T-cell receptor repertoire selection prediction with physical model augmented pseudo-labeling for personalized medicine decision making
Systems and methods for predicting T-Cell receptor (TCR)-peptide interaction, including training a deep learning model for the prediction of TCR-peptide interaction by determining a multiple sequence alignment (MSA) for TCR-peptide pair sequences from a dataset of TCR-peptide pair sequences using a sequence analyzer, building TCR structures and peptide structures using the MSA and corresponding structures from a Protein Data Bank (PDB) using a MODELLER, and generating an extended TCR-peptide training dataset based on docking energy scores determined by docking peptides to TCRs using physical modeling based on the TCR structures and peptide structures built using the MODELLER. TCR-peptide pairs are classified and labeled as positive or negative pairs using pseudo-labels based on the docking energy scores, and the deep learning model is iteratively retrained based on the extended TCR-peptide training dataset and the pseudo-labels until convergence.
1 . A method for predicting T-Cell receptor (TCR)-peptide interaction, comprising:
training a deep learning model for the predicting TCR-peptide interaction, the training comprising:
determining a multiple sequence alignment (MSA) for a plurality of TCR-peptide pair sequences from a dataset of TCR-peptide pair sequences using a sequence analyzer;
building TCR structures and peptide structures using the MSA and corresponding structures from a Protein Data Bank (PDB) using a MODELLER;
generating an extended TCR-peptide training dataset based on docking energy scores determined by docking peptides to TCRs using physical modeling based on the TCR structures and peptide structures built using the MODELLER; and
classifying and labeling TCR-peptide pairs as positive or negative pairs using pseudo-labels based on the docking energy scores; and
iteratively retraining the deep learning model based on the extended TCR-peptide training dataset and the pseudo-labels until convergence.
2 . The method as recited in claim 1 , wherein the dataset of TCR-peptide pairs includes positive and negative binding TCR-peptide pairs.
3 . The method as recited in claim 1 , wherein the classifying and labeling the TCR-peptide pairs further comprises pseudo-labeling the TCR-peptide pairs with a top x percentage of the energy scores as negative pairs, and a bottom y percentage of the energy scores as positive pairs.
4 . The method as recited in claim 1 , further comprising concatenating a peptide embedding vector and a TCR embedding vector from the dataset of TCR-peptide pair sequences.
5 . The method as recited in claim 1 , further comprising training an autoencoder by combining unlabeled TCRs from a TCR database and labeled TCRs from the training data.
6 . The method as recited in claim 1 , wherein the deep learning model is learned based on a standard cross-entropy loss from the plurality of TCR-peptide pair sequences, a divergence loss from the pseudo-labeled TCR-peptide pairs, and a cross-entropy loss based on physical properties between TCRs and peptides using physical modeling.
7 . The method as recited in claim 6 , wherein a final total loss (L total ) is determined as follows:
L total =L labeled +L pseudo-labeled +L physical
where L labeled represents the standard cross-entropy loss from the plurality of TCR-peptide pair sequences, L pseudo-labeled represents a divergence loss from the pseudo-labeled TCR-peptide pairs, and L physical represents the cross-entropy loss based on physical properties.
8 . A system for predicting T-Cell receptor (TCR)-peptide interaction, comprising:
a processor operatively coupled to a non-transitory computer readable storage medium, the processor being configured for:
training a deep learning model for the predicting TCR-peptide interaction, the training comprising:
determining a multiple sequence alignment (MSA) for a plurality of TCR-peptide pair sequences from a dataset of TCR-peptide pair sequences using a sequence analyzer;
building TCR structures and peptide structures using the MSA and corresponding structures from a Protein Data Bank (PDB) using a MODELLER;
generating an extended TCR-peptide training dataset based on docking energy scores determined by docking peptides to TCRs using physical modeling based on the TCR structures and peptide structures built using the MODELLER; and
classifying and labeling TCR-peptide pairs as positive or negative pairs using pseudo-labels based on the docking energy scores; and
iteratively retraining the deep learning model based on the extended TCR-peptide training dataset and the pseudo-labels until convergence.
9 . The system as recited in claim 8 , wherein the dataset of TCR-peptide pairs includes positive and negative binding TCR-peptide pairs.
10 . The system as recited in claim 8 , wherein the classifying and labeling the TCR-peptide pairs further comprises pseudo-labeling the TCR-peptide pairs with a top x percentage of the energy scores as negative pairs, and a bottom y percentage of the energy scores as positive pairs.
11 . The system as recited in claim 8 , wherein the processor is further configured for concatenating a peptide embedding vector and a TCR embedding vector from the dataset of TCR-peptide pair sequences.
12 . The system as recited in claim 8 , wherein the processor is further configured for training an autoencoder by combining unlabeled TCRs from a TCR database and labeled TCRs from the training data.
13 . The system as recited in claim 8 , wherein the deep learning model is learned based on a standard cross-entropy loss from the plurality of TCR-peptide pair sequences, a divergence loss from the pseudo-labeled TCR-peptide pairs, and a cross-entropy loss based on physical properties between TCRs and peptides using physical modeling.
14 . The system as recited in claim 13 , wherein a final total loss (L total ) is determined as follows:
L total =L labeled +L pseudo-labeled +L physical
where L labeled represents the standard cross-entropy loss from the plurality of TCR-peptide pair sequences, L pseudo-labeled represents a divergence loss from the pseudo-labeled TCR-peptide pairs, and L physical represents the cross-entropy loss based on physical properties.
15 . A non-transitory computer readable storage medium comprising a computer readable program operatively coupled to a processor device for predicting T-Cell receptor (TCR)-peptide interaction, wherein the computer readable program when executed on a computer causes the computer to perform the steps of:
training a deep learning model for the predicting the TCR-peptide interaction, the training comprising:
determining a multiple sequence alignment (MSA) for a plurality of TCR-peptide pair sequences from a dataset of TCR-peptide pair sequences using a sequence analyzer;
building TCR structures and peptide structures using the MSA and corresponding structures from a Protein Data Bank (PDB) using a MODELLER;
generating an extended TCR-peptide training dataset based on docking energy scores determined by docking peptides to TCRs using physical modeling based on the TCR structures and peptide structures built using the MODELLER; and
classifying and labeling TCR-peptide pairs as positive or negative pairs using pseudo-labels based on the docking energy scores; and
iteratively retraining the deep learning model based on the extended TCR-peptide training dataset and the pseudo-labels until convergence.
16 . The non-transitory computer readable storage medium as recited in claim 15 , wherein the dataset of TCR-peptide pairs includes positive and negative binding TCR-peptide pairs.
17 . The non-transitory computer readable storage medium as recited in claim 15 , wherein the classifying and labeling the TCR-peptide pairs further comprises pseudo-labeling the TCR-peptide pairs with a top x percentage of the energy scores as negative pairs, and a bottom y percentage of the energy scores as positive pairs.
18 . The non-transitory computer readable storage medium as recited in claim 15 , further comprising concatenating a peptide embedding vector and a TCR embedding vector from the dataset of TCR-peptide pair sequences.
19 . The non-transitory computer readable storage medium as recited in claim 15 , wherein the deep learning model is learned based on a standard cross-entropy loss from the plurality of TCR-peptide pair sequences, a divergence loss from the pseudo-labeled TCR-peptide pairs, and a cross-entropy loss based on physical properties between TCRs and peptides using physical modeling.
20 . The non-transitory computer readable storage medium as recited in claim 19 , wherein a final total loss (L total ) is determined as follows:
L total =L labeled +L pseudo-labeled +L physical
where L labeled represents the standard cross-entropy loss from the plurality of TCR-peptide pair sequences, L pseudo-labeled represents a divergence loss from the pseudo-labeled TCR-peptide pairs, and L physical represents the cross-entropy loss based on physical properties.