proteinglm/fluorescence_prediction

Fluorescence Prediction Dataset（荧光预测数据集）专注于预测绿色荧光蛋白突变体的荧光强度，这是生物学中的一项关键功能，允许研究人员推断细胞系和活生物体中蛋白质的存在。该回归任务利用训练和评估数据集，这些数据集包含三个或更少突变的突变体，而测试数据集则包含四个或更多突变的突变体。每个实例由一个蛋白质序列字符串和一个表示荧光强度的浮点数组成。数据集包含训练、验证和测试三个部分，分别包含21,446、5,362和27,217个实例。数据集来源于TAPE项目，并遵循Apache-2.0许可证。

The Fluorescence Prediction task focuses on predicting the fluorescence intensity of green fluorescent protein mutants, a crucial function in biology that allows researchers to infer the presence of proteins within cell lines and living organisms. This regression task utilizes training and evaluation datasets that feature mutants with three or fewer mutations, contrasting the testing dataset, which comprises mutants with four or more mutations. The dataset includes three splits: train (21,446 instances), valid (5,362 instances), and test (27,217 instances). Each instance contains a string representing the protein sequence and a float value indicating the fluorescence score. The dataset is sourced from the TAPE project and is released under the Apache-2.0 license.