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

Add filtering for start state cells prior to in silico perturbation when modeling cell states

Correct order of state dict in in silico perturber stats and tensor dims of alt state emb in in silico perturber

Add explanation of output columns and sort by largest shift

Add note to recommend tuning hyperparameters for downstream applications

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