valsv commited on
Commit
b5283a7
·
verified ·
1 Parent(s): bbb0ec1

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -56
README.md CHANGED
@@ -19,7 +19,7 @@ tags:
19
 
20
  <!-- Provide a quick summary of what the model is/does. -->
21
 
22
- An SCVI model and minified AnnData of the Tahoe-100M dataset from Vevo Tx.
23
 
24
  ## Model Details
25
 
@@ -152,7 +152,9 @@ BARCODE_SUB_LIB_ID
152
 
153
  <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
154
 
155
- Tahoe-100M (to be described)
 
 
156
 
157
  ### Training Procedure
158
 
@@ -187,57 +189,3 @@ Data in the minified AnnData where the 'plate' column equals '14' was held out f
187
 
188
  The main metric is reconstruction error, defined as the average negative log likelihood of the observed counts given the representation vectors. This model uses a negative binomial likelihood.
189
 
190
- ### Results
191
-
192
- [Update with numbers]
193
-
194
- #### Summary
195
-
196
- {{ results_summary | default("", true) }}
197
-
198
-
199
- ### Model Architecture and Objective
200
-
201
- {{ model_specs | default("[More Information Needed]", true)}}
202
-
203
- ### Compute Infrastructure
204
-
205
- {{ compute_infrastructure | default("[More Information Needed]", true)}}
206
-
207
- #### Hardware
208
-
209
- {{ hardware_requirements | default("[More Information Needed]", true)}}
210
-
211
- #### Software
212
-
213
- {{ software | default("[More Information Needed]", true)}}
214
-
215
- ## Citation [optional]
216
-
217
- <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
218
-
219
- **BibTeX:**
220
-
221
- {{ citation_bibtex | default("[More Information Needed]", true)}}
222
-
223
- **APA:**
224
-
225
- {{ citation_apa | default("[More Information Needed]", true)}}
226
-
227
- ## Glossary [optional]
228
-
229
- <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
230
-
231
- {{ glossary | default("[More Information Needed]", true)}}
232
-
233
- ## More Information [optional]
234
-
235
- {{ more_information | default("[More Information Needed]", true)}}
236
-
237
- ## Model Card Authors [optional]
238
-
239
- {{ model_card_authors | default("[More Information Needed]", true)}}
240
-
241
- ## Model Card Contact
242
-
243
- {{ model_card_contact | default("[More Information Needed]", true)}}
 
19
 
20
  <!-- Provide a quick summary of what the model is/does. -->
21
 
22
+ An SCVI model and minified AnnData of the [Tahoe-100M](https://doi.org/10.1101/2025.02.20.639398) dataset from Vevo Tx.
23
 
24
  ## Model Details
25
 
 
152
 
153
  <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
154
 
155
+ Tahoe-100M
156
+
157
+ Zhang, Jesse, Airol A. Ubas, Richard de Borja, Valentine Svensson, Nicole Thomas, Neha Thakar, Ian Lai, et al. 2025. “Tahoe-100M: A Giga-Scale Single-Cell Perturbation Atlas for Context-Dependent Gene Function and Cellular Modeling.” bioRxiv. https://doi.org/10.1101/2025.02.20.639398.
158
 
159
  ### Training Procedure
160
 
 
189
 
190
  The main metric is reconstruction error, defined as the average negative log likelihood of the observed counts given the representation vectors. This model uses a negative binomial likelihood.
191