K- Nearest Neighbors (KNN)

K- Nearest Neighbors (KNN)#

Hide code cell source

 
import logging

import pandas as pd
import sklearn
import sklearn.impute
from IPython.display import display

import pimmslearn
import pimmslearn.model
import pimmslearn.models as models
import pimmslearn.nb
from pimmslearn import sampling
from pimmslearn.io import datasplits
from pimmslearn.models import ae

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
folder_experiment: str = 'runs/example'  # Datasplit folder with data for experiment
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
batch_size: int = 64  # Batch size for training (and evaluation)
cuda: bool = True  # Whether to use a GPU for training
# model
neighbors: int = 3  # number of neigherst neighbors to use
force_train: bool = True  # Force training when saved model could be used. Per default re-train model
sample_idx_position: int = 0  # position of index which is sample ID
model: str = 'KNN'  # model name
model_key: str = 'KNN'  # 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 = "KNN"
neighbors = 5
file_format = "csv"
fn_rawfile_metadata = "https://raw.githubusercontent.com/RasmussenLab/njab/HEAD/docs/tutorial/data/alzheimer/meta.csv"
folder_experiment = "runs/alzheimer_study"
model_key = "KNN5"

Some argument transformations

Hide code cell source

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

{'batch_size': 64,
 'cuda': True,
 'data': Path('runs/alzheimer_study/data'),
 'epochs_max': 50,
 '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'),
 'force_train': True,
 'meta_cat_col': None,
 'meta_date_col': None,
 'model': 'KNN',
 'model_key': 'KNN5',
 'neighbors': 5,
 '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'),
 '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_049  O95467                                  14.593
Sample_093  A2A2V1;P04156;P04156-2                  21.897
Sample_151  A0A1B0GVB9;A0A1C7CYW4;O75787;O75787-2   19.224
Sample_060  Q969P0;Q969P0-3                         18.653
Sample_148  Q8IZS8                                  14.033
Name: intensity, dtype: float64

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#

Hide code cell source

 
freq_feat = sampling.frequency_by_index(data.train_X, 0)
freq_feat.head()  # training data

protein groups
A0A024QZX5;A0A087X1N8;P35237                                                     180
A0A024R0T9;K7ER74;P02655                                                         196
A0A024R3W6;A0A024R412;O60462;O60462-2;O60462-3;O60462-4;O60462-5;Q7LBX6;X5D2Q8   170
A0A024R644;A0A0A0MRU5;A0A1B0GWI2;O75503                                          194
A0A075B6H7                                                                        87
Name: intensity, dtype: int64

Simulated missing values#

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

Hide code cell source

 
val_pred_fake_na = data.val_y.to_frame(name='observed')
val_pred_fake_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_fake_na = data.test_y.to_frame(name='observed')
test_pred_fake_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#

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

Train#

model = ‘sklearn_knn’

Hide code cell source

 
knn_imputer = sklearn.impute.KNNImputer(n_neighbors=args.neighbors).fit(data.train_X)

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)

create predictions and select for split entries

Hide code cell source

 
pred = knn_imputer.transform(data.train_X)
pred = pd.DataFrame(pred, index=data.train_X.index, columns=data.train_X.columns).stack()
pred

Sample ID   protein groups                                                                
Sample_000  A0A024QZX5;A0A087X1N8;P35237                                                     15.912
            A0A024R0T9;K7ER74;P02655                                                         16.852
            A0A024R3W6;A0A024R412;O60462;O60462-2;O60462-3;O60462-4;O60462-5;Q7LBX6;X5D2Q8   15.570
            A0A024R644;A0A0A0MRU5;A0A1B0GWI2;O75503                                          16.481
            A0A075B6H7                                                                       17.301
                                                                                              ...  
Sample_209  Q9Y6R7                                                                           19.275
            Q9Y6X5                                                                           15.732
            Q9Y6Y8;Q9Y6Y8-2                                                                  19.577
            Q9Y6Y9                                                                           11.042
            S4R3U6                                                                           11.791
Length: 298410, dtype: float64

Hide code cell source

 
val_pred_fake_na[args.model_key] = pred
val_pred_fake_na
observed KNN5
Sample ID protein groups
Sample_158 Q9UN70;Q9UN70-2 14.630 15.449
Sample_050 Q9Y287 15.755 17.314
Sample_107 Q8N475;Q8N475-2 15.029 14.355
Sample_199 P06307 19.376 19.385
Sample_067 Q5VUB5 15.309 15.040
... ... ... ...
Sample_111 F6SYF8;Q9UBP4 22.822 22.899
Sample_002 A0A0A0MT36 18.165 16.142
Sample_049 Q8WY21;Q8WY21-2;Q8WY21-3;Q8WY21-4 15.525 15.574
Sample_182 Q8NFT8 14.379 13.480
Sample_123 Q16853;Q16853-2 14.504 14.627

12600 rows × 2 columns

Hide code cell source

 
test_pred_fake_na[args.model_key] = pred
test_pred_fake_na
observed KNN5
Sample ID protein groups
Sample_000 A0A075B6P5;P01615 17.016 17.207
A0A087X089;Q16627;Q16627-2 18.280 18.146
A0A0B4J2B5;S4R460 21.735 21.959
A0A140T971;O95865;Q5SRR8;Q5SSV3 14.603 15.143
A0A140TA33;A0A140TA41;A0A140TA52;P22105;P22105-3;P22105-4 16.143 16.743
... ... ... ...
Sample_209 Q96ID5 16.074 15.981
Q9H492;Q9H492-2 13.173 13.432
Q9HC57 14.207 14.131
Q9NPH3;Q9NPH3-2;Q9NPH3-5 14.962 15.123
Q9UGM5;Q9UGM5-2 16.871 16.378

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_fake_na.index,
                                         test_idx=test_pred_fake_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                 15.591
            A0A075B6Q5                 15.915
            A0A075B6R2                 16.857
            A0A075B6S5                 16.192
            A0A087WSY4                 16.490
                                        ...  
Sample_209  Q9P1W8;Q9P1W8-2;Q9P1W8-4   15.979
            Q9UI40;Q9UI40-2            16.704
            Q9UIW2                     17.246
            Q9UMX0;Q9UMX0-2;Q9UMX0-4   12.989
            Q9UP79                     15.647
Name: intensity, Length: 46401, dtype: float64

Plots#

  • validation data

Comparisons#

Validation data#

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

Does not make to much sense to compare collab and AEs, as the setup differs of training and validation data differs

Hide code cell source

 
# papermill_description=metrics
d_metrics = models.Metrics()

The fake 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_fake_na, 'valid_fake_na')
added_metrics

Selected as truth to compare to: observed

{'KNN5': {'MSE': 0.5165599266763434,
  'MAE': 0.4669947218139098,
  'N': 12600,
  'prop': 1.0}}

Test Datasplit#

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

Hide code cell source

 
added_metrics = d_metrics.add_metrics(test_pred_fake_na, 'test_fake_na')
added_metrics

Selected as truth to compare to: observed

{'KNN5': {'MSE': 0.5179350572570403,
  'MAE': 0.46923050106832126,
  '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_fake_na': { 'KNN5': { 'MAE': 0.46923050106832126,
                              'MSE': 0.5179350572570403,
                              'N': 12600,
                              'prop': 1.0}},
  'valid_fake_na': { 'KNN5': { 'MAE': 0.4669947218139098,
                               'MSE': 0.5165599266763434,
                               '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_fake_na test_fake_na
model metric_name
KNN5 MSE 0.517 0.518
MAE 0.467 0.469
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_fake_na.to_csv(args.out_preds / f"pred_val_{args.model_key}.csv")
test_pred_fake_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.n_params = 1  # the number of neighbors to consider
args.dump(fname=args.out_models / f"model_config_{args.model_key}.yaml")
args

{'M': 1421,
 'batch_size': 64,
 'cuda': True,
 'data': Path('runs/alzheimer_study/data'),
 'epochs_max': 50,
 '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'),
 'force_train': True,
 'meta_cat_col': None,
 'meta_date_col': None,
 'model': 'KNN',
 'model_key': 'KNN5',
 'n_params': 1,
 'neighbors': 5,
 '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'),
 'sample_idx_position': 0,
 'save_pred_real_na': True}
Contents