Document text
Principal Investigator: Jeniffer Bertha Hernandez
Organization: KECK GRADUATE INST OF APPLIED LIFE SCIS
Fiscal Year: 2023
Award: $1,219,945
Funding agency: National Institute of Allergy and Infectious Diseases
ABSTRACT
One of the “holy grails” in immunology is to be able to directly predict tight-binding variable chain antibody
sequences in silico against foreign or non-self `antigenic' proteins. Immunoglobulin chain rearrangement can
potentially encode approximately 1016 different variants of antibody heavy and light chain sequences. However,
only a small fraction of the sequence space is generally accessed for evolving antibodies against foreign proteins.
The computational challenge is to go from a model of the structure of an antigen to predicting a set of antibody
chain sequences that can bind tightly to the antigen. If solved, it might be possible to move in less than 24 hours
from the first cryo-electron-microscopic structure of a novel viral protein to advance a set of potent antibody-like
molecular candidates for testing. Towards solving this problem, this project aims to develop a deep learning
architecture that will take as input thermodynamic, quantum mechanical (density functional), and local structure-
based network topographical features of the antigens and their cognate antibodies, and will output their
respective binding affinity constants.
We will design a generative adversarial network (GAN), which we think is uniquely suited for regression-based
ML approaches for the immune system, to discover associations between the epitope and the variable chain
features. This approach requires a large data stream of antigen and cognate antibody sequences, which until
recently was difficult to obtain. A recently described single B-cell receptor (BCR) specific tagging method coupled
with single cell deep sequencing (“linking B cell receptor to antigen specificity through sequencing” or LIBRA-
seq) can rapidly isolate and sequence the BCR variable chain coding regions that can bind with high selectivity
to antigenic epitopes.
Towards the specific project goals, in Task 1, LIBRA-seq will be used to rapidly identify and generate candidate
immunoglobulin coding sequences in response to specific linear and nonlinear epitopes (against controls),
chosen through computational/molecular modeling and prioritized with SARS-CoV-2 Spike protein epitopes (but
not restricted to these), injected into a mouse model, to generate large training sets; in Task 2, these training
sets, along with other data sets already available in public databases, will generate a series of structural features
(described above), which will be used to train the GAN; in Task 3, the predicted epitope-antibody interactions
will be validated by direct experiments with synthetic antibody and phage-display systems. Thus, the proposed
strategy combines foundational principles in evolutionary biology, genomics, structural chemistry, and computer
science to the solution of a general biological engineering problem.
Results from this project are expected to lay the foundations for a rigorously tested and fully automated machine-
learning system that could rapidly generate synthetic antibody candidates from the structure of a novel virus
protein, which can enhance the rapid response ability against a future pandemic. The ability to develop targeted
antibody therapy against non-infectious or chronic diseases, and on the production of antibody-based industrial
enzymes, will also be dramatically enhanced if this project were to be successful.
The team: The team-leads of this multi-institutional research project comprise a computer scientist, a protein
crystallographer, an immunologist, and a molecular biologist.
1
Terms: <2019-nCoV S protein><2019-nCoV spike glycoprotein><2019-nCoV spike protein><3-D structure><3-dimensional structure><3D structure><Ab response><Affinity><Amino Acid Sequence><Antibodies><Antibody Formation><Antibody Production><Antibody Specificity><Antibody Therapy><Antigen-Antibody Complex><Antigenic Determinants><Antigens><Architecture><B blood cells><B cell><B cell receptor><B cells><B-Cell Antigen Receptor><B-Cell Receptor Binding><B-Cells><B-Lymphocytes><B-cell><Base Sequence><Binding><Binding Determinants><Biology><Biomedical Engineering><COVID-19 S protein><COVID-19 antigen><COVID-19 spike glycoprotein><COVID-19 spike protein><COVID19 S protein><COVID19 spike glycoprotein><COVID19 spike protein><Cancers><Cell Body><Cells><Chronic Disease><Chronic Illness><Code><Coding System><Computer Models><Computerized Models><Computers><Computing Methodologies><Connectionist Models><Coupled><DNA Molecular Biology><Data><Data Bases><Data Set><Databases><Degenerative Disorder><Development><Diagnosis><Economics><Electrons><Engineering / Architecture><Enzyme Gene><Enzymes><Epitopes><Equilibrium><Foundations><Future><Genes><Genomics><Goals><Hour><Immune Complex><Immune Globulins><Immune system><Immunize><Immunoassay><Immunoglobulins><Immunologist><Immunology><Industrialization><Institution><Ligands><Light><Link><Machine Learning><Malignant Neoplasms><Malignant Tumor><Measurable><Methods><Mice><Mice Mammals><Microscopic><Modeling><Molecular><Molecular Biology><Molecular Interaction><Molecular Modeling Nucleic Acid Biochemistry><Molecular Modeling Protein/Amino Acid Biochemistry><Molecular Models><Murine><Mus><Nature><Negative Beta Particle><Negatrons><Neural Network Models><Neural Network Simulation><Nucleotide Sequence><Output><Passive Immunotherapy><Perceptrons><Phage Display><Phase><Photoradiation><Play><Preparedness><Primary Protein Structure><Process><Production><Proteins><Quantum Mechanics><R-Series Research Projects><R01 Mechanism><R01 Program><Readiness><Reagent><Research Grants><Research Project Grants><Research Projects><SARS-CoV-2 S protein><SARS-CoV-2 antigen><SARS-CoV-2 spike glycoprotein><SARS-CoV-2 spike protein><SARS-CoV2 S protein><SARS-CoV2 antigen><SARS-CoV2 spike glycoprotein><SARS-CoV2 spike protein><Scientist><Series><Severe acute respiratory syndrome coronavirus 2 S protein><Severe acute respiratory syndrome coronavirus 2 spike glycoprotein><Severe acute respiratory syndrome coronavirus 2 spike protein><Specificity><Structural Chemistry><Structure><Surface Plasmon Resonance><System><Testing><Therapeutic><Therapeutic antibodies><Thermodynamic><Thermodynamics><Time><Training><Vaccines><Validation><Variant><Variation><Viral Antigens><Viral Gene Products><Viral Gene Proteins><Viral Proteins><Work><antibody based therapies><antibody biosynthesis><antibody treatment><antibody-based therapeutics><antibody-based treatment><balance><balance function><bio-engineered><bio-engineers><bioengineering><biological engineering><chronic disorder><combat><computational methodology><computational methods><computational modeling><computational models><computer based method><computer based models><computer methods><computer science><computerized modeling><computing method><coronavirus disease 2019 S protein><coronavirus disease 2019 antigen><coronavirus disease 2019 spike glycoprotein><coronavirus disease 2019 spike protein><data base><data base structure><data streams><database structure><deep learning><deep learning based neural network><deep learning neural network><deep neural net><deep neural network><deep sequencing><degenerative condition><degenerative disease><density><design><designing><developmental><economic><experiment><experimental research><experimental study><experiments><future pandemic><generative adversarial network><generative neural network><high dimensionality><immunogen><immunoglobulin biosynthesis><in silico><innovate><innovation><innovative><insight><large data sets><large datasets><machine based learning><machine learning based method><machine learning method><machine learning methodologies><malignancy><manufacture><molecular modeling><mouse model><murine model><neoplasm/cancer><neutralizing antibody><next pandemic><novel><novel virus><nucleic acid sequence><pandemic><pandemic containment><pandemic control><pandemic disease><pandemic disease preparedness><pandemic mitigation><pandemic planning><pandemic preparedness><pandemic readiness><pandemic response><passive immune therapy><passive immunotherapeutics><pathogen><physical property><protein sequence><protein structure><protein structures><proteins structure><public data base><public database><publicly accessible data base><publicly accessible database><publicly available data base><publicly available database><response><scaffold><scaffolding><severe acute respiratory syndrome coronavirus 2 antigen><simulation><single cell sequencing><synthetic antibodies><therapeutic evaluation><therapeutic testing><three dimensional structure><validations><viral pandemic><virus antigen><virus protein>