-resistance in NSCLC - Dr Martin Barr
Exploring chemo-resistance in NSCLC - Dr Martin BarrExploring chemo-resistance in NSCLC - Dr Martin Barr
Exploring chemo-resistance in NSCLC - Dr Martin Barr
 
Ultrasound reverses adriamycin resistance in non-small cell lung cancer via p...
Ultrasound reverses adriamycin resistance in non-small cell lung cancer via p...Ultrasound reverses adriamycin resistance in non-small cell lung cancer via p...
Ultrasound reverses adriamycin resistance in non-small cell lung cancer via p...
 
Personalizing Oncology with Genomics
Personalizing Oncology with GenomicsPersonalizing Oncology with Genomics
Personalizing Oncology with Genomics
 
Resveratrol induces apoptosis, autophagy and endoplasmic reticulum stress in ...
Resveratrol induces apoptosis, autophagy and endoplasmic reticulum stress in ...Resveratrol induces apoptosis, autophagy and endoplasmic reticulum stress in ...
Resveratrol induces apoptosis, autophagy and endoplasmic reticulum stress in ...
 
Solitary cerebral metastasis from undiagnosed prostate cancer. potential role...
Solitary cerebral metastasis from undiagnosed prostate cancer. potential role...Solitary cerebral metastasis from undiagnosed prostate cancer. potential role...
Solitary cerebral metastasis from undiagnosed prostate cancer. potential role...
 
Session 1.4 Steidl
Session 1.4 SteidlSession 1.4 Steidl
Session 1.4 Steidl
 
Session 1.4: Steidl
Session 1.4: SteidlSession 1.4: Steidl
Session 1.4: Steidl
 
Pharmacology Powered by Computational Analysis: Predicting Cardiotoxicity of ...
Pharmacology Powered by Computational Analysis: Predicting Cardiotoxicity of ...Pharmacology Powered by Computational Analysis: Predicting Cardiotoxicity of ...
Pharmacology Powered by Computational Analysis: Predicting Cardiotoxicity of ...
 
Mi r 449b inhibits the migration and invasion of colorectal cancer cells thro...
Mi r 449b inhibits the migration and invasion of colorectal cancer cells thro...Mi r 449b inhibits the migration and invasion of colorectal cancer cells thro...
Mi r 449b inhibits the migration and invasion of colorectal cancer cells thro...
 
Lnc rna nnt as1 affect progesterone resistance by regulating mir-542-3p or su...
Lnc rna nnt as1 affect progesterone resistance by regulating mir-542-3p or su...Lnc rna nnt as1 affect progesterone resistance by regulating mir-542-3p or su...
Lnc rna nnt as1 affect progesterone resistance by regulating mir-542-3p or su...
 
Integrative Analysis of Gene Expression and Promoter Methylation during Repro...
Integrative Analysis of Gene Expression and Promoter Methylation during Repro...Integrative Analysis of Gene Expression and Promoter Methylation during Repro...
Integrative Analysis of Gene Expression and Promoter Methylation during Repro...
 

Similar to Machine Learning Predicts Cancer Patient Survival Using Multi-Omics Data

Personalized Medicine in Diagnosis and Treatment of Cancer
Personalized Medicine in Diagnosis and Treatment of Cancer Personalized Medicine in Diagnosis and Treatment of Cancer
Personalized Medicine in Diagnosis and Treatment of Cancer Maryam Rafati
 
QMB_Poster_Tom_Kelly
QMB_Poster_Tom_KellyQMB_Poster_Tom_Kelly
QMB_Poster_Tom_KellyTom Kelly
 
Applications of Next generation sequencing in Drug Discovery
Applications of Next generation sequencing in Drug DiscoveryApplications of Next generation sequencing in Drug Discovery
Applications of Next generation sequencing in Drug Discoveryvjain38
 
Next generation Sequencing in Drug Discovery
Next generation Sequencing in Drug DiscoveryNext generation Sequencing in Drug Discovery
Next generation Sequencing in Drug DiscoveryVanshikaJain757478
 
Gene expression profiling reveals molecularly and clinically distinct subtype...
Gene expression profiling reveals molecularly and clinically distinct subtype...Gene expression profiling reveals molecularly and clinically distinct subtype...
Gene expression profiling reveals molecularly and clinically distinct subtype...Yu Liang
 
Open Source Pharma /Genomics and clinical practice / Prof Hosur
Open Source Pharma /Genomics and clinical practice / Prof Hosur Open Source Pharma /Genomics and clinical practice / Prof Hosur
Open Source Pharma /Genomics and clinical practice / Prof Hosur opensourcepharmafound
 
LLA 2011 - B. Cheson - Problems of the design and interpretation of very earl...
LLA 2011 - B. Cheson - Problems of the design and interpretation of very earl...LLA 2011 - B. Cheson - Problems of the design and interpretation of very earl...
LLA 2011 - B. Cheson - Problems of the design and interpretation of very earl...European School of Oncology
 
Developing a framework for for detection of low frequency somatic genetic alt...
Developing a framework for for detection of low frequency somatic genetic alt...Developing a framework for for detection of low frequency somatic genetic alt...
Developing a framework for for detection of low frequency somatic genetic alt...Ronak Shah
 
Journal club- breast ca basal like
Journal club- breast ca basal likeJournal club- breast ca basal like
Journal club- breast ca basal likeSakshi Gupta
 
Dr Nicholas Shackel - Bioinformatics and Personalised Medicine
Dr Nicholas Shackel - Bioinformatics and Personalised MedicineDr Nicholas Shackel - Bioinformatics and Personalised Medicine
Dr Nicholas Shackel - Bioinformatics and Personalised Medicinecentenaryinstitute
 
Пятницкий М.А. Подбор персонализированной противоопухолевой терапии путем сис...
Пятницкий М.А. Подбор персонализированной противоопухолевой терапии путем сис...Пятницкий М.А. Подбор персонализированной противоопухолевой терапии путем сис...
Пятницкий М.А. Подбор персонализированной противоопухолевой терапии путем сис...bigdatabm
 
A New Generation Of Mechanism-Based Biomarkers For The Clinic
A New Generation Of Mechanism-Based Biomarkers For The ClinicA New Generation Of Mechanism-Based Biomarkers For The Clinic
A New Generation Of Mechanism-Based Biomarkers For The ClinicJoaquin Dopazo
 
Molecular classification of endometrial cancer
Molecular classification of endometrial cancerMolecular classification of endometrial cancer
Molecular classification of endometrial cancerMohammed Nassar
 
MCO 2011 - Slide 33 - C. Svedman - Spotlight session - Criteria to evaluate g...
MCO 2011 - Slide 33 - C. Svedman - Spotlight session - Criteria to evaluate g...MCO 2011 - Slide 33 - C. Svedman - Spotlight session - Criteria to evaluate g...
MCO 2011 - Slide 33 - C. Svedman - Spotlight session - Criteria to evaluate g...European School of Oncology
 
全人關懷獎的簡報
全人關懷獎的簡報全人關懷獎的簡報
全人關懷獎的簡報bgbgbg
 
1-s2.0-S2211124714001612-main
1-s2.0-S2211124714001612-main1-s2.0-S2211124714001612-main
1-s2.0-S2211124714001612-mainAnirudh Prahallad
 
Bioinformatics-driven discovery of EGFR mutant Lung Cancer
Bioinformatics-driven discovery of EGFR mutant Lung CancerBioinformatics-driven discovery of EGFR mutant Lung Cancer
Bioinformatics-driven discovery of EGFR mutant Lung CancerPreveenRamamoorthy
 

Similar to Machine Learning Predicts Cancer Patient Survival Using Multi-Omics Data (20)

The Cancer Genome Atlas Update
The Cancer Genome Atlas UpdateThe Cancer Genome Atlas Update
The Cancer Genome Atlas Update
 
Personalized Medicine in Diagnosis and Treatment of Cancer
Personalized Medicine in Diagnosis and Treatment of Cancer Personalized Medicine in Diagnosis and Treatment of Cancer
Personalized Medicine in Diagnosis and Treatment of Cancer
 
QMB_Poster_Tom_Kelly
QMB_Poster_Tom_KellyQMB_Poster_Tom_Kelly
QMB_Poster_Tom_Kelly
 
Applications of Next generation sequencing in Drug Discovery
Applications of Next generation sequencing in Drug DiscoveryApplications of Next generation sequencing in Drug Discovery
Applications of Next generation sequencing in Drug Discovery
 
Next generation Sequencing in Drug Discovery
Next generation Sequencing in Drug DiscoveryNext generation Sequencing in Drug Discovery
Next generation Sequencing in Drug Discovery
 
Gene expression profiling reveals molecularly and clinically distinct subtype...
Gene expression profiling reveals molecularly and clinically distinct subtype...Gene expression profiling reveals molecularly and clinically distinct subtype...
Gene expression profiling reveals molecularly and clinically distinct subtype...
 
Open Source Pharma /Genomics and clinical practice / Prof Hosur
Open Source Pharma /Genomics and clinical practice / Prof Hosur Open Source Pharma /Genomics and clinical practice / Prof Hosur
Open Source Pharma /Genomics and clinical practice / Prof Hosur
 
LLA 2011 - B. Cheson - Problems of the design and interpretation of very earl...
LLA 2011 - B. Cheson - Problems of the design and interpretation of very earl...LLA 2011 - B. Cheson - Problems of the design and interpretation of very earl...
LLA 2011 - B. Cheson - Problems of the design and interpretation of very earl...
 
Developing a framework for for detection of low frequency somatic genetic alt...
Developing a framework for for detection of low frequency somatic genetic alt...Developing a framework for for detection of low frequency somatic genetic alt...
Developing a framework for for detection of low frequency somatic genetic alt...
 
Journal club- breast ca basal like
Journal club- breast ca basal likeJournal club- breast ca basal like
Journal club- breast ca basal like
 
ncomms11428
ncomms11428ncomms11428
ncomms11428
 
Dr Nicholas Shackel - Bioinformatics and Personalised Medicine
Dr Nicholas Shackel - Bioinformatics and Personalised MedicineDr Nicholas Shackel - Bioinformatics and Personalised Medicine
Dr Nicholas Shackel - Bioinformatics and Personalised Medicine
 
Пятницкий М.А. Подбор персонализированной противоопухолевой терапии путем сис...
Пятницкий М.А. Подбор персонализированной противоопухолевой терапии путем сис...Пятницкий М.А. Подбор персонализированной противоопухолевой терапии путем сис...
Пятницкий М.А. Подбор персонализированной противоопухолевой терапии путем сис...
 
PIIS0016508514604509
PIIS0016508514604509PIIS0016508514604509
PIIS0016508514604509
 
A New Generation Of Mechanism-Based Biomarkers For The Clinic
A New Generation Of Mechanism-Based Biomarkers For The ClinicA New Generation Of Mechanism-Based Biomarkers For The Clinic
A New Generation Of Mechanism-Based Biomarkers For The Clinic
 
Molecular classification of endometrial cancer
Molecular classification of endometrial cancerMolecular classification of endometrial cancer
Molecular classification of endometrial cancer
 
MCO 2011 - Slide 33 - C. Svedman - Spotlight session - Criteria to evaluate g...
MCO 2011 - Slide 33 - C. Svedman - Spotlight session - Criteria to evaluate g...MCO 2011 - Slide 33 - C. Svedman - Spotlight session - Criteria to evaluate g...
MCO 2011 - Slide 33 - C. Svedman - Spotlight session - Criteria to evaluate g...
 
全人關懷獎的簡報
全人關懷獎的簡報全人關懷獎的簡報
全人關懷獎的簡報
 
1-s2.0-S2211124714001612-main
1-s2.0-S2211124714001612-main1-s2.0-S2211124714001612-main
1-s2.0-S2211124714001612-main
 
Bioinformatics-driven discovery of EGFR mutant Lung Cancer
Bioinformatics-driven discovery of EGFR mutant Lung CancerBioinformatics-driven discovery of EGFR mutant Lung Cancer
Bioinformatics-driven discovery of EGFR mutant Lung Cancer
 

More from Gul Muneer

Universal Influenza Vaccine
Universal Influenza VaccineUniversal Influenza Vaccine
Universal Influenza VaccineGul Muneer
 
Structural basis of omalizumab therapy and omalizumab-mediated IgE exchange
Structural basis of omalizumab therapy and omalizumab-mediated IgE exchangeStructural basis of omalizumab therapy and omalizumab-mediated IgE exchange
Structural basis of omalizumab therapy and omalizumab-mediated IgE exchangeGul Muneer
 
L-arginine modulates T cell metabolism and enhances survival and anti-tumor A...
L-arginine modulates T cell metabolism and enhances survival and anti-tumor A...L-arginine modulates T cell metabolism and enhances survival and anti-tumor A...
L-arginine modulates T cell metabolism and enhances survival and anti-tumor A...Gul Muneer
 
SCS macrophages suppress melanoma by restricting tumor-derived vesicle–B cell...
SCS macrophages suppress melanoma by restricting tumor-derived vesicle–B cell...SCS macrophages suppress melanoma by restricting tumor-derived vesicle–B cell...
SCS macrophages suppress melanoma by restricting tumor-derived vesicle–B cell...Gul Muneer
 
Vitamin B3 Niacin
Vitamin B3 NiacinVitamin B3 Niacin
Vitamin B3 NiacinGul Muneer
 
Glycogenolysis
GlycogenolysisGlycogenolysis
GlycogenolysisGul Muneer
 
Plasma/Cell Membrane
Plasma/Cell MembranePlasma/Cell Membrane
Plasma/Cell MembraneGul Muneer
 

More from Gul Muneer (7)

Universal Influenza Vaccine
Universal Influenza VaccineUniversal Influenza Vaccine
Universal Influenza Vaccine
 
Structural basis of omalizumab therapy and omalizumab-mediated IgE exchange
Structural basis of omalizumab therapy and omalizumab-mediated IgE exchangeStructural basis of omalizumab therapy and omalizumab-mediated IgE exchange
Structural basis of omalizumab therapy and omalizumab-mediated IgE exchange
 
L-arginine modulates T cell metabolism and enhances survival and anti-tumor A...
L-arginine modulates T cell metabolism and enhances survival and anti-tumor A...L-arginine modulates T cell metabolism and enhances survival and anti-tumor A...
L-arginine modulates T cell metabolism and enhances survival and anti-tumor A...
 
SCS macrophages suppress melanoma by restricting tumor-derived vesicle–B cell...
SCS macrophages suppress melanoma by restricting tumor-derived vesicle–B cell...SCS macrophages suppress melanoma by restricting tumor-derived vesicle–B cell...
SCS macrophages suppress melanoma by restricting tumor-derived vesicle–B cell...
 
Vitamin B3 Niacin
Vitamin B3 NiacinVitamin B3 Niacin
Vitamin B3 Niacin
 
Glycogenolysis
GlycogenolysisGlycogenolysis
Glycogenolysis
 
Plasma/Cell Membrane
Plasma/Cell MembranePlasma/Cell Membrane
Plasma/Cell Membrane
 

Recently uploaded

Privatization and Disinvestment - Meaning, Objectives, Advantages and Disadva...
Privatization and Disinvestment - Meaning, Objectives, Advantages and Disadva...Privatization and Disinvestment - Meaning, Objectives, Advantages and Disadva...
Privatization and Disinvestment - Meaning, Objectives, Advantages and Disadva...RKavithamani
 
Student login on Anyboli platform.helpin
Student login on Anyboli platform.helpinStudent login on Anyboli platform.helpin
Student login on Anyboli platform.helpinRaunakKeshri1
 
Separation of Lanthanides/ Lanthanides and Actinides
Separation of Lanthanides/ Lanthanides and ActinidesSeparation of Lanthanides/ Lanthanides and Actinides
Separation of Lanthanides/ Lanthanides and ActinidesFatimaKhan178732
 
Advanced Views - Calendar View in Odoo 17
Advanced Views - Calendar View in Odoo 17Advanced Views - Calendar View in Odoo 17
Advanced Views - Calendar View in Odoo 17Celine George
 
A Critique of the Proposed National Education Policy Reform
A Critique of the Proposed National Education Policy ReformA Critique of the Proposed National Education Policy Reform
A Critique of the Proposed National Education Policy ReformChameera Dedduwage
 
Grant Readiness 101 TechSoup and Remy Consulting
Grant Readiness 101 TechSoup and Remy ConsultingGrant Readiness 101 TechSoup and Remy Consulting
Grant Readiness 101 TechSoup and Remy ConsultingTechSoup
 
How to Make a Pirate ship Primary Education.pptx
How to Make a Pirate ship Primary Education.pptxHow to Make a Pirate ship Primary Education.pptx
How to Make a Pirate ship Primary Education.pptxmanuelaromero2013
 
POINT- BIOCHEMISTRY SEM 2 ENZYMES UNIT 5.pptx
POINT- BIOCHEMISTRY SEM 2 ENZYMES UNIT 5.pptxPOINT- BIOCHEMISTRY SEM 2 ENZYMES UNIT 5.pptx
POINT- BIOCHEMISTRY SEM 2 ENZYMES UNIT 5.pptxSayali Powar
 
CARE OF CHILD IN INCUBATOR..........pptx
CARE OF CHILD IN INCUBATOR..........pptxCARE OF CHILD IN INCUBATOR..........pptx
CARE OF CHILD IN INCUBATOR..........pptxGaneshChakor2
 
mini mental status format.docx
mini    mental       status     format.docxmini    mental       status     format.docx
mini mental status format.docxPoojaSen20
 
Kisan Call Centre - To harness potential of ICT in Agriculture by answer farm...
Kisan Call Centre - To harness potential of ICT in Agriculture by answer farm...Kisan Call Centre - To harness potential of ICT in Agriculture by answer farm...
Kisan Call Centre - To harness potential of ICT in Agriculture by answer farm...Krashi Coaching
 
The basics of sentences session 2pptx copy.pptx
The basics of sentences session 2pptx copy.pptxThe basics of sentences session 2pptx copy.pptx
The basics of sentences session 2pptx copy.pptxheathfieldcps1
 
Beyond the EU: DORA and NIS 2 Directive's Global Impact
Beyond the EU: DORA and NIS 2 Directive's Global ImpactBeyond the EU: DORA and NIS 2 Directive's Global Impact
Beyond the EU: DORA and NIS 2 Directive's Global ImpactPECB
 
18-04-UA_REPORT_MEDIALITERAСY_INDEX-DM_23-1-final-eng.pdf
18-04-UA_REPORT_MEDIALITERAСY_INDEX-DM_23-1-final-eng.pdf18-04-UA_REPORT_MEDIALITERAСY_INDEX-DM_23-1-final-eng.pdf
18-04-UA_REPORT_MEDIALITERAСY_INDEX-DM_23-1-final-eng.pdfssuser54595a
 
Web & Social Media Analytics Previous Year Question Paper.pdf
Web & Social Media Analytics Previous Year Question Paper.pdfWeb & Social Media Analytics Previous Year Question Paper.pdf
Web & Social Media Analytics Previous Year Question Paper.pdfJayanti Pande
 
Introduction to AI in Higher Education_draft.pptx
Introduction to AI in Higher Education_draft.pptxIntroduction to AI in Higher Education_draft.pptx
Introduction to AI in Higher Education_draft.pptxpboyjonauth
 
Z Score,T Score, Percential Rank and Box Plot Graph
Z Score,T Score, Percential Rank and Box Plot GraphZ Score,T Score, Percential Rank and Box Plot Graph
Z Score,T Score, Percential Rank and Box Plot GraphThiyagu K
 

Recently uploaded (20)

Privatization and Disinvestment - Meaning, Objectives, Advantages and Disadva...
Privatization and Disinvestment - Meaning, Objectives, Advantages and Disadva...Privatization and Disinvestment - Meaning, Objectives, Advantages and Disadva...
Privatization and Disinvestment - Meaning, Objectives, Advantages and Disadva...
 
TataKelola dan KamSiber Kecerdasan Buatan v022.pdf
TataKelola dan KamSiber Kecerdasan Buatan v022.pdfTataKelola dan KamSiber Kecerdasan Buatan v022.pdf
TataKelola dan KamSiber Kecerdasan Buatan v022.pdf
 
Student login on Anyboli platform.helpin
Student login on Anyboli platform.helpinStudent login on Anyboli platform.helpin
Student login on Anyboli platform.helpin
 
Separation of Lanthanides/ Lanthanides and Actinides
Separation of Lanthanides/ Lanthanides and ActinidesSeparation of Lanthanides/ Lanthanides and Actinides
Separation of Lanthanides/ Lanthanides and Actinides
 
Advanced Views - Calendar View in Odoo 17
Advanced Views - Calendar View in Odoo 17Advanced Views - Calendar View in Odoo 17
Advanced Views - Calendar View in Odoo 17
 
A Critique of the Proposed National Education Policy Reform
A Critique of the Proposed National Education Policy ReformA Critique of the Proposed National Education Policy Reform
A Critique of the Proposed National Education Policy Reform
 
Grant Readiness 101 TechSoup and Remy Consulting
Grant Readiness 101 TechSoup and Remy ConsultingGrant Readiness 101 TechSoup and Remy Consulting
Grant Readiness 101 TechSoup and Remy Consulting
 
How to Make a Pirate ship Primary Education.pptx
How to Make a Pirate ship Primary Education.pptxHow to Make a Pirate ship Primary Education.pptx
How to Make a Pirate ship Primary Education.pptx
 
POINT- BIOCHEMISTRY SEM 2 ENZYMES UNIT 5.pptx
POINT- BIOCHEMISTRY SEM 2 ENZYMES UNIT 5.pptxPOINT- BIOCHEMISTRY SEM 2 ENZYMES UNIT 5.pptx
POINT- BIOCHEMISTRY SEM 2 ENZYMES UNIT 5.pptx
 
CARE OF CHILD IN INCUBATOR..........pptx
CARE OF CHILD IN INCUBATOR..........pptxCARE OF CHILD IN INCUBATOR..........pptx
CARE OF CHILD IN INCUBATOR..........pptx
 
mini mental status format.docx
mini    mental       status     format.docxmini    mental       status     format.docx
mini mental status format.docx
 
Kisan Call Centre - To harness potential of ICT in Agriculture by answer farm...
Kisan Call Centre - To harness potential of ICT in Agriculture by answer farm...Kisan Call Centre - To harness potential of ICT in Agriculture by answer farm...
Kisan Call Centre - To harness potential of ICT in Agriculture by answer farm...
 
The basics of sentences session 2pptx copy.pptx
The basics of sentences session 2pptx copy.pptxThe basics of sentences session 2pptx copy.pptx
The basics of sentences session 2pptx copy.pptx
 
Beyond the EU: DORA and NIS 2 Directive's Global Impact
Beyond the EU: DORA and NIS 2 Directive's Global ImpactBeyond the EU: DORA and NIS 2 Directive's Global Impact
Beyond the EU: DORA and NIS 2 Directive's Global Impact
 
18-04-UA_REPORT_MEDIALITERAСY_INDEX-DM_23-1-final-eng.pdf
18-04-UA_REPORT_MEDIALITERAСY_INDEX-DM_23-1-final-eng.pdf18-04-UA_REPORT_MEDIALITERAСY_INDEX-DM_23-1-final-eng.pdf
18-04-UA_REPORT_MEDIALITERAСY_INDEX-DM_23-1-final-eng.pdf
 
Web & Social Media Analytics Previous Year Question Paper.pdf
Web & Social Media Analytics Previous Year Question Paper.pdfWeb & Social Media Analytics Previous Year Question Paper.pdf
Web & Social Media Analytics Previous Year Question Paper.pdf
 
Introduction to AI in Higher Education_draft.pptx
Introduction to AI in Higher Education_draft.pptxIntroduction to AI in Higher Education_draft.pptx
Introduction to AI in Higher Education_draft.pptx
 
Mattingly "AI & Prompt Design: The Basics of Prompt Design"
Mattingly "AI & Prompt Design: The Basics of Prompt Design"Mattingly "AI & Prompt Design: The Basics of Prompt Design"
Mattingly "AI & Prompt Design: The Basics of Prompt Design"
 
Z Score,T Score, Percential Rank and Box Plot Graph
Z Score,T Score, Percential Rank and Box Plot GraphZ Score,T Score, Percential Rank and Box Plot Graph
Z Score,T Score, Percential Rank and Box Plot Graph
 
Código Creativo y Arte de Software | Unidad 1
Código Creativo y Arte de Software | Unidad 1Código Creativo y Arte de Software | Unidad 1
Código Creativo y Arte de Software | Unidad 1
 

Machine Learning Predicts Cancer Patient Survival Using Multi-Omics Data

  • 1. Academia Sinica Taiwan Gul Muneer INSTITUTE OF CHEMISTRY Coach Professor: Dr. Hwang Ming-Jing Sit-in Professor: Dr. Carmay Lim Class Coordinator: Dr. Takashi Angata ANALYSIS _computational BIOLOGY 1
  • 3. Predicting patient survival― How do clinicians predict? How do oncologists know how long you have left to live?  Prognostics ─ relating to “prediction” How long have I got, Doc?  Doctors can’t accurately predict the survival time (prognosis)  Survival prediction ─ task of predicting the remaining life  Prognosis─ guide doctors on planning future and selecting therapies 3
  • 4. Traditional prognosis Tumor stage Luminal A Luminal B ERB2+ Basal-like Luminal BBasal-like ERB2+ Luminal A ER + ER - Proliferation Differentiation 70-Gene signature 76-Gene signature Wound signature Recurrence score Genomic grade Invasiveness Gene signature Molecular classification Luminal BBasal ERB2+ Luminal A Good Prognosis Poor PrognosisS3 S2 S1 Traditional and recent prediction approaches for Prognosis Molecular Classification Molecular prognosis Genomic prognosis These studies have used “single-platform data” and have been limited to a “single cancer type” 4
  • 5. Aims and motivations of the study Kidney Glioblastoma Lung Ovarian Deletion Normal Amplif. Cytosine 5-Methyl Cytosine AAAA AAA AA Survival Clinical variables Somatic copy no. alteration DNA methylation mRNA expression miRNA expression Protein expression How and to what extent molecular profiling affect oncology practice? Prognostic utility (Survival prediction)? Therapeutic utility (Clinically actionable genes)?  Target selection for drug development  Clinical trail design  Identify patient populations for targeted therapies 5
  • 6. Data Training Data Test Data Feeds into Machine Learning Algorithm Model Schematic diagram of machine learning process Accuracy Test the Model Determine AccuracyProduce Model Produce Model Machine Learning is about using data to train a model 6
  • 7. Overview of TCGA samples kidney renal clear cell carcinoma (KIRC); glioblastoma multiforme (GBM) ovarian serous cystadenocarcinoma (OV); lung squamous cell carcinoma (LUSC) (i) SCNA: ~100 arm or focal alterations (ii) DNA methylation: ~20,000 genes (iii) mRNA expression: ~20,000 genes (iv) microRNA expression: >500 microRNAs (v) protein expression: ~170 proteins 7
  • 8. Overview of the computational approach Cox regression-builds a predictive model for time-to-event data LASSO-to identify good features and reduce feature redundancy Random survival forest-an algorithm for analysis of survival data C-Index-quantifies power of predictive model. C-index = 1 indicates perfect prediction accuracy C-index = 0.5 is as good as a random guess. 8
  • 9. Prognostic power of molecular and clinical data Integrated data showed higher predictive power for both cancers Kidney cancer Ovarian cancer 9
  • 10. Prognostic power of molecular and clinical data Lung cancer protein expression had predictive power comparable to clinical data Glioblastoma Lung cancer 10
  • 11. Predictive power of clinical, molecular and integrated data  Integrated models showed significant predictive power in 3 cancer types.  LUSC protein expression is only molecular data alone showed performance similar to clinical data  Similar trends in Cox and RSF models. 11
  • 12. Biological insights from prognostic models Building classifiers By 5-fold cross-validation NMF subtypes reveal Distinct survival patterns Predicted NMF subtypes show expected survival NMF subtypes (derived from miRNA expression) showed distinct survival patterns 12
  • 13. Survival pattern of NMF subtypes matches the survival correlation of individual protein markers. Molecular subtypes defined by LUSC protein expression 13
  • 14. KIRC miRNAs correlated with survival Higher or lower signature miRNAs are correlated with survival Better prognosis Worse prognosis Better prognosis 14
  • 16. KIRC protein-expression correlated with NMF subtypes KIRC protein expression data matches the distinct survival pattern 16
  • 17. C-index calculation Patient survival prediction using cross-tumor models Cross-tumor models could be used to predict patient survival. 17
  • 18. Common feature for cross-tumor predictive power “12q” crucial for cross-tumor predictive power Shared biological features provide insights into mechanistic connections b/w two cancer types 18
  • 19. Modeling factors affecting prediction of survival data Predictive power of molecular data strongly depend on the cancer type 19
  • 20. Variation by modeling factors and their interactions cancer type, data type, and their interactions are dominant sources of variability 35.7% 17.4% 11.8% 20
  • 21. Other (n = 623,096) Noalterations Nonsynonymous in 121 actionable genes (n=10,281) Somatic alterations in clinically relevant genes 10,281 somatic alterations across 12 tumor types in 2,928 of 3,277 patients (89.4%) ERBB2- Neratinib AKT1- AKT inhibitors FGFR1- FGFR inhibitors MAP2K1 & MAP2K2 MEK/ERK inhibitors 21
  • 22. Expanding genome profiling to exome sequencing ↑ % of Patients with clinically actionable alterations 22
  • 23. Alterations in clinically relevant genes Global surveys of mutational patterns may stratify patients resistant to certain therapies 23
  • 24. Conclusion Deletion Normal Amplif. Cytosine 5-Methyl Cytosine AAAA AAA AA Survival Clinical variables Somatic copy no. alteration DNA methylation mRNA expression miRNA expression Protein expression How and to what extent molecular profiling affect oncology practice? Prognostic utility (Survival prediction)? Therapeutic utility (Clinically actionable genes)? Survival prediction significantly improved for 3 cancer types (2.2 % to 23.9%, FDR < 0.05) 10,281 somatic mutations in 2,928 patients (89.4%) out of 3,277 patients across 12 cancer types This information could be helpful in setting treatment targets. 24
  • 25. Discussion and future perspective  No obvious improvement with addition of “OMICS” to clinical. Difference is unlikely predictive.  Predictive power of molecular data depended on cancer type but still cross-tumor models were used.  Upgrading from hotspot profiling to exome sequencing will yield a more complete and clinically useful patient tumor profile.  Genes rarely mutated in any given tumor type are more regularly altered when considering aggregate studies. 25
  • 26. Non-thesis? Manuscript?Revisions Reviewer? Thank you very much For Your Patience! Would you survive the Ph.D.? Machine learning has the answer! Study more at www.sinica.edu.tw 26
  • 27. 27

Editor's Notes

  1. Fortunately, doctors don’t use it! So, I’ll start with the definition of XXXX or prognosis. So these pictures here illustrate the concept of prediction
  2. Authors claimed study by mentioning