Selection and Monitoring Methods for Xenotransplantation

Abstract

A method for predictive engineering of a sample derived from a genetically optimized non-human donor suitable for xenotransplantation into a human having improved quality or performance is provided. The method includes constructing a training data set from a series of libraries, wherein at least one library in the series of libraries comprises genomic, proteomic, and research data specific to non-humans. The method includes developing a predictive machine learning model based on the constructed training data set. The method includes utilizing the predictive machine learning model to obtain a predicted quality or performance of a plurality of sequences for a candidate sample from the non-human donor specific to a human patient or patient population. The method includes selecting a subset of sequences for evaluation from the plurality of sequences based on the predicted quality or performance. The method includes designing candidate samples derived from the non-human donor using the selected subset of sequences. The method includes measuring a respective in silico performance of each designed candidate sample. The method includes selecting a designed candidate sample for manufacture based on the respective in silico performance of each designed candidate sample.

1 . A method for predictive engineering of a non-human tissue or organ sample for xenotransplantation into a human, the method comprising:
 obtaining data relating to one or more human patients or patient populations;   identifying, using a predictive machine learning model, one or more nucleotide sequences for introduction into a genome of a genetically optimized non-human donor based on the data relating to the one or more human patients or patient populations;   designing candidate non-human tissue or organ samples for xenotransplantation in the human patient or patient population using the identified one or more nucleotide sequences;   modeling, in silico, an outcome of xenotransplantation of each designed candidate non-human tissue or organ sample in the one or more human patients or patient populations;   selecting a designed candidate non-human tissue or organ sample based on the modeling;   manufacturing a prototype sample using the selected designed candidate non-human tissue or organ sample; and   treating the one or more human patients or patient populations with a tissue or organ transplant comprising the manufactured prototype sample.   
     
     
         2 . The method of  claim 1 , wherein the data comprises clinical qualities or attributes specific to the one or more human patients or patient populations, wherein the clinical qualities or attributes comprise one or more of:
 genomic, nucleotide or proteomic, amino acid sequences,   HLA sequences to one or more major histocompatibility complexes (MHC) serotype,   titers,   viability,   density,   concentration,   demographics,   results of diagnostic assays, in vitro assays, mixed lymphocyte reaction (MLR) assays,   current and past medical and family histories,   current and past medical diagnoses,   current and past clinical documentation,   current and past medications, or   observational or experimental data of a human recipient with an engineered sample.   
     
     
         3 . The method of  claim 1 , wherein the predictive machine learning model is a neural network model, a Bayesian network model, a support vector machine model, a k-nearest neighbors model, or a combination thereof. 
     
     
         4 . The method of  claim 1 , further comprising:
 constructing a training data set from a series of libraries, wherein the training data set comprises genomic, proteomic, and research data specific to non-humans, information specific to a human patient or patient population, and one or more of:   protein variant data,   genomic, proteomic, and research data specific to human vertebrates, or   genomic, proteomic, and research data specific to known pathogens and diseases; and   developing the predictive machine learning model based on the constructed training data set.   
     
     
         5 . The method of  claim 1 , further comprising:
 obtaining a measurement of an in vitro patient outcome of the manufactured prototype sample.   
     
     
         6 . The method of  claim 5 , further comprising:
 evaluating the in vitro patient outcome as compared to the in silico patient outcome; and   refining the predictive machine learning model based on the evaluating.   
     
     
         7 . The method of  claim 1 , wherein the plurality of nucleotide sequences comprise one or more genomic alterations to be introduced into the genome of the non-human donor. 
     
     
         8 . The method of  claim 1 , wherein identifying, using the predictive machine learning model, the one or more nucleotide sequences for introduction into a genome further comprises:
 inputting a variable representing one or more genomic nucleotide or proteomic, amino acid sequences specific to the one or more human patients or patient populations to be introduced as genomic alterations to create an optimized non-human donor suitable for xenotransplantation.   
     
     
         9 . The method of  claim 8 , wherein the one or more genomic alterations comprise at least one alteration selected from the group consisting of: a single nucleotide polymorphism, nucleotide sequence insertion, nucleotide sequence deletion, or nucleotide sequence replacements, or site-directed mutagenic substitution. 
     
     
         10 . The method of  claim 9 , wherein the one or more genomic alterations comprise sequences from human and non-human major histocompatibility complexes (MHC). 
     
     
         11 . The method of  claim 1 , wherein the prototype sample comprises a skin graft from the non-human donor. 
     
     
         12 . The method of  claim 1 , wherein the prototype sample comprises a nerve transplant from the non-human donor. 
     
     
         13 . The method of  claim 1 , wherein the non-human donor is a porcine donor. 
     
     
         14 . A system for predictive engineering of a non-human tissue or organ sample for xenotransplantation into a human, the system comprising a processor and a non-transitory memory, wherein the system is configured to:
 obtain data relating to one or more human patients or patient populations;   identify, using a predictive machine learning model, one or more nucleotide sequences for introduction into a genome of a genetically optimized non-human donor based on the data relating to the one or more human patients or patient populations;   design candidate non-human tissue or organ samples for xenotransplantation in the human patient or patient population using the identified one or more nucleotide sequences;   model, in silico, an outcome of xenotransplantation of each designed candidate non-human tissue or organ sample in the one or more human patients or patient populations;   select a designed candidate non-human tissue or organ sample based on the modeling; and   output the designed candidate non-human tissue or organ sample for manufacture as a prototype sample and treatment of the one or more human patients or patient populations with a tissue or organ transplant comprising the prototype sample.   
     
     
         15 . The system of  claim 14 , wherein the predictive machine learning model is a neural network model, a Bayesian network model, a support vector machine model, a k-nearest neighbors model, or a combination thereof. 
     
     
         16 . The system of  claim 15 , wherein the system is further configured to:
 construct a training data set from a series of libraries, wherein the training data set comprises genomic, proteomic, and research data specific to non-humans, information specific to a human patient or patient population, and one or more of:   protein variant data,   genomic, proteomic, and research data specific to human vertebrates, or   genomic, proteomic, and research data specific to known pathogens and diseases; and   develop the predictive machine learning model based on the constructed training data set.   
     
     
         17 . The system of  claim 15 , wherein the prototype sample comprises a skin graft from the non-human donor. 
     
     
         18 . The system of  claim 15 , wherein the prototype sample comprises a nerve transplant from the non-human donor. 
     
     
         19 . The system of  claim 15 , wherein the non-human donor is a porcine donor. 
     
     
         20 . A computer program product comprising a non-transitory computer-readable medium storing instructions thereon, wherein the instructions cause a computer to:
 obtain data relating to one or more human patients or patient populations;   identify, using a predictive machine learning model, one or more nucleotide sequences for introduction into a genome of a genetically optimized non-human donor based on the data relating to the one or more human patients or patient populations;   design candidate non-human tissue or organ samples for xenotransplantation in the human patient or patient population using the identified one or more nucleotide sequences;   model, in silico, an outcome of xenotransplantation of each designed candidate non-human tissue or organ sample in the one or more human patients or patient populations;   select a designed candidate non-human tissue or organ sample based on the modeling; and   output the designed candidate non-human tissue or organ sample for manufacture as a prototype sample and treatment of the one or more human patients or patient populations with a tissue or organ transplant comprising the prototype sample.