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_004  O60279                                  18.472
Sample_012  Q9Y279;Q9Y279-2                         16.822
Sample_105  Q9NY15                                  16.085
Sample_153  A0A1B0GVB9;A0A1C7CYW4;O75787;O75787-2   18.701
Sample_130  P26572                                  17.324
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/2c3fe386a854837253b75d6adbf2051ecb0d204cdfe48992f909c165d3709713.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 65421.988281 4084.004883 00:00
1 63818.140625 4085.867676 00:00
2 62464.582031 4047.527100 00:00
3 61154.707031 3959.391602 00:00
4 59835.042969 3839.641602 00:00
5 58523.066406 3698.016113 00:00
6 57213.156250 3559.187012 00:00
7 55939.421875 3430.649170 00:00
8 54708.878906 3322.787109 00:00
9 53480.734375 3232.010742 00:00
10 52283.765625 3149.336914 00:00
11 51138.562500 3080.233154 00:00
12 50021.410156 3023.130127 00:00
13 48987.605469 2963.635498 00:00
14 47997.105469 2884.520264 00:00
15 47063.308594 2795.945557 00:00
16 46134.773438 2718.859863 00:00
17 45275.929688 2673.689209 00:00
18 44465.863281 2637.421631 00:00
19 43726.578125 2595.788330 00:00
20 42974.789062 2554.034180 00:00
21 42267.625000 2522.792969 00:00
22 41589.359375 2491.516113 00:00
23 40891.171875 2459.127686 00:00
24 40266.996094 2445.865479 00:00
25 39661.500000 2421.149170 00:00
26 39060.355469 2409.549072 00:00
27 38488.144531 2384.733398 00:00
28 37977.960938 2361.665039 00:00
29 37485.042969 2356.338135 00:00
30 37016.011719 2334.299316 00:00
31 36522.644531 2317.604492 00:00
32 36034.894531 2304.509277 00:00
33 35565.667969 2295.675781 00:00
34 35179.171875 2311.285645 00:00
35 34769.796875 2291.909668 00:00
36 34380.238281 2276.851807 00:00
37 34038.742188 2288.376709 00:00
38 33629.527344 2248.846924 00:00
39 33298.425781 2231.951904 00:00
40 32922.789062 2247.028076 00:00
41 32569.193359 2233.238525 00:00
42 32263.031250 2242.594971 00:00
43 31950.861328 2237.665771 00:00
44 31702.222656 2224.034912 00:00
45 31409.310547 2244.667969 00:00
46 31187.919922 2221.500488 00:00
47 30999.255859 2231.090088 00:00
48 30790.195312 2210.052246 00:00
49 30570.246094 2233.743896 00:00
50 30371.298828 2241.040527 00:00
51 30156.585938 2224.928711 00:00
52 29946.757812 2195.060547 00:00
53 29781.380859 2212.551758 00:00
54 29633.927734 2225.436279 00:00
55 29476.900391 2260.423584 00:00
56 29375.552734 2252.812988 00:00
57 29269.521484 2250.977051 00:00
58 29173.689453 2246.173584 00:00
59 29055.085938 2298.910156 00:00
60 28946.507812 2286.254395 00:00
61 28897.400391 2305.281006 00:00
62 28850.726562 2273.139648 00:00
63 28763.185547 2286.024902 00:00
64 28690.425781 2227.016602 00:00
65 28565.396484 2283.581299 00:00
66 28465.058594 2229.015625 00:00
67 28339.099609 2241.744873 00:00
68 28230.410156 2220.960205 00:00
69 28161.056641 2304.402588 00:00
70 28069.998047 2210.191406 00:00
71 28014.843750 2223.531006 00:00
72 27952.525391 2215.776123 00:00
73 27862.570312 2244.852783 00:00
74 27769.716797 2240.280029 00:00
75 27659.826172 2222.663574 00:00
76 27611.308594 2207.023193 00:00
77 27565.005859 2218.444824 00:00 
No improvement since epoch 52: early stopping

Save number of actually trained epochs

Hide code cell source

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

78

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/4fde3a179162df764a8f872954fadc803863cce7e4c84f7fe41d6ed7c9e4bc96.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                                                     15.909
            A0A024R0T9;K7ER74;P02655                                                         16.668
            A0A024R3W6;A0A024R412;O60462;O60462-2;O60462-3;O60462-4;O60462-5;Q7LBX6;X5D2Q8   15.652
            A0A024R644;A0A0A0MRU5;A0A1B0GWI2;O75503                                          16.605
            A0A075B6H7                                                                       16.802
                                                                                              ...  
Sample_209  Q9Y6R7                                                                           19.209
            Q9Y6X5                                                                           15.838
            Q9Y6Y8;Q9Y6Y8-2                                                                  19.531
            Q9Y6Y9                                                                           11.648
            S4R3U6                                                                           11.451
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 15.730
Sample_050 Q9Y287 15.755 16.781
Sample_107 Q8N475;Q8N475-2 15.029 14.507
Sample_199 P06307 19.376 19.164
Sample_067 Q5VUB5 15.309 15.268
... ... ... ...
Sample_111 F6SYF8;Q9UBP4 22.822 23.005
Sample_002 A0A0A0MT36 18.165 15.694
Sample_049 Q8WY21;Q8WY21-2;Q8WY21-3;Q8WY21-4 15.525 15.847
Sample_182 Q8NFT8 14.379 13.751
Sample_123 Q16853;Q16853-2 14.504 14.545

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 17.225
A0A087X089;Q16627;Q16627-2 18.280 18.062
A0A0B4J2B5;S4R460 21.735 22.220
A0A140T971;O95865;Q5SRR8;Q5SSV3 14.603 15.214
A0A140TA33;A0A140TA41;A0A140TA52;P22105;P22105-3;P22105-4 16.143 16.600
... ... ... ...
Sample_209 Q96ID5 16.074 16.125
Q9H492;Q9H492-2 13.173 13.851
Q9HC57 14.207 13.592
Q9NPH3;Q9NPH3-2;Q9NPH3-5 14.962 14.903
Q9UGM5;Q9UGM5-2 16.871 16.285

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                 15.721
            A0A075B6Q5                 16.140
            A0A075B6R2                 16.703
            A0A075B6S5                 16.089
            A0A087WSY4                 16.425
                                        ...  
Sample_209  Q9P1W8;Q9P1W8-2;Q9P1W8-4   16.234
            Q9UI40;Q9UI40-2            16.992
            Q9UIW2                     16.621
            Q9UMX0;Q9UMX0-2;Q9UMX0-4   13.276
            Q9UP79                     16.033
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 3.965 3.468 -4.044 0.115 0.660 1.377 -0.961 3.105 -0.242 4.677
Sample_001 4.301 3.294 0.411 -0.899 2.480 1.391 0.398 3.022 -0.435 3.656
Sample_002 2.485 1.704 0.613 2.425 -0.807 2.020 0.456 -0.371 -3.182 3.931
Sample_003 3.986 3.970 -2.145 2.288 0.197 3.826 -0.745 1.476 0.084 4.275
Sample_004 2.223 3.149 -2.837 1.287 1.094 4.832 -0.301 3.258 -1.418 5.491
... ... ... ... ... ... ... ... ... ... ...
Sample_205 -1.097 2.661 -2.748 1.566 1.133 2.589 -0.327 -2.102 -1.259 0.290
Sample_206 0.431 -1.241 -1.478 -0.713 5.988 -1.937 0.162 -2.205 -0.734 2.751
Sample_207 -2.658 2.005 -3.657 -1.308 3.769 1.120 -2.161 1.411 -4.271 2.244
Sample_208 -2.361 4.211 0.037 -1.316 4.756 -0.205 2.150 0.409 -0.262 1.387
Sample_209 -1.113 3.304 1.776 2.669 5.220 1.567 -0.353 -1.150 -1.761 2.513

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': 0.4638920185918591,
  'MAE': 0.43776961966215294,
  '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': 0.48049603475877306,
  'MAE': 0.44229773641715575,
  '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': 0.44229773641715575,
                                  'MSE': 0.48049603475877306,
                                  'N': 12600,
                                  'prop': 1.0}},
  'valid_simulated_na': { 'DAE': { 'MAE': 0.43776961966215294,
                                   'MSE': 0.4638920185918591,
                                   '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 0.464 0.480
MAE 0.438 0.442
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': 78,
 '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}