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_119  P04114                                            14.998
Sample_088  Q86YZ3                                            13.173
Sample_207  P08670                                            16.372
Sample_102  I3L3E6;Q658N2                                     15.771
Sample_169  F5GZS6;J3KPF3;P08195;P08195-2;P08195-3;P08195-4   16.915
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, bias=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, bias=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/1da22bc658a18afd2cbe5301f5b1deba9aa2e9abc45f01a1c86063e84339e7be.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 65167.097656 4041.363281 00:00
1 63575.808594 4040.194580 00:00
2 62163.929688 3993.090576 00:00
3 60812.835938 3895.843750 00:00
4 59495.503906 3767.035156 00:00
5 58174.476562 3626.796631 00:00
6 56859.468750 3486.981934 00:00
7 55584.437500 3353.686035 00:00
8 54285.175781 3234.149170 00:00
9 53001.464844 3127.485352 00:00
10 51732.816406 3034.951416 00:00
11 50516.863281 2961.439697 00:00
12 49365.406250 2897.034912 00:00
13 48289.175781 2848.396484 00:00
14 47266.992188 2803.875000 00:00
15 46287.191406 2754.969971 00:00
16 45418.410156 2721.130371 00:00
17 44612.605469 2697.611328 00:00
18 43877.101562 2675.291260 00:00
19 43160.933594 2649.167969 00:00
20 42511.417969 2620.562500 00:00
21 41878.707031 2584.897949 00:00
22 41284.921875 2549.201904 00:00
23 40706.695312 2509.399170 00:00
24 40088.792969 2488.855469 00:00
25 39519.265625 2454.484863 00:00
26 38969.171875 2436.014160 00:00
27 38430.015625 2426.473633 00:00
28 37913.601562 2407.530273 00:00
29 37405.746094 2400.233643 00:00
30 37056.761719 2390.312988 00:00
31 36600.824219 2380.094482 00:00
32 36187.957031 2353.527344 00:00
33 35792.589844 2351.802246 00:00
34 35390.867188 2356.264160 00:00
35 35000.535156 2360.424561 00:00
36 34630.183594 2351.128418 00:00
37 34281.925781 2353.681396 00:00
38 33974.808594 2335.903320 00:00
39 33662.949219 2331.225342 00:00
40 33378.609375 2309.026367 00:00
41 33057.917969 2329.727783 00:00
42 32811.000000 2352.064697 00:00
43 32550.304688 2295.095459 00:00
44 32298.488281 2288.316406 00:00
45 32033.328125 2312.902344 00:00
46 31750.662109 2258.155762 00:00
47 31477.679688 2242.912598 00:00
48 31268.578125 2270.613037 00:00
49 31035.728516 2243.952637 00:00
50 30813.009766 2256.130859 00:00
51 30614.603516 2234.462402 00:00
52 30395.037109 2243.227295 00:00
53 30236.896484 2257.310059 00:00
54 30061.660156 2256.405273 00:00
55 29864.681641 2268.643066 00:00
56 29724.419922 2258.918945 00:00
57 29533.964844 2196.900391 00:00
58 29389.796875 2234.550781 00:00
59 29254.867188 2217.308105 00:00
60 29081.000000 2209.074463 00:00
61 28957.695312 2233.927490 00:00
62 28845.708984 2215.850098 00:00
63 28675.445312 2228.224854 00:00
64 28573.750000 2199.271240 00:00
65 28458.873047 2215.040283 00:00
66 28337.052734 2199.029297 00:00
67 28214.513672 2213.286865 00:00
68 28095.625000 2224.306641 00:00
69 28025.646484 2214.558105 00:00
70 27950.123047 2230.501709 00:00
71 27910.353516 2255.692627 00:00
72 27819.494141 2201.788086 00:00
73 27769.859375 2221.657227 00:00
74 27691.937500 2215.678955 00:00
75 27588.496094 2214.584473 00:00
76 27522.625000 2238.171387 00:00
77 27446.308594 2190.149170 00:00
78 27361.496094 2198.283203 00:00
79 27278.066406 2203.118652 00:00
80 27225.894531 2245.724121 00:00
81 27165.333984 2209.284912 00:00
82 27158.857422 2202.289307 00:00
83 27091.242188 2233.335938 00:00
84 27062.400391 2207.389893 00:00
85 27008.851562 2210.601562 00:00
86 26930.826172 2188.629883 00:00
87 26871.751953 2198.902588 00:00
88 26800.935547 2181.210449 00:00
89 26737.742188 2189.575928 00:00
90 26664.910156 2212.835449 00:00
91 26633.166016 2173.750244 00:00
92 26595.169922 2190.280518 00:00
93 26550.212891 2208.481689 00:00
94 26503.087891 2196.715820 00:00
95 26455.259766 2213.499512 00:00
96 26413.861328 2160.463623 00:00
97 26342.742188 2179.583740 00:00
98 26281.529297 2181.633545 00:00
99 26236.216797 2198.305176 00:00
100 26151.306641 2195.555176 00:00
101 26118.419922 2186.391846 00:00
102 26083.171875 2187.866455 00:00
103 26062.751953 2181.223145 00:00
104 26044.705078 2209.232422 00:00
105 26082.703125 2175.012695 00:00
106 26062.958984 2184.651611 00:00
107 26071.300781 2187.817139 00:00
108 26031.503906 2191.804688 00:00
109 25989.923828 2192.753662 00:00
110 25950.324219 2179.282715 00:00
111 25946.015625 2180.493164 00:00
112 25912.423828 2198.737793 00:00
113 25895.685547 2190.971924 00:00
114 25843.566406 2201.348145 00:00
115 25815.123047 2202.955322 00:00
116 25775.904297 2183.521729 00:00
117 25713.822266 2177.438232 00:00
118 25696.921875 2189.645020 00:00
119 25684.984375 2174.958252 00:00
120 25656.716797 2183.719238 00:00
121 25630.580078 2203.475342 00:00 
No improvement since epoch 96: early stopping

Save number of actually trained epochs

Hide code cell source

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

122

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/93b347b4a62367ae3de2eab6996fdd6af5d57dd376980d32ea208229c26e8094.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                                                     16.010
            A0A024R0T9;K7ER74;P02655                                                         16.637
            A0A024R3W6;A0A024R412;O60462;O60462-2;O60462-3;O60462-4;O60462-5;Q7LBX6;X5D2Q8   15.882
            A0A024R644;A0A0A0MRU5;A0A1B0GWI2;O75503                                          16.740
            A0A075B6H7                                                                       16.692
                                                                                              ...  
Sample_209  Q9Y6R7                                                                           19.285
            Q9Y6X5                                                                           15.624
            Q9Y6Y8;Q9Y6Y8-2                                                                  19.194
            Q9Y6Y9                                                                           11.292
            S4R3U6                                                                           11.370
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 15.710
Sample_050 Q9Y287 15.755 16.674
Sample_107 Q8N475;Q8N475-2 15.029 14.023
Sample_199 P06307 19.376 19.031
Sample_067 Q5VUB5 15.309 15.413
... ... ... ...
Sample_111 F6SYF8;Q9UBP4 22.822 23.001
Sample_002 A0A0A0MT36 18.165 15.874
Sample_049 Q8WY21;Q8WY21-2;Q8WY21-3;Q8WY21-4 15.525 15.650
Sample_182 Q8NFT8 14.379 14.262
Sample_123 Q16853;Q16853-2 14.504 14.673

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 17.081
A0A087X089;Q16627;Q16627-2 18.280 18.016
A0A0B4J2B5;S4R460 21.735 22.352
A0A140T971;O95865;Q5SRR8;Q5SSV3 14.603 15.374
A0A140TA33;A0A140TA41;A0A140TA52;P22105;P22105-3;P22105-4 16.143 16.747
... ... ... ...
Sample_209 Q96ID5 16.074 15.874
Q9H492;Q9H492-2 13.173 13.404
Q9HC57 14.207 13.993
Q9NPH3;Q9NPH3-2;Q9NPH3-5 14.962 15.117
Q9UGM5;Q9UGM5-2 16.871 16.401

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                 15.360
            A0A075B6Q5                 16.196
            A0A075B6R2                 16.464
            A0A075B6S5                 16.190
            A0A087WSY4                 16.358
                                        ...  
Sample_209  Q9P1W8;Q9P1W8-2;Q9P1W8-4   15.953
            Q9UI40;Q9UI40-2            16.564
            Q9UIW2                     17.033
            Q9UMX0;Q9UMX0-2;Q9UMX0-4   13.951
            Q9UP79                     15.793
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 -0.240 -0.022 2.758 1.699 5.858 -3.286 -1.958 3.230 1.390 -0.257
Sample_001 -1.999 0.530 1.927 0.114 3.451 -1.785 -1.175 1.050 1.773 0.670
Sample_002 -2.791 -1.729 0.947 0.804 1.991 -1.459 0.549 -0.214 -1.156 -1.827
Sample_003 -0.007 -2.601 2.779 0.503 4.183 -3.577 -1.139 0.945 1.541 -0.306
Sample_004 -0.655 -0.094 2.402 -0.882 3.438 -5.608 -2.480 0.987 1.106 -2.337
... ... ... ... ... ... ... ... ... ... ...
Sample_205 -0.779 -1.290 -2.811 0.457 -0.916 -1.482 -3.236 3.143 -0.822 -2.260
Sample_206 -2.280 2.127 0.132 0.896 -2.650 -2.818 1.488 4.631 0.504 2.572
Sample_207 1.275 1.207 1.809 -0.594 -0.532 -1.462 -5.106 7.742 2.661 -0.230
Sample_208 -2.168 1.278 1.708 2.209 -2.756 0.517 -4.917 2.248 1.291 2.518
Sample_209 -2.177 -0.897 5.544 1.641 -4.537 -2.373 -2.938 1.051 2.224 -0.096

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': 0.46784169499502054,
  'MAE': 0.4356743506263626,
  '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': 0.48555892856974264,
  'MAE': 0.4394878208649771,
  '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': 0.4394878208649771,
                                  'MSE': 0.48555892856974264,
                                  'N': 12600,
                                  'prop': 1.0}},
  'valid_simulated_na': { 'DAE': { 'MAE': 0.4356743506263626,
                                   'MSE': 0.46784169499502054,
                                   '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 0.468 0.486
MAE 0.436 0.439
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': 122,
 '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}