csPhenotype
Short Description
The csPhenotype function requires a phenotype workflow document to guide the algorithm in performing classification.
The phenotype workflow document is imported as a dataframe
and passed to the
phenotype
argument. It should follow the following structure:
(1) The first column
has to contain the cell that are to be classified.
(2) The second column
indicates the phenotype a particular cell will be assigned
if it satifies the conditions in the row.
(3) Column three
and onward represent protein markers. If the protein marker
is known to be expressed for that cell type, then it is denoted by either pos
,
allpos
. If the protein marker is known to not express for a cell type it
can be denoted by neg
, allneg
. If the protein marker is irrelevant or
uncertain to express for a cell type, then it is left empty. anypos
and
anyneg
are options for using a set of markers and if any of the marker is
positive or negative, the cell type is denoted accordingly.
To give users maximum flexibility in identifying desired cell types, we have implemented various classification arguments as described above for strategical classification. They include
- allpos
- allneg
- anypos
- anyneg
- pos
- neg
pos
: "Pos" looks for cells positive for a given marker. If multiple
markers are annotated as pos
, all must be positive to denote the cell type.
For example, a Regulatory T cell can be defined as CD3+CD4+FOXP3+
by passing
pos
to each marker. If one or more markers don't meet the criteria (e.g. CD4-),
the program will classify it as Likely-Regulatory-T cell
, pending user
confirmation. This is useful in cases of technical artifacts or when cell
types (such as cancer cells) are defined by marker loss (e.g. T-cell Lymphomas).
neg
: Same as pos
but looks for negativity of the defined markers.
allpos
: "Allpos" requires all defined markers to be positive. Unlike
pos
, it doesn't classify cells as Likely-cellType
, but strictly annotates
cells positive for all defined markers.
allneg
: Same as allpos
but looks for negativity of the defined markers.
anypos
: "Anypos" requires only one of the defined markers to be positive.
For example, to define macrophages, a cell could be designated as such if
any of CD68
, CD163
, or CD206
is positive.
anyneg
: Same as anyneg
but looks for negativity of the defined markers.
Function¶
csPhenotype(csObject, phenotype, midpoint=0.5, label='phenotype', imageid='imageid', pheno_threshold_percent=None, pheno_threshold_abs=None, fileName=None, verbose=True, projectDir=None)
¶
Parameters:
Name | Type | Description | Default |
---|---|---|---|
csObject |
anndata
|
Single or combined CSPOT object. |
required |
phenotype |
(dataframe, str)
|
A phenotyping workflow strategy either as a |
required |
midpoint |
float
|
By default, CSPOT normalizes the data in a way that cells with a value above 0.5 are considered positive. However, if you desire more selective threshold, the parameter can be adjusted accordingly. |
0.5
|
label |
str
|
Specify the column name under which the final phenotype classification will be saved. |
'phenotype'
|
imageid |
str
|
The name of the column that holds the unique image ID. |
'imageid'
|
pheno_threshold_percent |
float
|
The user-defined threshold, which can be set between 0-100, is used to recategorize any phenotype that falls below it as 'unknown'. This function is commonly used to address low background false positives. |
None
|
pheno_threshold_abs |
int
|
This function serves a similar purpose as the |
None
|
fileName |
string
|
File Name to be used while saving the CSPOT object. |
None
|
verbose |
bool
|
If True, print detailed information about the process to the console. |
True
|
projectDir |
string
|
Provide the path to the output directory. |
None
|
Returns:
Name | Type | Description |
---|---|---|
csObject |
anndata
|
Modified CSPOT object with the Phenotypes is returned. If |
Example
# set the Project directory
projectDir = '/Users/aj/Documents/cspotExampleData'
# Path to the CSPOT Object
csObject = projectDir + '/CSPOT/csObject/exampleImage_cspotPredict.ome.h5ad'
# load the phenotyping workflow
phenotype = pd.read_csv(str(projectDir) + '/phenotype_workflow.csv')
# Run Function
adata = cs.csPhenotype ( csObject=csObject,
phenotype=phenotype,
midpoint = 0.5,
label="phenotype",
imageid='imageid',
pheno_threshold_percent=None,
pheno_threshold_abs=None,
fileName=None,
projectDir=projectDir)
# Same function if the user wants to run it via Command Line Interface
python csPhenotype.py --csObject /Users/aj/Documents/cspotExampleData/CSPOT/csObject/exampleImage_cspotPredict.ome.h5ad --phenotype /Users/aj/Documents/cspotExampleData/phenotype_workflow.csv --projectDir /Users/aj/Documents/cspotExampleData
Source code in cspot/csPhenotype.py
72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 |
|