Denoising Autoencoder

Denoising Autoencoder#

Hide code cell source

 
import logging

import sklearn
from fastai import learner
from fastai.basics import *
from fastai.callback.all import *
from fastai.torch_basics import *
from IPython.display import display
from sklearn.impute import SimpleImputer
from sklearn.preprocessing import StandardScaler

import pimmslearn
import pimmslearn.model
import pimmslearn.models as models
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
# early_stopping:bool = True # Wheather to use early stopping or not
patience: int = 25  # Patience for early stopping
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, '128_64' for the encoder, reverse will be use for decoder
hidden_layers: str = '512'

sample_idx_position: int = 0  # position of index which is sample ID
model: str = 'DAE'  # model name
model_key: str = 'DAE'  # 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 = "DAE"
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 = "DAE"

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,
 'patience': 25,
 'batch_size': 64,
 'cuda': False,
 'latent_dim': 10,
 'hidden_layers': '64',
 'sample_idx_position': 0,
 'model': 'DAE',
 'model_key': 'DAE',
 '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': 'DAE',
 'model_key': 'DAE',
 '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': 25,
 '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_137  F8WE04;P04792    14.104
Sample_068  Q5SPY9;Q9NQX5    12.977
Sample_107  P01742           18.367
Sample_178  Q15113           19.910
Sample_069  A0A0U1RQC5       19.182
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

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

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

Denoising Autoencoder#

Analysis: DataLoaders, Model, transform#

Hide code cell source

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

analysis = ae.AutoEncoderAnalysis(
    train_df=data.train_X,
    val_df=data.val_y,
    model=ae.Autoencoder,
    transform=default_pipeline,
    decode=['normalize'],
    model_kwargs=dict(n_features=data.train_X.shape[-1],
                      n_neurons=args.hidden_layers,
                      last_decoder_activation=None,
                      dim_latent=args.latent_dim),
    bs=args.batch_size)
args.n_params = analysis.n_params_ae

if args.cuda:
    analysis.model = analysis.model.cuda()
analysis.model

Autoencoder(
  (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=10, 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=1421, bias=True)
  )
)

Training#

Hide code cell source

 
analysis.learn = Learner(dls=analysis.dls,
                         model=analysis.model,
                         loss_func=MSELossFlat(reduction='sum'),
                         cbs=[EarlyStoppingCallback(patience=args.patience),
                              ae.ModelAdapter(p=0.2)]
                         )

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   : [ModelAdapter, CastToTensor]
         - after_pred     : [ModelAdapter]
         - after_loss     : [ModelAdapter]
         - 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=0.019054606556892395)
_images/58e47fdd4d56bf60446ab3df7232fb96c458032304a8cd8cda10de0f5c2539bd.png

dump model config

Hide code cell source

 
pimmslearn.io.dump_json(analysis.params, args.out_models /
                        TEMPLATE_MODEL_PARAMS.format(args.model_key))

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 65002.917969 4045.061279 00:00
1 63314.085938 4027.020264 00:00
2 61894.058594 3962.450195 00:00
3 60502.464844 3857.962158 00:00
4 59093.429688 3728.370117 00:00
5 57717.972656 3588.760742 00:00
6 56365.960938 3449.551514 00:00
7 55021.558594 3313.929199 00:00
8 53651.035156 3197.911377 00:00
9 52336.496094 3100.087402 00:00
10 51114.496094 3023.931152 00:00
11 49934.375000 2969.193115 00:00
12 48785.789062 2912.542969 00:00
13 47762.863281 2843.558594 00:00
14 46803.207031 2795.947021 00:00
15 45917.484375 2743.076904 00:00
16 45098.398438 2691.372559 00:00
17 44299.406250 2646.625488 00:00
18 43568.789062 2600.220459 00:00
19 42841.480469 2565.581787 00:00
20 42135.148438 2533.124756 00:00
21 41486.675781 2497.457764 00:00
22 40869.441406 2474.675781 00:00
23 40239.757812 2468.565674 00:00
24 39659.492188 2441.065918 00:00
25 39089.554688 2421.241943 00:00
26 38526.484375 2407.016602 00:00
27 38036.601562 2401.210938 00:00
28 37519.957031 2392.945312 00:00
29 37029.628906 2362.765137 00:00
30 36565.273438 2358.863770 00:00
31 36136.730469 2349.886230 00:00
32 35774.527344 2339.795898 00:00
33 35387.816406 2321.933594 00:00
34 35013.593750 2340.554932 00:00
35 34673.410156 2334.715576 00:00
36 34332.773438 2322.361572 00:00
37 33997.835938 2328.472168 00:00
38 33674.050781 2314.470703 00:00
39 33373.988281 2306.414062 00:00
40 33093.554688 2322.077881 00:00
41 32819.289062 2304.332520 00:00
42 32552.427734 2287.223145 00:00
43 32271.947266 2292.134033 00:00
44 32024.626953 2292.601318 00:00
45 31792.214844 2296.230713 00:00
46 31554.642578 2256.862793 00:00
47 31303.300781 2248.208008 00:00
48 31076.529297 2272.790527 00:00
49 30902.435547 2254.845703 00:00
50 30698.267578 2278.974609 00:00
51 30519.890625 2268.012207 00:00
52 30347.113281 2273.012451 00:00
53 30145.714844 2286.565674 00:00
54 30047.281250 2282.713867 00:00
55 29882.919922 2317.576904 00:00
56 29705.130859 2353.680664 00:00
57 29560.232422 2331.623047 00:00
58 29459.181641 2341.174316 00:00
59 29333.689453 2338.856689 00:00
60 29230.041016 2246.905273 00:00
61 29103.416016 2251.561523 00:00
62 28965.677734 2247.955566 00:00
63 28840.509766 2254.363037 00:00
64 28742.685547 2224.609863 00:00
65 28636.369141 2257.565186 00:00
66 28519.111328 2204.981934 00:00
67 28413.441406 2231.166748 00:00
68 28337.906250 2231.011719 00:00
69 28249.269531 2211.728516 00:00
70 28113.943359 2234.889404 00:00
71 28014.195312 2209.684082 00:00
72 27897.753906 2194.407715 00:00
73 27802.175781 2211.524658 00:00
74 27724.882812 2246.486816 00:00
75 27610.228516 2231.846680 00:00
76 27554.283203 2239.367432 00:00
77 27511.433594 2214.609375 00:00
78 27426.509766 2227.199219 00:00
79 27318.203125 2190.445557 00:00
80 27241.490234 2215.956055 00:00
81 27150.675781 2202.796631 00:00
82 27109.103516 2193.553955 00:00
83 27043.857422 2225.579346 00:00
84 27003.794922 2212.295898 00:00
85 26934.875000 2216.331787 00:00
86 26856.279297 2193.947998 00:00
87 26791.341797 2250.476807 00:00
88 26731.785156 2184.603027 00:00
89 26667.652344 2228.449219 00:00
90 26614.562500 2204.157227 00:00
91 26588.505859 2217.975830 00:00
92 26552.238281 2175.820312 00:00
93 26521.072266 2205.719971 00:00
94 26491.107422 2218.263428 00:00
95 26449.472656 2201.537109 00:00
96 26388.552734 2244.622070 00:00
97 26336.363281 2202.004883 00:00
98 26244.095703 2209.449707 00:00
99 26221.265625 2193.099854 00:00
100 26195.919922 2207.344971 00:00
101 26143.548828 2212.516602 00:00
102 26131.076172 2201.515137 00:00
103 26140.496094 2203.062500 00:00
104 26148.599609 2199.807373 00:00
105 26101.966797 2199.721436 00:00
106 26085.728516 2233.840820 00:00
107 26074.435547 2185.741455 00:00
108 26019.355469 2177.695801 00:00
109 25994.490234 2186.942383 00:00
110 25946.757812 2209.610352 00:00
111 25874.150391 2195.255859 00:00
112 25878.562500 2193.068359 00:00
113 25869.705078 2208.444092 00:00
114 25855.814453 2214.193848 00:00
115 25799.027344 2187.009277 00:00
116 25811.468750 2203.609131 00:00
117 25775.851562 2186.638916 00:00 
No improvement since epoch 92: early stopping

Save number of actually trained epochs

Hide code cell source

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

118

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/dae_training
_images/a9db76e511104886a11331f9f0c17e09471de1e631b05c3a6da00ae736ad9920.png

Why is the validation loss better then the training loss?

  • during training input data is masked and needs to be reconstructed

  • when evaluating the model, all input data is provided and only the artifically masked data is used for evaluation.

Predictions#

  • data of training data set and validation dataset to create predictions is the same as training data.

  • predictions include missing values (which are not further compared)

  • [ ] double check ModelAdapter

create predictiona and select for validation data

Hide code cell source

 
analysis.model.eval()
pred, target = analysis.get_preds_from_df(df_wide=data.train_X)  # train_X
pred = pred.stack()
pred

Sample ID   protein groups                                                                
Sample_000  A0A024QZX5;A0A087X1N8;P35237                                                     15.919
            A0A024R0T9;K7ER74;P02655                                                         16.720
            A0A024R3W6;A0A024R412;O60462;O60462-2;O60462-3;O60462-4;O60462-5;Q7LBX6;X5D2Q8   15.824
            A0A024R644;A0A0A0MRU5;A0A1B0GWI2;O75503                                          16.792
            A0A075B6H7                                                                       16.800
                                                                                              ...  
Sample_209  Q9Y6R7                                                                           19.188
            Q9Y6X5                                                                           15.792
            Q9Y6Y8;Q9Y6Y8-2                                                                  19.422
            Q9Y6Y9                                                                           10.999
            S4R3U6                                                                           11.322
Length: 298410, dtype: float32

Hide code cell source

 
val_pred_simulated_na['DAE'] = pred  # model_key ?
val_pred_simulated_na
observed DAE
Sample ID protein groups
Sample_158 Q9UN70;Q9UN70-2 14.630 15.599
Sample_050 Q9Y287 15.755 16.924
Sample_107 Q8N475;Q8N475-2 15.029 14.335
Sample_199 P06307 19.376 19.050
Sample_067 Q5VUB5 15.309 14.976
... ... ... ...
Sample_111 F6SYF8;Q9UBP4 22.822 22.964
Sample_002 A0A0A0MT36 18.165 15.849
Sample_049 Q8WY21;Q8WY21-2;Q8WY21-3;Q8WY21-4 15.525 15.764
Sample_182 Q8NFT8 14.379 13.944
Sample_123 Q16853;Q16853-2 14.504 14.422

12600 rows × 2 columns

Hide code cell source

 
test_pred_simulated_na['DAE'] = pred  # model_key?
test_pred_simulated_na
observed DAE
Sample ID protein groups
Sample_000 A0A075B6P5;P01615 17.016 17.028
A0A087X089;Q16627;Q16627-2 18.280 17.984
A0A0B4J2B5;S4R460 21.735 22.286
A0A140T971;O95865;Q5SRR8;Q5SSV3 14.603 15.247
A0A140TA33;A0A140TA41;A0A140TA52;P22105;P22105-3;P22105-4 16.143 16.779
... ... ... ...
Sample_209 Q96ID5 16.074 16.021
Q9H492;Q9H492-2 13.173 13.360
Q9HC57 14.207 13.733
Q9NPH3;Q9NPH3-2;Q9NPH3-5 14.962 15.218
Q9UGM5;Q9UGM5-2 16.871 16.372

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                 15.429
            A0A075B6Q5                 15.763
            A0A075B6R2                 16.642
            A0A075B6S5                 15.938
            A0A087WSY4                 16.387
                                        ...  
Sample_209  Q9P1W8;Q9P1W8-2;Q9P1W8-4   15.959
            Q9UI40;Q9UI40-2            15.769
            Q9UIW2                     16.566
            Q9UMX0;Q9UMX0-2;Q9UMX0-4   13.352
            Q9UP79                     15.988
Name: intensity, Length: 46401, dtype: float32

Plots#

  • validation data

Hide code cell source

 
analysis.model.cpu()
df_latent = pimmslearn.model.get_latent_space(analysis.model.encoder,
                                              dl=analysis.dls.valid,
                                              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 -0.905 4.043 2.623 3.535 -0.234 -1.163 -3.534 3.812 -0.209 -0.926
Sample_001 1.529 3.252 3.897 3.636 -1.195 -0.321 -2.300 0.298 0.488 -1.193
Sample_002 4.432 3.462 2.947 3.272 2.463 1.479 1.972 5.474 0.124 -1.511
Sample_003 -0.497 3.897 3.246 3.344 1.239 0.871 -3.199 4.417 -2.113 -1.333
Sample_004 -1.036 5.066 2.683 4.227 1.390 -1.184 -1.148 1.814 -0.879 0.181
... ... ... ... ... ... ... ... ... ... ...
Sample_205 2.678 4.119 -1.004 -2.038 3.736 1.291 -0.517 1.485 2.105 1.853
Sample_206 6.814 2.888 -1.416 -1.369 -0.297 -3.705 -2.870 -0.342 -0.050 -2.648
Sample_207 -0.156 6.658 0.263 -2.422 3.522 -6.708 -0.792 -0.219 2.916 -0.972
Sample_208 2.361 5.283 -0.481 -1.349 0.385 -0.181 -0.830 -3.661 1.226 -2.874
Sample_209 3.217 4.365 2.953 -2.907 3.043 0.881 2.342 -0.953 -3.196 -6.760

210 rows × 10 columns

Hide code cell source

 
# ! calculate embeddings only if meta data is available? Optional argument to save embeddings?
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)

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()

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

{'DAE': {'MSE': 0.4628965604918746,
  'MAE': 0.43483768924660204,
  '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

{'DAE': {'MSE': 0.4756158306377139,
  'MAE': 0.43664295761063754,
  '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': { 'DAE': { 'MAE': 0.43664295761063754,
                                  'MSE': 0.4756158306377139,
                                  'N': 12600,
                                  'prop': 1.0}},
  'valid_simulated_na': { 'DAE': { 'MAE': 0.43483768924660204,
                                   'MSE': 0.4628965604918746,
                                   '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
DAE MSE 0.463 0.476
MAE 0.435 0.437
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': 118,
 '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': 'DAE',
 'model_key': 'DAE',
 'n_params': 184983,
 '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': 25,
 'sample_idx_position': 0,
 'save_pred_real_na': True}
Contents