Upload tokenizer.py

Add instructions to convert gene annotations w/ Ensembl Biomart

Update manuscript link to SharedIt

Update manuscript link in model card to ShareIt

Modify tokenizer to allow renaming attr names btwn loom and .dataset

Modify quant_layers to convert layer nums to integers before calculating max

Remove unused evalset variable from cell classification example

Modify documentation for modeling only 2 cell states

Add instructions for modeling only 2 states and modify stats script for that option

Update links including unsorted example lengths file

Add function to create remainder emb for in silico overexpression batch

Add mixture model option for gene-gene interaction stats

Add uniform max len for padding for predictions

Add stats with mixture model to determine whether test perturbation is in impact component

Update model card for 12 layer Geneformer model

Update model card for 12 layer Geneformer

Upload 12 layer Geneformer model

Fix bug in clearing cache

Add example code for obtaining non-zero median digests

Update model card with license Apache 2.0

Fix filter_data to allow value of None for no filtering

Add further explanation regarding input file format for transcriptome tokenizer

Update instructions in tokenizing example to clarify requirement for Ensembl ID

Update instructions in tokenizing example to clarify requirement for Ensembl ID

Add further explanation to tokenizer example script and updated tokenizer to match loompy raised error

Move example input files to dataset repository to include example datasets for fine-tuning

Update model card with information about fine-tuning

Add example for tokenizing .loom dataset

Update gene classification example to create directory after training arguments are defined

Subclass collator for cell classification

Update pretrainer for transformers==4.28.0

Upload gene_name_id_dict.pkl (#14)

Fixes to stats and adding gene dict attempt number 2 (#13)

Rename isp stats methods to clarify mode.

Reorder/sort isp stats output in vs_null mode

Moving merged in_silico_perturber_stats.py to geneformer folder

Added comparison to null distribution for stats (#9)

Add example input labels for distinguishing bivalent promoters.

Add in silico perturbation example notebook.

Add gitignore file

add in silico perturbation module

Add example input files for gene classification of TF dosage sensitivity

Update model card

Update model card

add in silico perturbation module

Add gene name : Ensembl ID dictionary

Add example for hyperparameter optimization for disease classifier

Update model card

Librarian Bot: Update dataset YAML metadata for model (#1)

Fix bug with metadata when processing multiple .loom files (#3)