PlasmoFAB

PlasmoFAB是由图宾根大学计算机科学系创建的一个专门用于训练机器学习模型预测恶性疟原虫蛋白抗原候选的数据集。该数据集包含822条经过精心标记的蛋白质序列，区分了抗原候选和细胞内蛋白质。数据集的创建结合了广泛的文献搜索和领域专业知识，确保了高质量的标签。PlasmoFAB的应用领域主要集中在加速抗疟疾药物和疫苗的开发，通过机器学习方法预筛选潜在的蛋白质抗原候选，从而减少实验探索的时间和成本。

PlasmoFAB is a dataset specifically developed by the Department of Computer Science at the University of Tübingen for training machine learning models to predict Plasmodium falciparum protein antigen candidates. This dataset contains 822 meticulously labeled protein sequences, distinguishing between antigen candidates and intracellular proteins. The creation of PlasmoFAB integrates extensive literature searches and domain expertise to ensure high-quality annotations. Its core applications focus on accelerating the development of antimalarial drugs and vaccines, by pre-screening potential protein antigen candidates via machine learning methods, thereby reducing the time and costs required for experimental exploration.