Closed MoriatyZy closed 2 months ago
Hi,
For the first problem:
Error: mkl-service + Intel(R) MKL: MKL_THREADING_LAYER=INTEL is incompatible with libgomp.so.1 library.
This is a system error.
One easy way to fix this is to revise the header in run_GCN.py as below:
import numpy as np
from data import load_data, preprocess_features, preprocess_adj, sample_mask
import model
from config import args
from utils import masked_loss, masked_acc
import pickle as pkl
import scipy.sparse as sp
import torch
from torch import nn
from torch import optim
from torch.nn import functional as F
Or you can download the latest run_GCN.py. I have updated them accordingly.
For the second problem:
ModuleNotFoundError: No module named 'sklearn'
Please try to install sklearn using
pip install scikit-learn
Or following the above suggestion (it will remove the sklearn header)
Best, Jiayu
Thank you for your prompt and useful reply! I have solved the problem according to your suggestion. Also, I would like to know if there is any command to specify the path to the output file? Because I want to run multiple phagcn2 jobs at the same time, this will cause the output file to be overwritten.
If you are only solving the phage-related task, PhaBOX will help.
However, I am only a collaborator of PhaGCN2 and the main manager is @yuanwenguang666. I am not sure whether he has time to upgrade the program.
As far as I know, I am afraid the current version does not have such a parameter for the user to specify the output path.
Best, Jiayu
I apologize for noticing this problem late.
The first issue has been fixed in the update of 18 February 2023. You can update it by cloning new code.
For the second question, as the software is run in batches, the current version does not have such a parameter for the user to specify the output path. But if you want to run multiple phagcn2 jobs, we recommend that you copy PhaGCN2's folder to predict multiple sequence files simultaneously. (ps: If you run too many at the same time, the memory may be insufficient. Please run it properly.)
for example: cp -r PhaGCN2.0 ~/PhaGCN2.1/ python3 PhaGCN2.0/run_Speed_up.py --contigs total1.fasta --len 2000 python3 PhaGCN2.1/run_Speed_up.py --contigs total2.fasta --len 2000
Thank you for your question.
All the best, Wen-Guang
Description of bug
Hello,
I used PhaGNC2 to classify the viral contigs, but it stopped after running for 20 hours. The log file was very long and there were several errors in it as follows:
I have tried to type in the command _export MKL_SERVICE_FORCEINTEL=1 before runing run_Speed_up.py, but it didn't work.
Besides, I would like to know how to specify the path to the output file. If I use the following command, the output files will appear in the installation packages folder (PhaGCN2.0).
$ python run_Speed_up.py --contigs contigs.fa --len 8000
Please help me troubleshoot. Much appreciated!
Thank you,
-Nora
log
PhaGCN.txt
Operating System
Linux 3.10.0-1062.el7.x86_64