Yang Tan

> I had similar issue with OP. I was set conda environment with python 3.8.x. pytorch 1.8.1 with cuda 11.1, and pyg 1.7.2. It works totally fine with cuda 11.1...

Hi, Ruiwen, Sorry for the late reply. I have tested the pre-train code just now (RTX 3090), but I didn't meet any wrong, can you provide more information? Thx 

Great! I will check the environment file soon.

Hi, Yuxuan Thank you for your kind reminder. I have added labels to your issue to help other possible users. In the future, I may refactor the code for project...

谢谢~ 其实ProtSSN这里没有用到这些手工特征了，不过非常感谢你的建议，我会再去研读一下PIFold

Hi, I have fixed the error, I have updated the mutation file due to issues with its generation. Thx

Hi, Wang, 1. Good question! From a biological perspective, the CATH domain already contains sufficient protein structure paradigms, but from a computational perspective, this is indeed a gap, and we...

我们在researchgate中上传的完整pdf，请[下载](https://www.researchgate.net/publication/378954165_MedChatZH_A_tuning_LLM_for_traditional_Chinese_medicine_consultations?_sg%5B0%5D=EmqOhAq9zNcq7Zssh_0zpUQPV-zNwmL0stymybJ-4uBrJWuFnDelxwBLqi7L9lbJnyWCfrB2O-r3ZIBrJ15wx7_4oPs5aOHR4IiOvdYs.NVZsQTDuj7Ozfr7o1FBcy4levJQw3CfFBkX9wGHXUezIPyAcTXQ1A6yWgG1Gv2-6jgnrTUbMmNqcyLaH_BJYeA&_tp=eyJjb250ZXh0Ijp7ImZpcnN0UGFnZSI6ImhvbWUiLCJwYWdlIjoicHJvZmlsZSIsInByZXZpb3VzUGFnZSI6InByb2ZpbGUiLCJwb3NpdGlvbiI6InBhZ2VDb250ZW50In19)~

We have updated the structure serialization module, and it is now very fast. Please try it out, thank you!

1. Sure. We support multi-mutation prediction. 2. To fit the format of ProteinGym, we updated the predict script name to `compute_fitness`, but they are the same.