lack of gninatypes files

[fengyuewuya]

Hi, I want to use the train_segmentation.py , but it is prompted that the gninatypes file is missing. Can you provide this part of the file?
or should I process these files?
THX

[RishalAggarwal]

if you are using a new dataset, you'd probably have to create them, if you are using a dataset we used in the publication then you can use the molcache files present in the dataset link provided on the README

[fengyuewuya]

Hi, I use the molcache holo4k.molcache2 and take the train_segmentation.py.
The code:
python train_segmentation.py --train_types train_segmentation_data/seg_holo4k_train.types --test_types train_segmentation_data/seg_holo4k_test.types -d tmp_data/holo4k_cavity/holo4k/ --train_recmolcache train_segmentation_data/holo4k.molcache2 --test_recmolcache train_segmentation_data/holo4k.molcache2 -b 8 -o model_saves/seg9 -e 200 -r seg9

The error result:

[fengyuewuya]

I can't find the directory named 4jpc_1 in the compressed package.
Can you show me your directory structure?

[fengyuewuya]

Hi, I use the molcache holo4k.molcache2 and take the train_segmentation.py. The code: python train_segmentation.py --train_types train_segmentation_data/seg_holo4k_train.types --test_types train_segmentation_data/seg_holo4k_test.types -d tmp_data/holo4k_cavity/holo4k/ --train_recmolcache train_segmentation_data/holo4k.molcache2 --test_recmolcache train_segmentation_data/holo4k.molcache2 -b 8 -o model_saves/seg9 -e 200 -r seg9 The error result: I can't find the directory named 4jpc_1 in the compressed package. Can you show me your directory structure? ------------------ 原始邮件 ------------------ 发件人: "devalab/DeepPocket" ***@***.***>; 发送时间: 2022年11月15日(星期二) 凌晨0:42 ***@***.***>; ***@***.******@***.***>; 主题: Re: [devalab/DeepPocket] lack of gninatypes files (Issue #18) Closed #18 as completed. — Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you authored the thread.Message ID: ***@***.***>

[RishalAggarwal]

I think your train recmolcache should be the scpdb recmocache

[fengyuewuya]

I take the scPDB molcache2 and types.
but there still report the error as bellow.
The code:
python train_segmentation.py
--train_types train_segmentation_data/seg_scPDB_train9.types
--test_types train_segmentation_data/seg_scPDB_test9.types
-d data/
--train_recmolcache train_segmentation_data/scPDB_new.molcache2
--test_recmolcache train_segmentation_data/scPDB_new.molcache2
-b 8
-o model_saves/seg9
-e 200
-r seg9

Error report:

Maybe the package environment is wrong?
or
Some files are missing?

[fengyuewuya]

I have solved this problem by downloading the scPDB original data and set the data_dir.
Thx a lot.

[mainguyenanhvu]

@fengyuewuya have you re-run data preparation for a custom data? If yes, please help me.

I am trying to use the instruction to prepare data for training a new classifier.
I have stuck in make_types step because I can't find train.txt and test.txt files.

Moreover, I have 4 questions:

1. If I want to add several pdb files to the available scPDB dataset, how can I complete it?
2. The instruction for preparing data only works for a single pdb file, does it? If not, I need to write a pipeline to wrap up it.
3. How to prepare train.txt and test.txt files to run make_types.py?
4. Could you please show me which file/folder needed inputting from previous to each step?

I am tried on this pdb.

Thank you very much.

p.s: I have asked in the issue #26.

[Satansu]

I have solved this problem by downloading the scPDB original data and set the data_dir. Thx a lot.

@fengyuewuya could you elaborate on how you fixed this issue? Because I've run into the exact same issue but no fix seems to work.