SlideShare a Scribd company logo
Therapeutic Cancer Vaccines: Where
Predictive Models Matter
Tim O’Donnell
NEC Laboratories Europe GmbH
Oct 15, 2021
1
The OpenVax Project
● Clinical Trials: help run personalized cancer vaccine trials at
Mount Sinai
● Software: open source tools for cancer genomics and
neoantigen prediction
○ www.github.com/openvax/
● Research: improve methods for predicting the immune
response to tumor antigens
2
Tim O’Donnell
Mount Sinai
Julia Kodysh
Mount Sinai
Alex Rubinsteyn
UNC Chapel Hill
Nina Bhardwaj
Mount Sinai
Talk Overview
1. Introduction to cancer vaccines
2. Introduction to MHC binding prediction
3. MHCflurry 2.0
3
Talk Overview
1. Introduction to cancer vaccines
2. Introduction to MHC binding prediction
3. MHCflurry 2.0
4
Two arms of adaptive immunity
5
Two arms of adaptive immunity
6
Cytotoxic T cells can kill diseased cells
7
Cytotoxic T cells can kill diseased cells
8
Short history of cancer immunotherapy
9
Alex Rubinsteyn
20th century
Dark Age of
radiation and
chemotherapy
1850s-1890s
Infection & fever =>
tumor regression?
1893
Coley’s Toxins
(complete response in
~10% of sarcomas)
2010s
~20 approved cancer
immunotherapies
Cancer immunotherapy
10
Alex Rubinsteyn
Checkpoint blockade Cellular therapies Vaccines
Disinhibit T-cells.
Antigens responsible for tumor
clearance typically unknown.
Success stories:
● 𝛂CTLA-4 (ipi)
● 𝛂PD-1 (pembro, nivo, cemi)
● 𝛂PD-L1 (atezo, ave, durva)
Ex-vivo expansion of patient T-cells
after receptor engineering and/or
selection.
Success stories:
● CAR T-cells for B-cell
malignancies (CD19, CD20,
CD22, BCMA)
Therapeutic vaccines against
specific tumor antigens, including
patient-specific mutated tumor
antigens.
Success stories:
● ???
● Hints of efficacy in neoantigen
vaccine trials
Anti-PD1 vs. chemotherapy in metastatic melanoma
11
Robert et al. Nivolumab in Previously Untreated Melanoma without BRAF Mutation. NEJM 2014
Combination checkpoint blockade in melanoma
12
Wolchok et al. Overall Survival with Combined Nivolumab and Ipilimumab in Advanced Melanoma. NEJM 2017
Combination checkpoint blockade in melanoma
13
Wolchok et al. Overall Survival with Combined Nivolumab and Ipilimumab in Advanced Melanoma. NEJM 2017
Additional
therapies needed
Cancer vaccines
● Elicit a new T cell response against tumor
antigens
● May also reinvigorate pre-existing
exhausted T cells
● Once tumor killing gets going, more T cell
can come along
14
Hu Z, Ott P, Wu C. Nature Reviews Immunology 2017
Tumor antigens
15
Jou et al. Clinical Cancer Research 2020
First generation shared antigen vaccines unsuccessful
16
Rosenberg et al. Cancer immunotherapy: moving beyond current vaccines. Nature Medicine 2004
Tumor antigens
17
Jou et al. Clinical Cancer Research 2020
Personalized vaccines
18
Ott et al. Nature 2017; Sahin et al Nature 2017
Talk Overview
1. Introduction to cancer vaccines
2. Introduction to MHC binding prediction
3. MHCflurry 2.0
19
Cytotoxic T cells can kill diseased cells
20
21
Cytotoxic T cells recognize peptides bound to MHC I
22
Cytotoxic T cells recognize peptides bound to MHC I
Only a minority of peptides are epitopes
23
T cell epitopes
T cell epitopes vary between people
24
T cell epitopes
Where’s the specificity and variability coming from?
25
MHC binding explains a lot
26
Specific interactions stabilize peptides with MHC
27
Khan et al. J. Immunol. 2000 [PDB: 1DUZ]
MHC genes are highly variable
28
MHC alleles
Different MHC alleles bind different peptides
29
MHC binding restricts the space of possible epitopes
30
Only about 5% of peptides bind to MHC
strongly enough to be presented.
Peptide binding to MHC can be measured in vitro
31
The binding preferences for hundreds of MHC alleles have been characterized using in vitro affinity
measurements
Mass spec is another source of MHC binding data
32
Purcell et al. Nature Protocols 2019
MHC binding can be predicted
33
MHC binding can be predicted
34
The most accurate predictors today are based on neural networks
Neural network
MHC binding can be predicted
35
Jurtz et al Journal of Immunology 2017
NetMHCpan 4.0
MHC binding prediction has been extremely successful
36
Talk Overview
1. Introduction to cancer vaccines
2. Introduction to MHC binding prediction
3. MHCflurry 2.0
37
How accurate are current predictors?
38
PPV
NetMHCpan 4.0 accuracy
39
Glioblastoma CLL Melanoma Ovarian
Shraibman et al. Mol. Cell Proteomics 2019 Sarkizova et al. Nature Biotechnology 2019
Glioblastoma
Can we do better?
Larger training datasets enable more sophisticated models
1. MHC binding prediction
2. Antigen processing prediction
40
Measurements
MHCflurry 2.0 pan-allele MHC binding predictor
41
O’Donnell et al. Cell Systems 2020
Motivation for peptide encoding
Binding predictor input encoding
42
O’Donnell et al. Cell Systems 2020
HLA-A*02:01
binding the 15-mer
peptide
FLNKDLEVDGHFVT
M
HLA-A*02:01
binding the 9-mer
peptide LLFGYPVYV
Binding predictor architecture
43
O’Donnell et al. Cell Systems 2020
Tricks
● Training loss: MSE with inequalities
● Pretrain on synthetic measurements from allele-
specific predictor (99 alleles)
● Random negatives to equalize number of non-
binder points for each peptide length per allele
● Early stopping
● Dropout after each dense layer (50%)
● Skip connections
● L1 regularization on dense layers
● Ensembles Training loss: MSE with inequalities
Mass spec hits are assigned “< 100nM”
Binding predictor shows improved accuracy (AUC)
44
MS-trained predictors outperform BA on PPV
45
MS trained
Antigen processing
46
Antigen processing
47
Proteasome
TAP
ERAP
Antigen processing model
48
TRAINING DATA
Presented peptides
detected by mass spec
Unobserved peptides
predicted to bind MHC
Training set generation for AP predictor
49
Consider only peptides
predicted to be top 2% in
binding affinity
Model learns to predict which
ones are actually detected in
MS experiments
AP predictor convolutional neural network
50
Intuition: MHC I ligands
must be cleaved at their
termini but not at interior
residues
AP predictor is surprisingly accurate
51
Modest correlation with BA predictions
52
Analysis of proteasome-cleaved peptides
53
Wolf-levy et al. Nature biotechnology 2018
Antigen processing motif
54
Enriched
Depleted
Antigen processing motif
55
Known bias:
Prefers C-terminal Y, F, L, R
Disfavors C-terminal D, E, N, S
Enriched
Depleted
Uebel et al PNAS 1997
TAP
Antigen processing motif
56
Cleaves after
● Chymotryptic: F, Y, L, W, but not G
● Tryptic: R, K
● Caspase: D, E
Enriched
Depleted
Nussbaum et al. 1998; Harris et al. 2001
Proteasome
Antigen processing motif
57
Known bias:
Unable to cleave the X-Proline bond. Can
trim until there is a P at the second
position
Enriched
Depleted
Serwold et al. Nature 2002
ERAP
Combining antigen processing and MHC binding
58
Logistic regression model: AP + BA
59
Train on MULTIALLELIC-OLD, evaluate on MULTIALLELIC-NEW
Combination model outperforms the others
60
Train on MULTIALLELIC-OLD, evaluate on MULTIALLELIC-NEW
Combination model outperforms the others
61
Train on MULTIALLELIC-OLD, evaluate on MULTIALLELIC-NEW
Neoantigen prediction
62
Robbins et al. Nature Medicine 2013, Tran et al. Science 2015, Gros et al. Nature Medicine 2016, Koşaloğlu-Yalçın et al. Oncoimmunology 2018
Steve Rosenberg group (NCI)
● 18 patients with melanoma or
gastrointestinal cancers
● 2,841 mutations screened
● 52 identified CD8+ T cell epitopes
Unbiased: mutations screened without
use of MHC binding prediction
Neoantigen results
63
Neoantigen results
64
Evaluation on viral epitopes
● Evaluation of CD8+ T cell epitopes
deposited in IEDB
● 1,380 epitopes + 527 non-epitopes
● Non-epitopes derive from the same proteins
as the epitopes and were assayed in the
same studies
● Surprisingly, MHCflurry 2.0 BA outperforms
MHCflurry 2.0 PS
● Suggests that to some extent the learned
antigen processing signals may be specific to
self proteins
65
Conclusions
● Larger training datasets and better modeling have enabled more accurate prediction of peptides
presented on MHC class I
● Antigen processing can be learned from MHC-presented peptides identified by mass spec. The
resulting predictors show agreement with the known biases of key processing steps
● Integration of antigen processing prediction with MHC binding can improve prediction of MHC-
presented peptides and tumor neoantigens
● Still significant room for improvement in CD8+ T cell epitope prediction
66
Future work
67
Sources of tumor T cell antigens
● Viral antigens
● Highly expressed genes in tumor cells (TAAs)
● Bacterial antigens
● Cancer-cell specific aberrations in...
○ The genome (mutation derived neoantigens)
○ Regulation of transcription (cancer testis antigens, endogenous retroviruses)
○ Splicing (intron retention, exon skipping)
○ RNA editing and RNA modifications
○ Translation (W-bumps)
○ Post translational modifications (phosphopeptides)
○ Antigen processing (?)
○ Metabolism (?)
○ … sensitivity to drugs that impact any of the above
68
Sources of tumor T cell antigens
● Viral antigens
● Highly expressed genes in tumor cells (TAAs)
● Bacterial antigens
● Cancer-cell specific aberrations in...
○ The genome (mutation derived neoantigens)
○ Regulation of transcription (cancer testis antigens, endogenous retroviruses)
○ Splicing (intron retention, exon skipping)
○ RNA editing and RNA modifications
○ Translation (W-bumps)
○ Post translational modifications (phosphopeptides)
○ Antigen processing (?)
○ Metabolism (?)
○ … sensitivity to drugs that impact any of the above
69
Predictors
needed
Emerging data identifies new candidate antigens
70
Reference Antigens Sequencing Mass spec
Griffin, …, Bernstein Nature 2021 Transposable elements (esp. LTR)
de-repressed by SETDB1 KO
RNA-seq, ATAC-seq MHC I MS, whole cell
lysate MS
Cuevas, …, Yewdell Cell Reports
2021
Novel isoforms, lncRNAs,
frameshifts
RNA-seq, ribo-seq MHC I MS, whole cell
lysate MS
Ouspenskaia, ... , Regev Biorxiv
2020
lncRNAs, pseudogenes, UTRs RNA-seq, ribo-seq MHC I MS
Chong, …, Bassani-Sternberg
Nature Communications 2020
lncRNAs, pseudogenes, UTRs,
TEs
WES, RNA-seq, sc-
RNA-seq, ribo-seq
MHC I and II MS
Laumont, …, Perreault Science
Translational Medicine 2018
lncRNAs, endogenous
retroelements
RNA-seq MHC I MS
Personalized tumor antigen detection from RNA-seq
Given tumor RNA-seq, identify candidate tumor specific antigens
71
Patient
RNA-seq
Database of tumor-
specific translation
products
Predicted
translated
peptides
Search
Vaccine prioritization
(MHC binding prediction,
expression levels)
Vaccine
Personalized tumor antigen detection from RNA-seq
Given tumor RNA-seq, identify candidate tumor specific antigens
72
Patient
RNA-seq
Database of tumor-
specific translation
products
Predicted
translated
peptides
Search
Vaccine prioritization
(MHC binding prediction,
expression levels)
Vaccine
Building the database is the main effort here
Experimenting with: logistic regression on RNA-seq k-mers
for each possible antigen to predict translation
Perspectives
● MHC binding prediction is reasonably well solved, T cell epitope prediction is not
● Immune monitoring from cancer vaccine studies will be useful to improve T cell epitope prediction
● Emerging high throughput readouts of TCR/pMHC interaction will eventually enable models of
TCR/pMHC binding
● For peptide vaccines, peptide pharmacokinetics likely has a huge impact on immunogenicity
● Other vaccine platforms such as mRNA will likely outperform peptide vaccines
● Casting a wider net for additional kinds of tumor antigens is likely to enable a new generation of
cancer vaccines - including semi-personalized vaccines
73
Thank you!
74
Nina Bhardwaj (Mount Sinai)
Alex Rubinsteyn (UNC Chapel Hill)
Julia Kodysh (Mount Sinai)
https://github.com/openvax/mhcflurry

More Related Content

What's hot

J Immunol-2008-Tagliani-3201-9
J Immunol-2008-Tagliani-3201-9J Immunol-2008-Tagliani-3201-9
J Immunol-2008-Tagliani-3201-9Federica Benvenuti
 
ICAAC 2013: Resumen
ICAAC 2013: ResumenICAAC 2013: Resumen
ICAAC 2013: Resumen
PROANTIBIOTICOS
 
Neoantigen vaccine creative peptides
Neoantigen vaccine creative peptidesNeoantigen vaccine creative peptides
Neoantigen vaccine creative peptides
Creative Peptides
 
ALETA CNS metastasis program 8 July 2020
ALETA CNS metastasis program 8 July 2020ALETA CNS metastasis program 8 July 2020
ALETA CNS metastasis program 8 July 2020
Paul D. Rennert
 
Prevalence of XMRV Nucleic Acid and Antibody in HIV-1 Infected Men and in Men...
Prevalence of XMRV Nucleic Acid and Antibody in HIV-1 Infected Men and in Men...Prevalence of XMRV Nucleic Acid and Antibody in HIV-1 Infected Men and in Men...
Prevalence of XMRV Nucleic Acid and Antibody in HIV-1 Infected Men and in Men...degarden
 
Evan Shegog Slide Presentation Sigma Xi Research Showcase 2014
Evan Shegog Slide Presentation Sigma Xi Research Showcase 2014 Evan Shegog Slide Presentation Sigma Xi Research Showcase 2014
Evan Shegog Slide Presentation Sigma Xi Research Showcase 2014
evanshegog
 
Present and future of oncolytic virus therapies
Present and future of oncolytic virus therapiesPresent and future of oncolytic virus therapies
Present and future of oncolytic virus therapies
Oncos Therapeutics
 
Use of Methylation Markers for Age Estimation of an unknown Individual based ...
Use of Methylation Markers for Age Estimation of an unknown Individual based ...Use of Methylation Markers for Age Estimation of an unknown Individual based ...
Use of Methylation Markers for Age Estimation of an unknown Individual based ...
QIAGEN
 
3768 rennert
3768 rennert3768 rennert
3768 rennert
Paul D. Rennert
 
Talimogene (T-VEC) : virotherapy in melanoma
Talimogene (T-VEC) : virotherapy in melanomaTalimogene (T-VEC) : virotherapy in melanoma
Talimogene (T-VEC) : virotherapy in melanoma
Lorenzo Alonso
 
Krug l.m.-et-al.-2010-cancer-immunology-immunotherapy
Krug l.m.-et-al.-2010-cancer-immunology-immunotherapyKrug l.m.-et-al.-2010-cancer-immunology-immunotherapy
Krug l.m.-et-al.-2010-cancer-immunology-immunotherapy
SellasCorp
 
2015 11 Inmunoterapia en nsclc
2015 11 Inmunoterapia en nsclc2015 11 Inmunoterapia en nsclc
2015 11 Inmunoterapia en nsclc
Martín Lázaro
 
Quiz (retroviruses)
Quiz (retroviruses)Quiz (retroviruses)
Quiz (retroviruses)
Yusri Arif Sapaee
 
Cavatak Oxford Virotherapy Symposium talk
Cavatak Oxford Virotherapy Symposium talkCavatak Oxford Virotherapy Symposium talk
Cavatak Oxford Virotherapy Symposium talk
Virotherapist
 
Pd 1 inhibitors (review and role in lymphoma)
Pd 1 inhibitors (review and role in lymphoma)Pd 1 inhibitors (review and role in lymphoma)
Pd 1 inhibitors (review and role in lymphoma)
Mary Ondinee Manalo Igot
 
Maslak p.g.-et-al.-2010-blood
Maslak p.g.-et-al.-2010-bloodMaslak p.g.-et-al.-2010-blood
Maslak p.g.-et-al.-2010-blood
SellasCorp
 
Oncolytic Virus Lecture
Oncolytic Virus LectureOncolytic Virus Lecture
Oncolytic Virus Lecturefondas vakalis
 
CAR-T Cell Therapy (Aliakbar Esfahani,Bsc of clinical laboratory sciences)
CAR-T Cell Therapy (Aliakbar Esfahani,Bsc of clinical laboratory sciences)CAR-T Cell Therapy (Aliakbar Esfahani,Bsc of clinical laboratory sciences)
CAR-T Cell Therapy (Aliakbar Esfahani,Bsc of clinical laboratory sciences)
Mashhad University of Medical Sciences
 

What's hot (20)

J Immunol-2008-Tagliani-3201-9
J Immunol-2008-Tagliani-3201-9J Immunol-2008-Tagliani-3201-9
J Immunol-2008-Tagliani-3201-9
 
ICAAC 2013: Resumen
ICAAC 2013: ResumenICAAC 2013: Resumen
ICAAC 2013: Resumen
 
Neoantigen vaccine creative peptides
Neoantigen vaccine creative peptidesNeoantigen vaccine creative peptides
Neoantigen vaccine creative peptides
 
ALETA CNS metastasis program 8 July 2020
ALETA CNS metastasis program 8 July 2020ALETA CNS metastasis program 8 July 2020
ALETA CNS metastasis program 8 July 2020
 
paper
paperpaper
paper
 
Prevalence of XMRV Nucleic Acid and Antibody in HIV-1 Infected Men and in Men...
Prevalence of XMRV Nucleic Acid and Antibody in HIV-1 Infected Men and in Men...Prevalence of XMRV Nucleic Acid and Antibody in HIV-1 Infected Men and in Men...
Prevalence of XMRV Nucleic Acid and Antibody in HIV-1 Infected Men and in Men...
 
Evan Shegog Slide Presentation Sigma Xi Research Showcase 2014
Evan Shegog Slide Presentation Sigma Xi Research Showcase 2014 Evan Shegog Slide Presentation Sigma Xi Research Showcase 2014
Evan Shegog Slide Presentation Sigma Xi Research Showcase 2014
 
Present and future of oncolytic virus therapies
Present and future of oncolytic virus therapiesPresent and future of oncolytic virus therapies
Present and future of oncolytic virus therapies
 
Use of Methylation Markers for Age Estimation of an unknown Individual based ...
Use of Methylation Markers for Age Estimation of an unknown Individual based ...Use of Methylation Markers for Age Estimation of an unknown Individual based ...
Use of Methylation Markers for Age Estimation of an unknown Individual based ...
 
3768 rennert
3768 rennert3768 rennert
3768 rennert
 
Talimogene (T-VEC) : virotherapy in melanoma
Talimogene (T-VEC) : virotherapy in melanomaTalimogene (T-VEC) : virotherapy in melanoma
Talimogene (T-VEC) : virotherapy in melanoma
 
Krug l.m.-et-al.-2010-cancer-immunology-immunotherapy
Krug l.m.-et-al.-2010-cancer-immunology-immunotherapyKrug l.m.-et-al.-2010-cancer-immunology-immunotherapy
Krug l.m.-et-al.-2010-cancer-immunology-immunotherapy
 
1475-2875-11-231
1475-2875-11-2311475-2875-11-231
1475-2875-11-231
 
2015 11 Inmunoterapia en nsclc
2015 11 Inmunoterapia en nsclc2015 11 Inmunoterapia en nsclc
2015 11 Inmunoterapia en nsclc
 
Quiz (retroviruses)
Quiz (retroviruses)Quiz (retroviruses)
Quiz (retroviruses)
 
Cavatak Oxford Virotherapy Symposium talk
Cavatak Oxford Virotherapy Symposium talkCavatak Oxford Virotherapy Symposium talk
Cavatak Oxford Virotherapy Symposium talk
 
Pd 1 inhibitors (review and role in lymphoma)
Pd 1 inhibitors (review and role in lymphoma)Pd 1 inhibitors (review and role in lymphoma)
Pd 1 inhibitors (review and role in lymphoma)
 
Maslak p.g.-et-al.-2010-blood
Maslak p.g.-et-al.-2010-bloodMaslak p.g.-et-al.-2010-blood
Maslak p.g.-et-al.-2010-blood
 
Oncolytic Virus Lecture
Oncolytic Virus LectureOncolytic Virus Lecture
Oncolytic Virus Lecture
 
CAR-T Cell Therapy (Aliakbar Esfahani,Bsc of clinical laboratory sciences)
CAR-T Cell Therapy (Aliakbar Esfahani,Bsc of clinical laboratory sciences)CAR-T Cell Therapy (Aliakbar Esfahani,Bsc of clinical laboratory sciences)
CAR-T Cell Therapy (Aliakbar Esfahani,Bsc of clinical laboratory sciences)
 

Similar to Therapeutic Cancer Vaccines: Where Predictive Models Matter

Data Science Salon: Machine Learning for Personalized Cancer Vaccines
Data Science Salon: Machine Learning for Personalized Cancer VaccinesData Science Salon: Machine Learning for Personalized Cancer Vaccines
Data Science Salon: Machine Learning for Personalized Cancer Vaccines
Formulatedby
 
Principles of cancer immunotherapy
Principles of cancer immunotherapyPrinciples of cancer immunotherapy
Principles of cancer immunotherapy
Ihor Arkhypov
 
Emerging Biomarkers, New Targets, and Rational Combinations: Are We on the Ve...
Emerging Biomarkers, New Targets, and Rational Combinations: Are We on the Ve...Emerging Biomarkers, New Targets, and Rational Combinations: Are We on the Ve...
Emerging Biomarkers, New Targets, and Rational Combinations: Are We on the Ve...
PVI, PeerView Institute for Medical Education
 
Integrative analysis of medical imaging and omics
Integrative analysis of medical imaging and omicsIntegrative analysis of medical imaging and omics
Integrative analysis of medical imaging and omics
Hongyoon Choi
 
Gene therapy for the treatmen of cancer
Gene therapy for the treatmen of cancerGene therapy for the treatmen of cancer
Gene therapy for the treatmen of cancer
grachea aeryndhien
 
Keeping Up With Advances in Cancer Immunotherapy and Biomarker Testing: Impli...
Keeping Up With Advances in Cancer Immunotherapy and Biomarker Testing: Impli...Keeping Up With Advances in Cancer Immunotherapy and Biomarker Testing: Impli...
Keeping Up With Advances in Cancer Immunotherapy and Biomarker Testing: Impli...
PVI, PeerView Institute for Medical Education
 
Cancer Immunogenomics
Cancer ImmunogenomicsCancer Immunogenomics
Cancer Immunogenomics
Thi K. Tran-Nguyen, PhD
 
JC_ frequency and prognostic impact of CD81 in multiple myeloma
JC_ frequency and prognostic impact of CD81 in multiple myelomaJC_ frequency and prognostic impact of CD81 in multiple myeloma
JC_ frequency and prognostic impact of CD81 in multiple myeloma
AIIMS
 
Provenge (sipuleucel t)
Provenge (sipuleucel t)Provenge (sipuleucel t)
Provenge (sipuleucel t)Vinblast
 
Provenge (Sipuleucel T)
Provenge (Sipuleucel T)Provenge (Sipuleucel T)
Provenge (Sipuleucel T)Cytokinine
 
Io combos and the big stick
Io combos and the big stick Io combos and the big stick
Io combos and the big stick
Paul D. Rennert
 
Proteogenomic analysis of human colon cancer reveals new therapeutic opportun...
Proteogenomic analysis of human colon cancer reveals new therapeutic opportun...Proteogenomic analysis of human colon cancer reveals new therapeutic opportun...
Proteogenomic analysis of human colon cancer reveals new therapeutic opportun...
Gul Muneer
 
Engineered T Cell Therapy for Gynecologic Malignancies Challenges and Opportu...
Engineered T Cell Therapy for
Gynecologic Malignancies
Challenges and Opportu...Engineered T Cell Therapy for
Gynecologic Malignancies
Challenges and Opportu...
Engineered T Cell Therapy for Gynecologic Malignancies Challenges and Opportu...
RudrikaChandra1
 
5th annual peptides congress 2018
5th annual peptides congress 20185th annual peptides congress 2018
5th annual peptides congress 2018
targovax2017
 
Epitope base editing CD45 in hematopoietic cells enables universal blood canc...
Epitope base editing CD45 in hematopoietic cells enables universal blood canc...Epitope base editing CD45 in hematopoietic cells enables universal blood canc...
Epitope base editing CD45 in hematopoietic cells enables universal blood canc...
Rajendra Gajula
 
Dendritic Vaccines Glioma 2016
Dendritic Vaccines Glioma 2016Dendritic Vaccines Glioma 2016
Dendritic Vaccines Glioma 2016
NeuroAcademy
 
Cellular Therapy for multiple myeloma
Cellular Therapy for multiple myelomaCellular Therapy for multiple myeloma
Cellular Therapy for multiple myeloma
spa718
 
ESMO-2022-Reck-Presentation_0.pptx
ESMO-2022-Reck-Presentation_0.pptxESMO-2022-Reck-Presentation_0.pptx
ESMO-2022-Reck-Presentation_0.pptx
Mrc Mrc
 

Similar to Therapeutic Cancer Vaccines: Where Predictive Models Matter (20)

Data Science Salon: Machine Learning for Personalized Cancer Vaccines
Data Science Salon: Machine Learning for Personalized Cancer VaccinesData Science Salon: Machine Learning for Personalized Cancer Vaccines
Data Science Salon: Machine Learning for Personalized Cancer Vaccines
 
Poster021808
Poster021808Poster021808
Poster021808
 
Principles of cancer immunotherapy
Principles of cancer immunotherapyPrinciples of cancer immunotherapy
Principles of cancer immunotherapy
 
Emerging Biomarkers, New Targets, and Rational Combinations: Are We on the Ve...
Emerging Biomarkers, New Targets, and Rational Combinations: Are We on the Ve...Emerging Biomarkers, New Targets, and Rational Combinations: Are We on the Ve...
Emerging Biomarkers, New Targets, and Rational Combinations: Are We on the Ve...
 
Integrative analysis of medical imaging and omics
Integrative analysis of medical imaging and omicsIntegrative analysis of medical imaging and omics
Integrative analysis of medical imaging and omics
 
Gene therapy for the treatmen of cancer
Gene therapy for the treatmen of cancerGene therapy for the treatmen of cancer
Gene therapy for the treatmen of cancer
 
Keeping Up With Advances in Cancer Immunotherapy and Biomarker Testing: Impli...
Keeping Up With Advances in Cancer Immunotherapy and Biomarker Testing: Impli...Keeping Up With Advances in Cancer Immunotherapy and Biomarker Testing: Impli...
Keeping Up With Advances in Cancer Immunotherapy and Biomarker Testing: Impli...
 
Cancer Immunogenomics
Cancer ImmunogenomicsCancer Immunogenomics
Cancer Immunogenomics
 
JC_ frequency and prognostic impact of CD81 in multiple myeloma
JC_ frequency and prognostic impact of CD81 in multiple myelomaJC_ frequency and prognostic impact of CD81 in multiple myeloma
JC_ frequency and prognostic impact of CD81 in multiple myeloma
 
Provenge (sipuleucel t)
Provenge (sipuleucel t)Provenge (sipuleucel t)
Provenge (sipuleucel t)
 
Provenge (Sipuleucel T)
Provenge (Sipuleucel T)Provenge (Sipuleucel T)
Provenge (Sipuleucel T)
 
Io combos and the big stick
Io combos and the big stick Io combos and the big stick
Io combos and the big stick
 
Proteogenomic analysis of human colon cancer reveals new therapeutic opportun...
Proteogenomic analysis of human colon cancer reveals new therapeutic opportun...Proteogenomic analysis of human colon cancer reveals new therapeutic opportun...
Proteogenomic analysis of human colon cancer reveals new therapeutic opportun...
 
Engineered T Cell Therapy for Gynecologic Malignancies Challenges and Opportu...
Engineered T Cell Therapy for
Gynecologic Malignancies
Challenges and Opportu...Engineered T Cell Therapy for
Gynecologic Malignancies
Challenges and Opportu...
Engineered T Cell Therapy for Gynecologic Malignancies Challenges and Opportu...
 
5th annual peptides congress 2018
5th annual peptides congress 20185th annual peptides congress 2018
5th annual peptides congress 2018
 
Epitope base editing CD45 in hematopoietic cells enables universal blood canc...
Epitope base editing CD45 in hematopoietic cells enables universal blood canc...Epitope base editing CD45 in hematopoietic cells enables universal blood canc...
Epitope base editing CD45 in hematopoietic cells enables universal blood canc...
 
Dendritic Vaccines Glioma 2016
Dendritic Vaccines Glioma 2016Dendritic Vaccines Glioma 2016
Dendritic Vaccines Glioma 2016
 
Cellular Therapy for multiple myeloma
Cellular Therapy for multiple myelomaCellular Therapy for multiple myeloma
Cellular Therapy for multiple myeloma
 
ESMO-2022-Reck-Presentation_0.pptx
ESMO-2022-Reck-Presentation_0.pptxESMO-2022-Reck-Presentation_0.pptx
ESMO-2022-Reck-Presentation_0.pptx
 
nature19764
nature19764nature19764
nature19764
 

Recently uploaded

Body fluids_tonicity_dehydration_hypovolemia_hypervolemia.pptx
Body fluids_tonicity_dehydration_hypovolemia_hypervolemia.pptxBody fluids_tonicity_dehydration_hypovolemia_hypervolemia.pptx
Body fluids_tonicity_dehydration_hypovolemia_hypervolemia.pptx
muralinath2
 
NuGOweek 2024 Ghent - programme - final version
NuGOweek 2024 Ghent - programme - final versionNuGOweek 2024 Ghent - programme - final version
NuGOweek 2024 Ghent - programme - final version
pablovgd
 
Cancer cell metabolism: special Reference to Lactate Pathway
Cancer cell metabolism: special Reference to Lactate PathwayCancer cell metabolism: special Reference to Lactate Pathway
Cancer cell metabolism: special Reference to Lactate Pathway
AADYARAJPANDEY1
 
Structural Classification Of Protein (SCOP)
Structural Classification Of Protein  (SCOP)Structural Classification Of Protein  (SCOP)
Structural Classification Of Protein (SCOP)
aishnasrivastava
 
Structures and textures of metamorphic rocks
Structures and textures of metamorphic rocksStructures and textures of metamorphic rocks
Structures and textures of metamorphic rocks
kumarmathi863
 
In silico drugs analogue design: novobiocin analogues.pptx
In silico drugs analogue design: novobiocin analogues.pptxIn silico drugs analogue design: novobiocin analogues.pptx
In silico drugs analogue design: novobiocin analogues.pptx
AlaminAfendy1
 
Mammalian Pineal Body Structure and Also Functions
Mammalian Pineal Body Structure and Also FunctionsMammalian Pineal Body Structure and Also Functions
Mammalian Pineal Body Structure and Also Functions
YOGESH DOGRA
 
insect morphology and physiology of insect
insect morphology and physiology of insectinsect morphology and physiology of insect
insect morphology and physiology of insect
anitaento25
 
Penicillin...........................pptx
Penicillin...........................pptxPenicillin...........................pptx
Penicillin...........................pptx
Cherry
 
Richard's aventures in two entangled wonderlands
Richard's aventures in two entangled wonderlandsRichard's aventures in two entangled wonderlands
Richard's aventures in two entangled wonderlands
Richard Gill
 
Multi-source connectivity as the driver of solar wind variability in the heli...
Multi-source connectivity as the driver of solar wind variability in the heli...Multi-source connectivity as the driver of solar wind variability in the heli...
Multi-source connectivity as the driver of solar wind variability in the heli...
Sérgio Sacani
 
FAIR & AI Ready KGs for Explainable Predictions
FAIR & AI Ready KGs for Explainable PredictionsFAIR & AI Ready KGs for Explainable Predictions
FAIR & AI Ready KGs for Explainable Predictions
Michel Dumontier
 
Earliest Galaxies in the JADES Origins Field: Luminosity Function and Cosmic ...
Earliest Galaxies in the JADES Origins Field: Luminosity Function and Cosmic ...Earliest Galaxies in the JADES Origins Field: Luminosity Function and Cosmic ...
Earliest Galaxies in the JADES Origins Field: Luminosity Function and Cosmic ...
Sérgio Sacani
 
platelets- lifespan -Clot retraction-disorders.pptx
platelets- lifespan -Clot retraction-disorders.pptxplatelets- lifespan -Clot retraction-disorders.pptx
platelets- lifespan -Clot retraction-disorders.pptx
muralinath2
 
Richard's entangled aventures in wonderland
Richard's entangled aventures in wonderlandRichard's entangled aventures in wonderland
Richard's entangled aventures in wonderland
Richard Gill
 
Seminar of U.V. Spectroscopy by SAMIR PANDA
 Seminar of U.V. Spectroscopy by SAMIR PANDA Seminar of U.V. Spectroscopy by SAMIR PANDA
Seminar of U.V. Spectroscopy by SAMIR PANDA
SAMIR PANDA
 
erythropoiesis-I_mechanism& clinical significance.pptx
erythropoiesis-I_mechanism& clinical significance.pptxerythropoiesis-I_mechanism& clinical significance.pptx
erythropoiesis-I_mechanism& clinical significance.pptx
muralinath2
 
Citrus Greening Disease and its Management
Citrus Greening Disease and its ManagementCitrus Greening Disease and its Management
Citrus Greening Disease and its Management
subedisuryaofficial
 
RNA INTERFERENCE: UNRAVELING GENETIC SILENCING
RNA INTERFERENCE: UNRAVELING GENETIC SILENCINGRNA INTERFERENCE: UNRAVELING GENETIC SILENCING
RNA INTERFERENCE: UNRAVELING GENETIC SILENCING
AADYARAJPANDEY1
 
EY - Supply Chain Services 2018_template.pptx
EY - Supply Chain Services 2018_template.pptxEY - Supply Chain Services 2018_template.pptx
EY - Supply Chain Services 2018_template.pptx
AlguinaldoKong
 

Recently uploaded (20)

Body fluids_tonicity_dehydration_hypovolemia_hypervolemia.pptx
Body fluids_tonicity_dehydration_hypovolemia_hypervolemia.pptxBody fluids_tonicity_dehydration_hypovolemia_hypervolemia.pptx
Body fluids_tonicity_dehydration_hypovolemia_hypervolemia.pptx
 
NuGOweek 2024 Ghent - programme - final version
NuGOweek 2024 Ghent - programme - final versionNuGOweek 2024 Ghent - programme - final version
NuGOweek 2024 Ghent - programme - final version
 
Cancer cell metabolism: special Reference to Lactate Pathway
Cancer cell metabolism: special Reference to Lactate PathwayCancer cell metabolism: special Reference to Lactate Pathway
Cancer cell metabolism: special Reference to Lactate Pathway
 
Structural Classification Of Protein (SCOP)
Structural Classification Of Protein  (SCOP)Structural Classification Of Protein  (SCOP)
Structural Classification Of Protein (SCOP)
 
Structures and textures of metamorphic rocks
Structures and textures of metamorphic rocksStructures and textures of metamorphic rocks
Structures and textures of metamorphic rocks
 
In silico drugs analogue design: novobiocin analogues.pptx
In silico drugs analogue design: novobiocin analogues.pptxIn silico drugs analogue design: novobiocin analogues.pptx
In silico drugs analogue design: novobiocin analogues.pptx
 
Mammalian Pineal Body Structure and Also Functions
Mammalian Pineal Body Structure and Also FunctionsMammalian Pineal Body Structure and Also Functions
Mammalian Pineal Body Structure and Also Functions
 
insect morphology and physiology of insect
insect morphology and physiology of insectinsect morphology and physiology of insect
insect morphology and physiology of insect
 
Penicillin...........................pptx
Penicillin...........................pptxPenicillin...........................pptx
Penicillin...........................pptx
 
Richard's aventures in two entangled wonderlands
Richard's aventures in two entangled wonderlandsRichard's aventures in two entangled wonderlands
Richard's aventures in two entangled wonderlands
 
Multi-source connectivity as the driver of solar wind variability in the heli...
Multi-source connectivity as the driver of solar wind variability in the heli...Multi-source connectivity as the driver of solar wind variability in the heli...
Multi-source connectivity as the driver of solar wind variability in the heli...
 
FAIR & AI Ready KGs for Explainable Predictions
FAIR & AI Ready KGs for Explainable PredictionsFAIR & AI Ready KGs for Explainable Predictions
FAIR & AI Ready KGs for Explainable Predictions
 
Earliest Galaxies in the JADES Origins Field: Luminosity Function and Cosmic ...
Earliest Galaxies in the JADES Origins Field: Luminosity Function and Cosmic ...Earliest Galaxies in the JADES Origins Field: Luminosity Function and Cosmic ...
Earliest Galaxies in the JADES Origins Field: Luminosity Function and Cosmic ...
 
platelets- lifespan -Clot retraction-disorders.pptx
platelets- lifespan -Clot retraction-disorders.pptxplatelets- lifespan -Clot retraction-disorders.pptx
platelets- lifespan -Clot retraction-disorders.pptx
 
Richard's entangled aventures in wonderland
Richard's entangled aventures in wonderlandRichard's entangled aventures in wonderland
Richard's entangled aventures in wonderland
 
Seminar of U.V. Spectroscopy by SAMIR PANDA
 Seminar of U.V. Spectroscopy by SAMIR PANDA Seminar of U.V. Spectroscopy by SAMIR PANDA
Seminar of U.V. Spectroscopy by SAMIR PANDA
 
erythropoiesis-I_mechanism& clinical significance.pptx
erythropoiesis-I_mechanism& clinical significance.pptxerythropoiesis-I_mechanism& clinical significance.pptx
erythropoiesis-I_mechanism& clinical significance.pptx
 
Citrus Greening Disease and its Management
Citrus Greening Disease and its ManagementCitrus Greening Disease and its Management
Citrus Greening Disease and its Management
 
RNA INTERFERENCE: UNRAVELING GENETIC SILENCING
RNA INTERFERENCE: UNRAVELING GENETIC SILENCINGRNA INTERFERENCE: UNRAVELING GENETIC SILENCING
RNA INTERFERENCE: UNRAVELING GENETIC SILENCING
 
EY - Supply Chain Services 2018_template.pptx
EY - Supply Chain Services 2018_template.pptxEY - Supply Chain Services 2018_template.pptx
EY - Supply Chain Services 2018_template.pptx
 

Therapeutic Cancer Vaccines: Where Predictive Models Matter

  • 1. Therapeutic Cancer Vaccines: Where Predictive Models Matter Tim O’Donnell NEC Laboratories Europe GmbH Oct 15, 2021 1
  • 2. The OpenVax Project ● Clinical Trials: help run personalized cancer vaccine trials at Mount Sinai ● Software: open source tools for cancer genomics and neoantigen prediction ○ www.github.com/openvax/ ● Research: improve methods for predicting the immune response to tumor antigens 2 Tim O’Donnell Mount Sinai Julia Kodysh Mount Sinai Alex Rubinsteyn UNC Chapel Hill Nina Bhardwaj Mount Sinai
  • 3. Talk Overview 1. Introduction to cancer vaccines 2. Introduction to MHC binding prediction 3. MHCflurry 2.0 3
  • 4. Talk Overview 1. Introduction to cancer vaccines 2. Introduction to MHC binding prediction 3. MHCflurry 2.0 4
  • 5. Two arms of adaptive immunity 5
  • 6. Two arms of adaptive immunity 6
  • 7. Cytotoxic T cells can kill diseased cells 7
  • 8. Cytotoxic T cells can kill diseased cells 8
  • 9. Short history of cancer immunotherapy 9 Alex Rubinsteyn 20th century Dark Age of radiation and chemotherapy 1850s-1890s Infection & fever => tumor regression? 1893 Coley’s Toxins (complete response in ~10% of sarcomas) 2010s ~20 approved cancer immunotherapies
  • 10. Cancer immunotherapy 10 Alex Rubinsteyn Checkpoint blockade Cellular therapies Vaccines Disinhibit T-cells. Antigens responsible for tumor clearance typically unknown. Success stories: ● 𝛂CTLA-4 (ipi) ● 𝛂PD-1 (pembro, nivo, cemi) ● 𝛂PD-L1 (atezo, ave, durva) Ex-vivo expansion of patient T-cells after receptor engineering and/or selection. Success stories: ● CAR T-cells for B-cell malignancies (CD19, CD20, CD22, BCMA) Therapeutic vaccines against specific tumor antigens, including patient-specific mutated tumor antigens. Success stories: ● ??? ● Hints of efficacy in neoantigen vaccine trials
  • 11. Anti-PD1 vs. chemotherapy in metastatic melanoma 11 Robert et al. Nivolumab in Previously Untreated Melanoma without BRAF Mutation. NEJM 2014
  • 12. Combination checkpoint blockade in melanoma 12 Wolchok et al. Overall Survival with Combined Nivolumab and Ipilimumab in Advanced Melanoma. NEJM 2017
  • 13. Combination checkpoint blockade in melanoma 13 Wolchok et al. Overall Survival with Combined Nivolumab and Ipilimumab in Advanced Melanoma. NEJM 2017 Additional therapies needed
  • 14. Cancer vaccines ● Elicit a new T cell response against tumor antigens ● May also reinvigorate pre-existing exhausted T cells ● Once tumor killing gets going, more T cell can come along 14 Hu Z, Ott P, Wu C. Nature Reviews Immunology 2017
  • 15. Tumor antigens 15 Jou et al. Clinical Cancer Research 2020
  • 16. First generation shared antigen vaccines unsuccessful 16 Rosenberg et al. Cancer immunotherapy: moving beyond current vaccines. Nature Medicine 2004
  • 17. Tumor antigens 17 Jou et al. Clinical Cancer Research 2020
  • 18. Personalized vaccines 18 Ott et al. Nature 2017; Sahin et al Nature 2017
  • 19. Talk Overview 1. Introduction to cancer vaccines 2. Introduction to MHC binding prediction 3. MHCflurry 2.0 19
  • 20. Cytotoxic T cells can kill diseased cells 20
  • 21. 21 Cytotoxic T cells recognize peptides bound to MHC I
  • 22. 22 Cytotoxic T cells recognize peptides bound to MHC I
  • 23. Only a minority of peptides are epitopes 23 T cell epitopes
  • 24. T cell epitopes vary between people 24 T cell epitopes
  • 25. Where’s the specificity and variability coming from? 25
  • 27. Specific interactions stabilize peptides with MHC 27 Khan et al. J. Immunol. 2000 [PDB: 1DUZ]
  • 28. MHC genes are highly variable 28 MHC alleles
  • 29. Different MHC alleles bind different peptides 29
  • 30. MHC binding restricts the space of possible epitopes 30 Only about 5% of peptides bind to MHC strongly enough to be presented.
  • 31. Peptide binding to MHC can be measured in vitro 31 The binding preferences for hundreds of MHC alleles have been characterized using in vitro affinity measurements
  • 32. Mass spec is another source of MHC binding data 32 Purcell et al. Nature Protocols 2019
  • 33. MHC binding can be predicted 33
  • 34. MHC binding can be predicted 34 The most accurate predictors today are based on neural networks Neural network
  • 35. MHC binding can be predicted 35 Jurtz et al Journal of Immunology 2017 NetMHCpan 4.0
  • 36. MHC binding prediction has been extremely successful 36
  • 37. Talk Overview 1. Introduction to cancer vaccines 2. Introduction to MHC binding prediction 3. MHCflurry 2.0 37
  • 38. How accurate are current predictors? 38 PPV
  • 39. NetMHCpan 4.0 accuracy 39 Glioblastoma CLL Melanoma Ovarian Shraibman et al. Mol. Cell Proteomics 2019 Sarkizova et al. Nature Biotechnology 2019 Glioblastoma
  • 40. Can we do better? Larger training datasets enable more sophisticated models 1. MHC binding prediction 2. Antigen processing prediction 40 Measurements
  • 41. MHCflurry 2.0 pan-allele MHC binding predictor 41 O’Donnell et al. Cell Systems 2020
  • 42. Motivation for peptide encoding Binding predictor input encoding 42 O’Donnell et al. Cell Systems 2020 HLA-A*02:01 binding the 15-mer peptide FLNKDLEVDGHFVT M HLA-A*02:01 binding the 9-mer peptide LLFGYPVYV
  • 43. Binding predictor architecture 43 O’Donnell et al. Cell Systems 2020 Tricks ● Training loss: MSE with inequalities ● Pretrain on synthetic measurements from allele- specific predictor (99 alleles) ● Random negatives to equalize number of non- binder points for each peptide length per allele ● Early stopping ● Dropout after each dense layer (50%) ● Skip connections ● L1 regularization on dense layers ● Ensembles Training loss: MSE with inequalities Mass spec hits are assigned “< 100nM”
  • 44. Binding predictor shows improved accuracy (AUC) 44
  • 45. MS-trained predictors outperform BA on PPV 45 MS trained
  • 48. Antigen processing model 48 TRAINING DATA Presented peptides detected by mass spec Unobserved peptides predicted to bind MHC
  • 49. Training set generation for AP predictor 49 Consider only peptides predicted to be top 2% in binding affinity Model learns to predict which ones are actually detected in MS experiments
  • 50. AP predictor convolutional neural network 50 Intuition: MHC I ligands must be cleaved at their termini but not at interior residues
  • 51. AP predictor is surprisingly accurate 51
  • 52. Modest correlation with BA predictions 52
  • 53. Analysis of proteasome-cleaved peptides 53 Wolf-levy et al. Nature biotechnology 2018
  • 55. Antigen processing motif 55 Known bias: Prefers C-terminal Y, F, L, R Disfavors C-terminal D, E, N, S Enriched Depleted Uebel et al PNAS 1997 TAP
  • 56. Antigen processing motif 56 Cleaves after ● Chymotryptic: F, Y, L, W, but not G ● Tryptic: R, K ● Caspase: D, E Enriched Depleted Nussbaum et al. 1998; Harris et al. 2001 Proteasome
  • 57. Antigen processing motif 57 Known bias: Unable to cleave the X-Proline bond. Can trim until there is a P at the second position Enriched Depleted Serwold et al. Nature 2002 ERAP
  • 58. Combining antigen processing and MHC binding 58
  • 59. Logistic regression model: AP + BA 59 Train on MULTIALLELIC-OLD, evaluate on MULTIALLELIC-NEW
  • 60. Combination model outperforms the others 60 Train on MULTIALLELIC-OLD, evaluate on MULTIALLELIC-NEW
  • 61. Combination model outperforms the others 61 Train on MULTIALLELIC-OLD, evaluate on MULTIALLELIC-NEW
  • 62. Neoantigen prediction 62 Robbins et al. Nature Medicine 2013, Tran et al. Science 2015, Gros et al. Nature Medicine 2016, Koşaloğlu-Yalçın et al. Oncoimmunology 2018 Steve Rosenberg group (NCI) ● 18 patients with melanoma or gastrointestinal cancers ● 2,841 mutations screened ● 52 identified CD8+ T cell epitopes Unbiased: mutations screened without use of MHC binding prediction
  • 65. Evaluation on viral epitopes ● Evaluation of CD8+ T cell epitopes deposited in IEDB ● 1,380 epitopes + 527 non-epitopes ● Non-epitopes derive from the same proteins as the epitopes and were assayed in the same studies ● Surprisingly, MHCflurry 2.0 BA outperforms MHCflurry 2.0 PS ● Suggests that to some extent the learned antigen processing signals may be specific to self proteins 65
  • 66. Conclusions ● Larger training datasets and better modeling have enabled more accurate prediction of peptides presented on MHC class I ● Antigen processing can be learned from MHC-presented peptides identified by mass spec. The resulting predictors show agreement with the known biases of key processing steps ● Integration of antigen processing prediction with MHC binding can improve prediction of MHC- presented peptides and tumor neoantigens ● Still significant room for improvement in CD8+ T cell epitope prediction 66
  • 68. Sources of tumor T cell antigens ● Viral antigens ● Highly expressed genes in tumor cells (TAAs) ● Bacterial antigens ● Cancer-cell specific aberrations in... ○ The genome (mutation derived neoantigens) ○ Regulation of transcription (cancer testis antigens, endogenous retroviruses) ○ Splicing (intron retention, exon skipping) ○ RNA editing and RNA modifications ○ Translation (W-bumps) ○ Post translational modifications (phosphopeptides) ○ Antigen processing (?) ○ Metabolism (?) ○ … sensitivity to drugs that impact any of the above 68
  • 69. Sources of tumor T cell antigens ● Viral antigens ● Highly expressed genes in tumor cells (TAAs) ● Bacterial antigens ● Cancer-cell specific aberrations in... ○ The genome (mutation derived neoantigens) ○ Regulation of transcription (cancer testis antigens, endogenous retroviruses) ○ Splicing (intron retention, exon skipping) ○ RNA editing and RNA modifications ○ Translation (W-bumps) ○ Post translational modifications (phosphopeptides) ○ Antigen processing (?) ○ Metabolism (?) ○ … sensitivity to drugs that impact any of the above 69 Predictors needed
  • 70. Emerging data identifies new candidate antigens 70 Reference Antigens Sequencing Mass spec Griffin, …, Bernstein Nature 2021 Transposable elements (esp. LTR) de-repressed by SETDB1 KO RNA-seq, ATAC-seq MHC I MS, whole cell lysate MS Cuevas, …, Yewdell Cell Reports 2021 Novel isoforms, lncRNAs, frameshifts RNA-seq, ribo-seq MHC I MS, whole cell lysate MS Ouspenskaia, ... , Regev Biorxiv 2020 lncRNAs, pseudogenes, UTRs RNA-seq, ribo-seq MHC I MS Chong, …, Bassani-Sternberg Nature Communications 2020 lncRNAs, pseudogenes, UTRs, TEs WES, RNA-seq, sc- RNA-seq, ribo-seq MHC I and II MS Laumont, …, Perreault Science Translational Medicine 2018 lncRNAs, endogenous retroelements RNA-seq MHC I MS
  • 71. Personalized tumor antigen detection from RNA-seq Given tumor RNA-seq, identify candidate tumor specific antigens 71 Patient RNA-seq Database of tumor- specific translation products Predicted translated peptides Search Vaccine prioritization (MHC binding prediction, expression levels) Vaccine
  • 72. Personalized tumor antigen detection from RNA-seq Given tumor RNA-seq, identify candidate tumor specific antigens 72 Patient RNA-seq Database of tumor- specific translation products Predicted translated peptides Search Vaccine prioritization (MHC binding prediction, expression levels) Vaccine Building the database is the main effort here Experimenting with: logistic regression on RNA-seq k-mers for each possible antigen to predict translation
  • 73. Perspectives ● MHC binding prediction is reasonably well solved, T cell epitope prediction is not ● Immune monitoring from cancer vaccine studies will be useful to improve T cell epitope prediction ● Emerging high throughput readouts of TCR/pMHC interaction will eventually enable models of TCR/pMHC binding ● For peptide vaccines, peptide pharmacokinetics likely has a huge impact on immunogenicity ● Other vaccine platforms such as mRNA will likely outperform peptide vaccines ● Casting a wider net for additional kinds of tumor antigens is likely to enable a new generation of cancer vaccines - including semi-personalized vaccines 73
  • 74. Thank you! 74 Nina Bhardwaj (Mount Sinai) Alex Rubinsteyn (UNC Chapel Hill) Julia Kodysh (Mount Sinai) https://github.com/openvax/mhcflurry

Editor's Notes

  1. Not always feasible to perform these experiments
  2. Not always feasible to perform these experiments
  3. Not always feasible to perform these experiments