Variational Autoencoder

Variational Autoencoder#

Hide code cell source

 
import logging
from functools import partial

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

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

learner.Recorder.plot_loss = plot_loss


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

figures = {}  # collection of ax or figures

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

Hide code cell source

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

Papermill script parameters:

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

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

Some argument transformations

Hide code cell source

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

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

Hide code cell source

 
args = pimmslearn.nb.args_from_dict(args)

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

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

Some naming conventions

Hide code cell source

 
TEMPLATE_MODEL_PARAMS = 'model_params_{}.json'

Load data in long format#

Hide code cell source

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

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

data is loaded in long format

Hide code cell source

 
data.train_X.sample(5)

Sample ID   protein groups                      
Sample_193  P07585                                 18.591
Sample_113  P56817;P56817-2                        16.075
Sample_131  B0QY80;Q96HU1;Q96HU1-2                 17.926
Sample_010  P61981                                 15.399
Sample_005  E9PHN6;E9PHN7;F6XZQ7;P28161;P28161-2   12.895
Name: intensity, dtype: float64

Infer index names from long format

Hide code cell source

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

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

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

load meta data for splits

Hide code cell source

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

210 rows × 11 columns

Initialize Comparison#

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

  • real test data:

    • Not used for predictions or early stopping.

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

Hide code cell source

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

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

Produce some addional simulated samples#

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

Hide code cell source

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

12600 rows × 1 columns

Hide code cell source

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

Data in wide format#

  • Autoencoder need data in wide format

Hide code cell source

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

5 rows × 1421 columns

Add interpolation performance#

Fill Validation data with potentially missing features#

Hide code cell source

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

210 rows × 1421 columns

Hide code cell source

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

210 rows × 1419 columns

Hide code cell source

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

210 rows × 1421 columns

Variational Autoencoder#

Analysis: DataLoaders, Model, transform#

Hide code cell source

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

Analysis: DataLoaders, Model#

Hide code cell source

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

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

Training#

Hide code cell source

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

Hide code cell source

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

analysis.learn.show_training_loop()

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

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

Hide code cell source

 
# learn.summary()

Hide code cell source

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

SuggestedLRs(valley=0.004365158267319202)
_images/ff97cf06d7ec26f38248e3f5c877fb1ba68e0c464d27a8e8c4f5fbc6493e6272.png

Hide code cell source

 
results.clear()  # reset results

dump model config

Hide code cell source

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

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

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

Hide code cell source

 
# papermill_description=train
analysis.learn.fit_one_cycle(args.epochs_max, lr_max=suggested_lr.valley)
epoch train_loss valid_loss time
0 1670.005371 93.020805 00:00
1 1672.870605 93.567970 00:00
2 1672.677368 93.602806 00:00
3 1674.823364 94.056862 00:00
4 1667.817871 94.565735 00:00
5 1663.531128 95.344986 00:00
6 1660.779907 94.716370 00:00
7 1658.170410 94.861481 00:00
8 1656.055054 95.068283 00:00
9 1652.100708 94.844032 00:00
10 1648.445068 94.482071 00:00
11 1643.605469 95.000168 00:00
12 1638.112305 94.630997 00:00
13 1634.861816 94.231369 00:00
14 1629.637085 93.986938 00:00
15 1625.240845 93.899338 00:00
16 1619.293213 94.020645 00:00
17 1612.560181 93.891258 00:00
18 1605.769287 93.671242 00:00
19 1598.018799 93.517860 00:00
20 1590.232788 93.474510 00:00
21 1582.432007 92.811729 00:00
22 1574.422119 92.844101 00:00
23 1565.321411 93.047134 00:00
24 1554.769897 93.230049 00:00
25 1544.778687 93.581520 00:00
26 1533.417603 93.334244 00:00
27 1522.163330 93.669914 00:00
28 1509.836426 93.421127 00:00
29 1497.522949 93.026405 00:00
30 1485.022217 93.122765 00:00
31 1473.200195 93.450035 00:00
32 1461.158081 94.270737 00:00
33 1448.713257 94.804161 00:00
34 1436.211792 95.670860 00:00
35 1425.332397 96.175323 00:00
36 1413.668091 96.519150 00:00
37 1402.999146 96.895370 00:00
38 1392.232056 96.338943 00:00
39 1382.445068 95.958458 00:00
40 1372.193604 95.323669 00:00
41 1363.368774 94.402435 00:00
42 1354.569824 93.082626 00:00
43 1346.365967 92.823059 00:00
44 1337.444580 92.594986 00:00
45 1327.744263 92.196739 00:00
46 1318.248413 91.714592 00:00
47 1310.245361 92.131973 00:00
48 1303.127441 92.494194 00:00
49 1295.703613 92.734001 00:00
50 1288.742188 92.499023 00:00
51 1280.599121 93.236977 00:00
52 1273.751465 93.602272 00:00
53 1266.048096 92.891098 00:00
54 1258.072021 93.037834 00:00
55 1251.133911 92.915092 00:00
56 1243.314941 93.559341 00:00
57 1237.307739 93.295151 00:00
58 1230.026489 93.429443 00:00
59 1224.229614 93.581993 00:00
60 1217.405273 93.047798 00:00
61 1211.338257 92.949730 00:00
62 1206.516113 93.733612 00:00
63 1200.527954 93.033234 00:00
64 1196.015381 92.630005 00:00
65 1189.518799 92.706390 00:00
66 1185.245239 92.949982 00:00
67 1180.121460 92.909645 00:00
68 1176.635498 93.001640 00:00
69 1172.164673 92.166451 00:00
70 1168.788086 92.386009 00:00
71 1164.473755 92.942093 00:00
72 1160.923950 92.148949 00:00
73 1156.535767 91.753220 00:00
74 1153.412476 92.383965 00:00
75 1150.612671 92.651337 00:00
76 1146.897583 93.188995 00:00
77 1144.704468 92.553795 00:00
78 1140.086914 92.302002 00:00
79 1136.103760 91.706322 00:00
80 1133.893188 91.894623 00:00
81 1132.013062 92.043037 00:00
82 1129.259399 92.854973 00:00
83 1126.406982 93.717094 00:00
84 1123.025879 93.248871 00:00
85 1120.201172 92.722069 00:00
86 1117.441406 92.657990 00:00
87 1113.708984 92.534630 00:00
88 1109.511230 92.244644 00:00
89 1106.449585 92.181801 00:00
90 1102.835938 92.817085 00:00
91 1101.448608 92.921844 00:00
92 1098.072266 92.181900 00:00
93 1094.613892 92.471207 00:00
94 1091.433594 92.530998 00:00
95 1089.120117 93.532188 00:00
96 1087.640991 94.337120 00:00
97 1085.556641 92.952538 00:00
98 1082.564087 92.425941 00:00
99 1081.607910 92.285461 00:00
100 1079.256226 92.910591 00:00
101 1077.492432 93.726349 00:00
102 1077.606079 93.344040 00:00
103 1074.779175 93.036118 00:00
104 1073.318115 93.114174 00:00
105 1071.263672 93.415108 00:00
106 1068.011353 94.080070 00:00
107 1067.127930 94.495285 00:00
108 1064.739746 94.754784 00:00
109 1062.570679 94.337303 00:00
110 1062.156006 93.372864 00:00
111 1061.945068 93.654762 00:00
112 1060.323242 93.614159 00:00
113 1057.946777 94.485138 00:00
114 1057.264893 94.362350 00:00
115 1054.691895 93.851852 00:00
116 1052.333496 93.540436 00:00
117 1051.563965 92.830917 00:00
118 1050.284668 93.560829 00:00
119 1050.216187 94.358009 00:00
120 1048.446167 94.127167 00:00
121 1047.019287 93.331467 00:00
122 1046.449707 93.492912 00:00
123 1044.270386 93.959244 00:00
124 1043.793335 94.835777 00:00
125 1042.116089 94.506439 00:00
126 1039.965698 94.613907 00:00
127 1038.456177 94.754654 00:00
128 1040.026733 94.321754 00:00
129 1038.004272 93.472282 00:00 
No improvement since epoch 79: early stopping

Save number of actually trained epochs

Hide code cell source

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

130

Loss normalized by total number of measurements#

Hide code cell source

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

pimmslearn.plotting - INFO     Saved Figures to runs/alzheimer_study/figures/vae_training
_images/df86bf933afdb6040e622be1b3c83cb7977a463d48a15f519e3540149b600640.png

Predictions#

create predictions and select validation data predictions

Hide code cell source

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

Sample ID   protein groups                                                                
Sample_000  A0A024QZX5;A0A087X1N8;P35237                                                     15.925
            A0A024R0T9;K7ER74;P02655                                                         16.801
            A0A024R3W6;A0A024R412;O60462;O60462-2;O60462-3;O60462-4;O60462-5;Q7LBX6;X5D2Q8   15.786
            A0A024R644;A0A0A0MRU5;A0A1B0GWI2;O75503                                          16.691
            A0A075B6H7                                                                       17.048
                                                                                              ...  
Sample_209  Q9Y6R7                                                                           19.091
            Q9Y6X5                                                                           15.698
            Q9Y6Y8;Q9Y6Y8-2                                                                  19.321
            Q9Y6Y9                                                                           12.267
            S4R3U6                                                                           11.398
Length: 298410, dtype: float32

Hide code cell source

 
val_pred_simulated_na['VAE'] = pred  # 'model_key' ?
val_pred_simulated_na
observed VAE
Sample ID protein groups
Sample_158 Q9UN70;Q9UN70-2 14.630 15.598
Sample_050 Q9Y287 15.755 16.743
Sample_107 Q8N475;Q8N475-2 15.029 14.624
Sample_199 P06307 19.376 19.215
Sample_067 Q5VUB5 15.309 15.067
... ... ... ...
Sample_111 F6SYF8;Q9UBP4 22.822 22.861
Sample_002 A0A0A0MT36 18.165 15.771
Sample_049 Q8WY21;Q8WY21-2;Q8WY21-3;Q8WY21-4 15.525 16.008
Sample_182 Q8NFT8 14.379 13.439
Sample_123 Q16853;Q16853-2 14.504 14.501

12600 rows × 2 columns

Hide code cell source

 
test_pred_simulated_na['VAE'] = pred  # model_key?
test_pred_simulated_na
observed VAE
Sample ID protein groups
Sample_000 A0A075B6P5;P01615 17.016 17.354
A0A087X089;Q16627;Q16627-2 18.280 18.009
A0A0B4J2B5;S4R460 21.735 22.169
A0A140T971;O95865;Q5SRR8;Q5SSV3 14.603 15.185
A0A140TA33;A0A140TA41;A0A140TA52;P22105;P22105-3;P22105-4 16.143 16.641
... ... ... ...
Sample_209 Q96ID5 16.074 16.028
Q9H492;Q9H492-2 13.173 13.340
Q9HC57 14.207 14.445
Q9NPH3;Q9NPH3-2;Q9NPH3-5 14.962 14.978
Q9UGM5;Q9UGM5-2 16.871 16.533

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                 15.586
            A0A075B6Q5                 15.767
            A0A075B6R2                 16.694
            A0A075B6S5                 16.178
            A0A087WSY4                 16.239
                                        ...  
Sample_209  Q9P1W8;Q9P1W8-2;Q9P1W8-4   16.018
            Q9UI40;Q9UI40-2            16.332
            Q9UIW2                     16.416
            Q9UMX0;Q9UMX0-2;Q9UMX0-4   13.855
            Q9UP79                     15.915
Name: intensity, Length: 46401, dtype: float32

Plots#

  • validation data

Hide code cell source

 
analysis.model = analysis.model.cpu()
# underlying data is train_X for both
# assert analysis.dls.valid.data.equals(analysis.dls.train.data)
# Reconstruct DataLoader for case that during training singleton batches were dropped
_dl = torch.utils.data.DataLoader(
    pimmslearn.io.datasets.DatasetWithTarget(
        analysis.dls.valid.data),
    batch_size=args.batch_size,
    shuffle=False)
df_latent = pimmslearn.model.get_latent_space(analysis.model.get_mu_and_logvar,
                                              dl=_dl,
                                              dl_index=analysis.dls.valid.data.index)
df_latent
latent dimension 1 latent dimension 2 latent dimension 3 latent dimension 4 latent dimension 5 latent dimension 6 latent dimension 7 latent dimension 8 latent dimension 9 latent dimension 10
Sample ID
Sample_000 -0.279 0.594 -1.780 -0.830 -0.294 1.600 -0.633 0.359 -1.724 -2.012
Sample_001 -0.773 0.196 -0.781 -0.541 -0.429 0.323 -0.116 1.510 -1.872 -2.261
Sample_002 0.013 -0.814 -2.139 -0.310 -0.098 1.069 -0.754 0.969 1.623 -2.933
Sample_003 -0.028 -0.189 -2.082 -0.225 -0.355 1.586 -1.098 -0.047 -0.716 -2.460
Sample_004 0.216 0.181 -0.863 0.472 -1.080 1.085 -0.664 0.133 -0.982 -2.491
... ... ... ... ... ... ... ... ... ... ...
Sample_205 -1.599 -1.902 -0.194 -1.010 -0.450 2.433 0.426 -0.127 0.719 -0.775
Sample_206 -1.028 1.207 2.017 -2.835 -0.268 0.387 -1.022 0.329 0.412 -0.036
Sample_207 -0.297 0.727 1.683 -0.391 -1.262 1.719 1.855 -1.429 -0.950 -1.631
Sample_208 -1.046 0.284 2.388 -0.509 1.157 0.977 1.406 1.130 0.454 -1.803
Sample_209 0.164 0.131 1.373 -0.290 -0.446 0.465 0.753 0.619 1.719 -1.817

210 rows × 10 columns

Hide code cell source

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

Hide code cell source

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

Hide code cell source

 
feat_freq_val = val_pred_simulated_na['observed'].groupby(level=-1).count()
feat_freq_val.name = 'freq_val'
ax = feat_freq_val.plot.box()
_images/cf9e9c20e966b08686dc7f1335a5340e530ffd0a521cae060530e7d2d1604f67.png

Hide code cell source

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

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

Hide code cell source

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


errors_val_smoothed = errors_val.copy()  # .loc[feat_freq_val > 1]
errors_val_smoothed[errors_val.columns[:-1]] = errors_val[errors_val.columns[:-1]
                                                          ].rolling(window=200, min_periods=1).mean()
ax = errors_val_smoothed.plot(x='freq', figsize=(15, 10))
# errors_val_smoothed
_images/3dd924791c301baf540d1749722ac3573c84bd1f420782f13355a5d0b1ed183e.png

Hide code cell source

 
errors_val = val_pred_simulated_na.drop('observed', axis=1).sub(
    val_pred_simulated_na['observed'], axis=0)
errors_val.abs().groupby(level=-1).agg(['mean', 'count'])
VAE
mean count
protein groups
A0A024QZX5;A0A087X1N8;P35237 0.167 7
A0A024R0T9;K7ER74;P02655 1.212 4
A0A024R3W6;A0A024R412;O60462;O60462-2;O60462-3;O60462-4;O60462-5;Q7LBX6;X5D2Q8 0.277 9
A0A024R644;A0A0A0MRU5;A0A1B0GWI2;O75503 0.240 6
A0A075B6H7 0.603 6
... ... ...
Q9Y6R7 0.436 10
Q9Y6X5 0.278 7
Q9Y6Y8;Q9Y6Y8-2 0.356 9
Q9Y6Y9 0.356 15
S4R3U6 0.469 24

1419 rows × 2 columns

Hide code cell source

 
errors_val
VAE
Sample ID protein groups
Sample_158 Q9UN70;Q9UN70-2 0.967
Sample_050 Q9Y287 0.988
Sample_107 Q8N475;Q8N475-2 -0.405
Sample_199 P06307 -0.161
Sample_067 Q5VUB5 -0.242
... ... ...
Sample_111 F6SYF8;Q9UBP4 0.039
Sample_002 A0A0A0MT36 -2.394
Sample_049 Q8WY21;Q8WY21-2;Q8WY21-3;Q8WY21-4 0.483
Sample_182 Q8NFT8 -0.940
Sample_123 Q16853;Q16853-2 -0.003

12600 rows × 1 columns

Comparisons#

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

Validation data#

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

Hide code cell source

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

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

Hide code cell source

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

Selected as truth to compare to: observed

{'VAE': {'MSE': 0.4607077799051976,
  'MAE': 0.43293038367340475,
  'N': 12600,
  'prop': 1.0}}

Test Datasplit#

Hide code cell source

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

Selected as truth to compare to: observed

{'VAE': {'MSE': 0.48127405799430295,
  'MAE': 0.4361880756465144,
  'N': 12600,
  'prop': 1.0}}

Save all metrics as json

Hide code cell source

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

{ 'test_simulated_na': { 'VAE': { 'MAE': 0.4361880756465144,
                                  'MSE': 0.48127405799430295,
                                  'N': 12600,
                                  'prop': 1.0}},
  'valid_simulated_na': { 'VAE': { 'MAE': 0.43293038367340475,
                                   'MSE': 0.4607077799051976,
                                   'N': 12600,
                                   'prop': 1.0}}}

Hide code cell source

 
metrics_df = models.get_df_from_nested_dict(
    d_metrics.metrics, column_levels=['model', 'metric_name']).T
metrics_df
subset valid_simulated_na test_simulated_na
model metric_name
VAE MSE 0.461 0.481
MAE 0.433 0.436
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': 130,
 'epochs_max': 300,
 'file_format': 'csv',
 'fn_rawfile_metadata': 'https://raw.githubusercontent.com/RasmussenLab/njab/HEAD/docs/tutorial/data/alzheimer/meta.csv',
 'folder_data': '',
 'folder_experiment': Path('runs/alzheimer_study'),
 'hidden_layers': [64],
 'latent_dim': 10,
 'meta_cat_col': None,
 'meta_date_col': None,
 'model': 'VAE',
 'model_key': 'VAE',
 'n_params': 277998,
 'out_figures': Path('runs/alzheimer_study/figures'),
 'out_folder': Path('runs/alzheimer_study'),
 'out_metrics': Path('runs/alzheimer_study'),
 'out_models': Path('runs/alzheimer_study'),
 'out_preds': Path('runs/alzheimer_study/preds'),
 'patience': 50,
 'sample_idx_position': 0,
 'save_pred_real_na': True}