The paccmann from drugilsberg

Could you provide a gene list that contained in "selected_genes_10" and "selected_genes_20"?

I want to implement paccmann with custom data.
I noticed that you used a PPI network for filtering genes, resulting in 1121 genes for "selected genes_10" and 2128 genes for "selected_genes_20".
Could you directly provide the gene list?
Thanks

Ensure compatibility with TF 2.0

Fix the deprecation warnings:

W0703 10:12:40.451035 140175339554560 lazy_loader.py:50] 
The TensorFlow contrib module will not be included in TensorFlow 2.0.
For more information, please see:
  * https://github.com/tensorflow/community/blob/master/rfcs/20180907-contrib-sunset.md
  * https://github.com/tensorflow/addons
  * https://github.com/tensorflow/io (for I/O related ops)
If you depend on functionality not listed there, please file an issue.

W0703 10:12:40.451593 140175339554560 deprecation_wrapper.py:119] From /home/ubuntu/.local/lib/python3.5/site-packages/paccmann/hyperparams.py:26: The name tf.losses.mean_squared_error is deprecated. Please use tf.compat.v1.losses.mean_squared_error instead.

W0703 10:12:40.451802 140175339554560 deprecation_wrapper.py:119] From /home/ubuntu/.local/lib/python3.5/site-packages/paccmann/hyperparams.py:40: The name tf.train.AdamOptimizer is deprecated. Please use tf.compat.v1.train.AdamOptimizer instead.

W0703 10:12:40.451945 140175339554560 deprecation_wrapper.py:119] From /home/ubuntu/.local/lib/python3.5/site-packages/paccmann/hyperparams.py:41: The name tf.train.RMSPropOptimizer is deprecated. Please use tf.compat.v1.train.RMSPropOptimizer instead.

W0703 10:12:40.452079 140175339554560 deprecation_wrapper.py:119] From /home/ubuntu/.local/lib/python3.5/site-packages/paccmann/hyperparams.py:42: The name tf.train.AdadeltaOptimizer is deprecated. Please use tf.compat.v1.train.AdadeltaOptimizer instead.

W0703 10:12:40.452214 140175339554560 deprecation_wrapper.py:119] From /home/ubuntu/.local/lib/python3.5/site-packages/paccmann/hyperparams.py:43: The name tf.train.AdagradDAOptimizer is deprecated. Please use tf.compat.v1.train.AdagradDAOptimizer instead.

W0703 10:12:40.452339 140175339554560 deprecation_wrapper.py:119] From /home/ubuntu/.local/lib/python3.5/site-packages/paccmann/hyperparams.py:44: The name tf.train.AdagradOptimizer is deprecated. Please use tf.compat.v1.train.AdagradOptimizer instead.

W0703 10:12:40.454350 140175339554560 deprecation_wrapper.py:119] From /home/ubuntu/.local/lib/python3.5/site-packages/paccmann/datasets.py:11: The name tf.FixedLenFeature is deprecated. Please use tf.io.FixedLenFeature instead.

W0703 10:12:40.458485 140175339554560 deprecation_wrapper.py:119] From /home/ubuntu/.local/bin/training_paccmann:246: The name tf.trainable_variables is deprecated. Please use tf.compat.v1.trainable_variables instead.

W0703 10:12:40.465688 140175339554560 deprecation.py:323] From /home/ubuntu/.local/lib/python3.5/site-packages/tensorflow/python/training/training_util.py:236: Variable.initialized_value (from tensorflow.python.ops.variables) is deprecated and will be removed in a future version.
Instructions for updating:
Use Variable.read_value. Variables in 2.X are initialized automatically both in eager and graph (inside tf.defun) contexts.
W0703 10:12:40.497479 140175339554560 deprecation.py:323] From /home/ubuntu/.local/lib/python3.5/site-packages/paccmann/learning.py:34: shuffle_and_repeat (from tensorflow.contrib.data.python.ops.shuffle_ops) is deprecated and will be removed in a future version.
Instructions for updating:
Use `tf.data.experimental.shuffle_and_repeat(...)`.
W0703 10:12:40.497655 140175339554560 deprecation.py:323] From /home/ubuntu/.local/lib/python3.5/site-packages/tensorflow/contrib/data/python/ops/shuffle_ops.py:54: shuffle_and_repeat (from tensorflow.python.data.experimental.ops.shuffle_ops) is deprecated and will be removed in a future version.
Instructions for updating:
Use `tf.data.Dataset.shuffle(buffer_size, seed)` followed by `tf.data.Dataset.repeat(count)`. Static tf.data optimizations will take care of using the fused implementation.
W0703 10:12:40.501213 140175339554560 deprecation.py:323] From /home/ubuntu/.local/lib/python3.5/site-packages/paccmann/learning.py:43: map_and_batch (from tensorflow.contrib.data.python.ops.batching) is deprecated and will be removed in a future version.
Instructions for updating:
Use `tf.data.experimental.map_and_batch(...)`.
W0703 10:12:40.501355 140175339554560 deprecation.py:323] From /home/ubuntu/.local/lib/python3.5/site-packages/tensorflow/contrib/data/python/ops/batching.py:273: map_and_batch (from tensorflow.python.data.experimental.ops.batching) is deprecated and will be removed in a future version.
Instructions for updating:
Use `tf.data.Dataset.map(map_func, num_parallel_calls)` followed by `tf.data.Dataset.batch(batch_size, drop_remainder)`. Static tf.data optimizations will take care of using the fused implementation.
W0703 10:12:40.504391 140175339554560 deprecation_wrapper.py:119] From /home/ubuntu/.local/lib/python3.5/site-packages/paccmann/datasets.py:80: The name tf.parse_single_example is deprecated. Please use tf.io.parse_single_example instead.

W0703 10:12:40.518158 140175339554560 deprecation.py:323] From /home/ubuntu/.local/lib/python3.5/site-packages/paccmann/learning.py:51: DatasetV1.make_one_shot_iterator (from tensorflow.python.data.ops.dataset_ops) is deprecated and will be removed in a future version.
Instructions for updating:
Use `for ... in dataset:` to iterate over a dataset. If using `tf.estimator`, return the `Dataset` object directly from your input function. As a last resort, you can use `tf.compat.v1.data.make_one_shot_iterator(dataset)`.
W0703 10:12:40.538470 140175339554560 deprecation_wrapper.py:119] From /home/ubuntu/.local/lib/python3.5/site-packages/paccmann/layers.py:186: The name tf.get_variable is deprecated. Please use tf.compat.v1.get_variable instead.

W0703 10:12:40.548993 140175339554560 deprecation.py:323] From /home/ubuntu/.local/lib/python3.5/site-packages/paccmann/layers.py:158: dense (from tensorflow.python.layers.core) is deprecated and will be removed in a future version.
Instructions for updating:
Use keras.layers.dense instead.
W0703 10:12:40.550927 140175339554560 deprecation.py:506] From /home/ubuntu/.local/lib/python3.5/site-packages/tensorflow/python/ops/init_ops.py:1251: calling VarianceScaling.__init__ (from tensorflow.python.ops.init_ops) with dtype is deprecated and will be removed in a future version.
Instructions for updating:
Call initializer instance with the dtype argument instead of passing it to the constructor
W0703 10:12:40.941185 140175339554560 deprecation.py:323] From /home/ubuntu/.local/lib/python3.5/site-packages/paccmann/models/model_specifications/mca.py:220: conv2d (from tensorflow.python.layers.convolutional) is deprecated and will be removed in a future version.
Instructions for updating:
Use `tf.keras.layers.Conv2D` instead.
W0703 10:12:41.151372 140175339554560 deprecation.py:323] From /home/ubuntu/.local/lib/python3.5/site-packages/paccmann/models/model_specifications/mca.py:220: dropout (from tensorflow.python.layers.core) is deprecated and will be removed in a future version.
Instructions for updating:
Use keras.layers.dropout instead.
W0703 10:12:41.197633 140175339554560 deprecation.py:323] From /home/ubuntu/.local/lib/python3.5/site-packages/paccmann/models/model_specifications/mca.py:220: batch_normalization (from tensorflow.python.layers.normalization) is deprecated and will be removed in a future version.
Instructions for updating:
Use keras.layers.BatchNormalization instead.  In particular, `tf.control_dependencies(tf.GraphKeys.UPDATE_OPS)` should not be used (consult the `tf.keras.layers.batch_normalization` documentation).
W0703 10:12:43.129756 140175339554560 deprecation.py:323] From /home/ubuntu/.local/lib/python3.5/site-packages/tensorflow/python/ops/losses/losses_impl.py:121: add_dispatch_support.<locals>.wrapper (from tensorflow.python.ops.array_ops) is deprecated and will be removed in a future version.
Instructions for updating:
Use tf.where in 2.0, which has the same broadcast rule as np.where
W0703 10:12:43.152237 140175339554560 deprecation_wrapper.py:119] From /home/ubuntu/.local/lib/python3.5/site-packages/paccmann/models/core.py:66: The name tf.metrics.mean_squared_error is deprecated. Please use tf.compat.v1.metrics.mean_squared_error instead.

W0703 10:12:43.298675 140175339554560 deprecation_wrapper.py:119] From /home/ubuntu/.local/lib/python3.5/site-packages/paccmann/models/core.py:82: The name tf.summary.scalar is deprecated. Please use tf.compat.v1.summary.scalar instead.

2019-07-03 10:12:51.714772: W tensorflow/compiler/jit/mark_for_compilation_pass.cc:1412] (One-time warning): Not using XLA:CPU for cluster because envvar TF_XLA_FLAGS=--tf_xla_cpu_global_jit was not set.  If you want XLA:CPU, either set that envvar, or use experimental_jit_scope to enable XLA:CPU.  To confirm that XLA is active, pass --vmodule=xla_compilation_cache=1 (as a proper command-line flag, not via TF_XLA_FLAGS) or set the envvar XLA_FLAGS=--xla_hlo_profile.
W0703 10:13:36.224379 140175339554560 deprecation.py:323] From /home/ubuntu/.local/lib/python3.5/site-packages/tensorflow/python/training/saver.py:1276: checkpoint_exists (from tensorflow.python.training.checkpoint_management) is deprecated and will be removed in a future version.
Instructions for updating:
Use standard file APIs to check for files with this prefix.
W0703 10:13:40.584729 140175339554560 deprecation.py:323] From /home/ubuntu/.local/lib/python3.5/site-packages/tensorflow/python/saved_model/signature_def_utils_impl.py:201: build_tensor_info (from tensorflow.python.saved_model.utils_impl) is deprecated and will be removed in a future version.
Instructions for updating:
This function will only be available through the v1 compatibility library as tf.compat.v1.saved_model.utils.build_tensor_info or tf.compat.v1.saved_model.build_tensor_info.

Implement a module for inference

This could be achieved by directly importing the paccmann submodule from depiction (https://github.com/IBM/dl-interpretability-compbio/tree/master/depiction/models/paccmann).

How can I run paccmann with my own data?

I want to run paccmann with my own data.
After I read the source code. It looks like I have to generate training and testing tfrecords data by myself. I referred to the provided example data and datasets.py.
The tfrecords contains so many feature (fingerpirnts, targets,...etc). Do I have to generate the tfrecords data containing all the features?
e.g. I only have gene expression data, drug data(smiles) and IC50, is it right that I should only need to generate tfrecords with 3 types of features: selected_genes_20, smiles_atom_tokens and ic50?
Another question is that could you provide a detailed description for the features contained in tfrecords? I have no idea how the smiles_atom_tokens is generated, it seems smiles sequence is encoded into a 155 dimensional and vector.
It would be better if you can provide a script for generate tfrecords.
Thanks so much!

drugilsberg / paccmann Goto Github PK

paccmann's People

Stargazers

Watchers

Forkers

paccmann's Issues

Could you provide a gene list that contained in "selected_genes_10" and "selected_genes_20"?

Ensure compatibility with TF 2.0

Implement a module for inference

How can I run paccmann with my own data?

I am using paccmann open source web server for anticancer drug sensitivity prediction. Now, the server is not working. Kindly rectify this issue or else kindly give me the alternate web server for prediction. Its very urgent. Please kindly help me as soon as possible, sir.

Recommend Projects

React

Vue.js

Typescript

TensorFlow

Django

Laravel

D3

Recommend Topics

javascript

web

server

Machine learning

Visualization

Game

Recommend Org

Facebook

Microsoft

Google

Alibaba

D3

Tencent