So, could we resurrect one starting from their protein sequences?

那么，我们能从它们的蛋白质序列入手并复活一只鱼龙吗？

But instead of being fed vast volumes of text, protein language models are trained on tens of millions of protein sequences.

但是蛋白质语言模型不是被输入大量的文本，而是在数以千万计的蛋白质序列上进行训练。

But models trained only on protein sequences might struggle to come up with truly new antibodies that recognize a specified protein.

但是，只对蛋白质序列进行训练的模型可能很难找到能够识别特定蛋白质的真正的新抗体。

The model was trained on only a few thousand antibody sequences, out of the nearly 100 million protein sequences it learnt from.

该模型只接受了数千个抗体序列的训练，而它所学习的蛋白质序列接近1亿个。

Using a model incorporating protein sequences, as well as experimental data, they generated new designs for several important regions of an antibody drug used to treat breast cancer.

通过结合蛋白质序列和实验数据的模型，他们对一种用于治疗乳腺癌的抗体药物的几个重要区域进行了新的设计。

Sequencing can also reveal what what the MHC molecules will look like and, together with the mutant protein sequences, this can predict which neoantigens cells will display.

测序还可以揭示 MHC 分子会是什么样子，并且与突变蛋白序列一起， 这可以预测哪些新抗原细胞会显示。