File size: 6,478 Bytes
1c2f864 2f25aea e2ee685 2f25aea e2ee685 2f25aea 1c2f864 acd253c 2f25aea 1c2f864 e2ee685 1c2f864 acd253c e2ee685 acd253c 2f25aea acd253c 1c2f864 e2ee685 acd253c e2ee685 acd253c 1c2f864 acd253c 1c2f864 e2ee685 1c2f864 acd253c 2f25aea 1c2f864 e2ee685 1c2f864 e2ee685 1c2f864 e2ee685 1c2f864 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 |
{
"cells": [
{
"cell_type": "code",
"execution_count": null,
"id": "e10ac0c9-40ce-41fb-b6fa-3d62b76f2e57",
"metadata": {},
"outputs": [],
"source": [
"from geneformer import InSilicoPerturber\n",
"from geneformer import InSilicoPerturberStats\n",
"from geneformer import EmbExtractor"
]
},
{
"cell_type": "markdown",
"id": "cbd6851c-060e-4967-b816-e605ffe58b23",
"metadata": {
"tags": []
},
"source": [
"### in silico perturbation in deletion mode to determine genes whose deletion in the dilated cardiomyopathy (dcm) state significantly shifts the embedding towards non-failing (nf) state"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "c53e98cd-c603-4878-82ba-db471181bb55",
"metadata": {},
"outputs": [],
"source": [
"# first obtain start, goal, and alt embedding positions\n",
"# this function was changed to be separate from perturb_data\n",
"# to avoid repeating calcuations when parallelizing perturb_data\n",
"cell_states_to_model={\"state_key\": \"disease\", \n",
" \"start_state\": \"dcm\", \n",
" \"goal_state\": \"nf\", \n",
" \"alt_states\": [\"hcm\"]}\n",
"\n",
"filter_data_dict={\"cell_type\":[\"Cardiomyocyte1\",\"Cardiomyocyte2\",\"Cardiomyocyte3\"]}\n",
"\n",
"# OF NOTE: token_dictionary_file must be set to the gc-30M token dictionary if using a 30M series model\n",
"# (otherwise the EmbExtractor will use the current default model dictionary)\n",
"# 30M token dictionary: https://huggingface.co/ctheodoris/Geneformer/blob/main/geneformer/gene_dictionaries_30m/token_dictionary_gc30M.pkl\n",
"embex = EmbExtractor(model_type=\"CellClassifier\", # if using previously fine-tuned cell classifier model\n",
" num_classes=3,\n",
" filter_data=filter_data_dict,\n",
" max_ncells=1000,\n",
" emb_layer=0,\n",
" summary_stat=\"exact_mean\",\n",
" forward_batch_size=256,\n",
" nproc=16)\n",
"\n",
"state_embs_dict = embex.get_state_embs(cell_states_to_model,\n",
" \"../fine_tuned_models/gf-6L-30M-i2048_CellClassifier_cardiomyopathies_220224\", # example 30M fine-tuned model\n",
" \"path/to/input_data\",\n",
" \"path/to/output_directory\",\n",
" \"output_prefix\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "981e1190-62da-4543-b7d3-6e2a2d6a6d56",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"# OF NOTE: token_dictionary_file must be set to the gc-30M token dictionary if using a 30M series model\n",
"# (otherwise the InSilicoPerturber will use the current default model dictionary)\n",
"# 30M token dictionary: https://huggingface.co/ctheodoris/Geneformer/blob/main/geneformer/gene_dictionaries_30m/token_dictionary_gc30M.pkl\n",
"isp = InSilicoPerturber(perturb_type=\"delete\",\n",
" perturb_rank_shift=None,\n",
" genes_to_perturb=\"all\",\n",
" combos=0,\n",
" anchor_gene=None,\n",
" model_type=\"CellClassifier\", # if using previously fine-tuned cell classifier model\n",
" num_classes=3,\n",
" emb_mode=\"cell\",\n",
" cell_emb_style=\"mean_pool\",\n",
" filter_data=filter_data_dict,\n",
" cell_states_to_model=cell_states_to_model,\n",
" state_embs_dict=state_embs_dict,\n",
" max_ncells=2000,\n",
" emb_layer=0,\n",
" forward_batch_size=400,\n",
" nproc=16)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "0525a663-871a-4ce0-a135-cc203817ffa9",
"metadata": {},
"outputs": [],
"source": [
"# outputs intermediate files from in silico perturbation\n",
"\n",
"isp.perturb_data(\"../fine_tuned_models/gf-6L-30M-i2048_CellClassifier_cardiomyopathies_220224\", # example 30M fine-tuned model\n",
" \"path/to/input_data\",\n",
" \"path/to/isp_output_directory\",\n",
" \"output_prefix\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "f8aadabb-516a-4dc0-b307-6de880e64e26",
"metadata": {},
"outputs": [],
"source": [
"# OF NOTE: token_dictionary_file must be set to the gc-30M token dictionary if using a 30M series model\n",
"# (otherwise the InSilicoPerturberStats will use the current default model dictionary)\n",
"# 30M token dictionary: https://huggingface.co/ctheodoris/Geneformer/blob/main/geneformer/gene_dictionaries_30m/token_dictionary_gc30M.pkl\n",
"ispstats = InSilicoPerturberStats(mode=\"goal_state_shift\",\n",
" genes_perturbed=\"all\",\n",
" combos=0,\n",
" anchor_gene=None,\n",
" cell_states_to_model=cell_states_to_model)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "ffecfae6-e737-43e3-99e9-fa37ff46610b",
"metadata": {},
"outputs": [],
"source": [
"# extracts data from intermediate files and processes stats to output in final .csv\n",
"ispstats.get_stats(\"path/to/isp_output_directory\", # this should be the directory \n",
" None,\n",
" \"path/to/isp_stats_output_directory\",\n",
" \"output_prefix\")"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.10.15"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
|