PharmacoNet icon indicating copy to clipboard operation
PharmacoNet copied to clipboard

Failed to establish a new connection: [Errno 101] Network is unreachable

Open zangsk opened this issue 1 year ago • 7 comments

Thanks for sharing your great work. When I use modeling.py for pharmacophore modeling, the following error is reported:

requests.exceptions.ConnectionError: HTTPSConnectionPool(host='drive.google.com', port=443): Max retries exceeded with url: /uc?id=1gzjdM7bD3jPm23LBcDXtkSk18nETL04p (Caused by NewConnectionError('<urllib3.connection.HTTPSConnection object at 0x2b0755d5eed0>: Failed to establish a new connection: [Errno 101] Network is unreachable'))

In fact, the computing cluster I am using now is not connected to the Internet. Could I run your code without an Internet connection?

Many thanks

zangsk avatar Dec 07 '24 03:12 zangsk

The internet is required only once to download the trained deep learning model file. I'll update the code so that you can download and load the model manually in 3-4 days.

SeonghwanSeo avatar Dec 07 '24 05:12 SeonghwanSeo

The internet is required only once to download the trained deep learning model file. I'll update the code so that you can download and load the model manually in 3-4 days.

Sorry I just saw the reply. Could you please explain it in the code after you update the code? So I can download and use it according to the instructions. Thank you very much for your help.

zangsk avatar Dec 11 '24 02:12 zangsk

The internet is required only once to download the trained deep learning model file. I'll update the code so that you can download and load the model manually in 3-4 days.

I apologize for the delay. I am currently participating the NeurIPS conference, and cannot access my school internal network due to VPN issue. I will update as soon as possible after the conference ends.

SeonghwanSeo avatar Dec 12 '24 20:12 SeonghwanSeo

The internet is required only once to download the trained deep learning model file. I'll update the code so that you can download and load the model manually in 3-4 days.

I apologize for the delay. I am currently participating the NeurIPS conference, and cannot access my school internal network due to VPN issue. I will update as soon as possible after the conference ends.

Hi,

I recently downloaded the following from a link I found in the code, but I don't know whether these are all the files I need and how to use them. image

If you have been quite busy recently, could you please let me know how to use these files? This would allow me to do some simple trials in the meantime. I would appreciate your reply and look forward to successfully using your code.

zangsk avatar Dec 24 '24 02:12 zangsk

Sorry. Now I'm fine.

I updated the code for pharmaconet, but I feel what you need is the offline setup for reward function. Right? (e.g., TacoGFN or RxnFlow)

It would be helpful for what function do you need.

SeonghwanSeo avatar Dec 25 '24 08:12 SeonghwanSeo

Sorry. Now I'm fine.

I updated the code for pharmaconet, but I feel what you need is the offline setup for reward function. Right? (e.g., TacoGFN or RxnFlow)

It would be helpful for what function do you need.

Thank you very much for your help, I ran screening.py successfully and got the results. The screening speed is very impressive, which is very helpful to me.

Thank you again for your patience and help

zangsk avatar Dec 30 '24 08:12 zangsk

I'm glad to hear that you solved the problem well.

SeonghwanSeo avatar Dec 30 '24 08:12 SeonghwanSeo