Supplementary materials for positive-unlabeled learning identifies vaccine candidate antigens in the malaria parasite Plasmodium falciparum

The research aims to identify and prioritize previously unknown vaccine antigen candidates with potentially high efficacy against the most prevalent malaria parasite Plasmodium falciparum. Positive-unlabeled random forest (PURF) was applied to learn from the small set of known Plasmodium falciparum antigens and the other proteins with unknown antigenic properties. The research notebook contains data and code generated in the study "Positive-unlabeled learning identifies vaccine candidate antigens in the malaria parasite Plasmodium falciparum." The notebook also includes instructions on installing the PURF package, retrieving protein variables and assembling machine learning input from the database, as well as code for experimental analysis and plotting.

本研究旨在鉴定并优先筛选此前未被发现的、针对最流行的疟原虫——恶性疟原虫（Plasmodium falciparum）的潜在高效疫苗抗原候选物。本研究应用正样本未标记随机森林（Positive-unlabeled random forest, PURF）模型，基于少量已知的恶性疟原虫抗原蛋白集合，以及抗原特性未知的其他蛋白开展学习。本研究的配套研究笔记本包含论文《正样本未标记学习在恶性疟原虫中鉴定疫苗候选抗原》（Positive-unlabeled learning identifies vaccine candidate antigens in the malaria parasite Plasmodium falciparum.）中生成的全部数据与代码。该研究笔记本同时涵盖了PURF包的安装指南、从数据库中获取蛋白变量并组装机器学习输入数据的方法，以及实验分析与绘图所用代码。