psipred / deepcov Goto Github PK

Hello,

I'm trying to run the training script that was given, and did not modify any code. I'm running it on GPU, and it throws this memory exception for the first training example:

Starting training...
Traceback (most recent call last):
  File "/home/jason/anaconda3/lib/python3.7/site-packages/theano/compile/function_module.py", line 903, in __call__
    self.fn() if output_subset is None else\
RuntimeError: GpuCorrMM failed to allocate working memory of 1600 x 246016


During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "lasagne_cov_train.py", line 249, in <module>
    main()
  File "lasagne_cov_train.py", line 176, in main
    train_err += train_func1(inputs, targets, wtmaps)
  File "/home/jason/anaconda3/lib/python3.7/site-packages/theano/compile/function_module.py", line 917, in __call__
    storage_map=getattr(self.fn, 'storage_map', None))
  File "/home/jason/anaconda3/lib/python3.7/site-packages/theano/gof/link.py", line 325, in raise_with_op
    reraise(exc_type, exc_value, exc_trace)
  File "/home/jason/anaconda3/lib/python3.7/site-packages/six.py", line 692, in reraise
    raise value.with_traceback(tb)
  File "/home/jason/anaconda3/lib/python3.7/site-packages/theano/compile/function_module.py", line 903, in __call__
    self.fn() if output_subset is None else\
RuntimeError: GpuCorrMM failed to allocate working memory of 1600 x 246016

Apply node that caused the error: GpuCorrMM{half, (1, 1), (1, 1), 1, False}(GpuContiguous.0, GpuContiguous.0)
Toposort index: 235
Inputs types: [GpuArrayType<None>(float32, (True, False, False, False)), GpuArrayType<None>(float32, 4D)]
Inputs shapes: [(1, 64, 496, 496), (64, 64, 5, 5)]
Inputs strides: [(62980096, 984064, 1984, 4), (6400, 100, 20, 4)]
Inputs values: ['not shown', 'not shown']
Outputs clients: [[GpuCAReduceCuda{add}{0, 2, 3}(GpuCorrMM{half, (1, 1), (1, 1), 1, False}.0), GpuElemwise{sub,no_inplace}(GpuCorrMM{half, (1, 1), (1, 1), 1, False}.0, GpuElemwise{Composite{(((i0 / i1) / i2) / i3)}}[]<gpuarray>.0), GpuElemwise{sub,no_inplace}(GpuCorrMM{half, (1, 1), (1, 1), 1, False}.0, InplaceGpuDimShuffle{x,0,x,x}.0)]]

I'm just wondering what's the GPU memory you guys ran this on? or is there any way to resolve this? I'm running this on a 8GB GeForce RTX 2070 Max-Q and a 32GB RAM, which is pretty decent but clearly cant handle the size of this matrix...

Hello,

Do you guys have the training data in FASTA format? Or is there a way I can convert the provided PSICOV-format data to FASTA? Thank you

Best,
Jason

Hello. Thank you very much for your great work! I really enjoyed your research.

I have followed the README and I was able to successfully run setup.sh and ./deepcov.sh -i test/example_io/1guuA.aln -o test/test.out. That was great. Thank you.
However, when doing Benchmarking scripts, 'all_windowsize_results_MEAN_covar_min6_max11.txt' does not show any results. It only shows window L L/2 L/5 L/10 L=100 and receptive field sizes.

Could you describe the potential reasons?

Hello, i have two questions hope i get the answers from you

1- first the rule of the sequence alignment is that to extract a chunks of subsequences represents the first sequence

2- and then those alignments are fed to the covariance matrix to extract a matrix called covariance matrix the measures the correlations between each of these alignments with each other

3-from what i understand it that proteins contact map describe the distance matrix as a label , like for example the distance between the first amino acid in the first chain and the first amino acid in the second chain is equal to 200 A, we set a threshold with 8 A so the proteins contact map description for this distance number will be "not in contact" "False" or in binary world "0" is im right with that understanding

My Questions
First
1-what is the rule of the covariance matrix
2- what is the rule of proteins contact map are those the labels of the matrix distances if so what is the rule of the covariance matrix
3- what is the input to the neural network model
A- what is the feature, are those the distance matrix if yes what is the rule of covariance matrix
B- what is the label of these features are Proteins contact map is the labels in (0's and 1's )

Second
1- i want from you kindly to give me a hint or steps which is the first script to use and second and so on cuz i want to cite your paper so i started to inspired from your great work

thanks in advance

Thank you for much for that .
I would like to ask where exactly I can find the function of calculating the covariance from the original data.
I hope you can help me in that

Thanks
Saida