Variational Autoencoder

Variational Autoencoder#

Hide code cell source

 
import logging
from functools import partial

import pandas as pd
import sklearn
import torch
from fastai import learner
from fastai.basics import *
from fastai.callback.all import *
from fastai.callback.all import EarlyStoppingCallback
from fastai.learner import Learner
from fastai.torch_basics import *
from IPython.display import display
from sklearn.impute import SimpleImputer
from sklearn.preprocessing import StandardScaler
from torch.nn import Sigmoid

import pimmslearn
import pimmslearn.model
import pimmslearn.models as models
import pimmslearn.nb
from pimmslearn.analyzers import analyzers
from pimmslearn.io import datasplits
# overwriting Recorder callback with custom plot_loss
from pimmslearn.models import ae, plot_loss

learner.Recorder.plot_loss = plot_loss


logger = pimmslearn.logging.setup_logger(logging.getLogger('pimmslearn'))
logger.info(
    "Experiment 03 - Analysis of latent spaces and performance comparisions")

figures = {}  # collection of ax or figures

pimmslearn - INFO     Experiment 03 - Analysis of latent spaces and performance comparisions

Hide code cell source

 
# catch passed parameters
args = None
args = dict(globals()).keys()

Papermill script parameters:

# files and folders
# Datasplit folder with data for experiment
folder_experiment: str = 'runs/example'
folder_data: str = ''  # specify data directory if needed
file_format: str = 'csv'  # file format of create splits, default pickle (pkl)
# Machine parsed metadata from rawfile workflow
fn_rawfile_metadata: str = 'data/dev_datasets/HeLa_6070/files_selected_metadata_N50.csv'
# training
epochs_max: int = 50  # Maximum number of epochs
batch_size: int = 64  # Batch size for training (and evaluation)
cuda: bool = True  # Whether to use a GPU for training
# model
# Dimensionality of encoding dimension (latent space of model)
latent_dim: int = 25
# A underscore separated string of layers, '256_128' for the encoder, reverse will be use for decoder
hidden_layers: str = '256_128'
# force_train:bool = True # Force training when saved model could be used. Per default re-train model
patience: int = 50  # Patience for early stopping
sample_idx_position: int = 0  # position of index which is sample ID
model: str = 'VAE'  # model name
model_key: str = 'VAE'  # potentially alternative key for model (grid search)
save_pred_real_na: bool = True  # Save all predictions for missing values
# metadata -> defaults for metadata extracted from machine data
meta_date_col: str = None  # date column in meta data
meta_cat_col: str = None  # category column in meta data

# Parameters
model = "VAE"
latent_dim = 10
batch_size = 64
epochs_max = 300
hidden_layers = "64"
sample_idx_position = 0
cuda = False
save_pred_real_na = True
fn_rawfile_metadata = "https://raw.githubusercontent.com/RasmussenLab/njab/HEAD/docs/tutorial/data/alzheimer/meta.csv"
folder_experiment = "runs/alzheimer_study"
model_key = "VAE"

Some argument transformations

Hide code cell source

 
args = pimmslearn.nb.get_params(args, globals=globals())
args

{'folder_experiment': 'runs/alzheimer_study',
 'folder_data': '',
 'file_format': 'csv',
 'fn_rawfile_metadata': 'https://raw.githubusercontent.com/RasmussenLab/njab/HEAD/docs/tutorial/data/alzheimer/meta.csv',
 'epochs_max': 300,
 'batch_size': 64,
 'cuda': False,
 'latent_dim': 10,
 'hidden_layers': '64',
 'patience': 50,
 'sample_idx_position': 0,
 'model': 'VAE',
 'model_key': 'VAE',
 'save_pred_real_na': True,
 'meta_date_col': None,
 'meta_cat_col': None}

Hide code cell source

 
args = pimmslearn.nb.args_from_dict(args)

if isinstance(args.hidden_layers, str):
    args.overwrite_entry("hidden_layers", [int(x)
                         for x in args.hidden_layers.split('_')])
else:
    raise ValueError(
        f"hidden_layers is of unknown type {type(args.hidden_layers)}")
args

{'batch_size': 64,
 'cuda': False,
 'data': Path('runs/alzheimer_study/data'),
 'epochs_max': 300,
 'file_format': 'csv',
 'fn_rawfile_metadata': 'https://raw.githubusercontent.com/RasmussenLab/njab/HEAD/docs/tutorial/data/alzheimer/meta.csv',
 'folder_data': '',
 'folder_experiment': Path('runs/alzheimer_study'),
 'hidden_layers': [64],
 'latent_dim': 10,
 'meta_cat_col': None,
 'meta_date_col': None,
 'model': 'VAE',
 'model_key': 'VAE',
 'out_figures': Path('runs/alzheimer_study/figures'),
 'out_folder': Path('runs/alzheimer_study'),
 'out_metrics': Path('runs/alzheimer_study'),
 'out_models': Path('runs/alzheimer_study'),
 'out_preds': Path('runs/alzheimer_study/preds'),
 'patience': 50,
 'sample_idx_position': 0,
 'save_pred_real_na': True}

Some naming conventions

Hide code cell source

 
TEMPLATE_MODEL_PARAMS = 'model_params_{}.json'

Load data in long format#

Hide code cell source

 
data = datasplits.DataSplits.from_folder(
    args.data, file_format=args.file_format)

pimmslearn.io.datasplits - INFO     Loaded 'train_X' from file: runs/alzheimer_study/data/train_X.csv
pimmslearn.io.datasplits - INFO     Loaded 'val_y' from file: runs/alzheimer_study/data/val_y.csv
pimmslearn.io.datasplits - INFO     Loaded 'test_y' from file: runs/alzheimer_study/data/test_y.csv

data is loaded in long format

Hide code cell source

 
data.train_X.sample(5)

Sample ID   protein groups 
Sample_008  P18669            17.218
Sample_065  I3L0N3;P46459     15.545
Sample_082  Q06828            17.710
Sample_103  Q02487;Q02487-2   17.373
Sample_157  Q9P0K9            16.817
Name: intensity, dtype: float64

Infer index names from long format

Hide code cell source

 
index_columns = list(data.train_X.index.names)
sample_id = index_columns.pop(args.sample_idx_position)
if len(index_columns) == 1:
    index_column = index_columns.pop()
    index_columns = None
    logger.info(f"{sample_id = }, single feature: {index_column = }")
else:
    logger.info(f"{sample_id = }, multiple features: {index_columns = }")

if not index_columns:
    index_columns = [sample_id, index_column]
else:
    raise NotImplementedError(
        "More than one feature: Needs to be implemented. see above logging output.")

pimmslearn - INFO     sample_id = 'Sample ID', single feature: index_column = 'protein groups'

load meta data for splits

Hide code cell source

 
if args.fn_rawfile_metadata:
    df_meta = pd.read_csv(args.fn_rawfile_metadata, index_col=0)
    display(df_meta.loc[data.train_X.index.levels[0]])
else:
    df_meta = None
_collection site _age at CSF collection _gender _t-tau [ng/L] _p-tau [ng/L] _Abeta-42 [ng/L] _Abeta-40 [ng/L] _Abeta-42/Abeta-40 ratio _primary biochemical AD classification _clinical AD diagnosis _MMSE score
Sample ID
Sample_000 Sweden 71.000 f 703.000 85.000 562.000 NaN NaN biochemical control NaN NaN
Sample_001 Sweden 77.000 m 518.000 91.000 334.000 NaN NaN biochemical AD NaN NaN
Sample_002 Sweden 75.000 m 974.000 87.000 515.000 NaN NaN biochemical AD NaN NaN
Sample_003 Sweden 72.000 f 950.000 109.000 394.000 NaN NaN biochemical AD NaN NaN
Sample_004 Sweden 63.000 f 873.000 88.000 234.000 NaN NaN biochemical AD NaN NaN
... ... ... ... ... ... ... ... ... ... ... ...
Sample_205 Berlin 69.000 f 1,945.000 NaN 699.000 12,140.000 0.058 biochemical AD AD 17.000
Sample_206 Berlin 73.000 m 299.000 NaN 1,420.000 16,571.000 0.086 biochemical control non-AD 28.000
Sample_207 Berlin 71.000 f 262.000 NaN 639.000 9,663.000 0.066 biochemical control non-AD 28.000
Sample_208 Berlin 83.000 m 289.000 NaN 1,436.000 11,285.000 0.127 biochemical control non-AD 24.000
Sample_209 Berlin 63.000 f 591.000 NaN 1,299.000 11,232.000 0.116 biochemical control non-AD 29.000

210 rows × 11 columns

Initialize Comparison#

  • replicates idea for truely missing values: Define truth as by using n=3 replicates to impute each sample

  • real test data:

    • Not used for predictions or early stopping.

    • [x] add some additional NAs based on distribution of data

Hide code cell source

 
freq_feat = pimmslearn.io.datasplits.load_freq(args.data)
freq_feat.head()  # training data

protein groups
A0A024QZX5;A0A087X1N8;P35237                                                     197
A0A024R0T9;K7ER74;P02655                                                         208
A0A024R3W6;A0A024R412;O60462;O60462-2;O60462-3;O60462-4;O60462-5;Q7LBX6;X5D2Q8   185
A0A024R644;A0A0A0MRU5;A0A1B0GWI2;O75503                                          208
A0A075B6H7                                                                        97
Name: freq, dtype: int64

Produce some addional simulated samples#

The validation simulated NA is used to by all models to evaluate training performance.

Hide code cell source

 
val_pred_simulated_na = data.val_y.to_frame(name='observed')
val_pred_simulated_na
observed
Sample ID protein groups
Sample_158 Q9UN70;Q9UN70-2 14.630
Sample_050 Q9Y287 15.755
Sample_107 Q8N475;Q8N475-2 15.029
Sample_199 P06307 19.376
Sample_067 Q5VUB5 15.309
... ... ...
Sample_111 F6SYF8;Q9UBP4 22.822
Sample_002 A0A0A0MT36 18.165
Sample_049 Q8WY21;Q8WY21-2;Q8WY21-3;Q8WY21-4 15.525
Sample_182 Q8NFT8 14.379
Sample_123 Q16853;Q16853-2 14.504

12600 rows × 1 columns

Hide code cell source

 
test_pred_simulated_na = data.test_y.to_frame(name='observed')
test_pred_simulated_na.describe()
observed
count 12,600.000
mean 16.339
std 2.741
min 7.209
25% 14.412
50% 15.935
75% 17.910
max 30.140

Data in wide format#

  • Autoencoder need data in wide format

Hide code cell source

 
data.to_wide_format()
args.M = data.train_X.shape[-1]
data.train_X.head()
protein groups A0A024QZX5;A0A087X1N8;P35237 A0A024R0T9;K7ER74;P02655 A0A024R3W6;A0A024R412;O60462;O60462-2;O60462-3;O60462-4;O60462-5;Q7LBX6;X5D2Q8 A0A024R644;A0A0A0MRU5;A0A1B0GWI2;O75503 A0A075B6H7 A0A075B6H9 A0A075B6I0 A0A075B6I1 A0A075B6I6 A0A075B6I9 ... Q9Y653;Q9Y653-2;Q9Y653-3 Q9Y696 Q9Y6C2 Q9Y6N6 Q9Y6N7;Q9Y6N7-2;Q9Y6N7-4 Q9Y6R7 Q9Y6X5 Q9Y6Y8;Q9Y6Y8-2 Q9Y6Y9 S4R3U6
Sample ID
Sample_000 15.912 16.852 15.570 16.481 17.301 20.246 16.764 17.584 16.988 20.054 ... 16.012 15.178 NaN 15.050 16.842 NaN NaN 19.563 NaN 12.805
Sample_001 NaN 16.874 15.519 16.387 NaN 19.941 18.786 17.144 NaN 19.067 ... 15.528 15.576 NaN 14.833 16.597 20.299 15.556 19.386 13.970 12.442
Sample_002 16.111 NaN 15.935 16.416 18.175 19.251 16.832 15.671 17.012 18.569 ... 15.229 14.728 13.757 15.118 17.440 19.598 15.735 20.447 12.636 12.505
Sample_003 16.107 17.032 15.802 16.979 15.963 19.628 17.852 18.877 14.182 18.985 ... 15.495 14.590 14.682 15.140 17.356 19.429 NaN 20.216 NaN 12.445
Sample_004 15.603 15.331 15.375 16.679 NaN 20.450 18.682 17.081 14.140 19.686 ... 14.757 NaN NaN 15.256 17.075 19.582 15.328 NaN 13.145 NaN

5 rows × 1421 columns

Add interpolation performance#

Fill Validation data with potentially missing features#

Hide code cell source

 
data.train_X
protein groups A0A024QZX5;A0A087X1N8;P35237 A0A024R0T9;K7ER74;P02655 A0A024R3W6;A0A024R412;O60462;O60462-2;O60462-3;O60462-4;O60462-5;Q7LBX6;X5D2Q8 A0A024R644;A0A0A0MRU5;A0A1B0GWI2;O75503 A0A075B6H7 A0A075B6H9 A0A075B6I0 A0A075B6I1 A0A075B6I6 A0A075B6I9 ... Q9Y653;Q9Y653-2;Q9Y653-3 Q9Y696 Q9Y6C2 Q9Y6N6 Q9Y6N7;Q9Y6N7-2;Q9Y6N7-4 Q9Y6R7 Q9Y6X5 Q9Y6Y8;Q9Y6Y8-2 Q9Y6Y9 S4R3U6
Sample ID
Sample_000 15.912 16.852 15.570 16.481 17.301 20.246 16.764 17.584 16.988 20.054 ... 16.012 15.178 NaN 15.050 16.842 NaN NaN 19.563 NaN 12.805
Sample_001 NaN 16.874 15.519 16.387 NaN 19.941 18.786 17.144 NaN 19.067 ... 15.528 15.576 NaN 14.833 16.597 20.299 15.556 19.386 13.970 12.442
Sample_002 16.111 NaN 15.935 16.416 18.175 19.251 16.832 15.671 17.012 18.569 ... 15.229 14.728 13.757 15.118 17.440 19.598 15.735 20.447 12.636 12.505
Sample_003 16.107 17.032 15.802 16.979 15.963 19.628 17.852 18.877 14.182 18.985 ... 15.495 14.590 14.682 15.140 17.356 19.429 NaN 20.216 NaN 12.445
Sample_004 15.603 15.331 15.375 16.679 NaN 20.450 18.682 17.081 14.140 19.686 ... 14.757 NaN NaN 15.256 17.075 19.582 15.328 NaN 13.145 NaN
... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ...
Sample_205 15.682 16.886 14.910 16.482 NaN 17.705 17.039 NaN 16.413 19.102 ... NaN 15.684 14.236 15.415 17.551 17.922 16.340 19.928 12.929 NaN
Sample_206 15.798 17.554 15.600 15.938 NaN 18.154 18.152 16.503 16.860 18.538 ... 15.422 16.106 NaN 15.345 17.084 18.708 NaN 19.433 NaN NaN
Sample_207 15.739 NaN 15.469 16.898 NaN 18.636 17.950 16.321 16.401 18.849 ... 15.808 16.098 14.403 15.715 NaN 18.725 16.138 19.599 13.637 11.174
Sample_208 15.477 16.779 14.995 16.132 NaN 14.908 NaN NaN 16.119 18.368 ... 15.157 16.712 NaN 14.640 16.533 19.411 15.807 19.545 NaN NaN
Sample_209 NaN 17.261 15.175 16.235 NaN 17.893 17.744 16.371 15.780 18.806 ... 15.237 15.652 15.211 14.205 16.749 19.275 15.732 19.577 11.042 11.791

210 rows × 1421 columns

Hide code cell source

 
data.val_y  # potentially has less features
protein groups A0A024QZX5;A0A087X1N8;P35237 A0A024R0T9;K7ER74;P02655 A0A024R3W6;A0A024R412;O60462;O60462-2;O60462-3;O60462-4;O60462-5;Q7LBX6;X5D2Q8 A0A024R644;A0A0A0MRU5;A0A1B0GWI2;O75503 A0A075B6H7 A0A075B6H9 A0A075B6I0 A0A075B6I1 A0A075B6I6 A0A075B6I9 ... Q9Y653;Q9Y653-2;Q9Y653-3 Q9Y696 Q9Y6C2 Q9Y6N6 Q9Y6N7;Q9Y6N7-2;Q9Y6N7-4 Q9Y6R7 Q9Y6X5 Q9Y6Y8;Q9Y6Y8-2 Q9Y6Y9 S4R3U6
Sample ID
Sample_000 NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN ... NaN NaN NaN NaN NaN 19.863 NaN NaN NaN NaN
Sample_001 NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN ... NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN
Sample_002 NaN 14.523 NaN NaN NaN NaN NaN NaN NaN NaN ... NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN
Sample_003 NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN ... NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN
Sample_004 NaN NaN NaN NaN 15.473 NaN NaN NaN NaN NaN ... NaN NaN 14.048 NaN NaN NaN NaN 19.867 NaN 12.235
... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ...
Sample_205 NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN ... NaN NaN NaN NaN NaN NaN NaN NaN NaN 11.802
Sample_206 NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN ... NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN
Sample_207 NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN ... NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN
Sample_208 NaN NaN NaN NaN NaN NaN 17.530 NaN NaN NaN ... NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN
Sample_209 15.727 NaN NaN NaN NaN NaN NaN NaN NaN NaN ... NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN

210 rows × 1419 columns

Hide code cell source

 
data.val_y = pd.DataFrame(pd.NA, index=data.train_X.index,
                          columns=data.train_X.columns).fillna(data.val_y)
data.val_y
protein groups A0A024QZX5;A0A087X1N8;P35237 A0A024R0T9;K7ER74;P02655 A0A024R3W6;A0A024R412;O60462;O60462-2;O60462-3;O60462-4;O60462-5;Q7LBX6;X5D2Q8 A0A024R644;A0A0A0MRU5;A0A1B0GWI2;O75503 A0A075B6H7 A0A075B6H9 A0A075B6I0 A0A075B6I1 A0A075B6I6 A0A075B6I9 ... Q9Y653;Q9Y653-2;Q9Y653-3 Q9Y696 Q9Y6C2 Q9Y6N6 Q9Y6N7;Q9Y6N7-2;Q9Y6N7-4 Q9Y6R7 Q9Y6X5 Q9Y6Y8;Q9Y6Y8-2 Q9Y6Y9 S4R3U6
Sample ID
Sample_000 NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN ... NaN NaN NaN NaN NaN 19.863 NaN NaN NaN NaN
Sample_001 NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN ... NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN
Sample_002 NaN 14.523 NaN NaN NaN NaN NaN NaN NaN NaN ... NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN
Sample_003 NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN ... NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN
Sample_004 NaN NaN NaN NaN 15.473 NaN NaN NaN NaN NaN ... NaN NaN 14.048 NaN NaN NaN NaN 19.867 NaN 12.235
... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ...
Sample_205 NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN ... NaN NaN NaN NaN NaN NaN NaN NaN NaN 11.802
Sample_206 NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN ... NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN
Sample_207 NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN ... NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN
Sample_208 NaN NaN NaN NaN NaN NaN 17.530 NaN NaN NaN ... NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN
Sample_209 15.727 NaN NaN NaN NaN NaN NaN NaN NaN NaN ... NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN

210 rows × 1421 columns

Variational Autoencoder#

Analysis: DataLoaders, Model, transform#

Hide code cell source

 
default_pipeline = sklearn.pipeline.Pipeline(
    [
        ('normalize', StandardScaler()),
        ('impute', SimpleImputer(add_indicator=False))
    ])

Analysis: DataLoaders, Model#

Hide code cell source

 
analysis = ae.AutoEncoderAnalysis(  # datasplits=data,
    train_df=data.train_X,
    val_df=data.val_y,
    model=models.vae.VAE,
    model_kwargs=dict(n_features=data.train_X.shape[-1],
                      n_neurons=args.hidden_layers,
                      # last_encoder_activation=None,
                      last_decoder_activation=None,
                      dim_latent=args.latent_dim),
    transform=default_pipeline,
    decode=['normalize'],
    bs=args.batch_size)
args.n_params = analysis.n_params_ae
if args.cuda:
    analysis.model = analysis.model.cuda()
analysis.model

VAE(
  (encoder): Sequential(
    (0): Linear(in_features=1421, out_features=64, bias=True)
    (1): Dropout(p=0.2, inplace=False)
    (2): BatchNorm1d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    (3): LeakyReLU(negative_slope=0.1)
    (4): Linear(in_features=64, out_features=20, bias=True)
  )
  (decoder): Sequential(
    (0): Linear(in_features=10, out_features=64, bias=True)
    (1): Dropout(p=0.2, inplace=False)
    (2): BatchNorm1d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    (3): LeakyReLU(negative_slope=0.1)
    (4): Linear(in_features=64, out_features=2842, bias=True)
  )
)

Training#

Hide code cell source

 
results = []
loss_fct = partial(models.vae.loss_fct, results=results)

Hide code cell source

 
analysis.learn = Learner(dls=analysis.dls,
                         model=analysis.model,
                         loss_func=loss_fct,
                         cbs=[ae.ModelAdapterVAE(),
                              EarlyStoppingCallback(patience=args.patience)
                              ])

analysis.learn.show_training_loop()

Start Fit
   - before_fit     : [TrainEvalCallback, Recorder, ProgressCallback, EarlyStoppingCallback]
  Start Epoch Loop
     - before_epoch   : [Recorder, ProgressCallback]
    Start Train
       - before_train   : [TrainEvalCallback, Recorder, ProgressCallback]
      Start Batch Loop
         - before_batch   : [ModelAdapterVAE, CastToTensor]
         - after_pred     : [ModelAdapterVAE]
         - after_loss     : [ModelAdapterVAE]
         - before_backward: []
         - before_step    : []
         - after_step     : []
         - after_cancel_batch: []
         - after_batch    : [TrainEvalCallback, Recorder, ProgressCallback]
      End Batch Loop
    End Train
     - after_cancel_train: [Recorder]
     - after_train    : [Recorder, ProgressCallback]
    Start Valid
       - before_validate: [TrainEvalCallback, Recorder, ProgressCallback]
      Start Batch Loop
         - **CBs same as train batch**: []
      End Batch Loop
    End Valid
     - after_cancel_validate: [Recorder]
     - after_validate : [Recorder, ProgressCallback]
  End Epoch Loop
   - after_cancel_epoch: []
   - after_epoch    : [Recorder, EarlyStoppingCallback]
End Fit
 - after_cancel_fit: []
 - after_fit      : [ProgressCallback, EarlyStoppingCallback]

Adding a EarlyStoppingCallback results in an error. Potential fix in PR3509 is not yet in current version. Try again later

Hide code cell source

 
# learn.summary()

Hide code cell source

 
suggested_lr = analysis.learn.lr_find()
analysis.params['suggested_inital_lr'] = suggested_lr.valley
suggested_lr

SuggestedLRs(valley=0.004365158267319202)
_images/493dd9364fcbed073b59e4d485f15e40b49d0c700df0918cb8b9ab82ffc4fc1c.png

Hide code cell source

 
results.clear()  # reset results

dump model config

Hide code cell source

 
# needs class as argument, not instance, but serialization needs instance
analysis.params['last_decoder_activation'] = Sigmoid()

pimmslearn.io.dump_json(
    pimmslearn.io.parse_dict(
        analysis.params, types=[
            (torch.nn.modules.module.Module, lambda m: str(m))
        ]),
    args.out_models / TEMPLATE_MODEL_PARAMS.format(args.model_key))

# restore original value
analysis.params['last_decoder_activation'] = Sigmoid

Hide code cell source

 
# papermill_description=train
analysis.learn.fit_one_cycle(args.epochs_max, lr_max=suggested_lr.valley)
epoch train_loss valid_loss time
0 1681.260010 92.933205 00:00
1 1677.450073 93.197266 00:00
2 1676.770386 93.968567 00:00
3 1670.359009 94.387527 00:00
4 1667.820068 94.632935 00:00
5 1665.179565 95.508972 00:00
6 1661.601318 95.151268 00:00
7 1658.818848 95.213013 00:00
8 1653.829956 95.275299 00:00
9 1651.753784 95.326698 00:00
10 1647.774902 95.325226 00:00
11 1642.565918 95.175858 00:00
12 1636.571167 94.771996 00:00
13 1630.033936 94.969894 00:00
14 1623.838257 94.011261 00:00
15 1617.940063 93.753952 00:00
16 1611.727295 93.625000 00:00
17 1605.685059 93.076286 00:00
18 1596.703369 92.917961 00:00
19 1588.318726 92.697433 00:00
20 1580.251587 92.167198 00:00
21 1572.025146 92.470650 00:00
22 1562.621338 92.372658 00:00
23 1552.168335 92.248528 00:00
24 1541.813965 92.515396 00:00
25 1530.719360 92.725372 00:00
26 1519.046997 92.691254 00:00
27 1507.603760 92.719414 00:00
28 1497.102783 92.570152 00:00
29 1486.316162 92.058990 00:00
30 1474.222412 92.939224 00:00
31 1462.927124 92.705879 00:00
32 1451.918091 93.054527 00:00
33 1439.776855 93.495575 00:00
34 1430.229126 94.568779 00:00
35 1419.189209 94.725548 00:00
36 1409.200684 94.876076 00:00
37 1399.114990 95.296013 00:00
38 1389.443115 94.942818 00:00
39 1379.382324 95.005264 00:00
40 1369.353149 94.872528 00:00
41 1359.266724 94.546623 00:00
42 1349.156860 93.559479 00:00
43 1339.177612 93.103928 00:00
44 1329.869629 93.074844 00:00
45 1321.256836 92.431213 00:00
46 1312.543579 91.778519 00:00
47 1305.022339 91.950966 00:00
48 1297.779053 92.367325 00:00
49 1290.531250 91.971901 00:00
50 1283.642578 92.359161 00:00
51 1274.620239 92.333214 00:00
52 1269.216431 91.942368 00:00
53 1263.001709 91.799011 00:00
54 1256.208618 92.077408 00:00
55 1249.145752 91.962097 00:00
56 1241.852783 91.425781 00:00
57 1236.193115 91.663345 00:00
58 1229.466431 91.787544 00:00
59 1222.492676 91.886932 00:00
60 1218.031860 91.858109 00:00
61 1211.416748 92.664055 00:00
62 1205.817993 92.675346 00:00
63 1200.116577 91.576729 00:00
64 1194.683838 92.051529 00:00
65 1189.678955 92.148064 00:00
66 1183.853394 91.904091 00:00
67 1180.686523 92.228996 00:00
68 1176.490967 92.599709 00:00
69 1173.830688 92.476151 00:00
70 1169.118774 92.980522 00:00
71 1166.697388 93.198235 00:00
72 1162.679932 92.535194 00:00
73 1159.002075 91.792870 00:00
74 1154.085449 91.593491 00:00
75 1151.417847 91.624886 00:00
76 1149.590942 91.542877 00:00
77 1145.024048 92.156807 00:00
78 1141.539062 92.733093 00:00
79 1138.490234 92.969772 00:00
80 1135.895508 92.002029 00:00
81 1131.641235 92.181732 00:00
82 1129.402344 92.788414 00:00
83 1126.167969 92.456902 00:00
84 1122.417114 91.888458 00:00
85 1118.484863 91.517410 00:00
86 1116.457397 91.753662 00:00
87 1113.608765 92.899895 00:00
88 1111.304443 92.329819 00:00
89 1108.042114 92.442894 00:00
90 1106.831543 92.127449 00:00
91 1104.108521 92.666824 00:00
92 1103.404541 92.222954 00:00
93 1101.389160 92.531891 00:00
94 1098.035156 92.592186 00:00
95 1095.347412 92.046753 00:00
96 1092.231445 91.951965 00:00
97 1089.109741 92.109200 00:00
98 1087.489258 92.385918 00:00
99 1085.430420 91.938026 00:00
100 1084.357056 92.421646 00:00
101 1082.756592 92.208168 00:00
102 1080.615234 91.822823 00:00
103 1081.621948 92.788315 00:00
104 1080.165771 92.481972 00:00
105 1078.049072 92.701241 00:00
106 1076.205933 92.097954 00:00 
No improvement since epoch 56: early stopping

Save number of actually trained epochs

Hide code cell source

 
args.epoch_trained = analysis.learn.epoch + 1
args.epoch_trained

107

Loss normalized by total number of measurements#

Hide code cell source

 
N_train_notna = data.train_X.notna().sum().sum()
N_val_notna = data.val_y.notna().sum().sum()
fig = models.plot_training_losses(analysis.learn, args.model_key,
                                  folder=args.out_figures,
                                  norm_factors=[N_train_notna, N_val_notna])

pimmslearn.plotting - INFO     Saved Figures to runs/alzheimer_study/figures/vae_training
_images/5ed7afef32087fdbc456c4907bc423b87c805f849f1bca9e2b7b419b6777ae43.png

Predictions#

create predictions and select validation data predictions

Hide code cell source

 
analysis.model.eval()
pred, target = res = ae.get_preds_from_df(df=data.train_X, learn=analysis.learn,
                                          position_pred_tuple=0,
                                          transformer=analysis.transform)
pred = pred.stack()
pred

Sample ID   protein groups                                                                
Sample_000  A0A024QZX5;A0A087X1N8;P35237                                                     15.896
            A0A024R0T9;K7ER74;P02655                                                         16.885
            A0A024R3W6;A0A024R412;O60462;O60462-2;O60462-3;O60462-4;O60462-5;Q7LBX6;X5D2Q8   15.779
            A0A024R644;A0A0A0MRU5;A0A1B0GWI2;O75503                                          16.635
            A0A075B6H7                                                                       16.771
                                                                                              ...  
Sample_209  Q9Y6R7                                                                           18.995
            Q9Y6X5                                                                           15.681
            Q9Y6Y8;Q9Y6Y8-2                                                                  19.424
            Q9Y6Y9                                                                           11.946
            S4R3U6                                                                           11.373
Length: 298410, dtype: float32

Hide code cell source

 
val_pred_simulated_na['VAE'] = pred  # 'model_key' ?
val_pred_simulated_na
observed VAE
Sample ID protein groups
Sample_158 Q9UN70;Q9UN70-2 14.630 15.716
Sample_050 Q9Y287 15.755 16.778
Sample_107 Q8N475;Q8N475-2 15.029 14.275
Sample_199 P06307 19.376 19.127
Sample_067 Q5VUB5 15.309 14.968
... ... ... ...
Sample_111 F6SYF8;Q9UBP4 22.822 22.869
Sample_002 A0A0A0MT36 18.165 16.131
Sample_049 Q8WY21;Q8WY21-2;Q8WY21-3;Q8WY21-4 15.525 15.699
Sample_182 Q8NFT8 14.379 13.283
Sample_123 Q16853;Q16853-2 14.504 14.566

12600 rows × 2 columns

Hide code cell source

 
test_pred_simulated_na['VAE'] = pred  # model_key?
test_pred_simulated_na
observed VAE
Sample ID protein groups
Sample_000 A0A075B6P5;P01615 17.016 17.433
A0A087X089;Q16627;Q16627-2 18.280 17.838
A0A0B4J2B5;S4R460 21.735 22.173
A0A140T971;O95865;Q5SRR8;Q5SSV3 14.603 15.235
A0A140TA33;A0A140TA41;A0A140TA52;P22105;P22105-3;P22105-4 16.143 16.620
... ... ... ...
Sample_209 Q96ID5 16.074 16.063
Q9H492;Q9H492-2 13.173 13.373
Q9HC57 14.207 14.448
Q9NPH3;Q9NPH3-2;Q9NPH3-5 14.962 15.174
Q9UGM5;Q9UGM5-2 16.871 16.583

12600 rows × 2 columns

save missing values predictions

Hide code cell source

 
if args.save_pred_real_na:
    pred_real_na = ae.get_missing_values(df_train_wide=data.train_X,
                                         val_idx=val_pred_simulated_na.index,
                                         test_idx=test_pred_simulated_na.index,
                                         pred=pred)
    display(pred_real_na)
    pred_real_na.to_csv(args.out_preds / f"pred_real_na_{args.model_key}.csv")

Sample ID   protein groups          
Sample_000  A0A075B6J9                 15.967
            A0A075B6Q5                 15.942
            A0A075B6R2                 16.766
            A0A075B6S5                 16.407
            A0A087WSY4                 16.510
                                        ...  
Sample_209  Q9P1W8;Q9P1W8-2;Q9P1W8-4   16.138
            Q9UI40;Q9UI40-2            16.397
            Q9UIW2                     16.973
            Q9UMX0;Q9UMX0-2;Q9UMX0-4   13.600
            Q9UP79                     15.994
Name: intensity, Length: 46401, dtype: float32

Plots#

  • validation data

Hide code cell source

 
analysis.model = analysis.model.cpu()
# underlying data is train_X for both
# assert analysis.dls.valid.data.equals(analysis.dls.train.data)
# Reconstruct DataLoader for case that during training singleton batches were dropped
_dl = torch.utils.data.DataLoader(
    pimmslearn.io.datasets.DatasetWithTarget(
        analysis.dls.valid.data),
    batch_size=args.batch_size,
    shuffle=False)
df_latent = pimmslearn.model.get_latent_space(analysis.model.get_mu_and_logvar,
                                              dl=_dl,
                                              dl_index=analysis.dls.valid.data.index)
df_latent
latent dimension 1 latent dimension 2 latent dimension 3 latent dimension 4 latent dimension 5 latent dimension 6 latent dimension 7 latent dimension 8 latent dimension 9 latent dimension 10
Sample ID
Sample_000 0.945 0.319 2.111 -1.097 0.952 0.570 -0.192 0.714 -0.092 2.170
Sample_001 -0.018 -0.527 1.519 -2.022 0.367 -0.017 -1.011 -0.641 0.307 1.101
Sample_002 -0.541 0.112 0.435 -0.732 2.837 -1.790 0.034 0.758 0.677 1.809
Sample_003 0.129 -0.480 2.092 -0.557 1.759 -0.191 0.301 1.337 0.475 1.848
Sample_004 -0.124 0.422 2.023 -1.432 0.810 -0.590 -0.300 0.389 0.296 1.267
... ... ... ... ... ... ... ... ... ... ...
Sample_205 -1.536 0.567 0.713 0.780 -0.896 -1.529 0.909 1.067 -0.728 1.864
Sample_206 0.189 0.632 -2.480 -0.475 -0.803 0.649 -1.662 0.682 0.512 1.788
Sample_207 1.316 1.313 0.560 0.870 -1.264 -2.113 -1.476 -0.019 0.937 2.552
Sample_208 0.185 0.485 -0.974 -0.614 -1.916 -1.640 -0.649 0.035 1.975 0.187
Sample_209 -0.382 0.076 -1.376 0.494 -0.018 -2.021 0.106 0.859 2.447 0.230

210 rows × 10 columns

Hide code cell source

 
ana_latent = analyzers.LatentAnalysis(df_latent,
                                      df_meta,
                                      args.model_key,
                                      folder=args.out_figures)
if args.meta_date_col and df_meta is not None:
    figures[f'latent_{args.model_key}_by_date'], ax = ana_latent.plot_by_date(
        args.meta_date_col)

Hide code cell source

 
if args.meta_cat_col and df_meta is not None:
    figures[f'latent_{args.model_key}_by_{"_".join(args.meta_cat_col.split())}'], ax = ana_latent.plot_by_category(
        args.meta_cat_col)

Hide code cell source

 
feat_freq_val = val_pred_simulated_na['observed'].groupby(level=-1).count()
feat_freq_val.name = 'freq_val'
ax = feat_freq_val.plot.box()
_images/96272a0cb3cf2da9c48f374842e3dd120b7161772dfd94ca21b26df8f29a9a27.png

Hide code cell source

 
feat_freq_val.value_counts().sort_index().head()  # require more than one feat?

freq_val
1    12
2    18
3    50
4    82
5   108
Name: count, dtype: int64

Hide code cell source

 
errors_val = val_pred_simulated_na.drop('observed', axis=1).sub(
    val_pred_simulated_na['observed'], axis=0)
errors_val = errors_val.abs().groupby(level=-1).mean()
errors_val = errors_val.join(freq_feat).sort_values(by='freq', ascending=True)


errors_val_smoothed = errors_val.copy()  # .loc[feat_freq_val > 1]
errors_val_smoothed[errors_val.columns[:-1]] = errors_val[errors_val.columns[:-1]
                                                          ].rolling(window=200, min_periods=1).mean()
ax = errors_val_smoothed.plot(x='freq', figsize=(15, 10))
# errors_val_smoothed
_images/afb4c30e98bc8b21961e7d1265e879e16599273218fdd1c6d770aedc2db155a7.png

Hide code cell source

 
errors_val = val_pred_simulated_na.drop('observed', axis=1).sub(
    val_pred_simulated_na['observed'], axis=0)
errors_val.abs().groupby(level=-1).agg(['mean', 'count'])
VAE
mean count
protein groups
A0A024QZX5;A0A087X1N8;P35237 0.137 7
A0A024R0T9;K7ER74;P02655 1.248 4
A0A024R3W6;A0A024R412;O60462;O60462-2;O60462-3;O60462-4;O60462-5;Q7LBX6;X5D2Q8 0.242 9
A0A024R644;A0A0A0MRU5;A0A1B0GWI2;O75503 0.312 6
A0A075B6H7 0.659 6
... ... ...
Q9Y6R7 0.421 10
Q9Y6X5 0.232 7
Q9Y6Y8;Q9Y6Y8-2 0.347 9
Q9Y6Y9 0.446 15
S4R3U6 0.483 24

1419 rows × 2 columns

Hide code cell source

 
errors_val
VAE
Sample ID protein groups
Sample_158 Q9UN70;Q9UN70-2 1.085
Sample_050 Q9Y287 1.023
Sample_107 Q8N475;Q8N475-2 -0.754
Sample_199 P06307 -0.249
Sample_067 Q5VUB5 -0.341
... ... ...
Sample_111 F6SYF8;Q9UBP4 0.047
Sample_002 A0A0A0MT36 -2.034
Sample_049 Q8WY21;Q8WY21-2;Q8WY21-3;Q8WY21-4 0.173
Sample_182 Q8NFT8 -1.096
Sample_123 Q16853;Q16853-2 0.062

12600 rows × 1 columns

Comparisons#

Simulated NAs : Artificially created NAs. Some data was sampled and set explicitly to misssing before it was fed to the model for reconstruction.

Validation data#

  • all measured (identified, observed) peptides in validation data

Hide code cell source

 
# papermill_description=metrics
# d_metrics = models.Metrics(no_na_key='NA interpolated', with_na_key='NA not interpolated')
d_metrics = models.Metrics()

The simulated NA for the validation step are real test data (not used for training nor early stopping)

Hide code cell source

 
added_metrics = d_metrics.add_metrics(val_pred_simulated_na, 'valid_simulated_na')
added_metrics

Selected as truth to compare to: observed

{'VAE': {'MSE': 0.4570371945045525,
  'MAE': 0.42994737989145104,
  'N': 12600,
  'prop': 1.0}}

Test Datasplit#

Hide code cell source

 
added_metrics = d_metrics.add_metrics(test_pred_simulated_na, 'test_simulated_na')
added_metrics

Selected as truth to compare to: observed

{'VAE': {'MSE': 0.4769721212935629,
  'MAE': 0.4353523445903286,
  'N': 12600,
  'prop': 1.0}}

Save all metrics as json

Hide code cell source

 
pimmslearn.io.dump_json(d_metrics.metrics, args.out_metrics /
                        f'metrics_{args.model_key}.json')
d_metrics

{ 'test_simulated_na': { 'VAE': { 'MAE': 0.4353523445903286,
                                  'MSE': 0.4769721212935629,
                                  'N': 12600,
                                  'prop': 1.0}},
  'valid_simulated_na': { 'VAE': { 'MAE': 0.42994737989145104,
                                   'MSE': 0.4570371945045525,
                                   'N': 12600,
                                   'prop': 1.0}}}

Hide code cell source

 
metrics_df = models.get_df_from_nested_dict(
    d_metrics.metrics, column_levels=['model', 'metric_name']).T
metrics_df
subset valid_simulated_na test_simulated_na
model metric_name
VAE MSE 0.457 0.477
MAE 0.430 0.435
N 12,600.000 12,600.000
prop 1.000 1.000

Save predictions#

Hide code cell source

 
# save simulated missing values for both splits
val_pred_simulated_na.to_csv(args.out_preds / f"pred_val_{args.model_key}.csv")
test_pred_simulated_na.to_csv(args.out_preds / f"pred_test_{args.model_key}.csv")

Config#

Hide code cell source

 
figures  # switch to fnames?

{}

Hide code cell source

 
args.dump(fname=args.out_models / f"model_config_{args.model_key}.yaml")
args

{'M': 1421,
 'batch_size': 64,
 'cuda': False,
 'data': Path('runs/alzheimer_study/data'),
 'epoch_trained': 107,
 'epochs_max': 300,
 'file_format': 'csv',
 'fn_rawfile_metadata': 'https://raw.githubusercontent.com/RasmussenLab/njab/HEAD/docs/tutorial/data/alzheimer/meta.csv',
 'folder_data': '',
 'folder_experiment': Path('runs/alzheimer_study'),
 'hidden_layers': [64],
 'latent_dim': 10,
 'meta_cat_col': None,
 'meta_date_col': None,
 'model': 'VAE',
 'model_key': 'VAE',
 'n_params': 277998,
 'out_figures': Path('runs/alzheimer_study/figures'),
 'out_folder': Path('runs/alzheimer_study'),
 'out_metrics': Path('runs/alzheimer_study'),
 'out_models': Path('runs/alzheimer_study'),
 'out_preds': Path('runs/alzheimer_study/preds'),
 'patience': 50,
 'sample_idx_position': 0,
 'save_pred_real_na': True}
Contents