Commit History
update to account for set of perturbed genes with aggregate_data
eb038a6
update to enable cls emb
b2bbd7c
update tokenizer to include eos token
ead0550
Christina Theodoris
commited on
Update geneformer/emb_extractor.py (#350)
471eefc
verified
Upload in_silico_perturber_stats.py (#313)
8aee0ff
verified
fix cell state gene embeddings bug (#345)
c0e7b19
verified
patch datasets save_to_disk
75c67a1
Christina Theodoris
commited on
update kwargs for pretrainer
fb130e6
Christina Theodoris
commited on
refer to token dictionary in self
86fe0dd
Christina Theodoris
commited on
Update for gene classification (#330)
94095d1
verified
Update with gene classifier, custom token dict, and str validate options (#329)
0568479
verified
add option for hyperparameter tuning to cc.validate
4bddd45
Christina Theodoris
commited on
correct typo
5a43832
verified
update examples for predict_eval and handle roc for 2 cell classes
eeba323
Christina Theodoris
commited on
Update readthedocs for classifier
f75f5ac
Christina Theodoris
commited on
Get the gene keys and gene list keys from the token dictionary instead of medians (#304)
b294421
verified
Prevent ruff/isort on init
941390d
Christina Theodoris
commited on
Add classifier module and examples
9e9cca9
Christina Theodoris
commited on
Update geneformer/emb_extractor.py (#303)
d6c634c
verified
Fix typo (#301)
075bd53
verified
Add option for variable input_size and to add CLS/SEP Tokens (#299)
aa25cd2
verified
add load model for train and fix validate anchor gene error
0d675a3
Christina Theodoris
commited on
Handle case of single gene del for isp modeling of gene embs
316d817
Christina Theodoris
commited on
edit docstring format to highlight options
e3330a6
Christina Theodoris
commited on
edit docstring codeblock highlighting
d1931b1
Christina Theodoris
commited on
update type of null_dict_list in docstring
79788b6
Christina Theodoris
commited on
change doc formatting
17f036a
Christina Theodoris
commited on
add sphinx docs
2a0dcbe
Christina Theodoris
commited on
update dependencies, reinstate compatibility with python<3.9 with typing for List
10d3f10
Christina Theodoris
commited on
Add option for modified batch size for loom tokenizer
0960cf6
Christina Theodoris
commited on
Add functions for extracting gene embeddings, move state_embs_dict outside isp, fix bugs in isp
2f25aea
Christina Theodoris
commited on
Add option for modifying chunk size for anndata tokenizer
fd93ebf
Christina Theodoris
commited on
tokenizer-uncropped-input_ids (#275)
8df5dc1
fix: incorrect condition control flow (#261)
1366905
Add option to output embs as tensor
624349c
Christina Theodoris
commited on
anndata_tokenizer (#170)
4302f48
Fixed bugs related to overexpressing genes (#229)
39ab62e
Add memory-efficient method for computing emb summary statistics
6caf480
Christina Theodoris
commited on
Fixed bug with the double removing of indices when cell_states_to_model is false (#188)
0adfe67
Upload in_silico_perturber.py (#187)
8180caa
Added feature to perturb a set of indices to help with debugging and with very large runtimes (#175)
f115e8f
Re-update stats to handle case of empty alt_states
78517d8
Christina Theodoris
commited on
Add handling for case of alt_states being empty list
9e8dbe5
Christina Theodoris
commited on
Remove print statement from PR
c4b1f94
Fixed bug in gen_attention_mask with len > max_len (#158)
3a94209
Fixed error with perturbing individual genes and updated ways to specify cell_states_to_model (#146)
9169bfd
Add error message for "gene" embedding extraction under development.
65b4915
Christina Theodoris
commited on
Rename heatmap legend to be correct label
badcca6
Christina Theodoris
commited on
Add function to extract and plot cell embeddings
d154fee
Christina Theodoris
commited on