File size: 8,621 Bytes
0b11a42 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 |
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/nfs/home/yat_ldap/conda/envs/hbdx/envs/transforna/lib/python3.9/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
" from .autonotebook import tqdm as notebook_tqdm\n"
]
}
],
"source": [
"from transforna import load,predict_transforna_all_models,predict_transforna,fold_sequences\n",
"models_path = '/nfs/home/yat_ldap/VS_Projects/TransfoRNA-Framework/models/tcga/'\n",
"lc_path = '/media/ftp_share/hbdx/annotation/feature_annotation/ANNOTATION/HBDxBase_annotation/TransfoRNA/compare_binning_strategies/v05/2024-04-19__230126_LC_DI_HB_GEL_v23.01.00/sRNA_anno_aggregated_on_seq.csv'\n",
"tcga_path = '/media/ftp_share/hbdx/data_for_upload/TransfoRNA/data/TCGA__ngs__miRNA_log2RPM-24.04.0__var.csv'\n",
"\n",
"tcga_df = load(tcga_path)\n",
"lc_df = load(lc_path)\n",
"\n",
"lc_df = lc_df[lc_df.sequence.str.len() <= 30]\n",
"\n",
"all_seqs = lc_df.sequence.tolist()+tcga_df.sequence.tolist()\n",
"\n",
"mapping_dict_path = '/media/ftp_share/hbdx/data_for_upload/TransfoRNA//data/subclass_to_annotation.json'\n",
"mapping_dict = load(mapping_dict_path)\n",
" "
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"predictions = predict_transforna_all_models(all_seqs,trained_on='full',path_to_models=models_path)\n",
"predictions.to_csv('predictions_lc_tcga.csv',index=False)"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"#read predictions\n",
"predictions = load('predictions_lc_tcga.csv')"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"umaps = {}\n",
"models = predictions['Model'].unique()\n",
"for model in models:\n",
" if model == 'Ensemble':\n",
" continue\n",
" #get predictions\n",
" model_predictions = predictions[predictions['Model']==model]\n",
" #get is familiar rows\n",
" familiar_df = model_predictions[model_predictions['Is Familiar?']==True]\n",
" #get umap\n",
" umap_df = predict_transforna(model_predictions['Sequence'].tolist(),model=model,trained_on='full',path_to_models=models_path,umap_flag=True)\n",
" umaps[model] = umap_df"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"\n",
"import plotly.express as px\n",
"import numpy as np\n",
"mcs = np.unique(umaps['Seq']['Net-Label'].map(mapping_dict))\n",
"#filter out the classes that contain ;\n",
"mcs = [mc for mc in mcs if ';' not in mc]\n",
"colors = px.colors.qualitative.Plotly\n",
"color_mapping = dict(zip(mcs,colors))\n",
"for model,umap_df in umaps.items():\n",
" umap_df['Major Class'] = umap_df['Net-Label'].map(mapping_dict)\n",
" umap_df_copy = umap_df.copy()\n",
" #remove rows with Major Class containing ;\n",
" umap_df = umap_df[~umap_df['Major Class'].str.contains(';')]\n",
" fig = px.scatter(umap_df,x='UMAP1',y='UMAP2',color='Major Class',hover_data\n",
" =['Sequence'],title=model,\\\n",
" width = 800, height=800,color_discrete_map=color_mapping)\n",
" fig.update_traces(marker=dict(size=1))\n",
" #white background\n",
" fig.update_layout(plot_bgcolor='rgba(0,0,0,0)')\n",
" #only show UMAP1 from 4.3 to 11\n",
" fig.update_xaxes(range=[4.3,11])\n",
" #and UMAP2 from -2.3 to 6.8\n",
" fig.update_yaxes(range=[-2.3,6.8])\n",
" #fig.show()\n",
" fig.write_image(f'lc_figures/lc_tcga_umap_selected_{model}.png')\n",
" fig.write_image(f'lc_figures/lc_tcga_umap_selected_{model}.svg')\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import plotly.express as px\n",
"import numpy as np\n",
"mcs = np.unique(umaps['Seq']['Net-Label'].map(mapping_dict))\n",
"#filter out the classes that contain ;\n",
"mcs = [mc for mc in mcs if ';' not in mc]\n",
"colors = px.colors.qualitative.Plotly + px.colors.qualitative.Light24\n",
"color_mapping = dict(zip(mcs,colors))\n",
"for model,umap_df in umaps.items():\n",
" umap_df['Major Class'] = umap_df['Net-Label'].map(mapping_dict)\n",
" umap_df_copy = umap_df.copy()\n",
" #remove rows with Major Class containing ;\n",
" umap_df = umap_df[~umap_df['Major Class'].str.contains(';')]\n",
" fig = px.scatter(umap_df,x='UMAP1',y='UMAP2',color='Major Class',hover_data\n",
" =['Sequence'],title=model,\\\n",
" width = 800, height=800,color_discrete_map=color_mapping)\n",
" fig.update_traces(marker=dict(size=1))\n",
" #white background\n",
" fig.update_layout(plot_bgcolor='rgba(0,0,0,0)')\n",
" #fig.show()\n",
" fig.write_image(f'lc_figures/lc_tcga_umap_{model}.png')\n",
" fig.write_image(f'lc_figures/lc_tcga_umap_{model}.svg')\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"#plot umap using px.scatter for each model\n",
"import plotly.express as px\n",
"import numpy as np\n",
"mcs = np.unique(umaps['Seq']['Net-Label'].map(mapping_dict))\n",
"#filter out the classes that contain ;\n",
"mcs = [mc for mc in mcs if ';' not in mc]\n",
"colors = px.colors.qualitative.Plotly\n",
"color_mapping = dict(zip(mcs,colors))\n",
"umap_df = umaps['Seq']\n",
"umap_df['Major Class'] = umap_df['Net-Label'].map(mapping_dict)\n",
"umap_df_copy = umap_df.copy()\n",
"#display points contained within the circle at center (7.9,2.5) and radius 4.3\n",
"umap_df_copy['distance'] = np.sqrt((umap_df_copy['UMAP1']-7.9)**2+(umap_df_copy['UMAP2']-2.5)**2)\n",
"umap_df_copy = umap_df_copy[umap_df_copy['distance']<=4.3]\n",
"#remove rows with Major Class containing ;\n",
"umap_df_copy = umap_df_copy[~umap_df_copy['Major Class'].str.contains(';')]\n",
"fig = px.scatter(umap_df_copy,x='UMAP1',y='UMAP2',color='Major Class',hover_data\n",
" =['Sequence'],title=model,\\\n",
" width = 800, height=800,color_discrete_map=color_mapping)\n",
"fig.update_traces(marker=dict(size=1))\n",
"#white background\n",
"fig.update_layout(plot_bgcolor='rgba(0,0,0,0)')\n",
"fig.show()\n",
"#fig.write_image(f'lc_figures/lc_tcga_umap_selected_{model}.png')\n",
"#fig.write_image(f'lc_figures/lc_tcga_umap_selected_{model}.svg')\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"#plot\n",
"sec_struct = fold_sequences(model_predictions['Sequence'].tolist())['structure_37']\n",
"#sec struct ratio is calculated as the number of non '.' characters divided by the length of the sequence\n",
"sec_struct_ratio = sec_struct.apply(lambda x: (len(x)-x.count('.'))/len(x))\n"
]
},
{
"cell_type": "code",
"execution_count": 40,
"metadata": {},
"outputs": [],
"source": [
"umap_df = umaps['Seq-Struct']\n",
"fig = px.scatter(umap_df,x='UMAP1',y='UMAP2',color=sec_struct_ratio,hover_data=['Sequence'],title=model,\\\n",
" width = 800, height=800,color_continuous_scale='Viridis')\n",
"fig.update_traces(marker=dict(size=1))\n",
"fig.update_layout(plot_bgcolor='rgba(0,0,0,0)')\n",
"#save\n",
"fig.write_image(f'lc_figures/lc_tcga_umap_{model}_dot_bracket.png')\n",
"fig.write_image(f'lc_figures/lc_tcga_umap_{model}_dot_bracket.svg')"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "transforna",
"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": "3.9.18"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
|