jiujiezz / deephlapan Goto Github PK

补充材料按照链接找不到，请问可以提供一份么

How to contact you? what's your email address? I have several questions about deephlapan.

Help:I have installed Nvidia384.81,Cuda 9.0.176 and cudnn7.4.2 for cuda9.0 on Debian and it seems to be installed properly as type nvcc and nvidia-smi and tensorflow also be successfully tested, I get proper response:

=====================================================================
        DeepHLApan is a deep learning approach used for predicting high-confidence 
        neoantigens by considering both the presentation possibilities of 
        mutant peptides and the potential immunogenicity of pMHC.

        Usage:

        Single peptide and HLA:

            deephlapan -P LNIMNKLNI -H HLA-A02:01 

        List of peptides and HLA alleles in a file:

            deephlapan -F [file] -O [output directory]  

            (see 1.csv in demo/ for the detailed format of input file)
        =====================================================================

SyntaxError: invalid syntax
deephlapan 1.1 is already the active version in easy-install.pth
Installing deephlahan script to /usr/local/bin

Installed /usr/local/lib/python3.7/dist-packages/deephlapan-1.1-py3.7.egg
Processing dependencies for deephlapan==1.1
Searching for tensorflow-gpu==1.15.0
Reading https://pypi.org/simple/tensorflow-gpu
No local packages or working download links found for tensorflow-gpu==1.15.0
error: Could not find suitable distribution for Requirement.parse('tensorflow-gpu==1.15.0')

I tried tensorflow1.15, tensorflow1.12 or other version and reinstalled nvidia drive,but they didn't work.please tell me how to solve this problem and are the drives the correct version.

在使用setup.py安装之后，使用推荐的单肽段检测方法，会出现如下的问题，这个问题应该怎么解决呢？
(wanggj) wanggj@kemove-System-Product-Name:~$ deephlapan -P LNIMNKLNI -H HLA-A02:01
Traceback (most recent call last):
File "/home/wanggj/.conda/envs/wanggj/bin/deephlapan", line 4, in
import('pkg_resources').run_script('deephlapan==1.1', 'deephlapan')
File "/home/wanggj/.conda/envs/wanggj/lib/python3.7/site-packages/pkg_resources/init.py", line 662, in run_script
self.require(requires)[0].run_script(script_name, ns)
File "/home/wanggj/.conda/envs/wanggj/lib/python3.7/site-packages/pkg_resources/init.py", line 1459, in run_script
exec(code, namespace, namespace)
File "/home/wanggj/.conda/envs/wanggj/lib/python3.7/site-packages/deephlapan-1.1-py3.7.egg/EGG-INFO/scripts/deephlapan", line 3, in
from deephlapan.deephlapan_main import *
File "/home/wanggj/.conda/envs/wanggj/lib/python3.7/site-packages/deephlapan-1.1-py3.7.egg/deephlapan/deephlapan_main.py", line 13, in
from attention import Attention
ModuleNotFoundError: No module named 'attention'

如果直接使用deephlapan_main.py， 不会报任何错误但也不会有任何输出？
感谢您的回复

Is there a way to tile your peptides before using deephlapan?

Help: please tell me how to solve this problem, thanks!

$ /path/Anaconda2/bin/deephlapan -P LNIMNKLNI -H HLA-A02:01
Using TensorFlow backend.

    =====================================================================
    DeepHLApan is a deep learning approach used for predicting high-confidence 
    neoantigens by considering both the presentation possibilities of 
    mutant peptides and the potential immunogenicity of pMHC.

    Usage:

    Single peptide and HLA:

        deephlapan -P LNIMNKLNI -H HLA-A02:01 

    List of peptides and HLA alleles in a file:

        deephlapan -F [file] -O [output directory]  

        (see 1.csv in demo/ for the detailed format of input file)
    =====================================================================

2019-06-06 10:31:48.171028 Prediction starting.....

WARNING:tensorflow:From /path/Anaconda2/lib/python2.7/site-packages/tensorflow/python/framework/op_def_library.py:263: colocate_with (from tensorflow.python.framework.ops) is deprecated and will be removed in a future version.
Instructions for updating:
Colocations handled automatically by placer.
WARNING:tensorflow:From /path/Anaconda2/lib/python2.7/site-packages/Keras-2.2.4-py2.7.egg/keras/backend/tensorflow_backend.py:3445: calling dropout (from tensorflow.python.ops.nn_ops) with keep_prob is deprecated and will be removed in a future version.
Instructions for updating:
Please use rate instead of keep_prob. Rate should be set to rate = 1 - keep_prob.
2019-06-06 10:31:52.526305: I tensorflow/core/platform/profile_utils/cpu_utils.cc:94] CPU Frequency: 2399935000 Hz
2019-06-06 10:31:52.535517: I tensorflow/compiler/xla/service/service.cc:150] XLA service 0x55c0337b5540 executing computations on platform Host. Devices:
2019-06-06 10:31:52.535933: I tensorflow/compiler/xla/service/service.cc:158] StreamExecutor device (0): ,
WARNING:tensorflow:From /path/Anaconda2/lib/python2.7/site-packages/tensorflow/python/ops/math_ops.py:3066: to_int32 (from tensorflow.python.ops.math_ops) is deprecated and will be removed in a future version.
Instructions for updating:
Use tf.cast instead.
/path/Anaconda2/lib/python2.7/site-packages/Keras-2.2.4-py2.7.egg/keras/engine/saving.py:327: UserWarning: Error in loading the saved optimizer state. As a result, your model is starting with a freshly initialized optimizer.
warnings.warn('Error in loading the saved optimizer '
2019-06-06 10:36:54.549616 Prediction end

Hello, I am having an issue using deephlapan.
I used the docker installation on MacOS. When I run the program on a test peptide or a file of several peptides, it stop at the same step.
First, I get several copies of the same warnings:

WARNING:tensorflow:From /usr/local/lib/python2.7/dist-packages/Keras-2.0.8-py2.7.egg/keras/backend/tensorflow_backend.py:1290: calling reduce_mean (from tensorflow.python.ops.math_ops) with keep_dims is deprecated and will be removed in a future version.
Instructions for updating:
keep_dims is deprecated, use keepdims instead

Then a progress bar is shown:

100/100 [==============================] - 2s     
100/100 [==============================] - 3s     
100/100 [==============================] - 3s     
100/100 [==============================] - 3s     
100/100 [==============================] - 4s     
100/100 [==============================] - 1s

Then the program does not progress or fail.

If I stop the program, it says it stopped here:

Process PoolWorker-531:
Traceback (most recent call last):
  File "/usr/lib/python2.7/multiprocessing/process.py", line 258, in _bootstrap
    self.run()
  File "/usr/lib/python2.7/multiprocessing/process.py", line 114, in run
    self._target(*self._args, **self._kwargs)
  File "/usr/lib/python2.7/multiprocessing/pool.py", line 102, in worker
    task = get()
  File "/usr/lib/python2.7/multiprocessing/queues.py", line 376, in get
    racquire()
KeyboardInterrupt

I can provide more information if needed. Any guidance would be appreciated.
Thank you!

I managed to succesfully run DeepHLApan. However, I would like some help interpreting the output. If understood the method correctly the score ("binding score") that i get as an ouptut (see the example below) is the probability that the given peptide is presented to the MHC-I. Is this correct ? I would like to come up with a cutoff, so I thought anything with a ("binding score") >= 0.9 could be considereded as presented to the MHC-I . Or would you have another suggestion ?

Thanks a lot in advance !