Skip to content

Commit 4e0b69f

Browse files
Lucas CamilloLucas Camillo
Lucas Camillo
authored and
Lucas Camillo
committed
bump up v0.0.2
1 parent c04837d commit 4e0b69f

9 files changed

+841
-384
lines changed

Diff for: ‎docs/source/conf.py

+1-1
Original file line numberDiff line numberDiff line change
@@ -13,7 +13,7 @@
1313
project = 'pyaging'
1414
copyright = '2023, Lucas Paulo de Lima Camillo'
1515
author = 'Lucas Paulo de Lima Camillo'
16-
release = '0.0.1'
16+
release = '0.0.2'
1717

1818
# -- General configuration ---------------------------------------------------
1919
# https://www.sphinx-doc.org/en/master/usage/configuration.html#general-configuration

Diff for: ‎pyaging/preprocess/_preprocess.py

+2-1
Original file line numberDiff line numberDiff line change
@@ -127,7 +127,8 @@ def df_to_adata(
127127
The DataFrame containing biological data. Rows represent samples, and columns represent features.
128128
129129
metadata_cols : List[str]
130-
A list with the name of the columns in 'df' which are part of the metadata.
130+
A list with the name of the columns in 'df' which are part of the metadata. They will be added
131+
to adata.obs rather than adata.X.
131132
132133
imputer_strategy : str, optional
133134
The strategy for imputing missing values in 'df'. Supported strategies include 'mean',

Diff for: ‎pyproject.toml

+1-1
Original file line numberDiff line numberDiff line change
@@ -1,6 +1,6 @@
11
[tool.poetry]
22
name = "pyaging"
3-
version = "0.0.1"
3+
version = "0.0.2"
44
description = "A Python-based compendium of GPU-optimized aging clocks."
55
authors = ["Lucas Paulo de Lima Camillo <[email protected]>"]
66
license = "BSD"

Diff for: ‎tutorials/tutorial_atacseq.ipynb

+111-40
Original file line numberDiff line numberDiff line change
@@ -72,8 +72,8 @@
7272
"|-----> 🏗️ Starting download_example_data function\n",
7373
"|-----> ⚙️ Download data started\n",
7474
"|-----------> Data found in pyaging_data/atac_example.pkl\n",
75-
"|-----> ✅ Download data finished [0.0007s]\n",
76-
"|-----> 🎉 Done! [0.0014s]\n"
75+
"|-----> ✅ Download data finished [0.0008s]\n",
76+
"|-----> 🎉 Done! [0.0017s]\n"
7777
]
7878
}
7979
],
@@ -308,6 +308,14 @@
308308
"df.head()"
309309
]
310310
},
311+
{
312+
"cell_type": "markdown",
313+
"id": "4ca435ec-3480-4167-ad55-b8a28b23a843",
314+
"metadata": {},
315+
"source": [
316+
"This is what the adata object looks like:"
317+
]
318+
},
311319
{
312320
"cell_type": "markdown",
313321
"id": "251495e7-082f-45ae-841c-a2dd86a3cb15",
@@ -336,29 +344,60 @@
336344
"text": [
337345
"|-----> 🏗️ Starting df_to_adata function\n",
338346
"|-----> ⚙️ Create anndata object started\n",
339-
"|-----> ✅ Create anndata object finished [0.0018s]\n",
347+
"|-----> ✅ Create anndata object finished [0.0009s]\n",
340348
"|-----> ⚙️ Add metadata to anndata started\n",
341349
"|-----------? No metadata provided. Leaving adata.obs empty\n",
342-
"|-----> ⚠️ Add metadata to anndata finished [0.0082s]\n",
350+
"|-----> ⚠️ Add metadata to anndata finished [0.0021s]\n",
343351
"|-----> ⚙️ Log data statistics started\n",
344352
"|-----------> There are 10 observations\n",
345353
"|-----------> There are 80400 features\n",
346354
"|-----------> Total missing values: 0\n",
347355
"|-----------> Percentage of missing values: 0.00%\n",
348-
"|-----> ✅ Log data statistics finished [0.0026s]\n",
356+
"|-----> ✅ Log data statistics finished [0.0011s]\n",
349357
"|-----> ⚙️ Impute missing values started\n",
350358
"|-----------> No missing values found. No imputation necessary\n",
351-
"|-----> ✅ Impute missing values finished [0.0056s]\n",
359+
"|-----> ✅ Impute missing values finished [0.0022s]\n",
352360
"|-----> ⚙️ Add unstructured data to anndata started\n",
353-
"|-----> ✅ Add unstructured data to anndata finished [0.0074s]\n",
354-
"|-----> 🎉 Done! [0.0288s]\n"
361+
"|-----> ✅ Add unstructured data to anndata finished [0.0042s]\n",
362+
"|-----> 🎉 Done! [0.0111s]\n"
355363
]
356364
}
357365
],
358366
"source": [
359367
"adata = pya.preprocess.df_to_adata(df)"
360368
]
361369
},
370+
{
371+
"cell_type": "markdown",
372+
"id": "5042e04f-17c0-4eb2-8c5d-2c2fc5d6d2d6",
373+
"metadata": {},
374+
"source": [
375+
"This is what the `adata` object looks like:"
376+
]
377+
},
378+
{
379+
"cell_type": "code",
380+
"execution_count": 6,
381+
"id": "503da312-2256-4e67-9747-107f5c4587ec",
382+
"metadata": {},
383+
"outputs": [
384+
{
385+
"data": {
386+
"text/plain": [
387+
"AnnData object with n_obs × n_vars = 10 × 80400\n",
388+
" var: 'percent_na'\n",
389+
" uns: 'imputer_strategy', 'data_type'"
390+
]
391+
},
392+
"execution_count": 6,
393+
"metadata": {},
394+
"output_type": "execute_result"
395+
}
396+
],
397+
"source": [
398+
"adata"
399+
]
400+
},
362401
{
363402
"cell_type": "markdown",
364403
"id": "c072990d-0f54-49b3-bb7a-7bbd13301e2a",
@@ -377,7 +416,7 @@
377416
},
378417
{
379418
"cell_type": "code",
380-
"execution_count": 6,
419+
"execution_count": 7,
381420
"id": "26398785-d1ea-4ce8-b1d9-7234f8f46ef6",
382421
"metadata": {},
383422
"outputs": [
@@ -388,70 +427,70 @@
388427
"|-----> 🏗️ Starting predict_age function\n",
389428
"|-----> ⚙️ Set PyTorch device started\n",
390429
"|-----------> Using device: cpu\n",
391-
"|-----> ✅ Set PyTorch device finished [0.0021s]\n",
430+
"|-----> ✅ Set PyTorch device finished [0.0009s]\n",
392431
"|-----> Processing clock: OcampoATAC1\n",
393432
"|-----------> ⚙️ Load clock started\n",
394433
"|-----------> ⚙️ Download data started\n",
395434
"|-----------> Data found in pyaging_data/ocampoatac1.pt\n",
396-
"|-----------> ✅ Download data finished [0.0006s]\n",
397-
"|-----------> ✅ Load clock finished [0.0006s]\n",
435+
"|-----------> ✅ Download data finished [0.0003s]\n",
436+
"|-----------> ✅ Load clock finished [0.0003s]\n",
398437
"|-----------> ⚙️ Check features in adata started\n",
399438
"|-----------> All features are present in adata.var_names.\n",
400-
"|-----------> ✅ Check features in adata finished [0.0062s]\n",
439+
"|-----------> ✅ Check features in adata finished [0.0030s]\n",
401440
"|-----------> ⚙️ Filter features and extract data matrix started\n",
402-
"|-----------> ✅ Filter features and extract data matrix finished [0.0030s]\n",
441+
"|-----------> ✅ Filter features and extract data matrix finished [0.0012s]\n",
403442
"|-----------> ⚙️ Preprocess data started\n",
404443
"|-----------------> Preprocessing data with function log1p\n",
405-
"|-----------> ✅ Preprocess data finished [0.0054s]\n",
444+
"|-----------> ✅ Preprocess data finished [0.0027s]\n",
406445
"|-----------> ⚙️ Convert numpy array to tensor started\n",
407-
"|-----------> ✅ Convert numpy array to tensor finished [0.0028s]\n",
446+
"|-----------> ✅ Convert numpy array to tensor finished [0.0015s]\n",
408447
"|-----------> ⚙️ Initialize model started\n",
409-
"|-----------> ✅ Initialize model finished [0.0023s]\n",
448+
"|-----------> ✅ Initialize model finished [0.0013s]\n",
410449
"|-----------> ⚙️ Predict ages with model started\n",
411-
"|-----------> ✅ Predict ages with model finished [0.0036s]\n",
450+
"|-----------> ✅ Predict ages with model finished [0.0015s]\n",
412451
"|-----------> ⚙️ Convert tensor to numpy array started\n",
413-
"|-----------> ✅ Convert tensor to numpy array finished [0.0016s]\n",
452+
"|-----------> ✅ Convert tensor to numpy array finished [0.0015s]\n",
414453
"|-----------> ⚙️ Add predicted ages to adata started\n",
415454
"|-----------> ✅ Add predicted ages to adata finished [0.0013s]\n",
416455
"|-----------> ⚙️ Load all clock metadata started\n",
417456
"|-----------> ⚙️ Download data started\n",
418457
"|-----------> Data found in pyaging_data/all_clock_metadata.pt\n",
419-
"|-----------> ✅ Download data finished [0.0005s]\n",
420-
"|-----------> ✅ Load all clock metadata finished [0.0005s]\n",
458+
"|-----------> ✅ Download data finished [0.0003s]\n",
459+
"|-----------> ✅ Load all clock metadata finished [0.0003s]\n",
421460
"|-----------> ⚙️ Add clock metadata to adata.uns started\n",
422461
"|-----------> ✅ Add clock metadata to adata.uns finished [0.0039s]\n",
423462
"|-----> Processing clock: OcampoATAC2\n",
424463
"|-----------> ⚙️ Load clock started\n",
425464
"|-----------> ⚙️ Download data started\n",
426465
"|-----------> Data found in pyaging_data/ocampoatac2.pt\n",
427-
"|-----------> ✅ Download data finished [0.0004s]\n",
428-
"|-----------> ✅ Load clock finished [0.0004s]\n",
466+
"|-----------> ✅ Download data finished [0.0006s]\n",
467+
"|-----------> ✅ Load clock finished [0.0006s]\n",
429468
"|-----------> ⚙️ Check features in adata started\n",
430469
"|-----------> All features are present in adata.var_names.\n",
431-
"|-----------> ✅ Check features in adata finished [0.0034s]\n",
470+
"|-----------> ✅ Check features in adata finished [0.0027s]\n",
432471
"|-----------> ⚙️ Filter features and extract data matrix started\n",
433-
"|-----------> ✅ Filter features and extract data matrix finished [0.0022s]\n",
472+
"|-----------> ✅ Filter features and extract data matrix finished [0.0013s]\n",
434473
"|-----------> ⚙️ Preprocess data started\n",
435474
"|-----------------> Preprocessing data with function log1p\n",
436-
"|-----------> ✅ Preprocess data finished [0.0024s]\n",
475+
"|-----------> ✅ Preprocess data finished [0.0016s]\n",
437476
"|-----------> ⚙️ Convert numpy array to tensor started\n",
438-
"|-----------> ✅ Convert numpy array to tensor finished [0.0019s]\n",
477+
"|-----------> ✅ Convert numpy array to tensor finished [0.0009s]\n",
439478
"|-----------> ⚙️ Initialize model started\n",
440-
"|-----------> ✅ Initialize model finished [0.0021s]\n",
479+
"|-----------> ✅ Initialize model finished [0.0007s]\n",
441480
"|-----------> ⚙️ Predict ages with model started\n",
442-
"|-----------> ✅ Predict ages with model finished [0.0020s]\n",
481+
"|-----------> ✅ Predict ages with model finished [0.0012s]\n",
443482
"|-----------> ⚙️ Convert tensor to numpy array started\n",
444-
"|-----------> ✅ Convert tensor to numpy array finished [0.0010s]\n",
483+
"|-----------> ✅ Convert tensor to numpy array finished [0.0013s]\n",
445484
"|-----------> ⚙️ Add predicted ages to adata started\n",
446-
"|-----------> ✅ Add predicted ages to adata finished [0.0008s]\n",
485+
"|-----------> ✅ Add predicted ages to adata finished [0.0011s]\n",
447486
"|-----------> ⚙️ Load all clock metadata started\n",
448487
"|-----------> ⚙️ Download data started\n",
449488
"|-----------> Data found in pyaging_data/all_clock_metadata.pt\n",
450-
"|-----------> ✅ Download data finished [0.0005s]\n",
451-
"|-----------> ✅ Load all clock metadata finished [0.0005s]\n",
489+
"|-----------> ✅ Download data finished [0.0003s]\n",
490+
"|-----------> ✅ Load all clock metadata finished [0.0003s]\n",
452491
"|-----------> ⚙️ Add clock metadata to adata.uns started\n",
453-
"|-----------> ✅ Add clock metadata to adata.uns finished [0.0025s]\n",
454-
"|-----> 🎉 Done! [0.0612s]\n"
492+
"|-----------> ✅ Add clock metadata to adata.uns finished [0.0023s]\n",
493+
"|-----> 🎉 Done! [0.0396s]\n"
455494
]
456495
}
457496
],
@@ -469,7 +508,7 @@
469508
},
470509
{
471510
"cell_type": "code",
472-
"execution_count": 7,
511+
"execution_count": 8,
473512
"id": "055761d9-7e22-49f3-a1db-31c3ed3749ba",
474513
"metadata": {},
475514
"outputs": [],
@@ -482,7 +521,7 @@
482521
},
483522
{
484523
"cell_type": "code",
485-
"execution_count": 8,
524+
"execution_count": 9,
486525
"id": "fdd9d6c2-7f0a-4f96-a095-4a492ed73f8d",
487526
"metadata": {},
488527
"outputs": [
@@ -550,7 +589,7 @@
550589
"Sample_5 38.929848 33.717129"
551590
]
552591
},
553-
"execution_count": 8,
592+
"execution_count": 9,
554593
"metadata": {},
555594
"output_type": "execute_result"
556595
}
@@ -559,6 +598,38 @@
559598
"adata.obs.head()"
560599
]
561600
},
601+
{
602+
"cell_type": "markdown",
603+
"id": "4bad3df8-f868-4cf5-be74-00ffd02c18f5",
604+
"metadata": {},
605+
"source": [
606+
"After age prediction, the clocks are added to `adata.obs`. Moreover, the percent of missing values for each clock and other metadata are included in `adata.uns`."
607+
]
608+
},
609+
{
610+
"cell_type": "code",
611+
"execution_count": 10,
612+
"id": "0d13fb55-8a12-4d28-83e9-ec7c9fbbe30c",
613+
"metadata": {},
614+
"outputs": [
615+
{
616+
"data": {
617+
"text/plain": [
618+
"AnnData object with n_obs × n_vars = 10 × 80400\n",
619+
" obs: 'ocampoatac1', 'ocampoatac2'\n",
620+
" var: 'percent_na'\n",
621+
" uns: 'imputer_strategy', 'data_type', 'ocampoatac1_percent_na', 'ocampoatac1_metadata', 'ocampoatac2_percent_na', 'ocampoatac2_metadata'"
622+
]
623+
},
624+
"execution_count": 10,
625+
"metadata": {},
626+
"output_type": "execute_result"
627+
}
628+
],
629+
"source": [
630+
"adata"
631+
]
632+
},
562633
{
563634
"cell_type": "markdown",
564635
"id": "a4e7ad8d-44ae-4ced-a626-f9e3b2d04114",
@@ -577,7 +648,7 @@
577648
},
578649
{
579650
"cell_type": "code",
580-
"execution_count": 10,
651+
"execution_count": 11,
581652
"id": "6b368506-55d1-4b74-be61-817bcf575ade",
582653
"metadata": {},
583654
"outputs": [
@@ -591,7 +662,7 @@
591662
" 'doi': 'https://doi.org/10.1007/s11357-023-00986-0'}"
592663
]
593664
},
594-
"execution_count": 10,
665+
"execution_count": 11,
595666
"metadata": {},
596667
"output_type": "execute_result"
597668
}

0 commit comments

Comments
 (0)