Machine learning techniques for predicting surface presenting peptides

The present disclosure provides methods for predicting surface presenting peptides using binding and surface presenting characteristics. The method may include accessing a trained machine learning model configured to generate an output indicative of a degree to which one or more expression levels are associated with one or more peptide presentation metrics according to a population-level relationship between the expression and presentation. For each peptide in a set of peptides of a tissue sample, a score may be determined using a machine learning model and genomic and transcriptome data corresponding to the peptide. The score may predict whether the corresponding peptide is a surface presenting peptide that binds to an MHC molecule and is presented on the surface of the cell. 本公开内容提供了使用结合和表面呈递特性预测表面呈递肽的方法。所述方法可以包括访问训练的机器学习模型，所述训练的机器学习模型被配置为产生输出，所述输出指示一个或多个表达水平与一种或多种肽呈递度量根据表达与呈递之间的群体-水平关系而关联的程度。对于组织样品的肽集合中的每个肽，可以使用机器学习模型和对应于所述肽的基因组和转录组数据来测定得分。所述得分可以预测相应的肽是否是结合MHC分子并且被呈递在细胞表面上的表面呈递肽。