genbio-ai/protein-inverse-folding

本数据集包含CATH-4.2，TS50和TS500三个数据集，这些数据集经过预处理，适用于AIDO.ProteinIF-16B模型。CATH-4.2数据集由Ingraham等人根据2019年的论文《Generative models for graph-based protein design》准备。TS50和TS500数据集由Li等人根据2014年的论文《Direct prediction of profiles of sequences compatible with a protein structure by neural networks with fragment-based local and energy-based nonlocal profiles》准备。This dataset includes three datasets: CATH-4.2, TS50, and TS500, which have been preprocessed for direct use with the AIDO.ProteinIF-16B model. The CATH-4.2 dataset was prepared by Ingraham et al. based on the 2019 paper Generative models for graph-based protein design. The TS50 and TS500 datasets were prepared by Li et al. based on the 2014 paper Direct prediction of profiles of sequences compatible with a protein structure by neural networks with fragment-based local and energy-based nonlocal profiles.