#Welcome to the ```deepchem``` tutorial. In this iPython Notebook, one can follow along with the code below to learn how to fit machine learning models with rich predictive power on chemical datasets.
%% Cell type:markdown id: tags:
Overview:
In this tutorial, you will trace an arc from loading a raw dataset to fitting a cutting edge ML technique for predicting binding affinities. This will be accomplished by writing simple commands to access the deepchem Python API, encompassing the following broad steps:
1. Loading a chemical dataset, consisting of a series of protein-ligand complexes.
2. Featurizing each protein-ligand complexes with various featurization schemes.
3. Fitting a series of models with these featurized protein-ligand complexes.
4. Visualizing the results.
%% Cell type:markdown id: tags:
First, let's point to a "dataset" file. This can come in the format of a CSV file or Pandas DataFrame. Regardless
of file format, it must be columnar data, where each row is a molecular system, and each column represents
a different piece of information about that system. For instance, in this example, every row reflects a
protein-ligand complex, and the following columns are present: a unique complex identifier; the SMILES string
of the ligand; the binding affinity (Ki) of the ligand to the protein in the complex; a Python `list` of all lines
in a PDB file for the protein alone; and a Python `list` of all lines in a ligand file for the ligand alone.
This should become clearer with the example.
%% Cell type:code id: tags:
``` python
%autoreload2
%pdboff
importwarnings
warnings.filterwarnings('ignore')
```
%% Cell type:code id: tags:
``` python
dataset_file="../datasets/pdbbind_core_df.pkl.gz"
fromdeepchem.utils.saveimportload_from_disk
dataset=load_from_disk(dataset_file)
```
%% Cell type:markdown id: tags:
Let's see what `dataset` looks like:
%% Cell type:code id: tags:
``` python
print("Type of dataset is: %s"%str(type(dataset)))
print(dataset[:5])
print("Shape of dataset is: %s"%str(dataset.shape))
```
%% Output
Type of dataset is: <class 'pandas.core.frame.DataFrame'>
0 [### \n, ### Created by X-TOOL on Thu Aug 28 2... 6.92
1 [### \n, ### Created by X-TOOL on Thu Aug 28 2... 8.00
2 [### \n, ### Created by X-TOOL on Fri Aug 29 0... 6.52
3 [### \n, ### Created by X-TOOL on Thu Aug 28 2... 4.89
4 [### \n, ### Created by X-TOOL on Thu Aug 28 2... 8.05
Shape of dataset is: (193, 7)
%% Cell type:markdown id: tags:
One of the missions of ```deepchem``` is to form a synapse between the chemical and the algorithmic worlds: to be able to leverage the powerful and diverse array of tools available in Python to analyze molecules. This ethos applies to visual as much as quantitative examination:
binding_pocket_residues=" or ".join(binding_pocket_residues)
traj=nglview.MDTrajTrajectory(complex_mdtraj)# load file from RCSB PDB
ngltraj=nglview.NGLWidget(traj)
ngltraj.representations=[
{"type":"cartoon","params":{
"sele":"protein","color":"residueindex"
}},
{"type":"licorice","params":{
"sele":"(not hydrogen) and (resi (%s))"%binding_pocket_residues
}},
{"type":"ball+stick","params":{
"sele":"resn LIG"
}}
]
returnngltraj
```
%% Cell type:code id: tags:
``` python
ngltraj=visualize_complex(complex_mdtraj)
ngltraj
```
%% Output
/home/enf/anaconda/lib/python2.7/site-packages/ipywidgets/widgets/widget.py:157: DeprecationWarning: Widget._keys_default is deprecated: use @default decorator instead.
def _keys_default(self):
/home/enf/anaconda/lib/python2.7/site-packages/ipywidgets/widgets/widget.py:157: DeprecationWarning: Widget._keys_default is deprecated: use @default decorator instead.
def _keys_default(self):
/home/enf/anaconda/lib/python2.7/site-packages/ipykernel/comm/comm.py:52: DeprecationWarning: Comm._comm_id_default is deprecated: use @default decorator instead.
def _comm_id_default(self):
/home/enf/anaconda/lib/python2.7/site-packages/ipykernel/comm/comm.py:29: DeprecationWarning: Comm._iopub_socket_default is deprecated: use @default decorator instead.
def _iopub_socket_default(self):
/home/enf/anaconda/lib/python2.7/site-packages/ipykernel/comm/comm.py:24: DeprecationWarning: Comm._kernel_default is deprecated: use @default decorator instead.
def _kernel_default(self):
/home/enf/anaconda/lib/python2.7/site-packages/ipykernel/comm/comm.py:32: DeprecationWarning: Comm._session_default is deprecated: use @default decorator instead.
def _session_default(self):
/home/enf/anaconda/lib/python2.7/site-packages/ipykernel/comm/comm.py:41: DeprecationWarning: Comm._topic_default is deprecated: use @default decorator instead.
def _topic_default(self):
/home/enf/anaconda/lib/python2.7/site-packages/ipykernel/comm/comm.py:24: DeprecationWarning: Comm._kernel_default is deprecated: use @default decorator instead.
def _kernel_default(self):
/home/enf/anaconda/lib/python2.7/site-packages/ipykernel/comm/comm.py:52: DeprecationWarning: Comm._comm_id_default is deprecated: use @default decorator instead.
def _comm_id_default(self):
/home/enf/anaconda/lib/python2.7/site-packages/ipykernel/comm/manager.py:37: DeprecationWarning: CommManager._iopub_socket_default is deprecated: use @default decorator instead.
def _iopub_socket_default(self):
/home/enf/anaconda/lib/python2.7/site-packages/ipykernel/comm/comm.py:32: DeprecationWarning: Comm._session_default is deprecated: use @default decorator instead.
def _session_default(self):
/home/enf/anaconda/lib/python2.7/site-packages/ipykernel/comm/comm.py:41: DeprecationWarning: Comm._topic_default is deprecated: use @default decorator instead.
def _topic_default(self):
/home/enf/anaconda/lib/python2.7/site-packages/ipywidgets/widgets/widget.py:194: DeprecationWarning: NGLWidget._comm_changed is deprecated: use @observe and @unobserve instead.
def _comm_changed(self, name, new):
/home/enf/anaconda/lib/python2.7/site-packages/ipywidgets/widgets/widget.py:513: DeprecationWarning: on_trait_change is deprecated: use observe instead
/home/enf/anaconda/lib/python2.7/site-packages/IPython/core/formatters.py:92: DeprecationWarning: DisplayFormatter._ipython_display_formatter_default is deprecated: use @default decorator instead.
def _ipython_display_formatter_default(self):
%% Cell type:markdown id: tags:
Now that we're oriented, let's use ML to do some chemistry.
So, step (2) will entail featurizing the dataset.
The available featurizations that come standard with deepchem are ECFP4 fingerprints, RDKit descriptors, NNScore-style bdescriptors, and hybrid binding pocket descriptors. Details can be found on ```deepchem.io```.
Note how we separate our featurizers into those that featurize individual chemical compounds, compound_featurizers, and those that featurize molecular complexes, complex_featurizers.
Now, let's perform the actual featurization. Calling ```featurizer.featurize()``` will return an instance of class ```FeaturizedSamples```. Internally, ```featurizer.featurize()``` (a) computes the user-specified features on the data, (b) transforms the inputs into X and y NumPy arrays suitable for ML algorithms, and (c) constructs a ```FeaturizedSamples()``` instance that has useful methods, such as an iterator, over the featurized data.
%% Cell type:code id: tags:
``` python
#Make a directory in which to store the featurized complexes.
/home/enf/anaconda/lib/python2.7/site-packages/ipyparallel/client/client.py:306: DeprecationWarning: Client._profile_default is deprecated: use @default decorator instead.
def _profile_default(self):
/home/enf/anaconda/lib/python2.7/site-packages/ipyparallel/client/client.py:306: DeprecationWarning: Client._profile_default is deprecated: use @default decorator instead.
def _profile_default(self):
/home/enf/anaconda/lib/python2.7/site-packages/IPython/core/profiledir.py:57: DeprecationWarning: ProfileDir._location_changed is deprecated: use @observe and @unobserve instead.
def _location_changed(self, name, old, new):
/home/enf/anaconda/lib/python2.7/site-packages/IPython/core/profiledir.py:126: DeprecationWarning: ProfileDir._security_dir_changed is deprecated: use @observe and @unobserve instead.
def _security_dir_changed(self, name, old, new):
/home/enf/anaconda/lib/python2.7/site-packages/IPython/core/profiledir.py:71: DeprecationWarning: ProfileDir._log_dir_changed is deprecated: use @observe and @unobserve instead.
def _log_dir_changed(self, name, old, new):
/home/enf/anaconda/lib/python2.7/site-packages/IPython/core/profiledir.py:111: DeprecationWarning: ProfileDir._startup_dir_changed is deprecated: use @observe and @unobserve instead.
def _startup_dir_changed(self, name, old, new):
/home/enf/anaconda/lib/python2.7/site-packages/IPython/core/profiledir.py:132: DeprecationWarning: ProfileDir._pid_dir_changed is deprecated: use @observe and @unobserve instead.
def _pid_dir_changed(self, name, old, new):
/home/enf/anaconda/lib/python2.7/site-packages/IPython/core/profiledir.py:138: DeprecationWarning: ProfileDir._static_dir_changed is deprecated: use @observe and @unobserve instead.
def _static_dir_changed(self, name, old, new):
/home/enf/anaconda/lib/python2.7/site-packages/jupyter_client/session.py:351: DeprecationWarning: Session._digest_mod_default is deprecated: use @default decorator instead.
def _digest_mod_default(self):
/home/enf/anaconda/lib/python2.7/site-packages/jupyter_client/session.py:331: DeprecationWarning: Session._key_default is deprecated: use @default decorator instead.
def _key_default(self):
/home/enf/anaconda/lib/python2.7/site-packages/jupyter_client/session.py:306: DeprecationWarning: Session._session_default is deprecated: use @default decorator instead.
def _session_default(self):
/home/enf/anaconda/lib/python2.7/site-packages/jupyter_client/session.py:334: DeprecationWarning: Session._key_changed is deprecated: use @observe and @unobserve instead.
def _key_changed(self):
/home/enf/anaconda/lib/python2.7/site-packages/jupyter_client/session.py:351: DeprecationWarning: Session._digest_mod_default is deprecated: use @default decorator instead.
def _digest_mod_default(self):
/home/enf/anaconda/lib/python2.7/site-packages/jupyter_client/session.py:306: DeprecationWarning: Session._session_default is deprecated: use @default decorator instead.
Now, we conduct a train-test split. If you'd like, you can choose `splittype="scaffold"` instead to perform a train-test split based on Bemis-Murcko scaffolds.
/scratch/users/enf/deep-docking/deepchem/deepchem/featurizers/featurize.py:470: DeprecationWarning: using a non-integer number instead of an integer will result in an error in the future
/scratch/users/enf/deep-docking/deepchem/deepchem/featurizers/featurize.py:470: DeprecationWarning: using a non-integer number instead of an integer will result in an error in the future
/scratch/users/enf/deep-docking/deepchem/deepchem/featurizers/featurize.py:470: DeprecationWarning: using a non-integer number instead of an integer will result in an error in the future
/scratch/users/enf/deep-docking/deepchem/deepchem/featurizers/featurize.py:471: DeprecationWarning: using a non-integer number instead of an integer will result in an error in the future
shuffled[valid_cutoff:])
%% Cell type:markdown id: tags:
We generate separate instances of the Dataset() object to hermetically seal the train dataset from the test dataset. This style lends itself easily to validation-set type hyperparameter searches, which we will illustate in a separate section of this tutorial.
Now, we're ready to do some learning! To set up a model, we will need: (a) a dictionary ```task_types``` that maps a task, in this case ```label```, i.e. the Ki, to the type of the task, in this case ```regression```. For the multitask use case, one will have a series of keys, each of which is a different task (Ki, solubility, renal half-life, etc.) that maps to a different task type (regression or classification).
To fit a deepchem model, first we instantiate one of the provided (or user-written) model classes. In this case, we have a created a convenience class to wrap around any ML model available in Sci-Kit Learn that can in turn be used to interoperate with deepchem. To instantiate an ```SklearnModel```, you will need (a) task_types, (b) model_params, another ```dict``` as illustrated below, and (c) a ```model_instance``` defining the type of model you would like to fit, in this case a ```RandomForestRegressor```.
Saving predictions to <open file '<fdopen>', mode 'w+b' at 0x7f42c787d390>
Saving model performance scores to <open file '<fdopen>', mode 'w+b' at 0x7f42c787d540>
Saving predictions to <open file '<fdopen>', mode 'w+b' at 0x7f42c787d4b0>
Saving model performance scores to <open file '<fdopen>', mode 'w+b' at 0x7f42c787d780>
/local-scratch/enf/7438120/tmp1Yjtiz
/home/enf/anaconda/lib/python2.7/site-packages/IPython/core/formatters.py:98: DeprecationWarning: DisplayFormatter._formatters_default is deprecated: use @default decorator instead.
def _formatters_default(self):
/home/enf/anaconda/lib/python2.7/site-packages/IPython/core/formatters.py:677: DeprecationWarning: PlainTextFormatter._deferred_printers_default is deprecated: use @default decorator instead.
def _deferred_printers_default(self):
/home/enf/anaconda/lib/python2.7/site-packages/IPython/core/formatters.py:669: DeprecationWarning: PlainTextFormatter._singleton_printers_default is deprecated: use @default decorator instead.
def _singleton_printers_default(self):
/home/enf/anaconda/lib/python2.7/site-packages/IPython/core/formatters.py:672: DeprecationWarning: PlainTextFormatter._type_printers_default is deprecated: use @default decorator instead.
def _type_printers_default(self):
/home/enf/anaconda/lib/python2.7/site-packages/IPython/core/formatters.py:669: DeprecationWarning: PlainTextFormatter._singleton_printers_default is deprecated: use @default decorator instead.
def _singleton_printers_default(self):
/home/enf/anaconda/lib/python2.7/site-packages/IPython/core/formatters.py:672: DeprecationWarning: PlainTextFormatter._type_printers_default is deprecated: use @default decorator instead.
def _type_printers_default(self):
/home/enf/anaconda/lib/python2.7/site-packages/IPython/core/formatters.py:677: DeprecationWarning: PlainTextFormatter._deferred_printers_default is deprecated: use @default decorator instead.
def _deferred_printers_default(self):
task_name r2_score rms_error split
0 label 0.806727 0.988301 train
0 label 0.342652 1.805124 test
%% Cell type:markdown id: tags:
In this simple example, in few yet intuitive lines of code, we traced the machine learning arc from featurizing a raw dataset to fitting and evaluating a model.
Here, we featurized only the ligand. The signal we observed in R^2 reflects the ability of circular fingerprints and random forests to learn general features that make ligands "drug-like."
Let's take a quick look at what the algorithm determines to be high- and low-affinity drugs.
The preceding simple example, in few yet intuitive lines of code, traces the machine learning arc from featurizing a raw dataset to fitting and evaluating a model.
In this next section, we illustrate ```deepchem```'s modularity, and thereby the ease with which one can explore different featurization schemes, different models, and combinations thereof, to achieve the best performance on a given dataset. We will demonstrate this by examining protein-ligand interactions.
%% Cell type:markdown id: tags:
In the previous section, we featurized only the ligand. The signal we observed in R^2 reflects the ability of circular fingerprints and random forests to learn general features that make ligands "drug-like." However, the affinity of a drug for a target is determined not only by the drug itself, of course, but the way in which it interacts with a protein.
