Add classifier module and examples

Update geneformer/emb_extractor.py (#303)

Fix typo (#301)

Add option for variable input_size and to add CLS/SEP Tokens (#299)

add load model for train and fix validate anchor gene error

Handle case of single gene del for isp modeling of gene embs

edit docstring format to highlight options

edit docstring codeblock highlighting

update type of null_dict_list in docstring

add readthedocs link to model card

update doc css

change doc formatting

update readthedocs.yaml

add readthedocs yaml and req

add sphinx docs

update dependencies, reinstate compatibility with python<3.9 with typing for List

Add option for modified batch size for loom tokenizer

Add functions for extracting gene embeddings, move state_embs_dict outside isp, fix bugs in isp

Add option for modifying chunk size for anndata tokenizer

Add pre-commit config

tokenizer-uncropped-input_ids (#275)

fix: incorrect condition control flow (#261)

Update model card to emphasize need to install git-lfs and suggest https method

Add option to output embs as tensor

anndata_tokenizer (#170)

Fixed bugs related to overexpressing genes (#229)

Update installation instructions to include git lfs install and ssh method

Config head node runtime via IP (#234)

Add memory-efficient method for computing emb summary statistics

Adding `safetensors` variant of this model (#209)

Fixed bug with the double removing of indices when cell_states_to_model is false (#188)

Upload in_silico_perturber.py (#187)

Added feature to perturb a set of indices to help with debugging and with very large runtimes (#175)

Re-update stats to handle case of empty alt_states

Add handling for case of alt_states being empty list

Remove print statement from PR

Fixed bug in gen_attention_mask with len > max_len (#158)

Fixed error with perturbing individual genes and updated ways to specify cell_states_to_model (#146)

Add error message for "gene" embedding extraction under development.

Update README.md

Rename heatmap legend to be correct label

Add function to extract and plot cell embeddings

Add fine-tuned CellClassifier for cardiomyopathy

Add error for no files found and suppress loompy import warning

Add sorting for aggregating data for goal state shifts

Fix min_genes to be >= tokens to perturb as a group

Update tokenizer to allow tokenization without custom cell attributes

Update isp to allow modeling single perturbation in multiple cells as batches

Change list of individual IDs to set to ensure unique before subsetting into train/valid/test sets

Update internal format of anchor token to list for consistency with genes to perturb