Commit History

  1. fix: incorrect condition control flow⁠

    4f17a92

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

    dbfac41

  1. Add option to output embs as tensor

    Christina Theodoris
    624349c

  1. anndata_tokenizer (#170)⁠

    ctheodoris +1: ricomnl
    4302f48

  1. Fixed bugs related to overexpressing genes (#229)⁠

    ctheodoris +1: davidjwen
    39ab62e

  1. Update installation instructions to include git lfs install and ssh method

    4ce81ab

  1. Config head node runtime via IP (#234)⁠

    ctheodoris +1: madhavanvenkatesh
    b8fda63

  1. Add memory-efficient method for computing emb summary statistics

    Christina Theodoris
    6caf480

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

    ctheodoris +1: SFconvertbot
    61f15d2

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

    ctheodoris +1: davidjwen
    0adfe67
  2. Upload in_silico_perturber.py (#187)⁠

    ctheodoris +1: davidjwen
    8180caa

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

    ctheodoris +1: davidjwen
    f115e8f

  1. Re-update stats to handle case of empty alt_states

    Christina Theodoris
    78517d8
  2. Add handling for case of alt_states being empty list

    Christina Theodoris
    9e8dbe5

  1. Remove print statement from PR

    c4b1f94
  2. Fixed bug in gen_attention_mask with len > max_len (#158)⁠

    ctheodoris +1: davidjwen
    3a94209
  3. Fixed error with perturbing individual genes and updated ways to specify cell_states_to_model (#146)⁠

    ctheodoris +1: davidjwen
    9169bfd

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

    Christina Theodoris
    65b4915
  2. Update README.md⁠

    e820326
  3. Rename heatmap legend to be correct label

    Christina Theodoris
    badcca6
  4. Add function to extract and plot cell embeddings

    Christina Theodoris
    d154fee
  5. Add fine-tuned CellClassifier for cardiomyopathy

    Christina Theodoris
    1786b44
  6. Add error for no files found and suppress loompy import warning

    Christina Theodoris
    abdf980

  1. Add sorting for aggregating data for goal state shifts

    Christina Theodoris
    50e921d
  2. Fix min_genes to be >= tokens to perturb as a group

    Christina Theodoris
    268e566

  1. Update tokenizer to allow tokenization without custom cell attributes

    Christina Theodoris
    57b9778
  2. Update isp to allow modeling single perturbation in multiple cells as batches

    Christina Theodoris
    acd253c

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

    Christina Theodoris
    45b9d69

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

    Christina Theodoris
    b36d210

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

    Christina Theodoris
    bb217cf

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

    Christina Theodoris
    3d06203
  2. Add explanation of output columns and sort by largest shift

    Christina Theodoris
    3072225

  1. Add note to recommend tuning hyperparameters for downstream applications

    Christina Theodoris
    98ce6d7

  1. Add instructions to convert gene annotations w/ Ensembl Biomart

    Christina Theodoris
    77eb432

  1. Update manuscript link to SharedIt

    4f6115b
  2. Update manuscript link in model card to ShareIt

    dd016da

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

    Christina Theodoris
    e78c44d
  2. Modify quant_layers to convert layer nums to integers before calculating max

    Christina Theodoris
    2181aa4

  1. Remove unused evalset variable from cell classification example

    Christina Theodoris
    879a878

  1. Modify documentation for modeling only 2 cell states

    Christina Theodoris
    019165f
  2. Add instructions for modeling only 2 states and modify stats script for that option

    Christina Theodoris
    912860d

  1. Update links including unsorted example lengths file

    Christina Theodoris
    f0b6641

  1. Add function to create remainder emb for in silico overexpression batch

    Christina Theodoris
    feeecd0

  1. Add mixture model option for gene-gene interaction stats

    Christina Theodoris
    dc1481d
  2. Add uniform max len for padding for predictions

    Christina Theodoris
    67f674c

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

    Christina Theodoris
    d20ad0a
  2. Update model card for 12 layer Geneformer model

    0637325
  3. Update model card for 12 layer Geneformer

    514c5fb
  4. Upload 12 layer Geneformer model

    9d41e70

  1. Fix bug in clearing cache

    Christina Theodoris
    8c2fae7