Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Update custom kinfraglib #71

Merged
merged 7 commits into from
May 27, 2024
Merged

Update custom kinfraglib #71

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
03592a7
wip update
kabu00002 May 27, 2024
a633d4c
running notebook
kabu00002 May 27, 2024
17c7950
finalized
kabu00002 May 27, 2024
3c10589
added missing HTML
kabu00002 May 27, 2024
cc98cdd
solving merge conflict
kabu00002 May 27, 2024
0125ee6
fixed HTML
kabu00002 May 27, 2024
04786e1
auto reload
kabu00002 May 27, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
147 changes: 43 additions & 104 deletions notebooks/custom_kinfraglib/1_1_custom_filters_unwanted_substructures.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -357,68 +357,7 @@
"</div>"
],
"text/plain": [
" subpocket smiles \\\n",
"0 AP Nc1c[nH]c2ncccc12 \n",
"1 AP N/C(=C1\\C(=O)Nc2ccccc21)c1ccccc1 \n",
"2 AP CC1=C2/C(=N/c3ccccc3)N=CN=[N+]2C=C1 \n",
"3 AP Nc1ncnn2cccc12 \n",
"4 AP Cc1cc(N)[nH]n1 \n",
"\n",
" ROMol \\\n",
"0 <img data-content=\"rdkit/molecule\" src=\"data:i... \n",
"1 <img data-content=\"rdkit/molecule\" src=\"data:i... \n",
"2 <img data-content=\"rdkit/molecule\" src=\"data:i... \n",
"3 <img data-content=\"rdkit/molecule\" src=\"data:i... \n",
"4 <img data-content=\"rdkit/molecule\" src=\"data:i... \n",
"\n",
" ROMol_dummy \\\n",
"0 <img data-content=\"rdkit/molecule\" src=\"data:i... \n",
"1 <img data-content=\"rdkit/molecule\" src=\"data:i... \n",
"2 <img data-content=\"rdkit/molecule\" src=\"data:i... \n",
"3 <img data-content=\"rdkit/molecule\" src=\"data:i... \n",
"4 <img data-content=\"rdkit/molecule\" src=\"data:i... \n",
"\n",
" ROMol_original kinase family group \\\n",
"0 <img data-content=\"rdkit/molecule\" src=\"data:i... AAK1 NAK Other \n",
"1 <img data-content=\"rdkit/molecule\" src=\"data:i... AAK1 NAK Other \n",
"2 <img data-content=\"rdkit/molecule\" src=\"data:i... AAK1 NAK Other \n",
"3 <img data-content=\"rdkit/molecule\" src=\"data:i... AAK1 NAK Other \n",
"4 <img data-content=\"rdkit/molecule\" src=\"data:i... ABL1 Abl TK \n",
"\n",
" complex_pdb ligand_pdb alt chain \\\n",
"0 5l4q LKB A A \n",
"1 5te0 XIN A \n",
"2 8gmc YFV A \n",
"3 8gmd ZRR A \n",
"4 2f4j VX6 A \n",
"\n",
" atom_subpockets \\\n",
"0 AP AP AP AP AP AP AP AP AP AP AP AP AP AP AP F... \n",
"1 AP AP AP AP AP AP AP AP AP AP AP AP AP AP AP A... \n",
"2 AP AP AP AP AP AP AP AP AP AP AP AP AP AP AP A... \n",
"3 AP AP AP AP AP AP AP AP AP AP AP AP AP AP GA FP \n",
"4 AP AP AP AP AP AP AP AP AP AP AP AP AP SE \n",
"\n",
" atom_environments \\\n",
"0 16 16 16 16 16 16 16 16 16 16 16 16 16 5 5 na na \n",
"1 7 16 7 16 16 16 16 5 16 16 16 16 16 5 5 5 5 5 ... \n",
"2 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 16 4 4 4 4... \n",
"3 14 14 14 14 14 14 14 16 14 14 14 14 5 5 na na \n",
"4 5 5 14 14 14 14 14 14 14 8 8 8 8 na \n",
"\n",
" smiles_dummy fragment_count \\\n",
"0 [11*]c1cnc2[nH]cc(N[27*])c2c1 3 \n",
"1 [12*]N/C(=C1\\C(=O)Nc2cc([20*])ccc21)c1ccccc1 3 \n",
"2 [39*]c1cccc(/N=C2\\N=CN=[N+]3C=CC(C[42*])=C23)c1 1 \n",
"3 *Nc1ncnn2ccc([25*])c12 6 \n",
"4 [22*]Nc1cc(C)n[nH]1 10 \n",
"\n",
" connections connections_name \n",
"0 [FP, SE] [AP=FP, AP=SE] \n",
"1 [SE, GA] [AP=SE, AP=GA] \n",
"2 [FP, FP] [AP=FP, AP=FP] \n",
"3 [GA, FP] [AP=GA, AP=FP] \n",
"4 [SE] [AP=SE] "
"<IPython.core.display.HTML object>"
]
},
"execution_count": 9,
Expand All @@ -427,7 +366,7 @@
}
],
"source": [
"fragment_library[\"AP\"].head()"
"HTML(fragment_library[\"AP\"].head().to_html(notebook=True))"
]
},
{
Expand Down Expand Up @@ -1523,72 +1462,72 @@
"text/html": [
"<style type=\"text/css\">\n",
"</style>\n",
"<table id=\"T_3771a\">\n",
"<table id=\"T_be752\">\n",
" <caption>unwanted substrutcures filters</caption>\n",
" <thead>\n",
" <tr>\n",
" <th class=\"blank level0\" >&nbsp;</th>\n",
" <th id=\"T_3771a_level0_col0\" class=\"col_heading level0 col0\" >pre-filtered</th>\n",
" <th id=\"T_3771a_level0_col1\" class=\"col_heading level0 col1\" >accepted by 2</th>\n",
" <th id=\"T_3771a_level0_col2\" class=\"col_heading level0 col2\" >accepted by 1</th>\n",
" <th id=\"T_3771a_level0_col3\" class=\"col_heading level0 col3\" >accepted by 0</th>\n",
" <th id=\"T_be752_level0_col0\" class=\"col_heading level0 col0\" >pre-filtered</th>\n",
" <th id=\"T_be752_level0_col1\" class=\"col_heading level0 col1\" >accepted by 2</th>\n",
" <th id=\"T_be752_level0_col2\" class=\"col_heading level0 col2\" >accepted by 1</th>\n",
" <th id=\"T_be752_level0_col3\" class=\"col_heading level0 col3\" >accepted by 0</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th id=\"T_3771a_level0_row0\" class=\"row_heading level0 row0\" >AP</th>\n",
" <td id=\"T_3771a_row0_col0\" class=\"data row0 col0\" >1201</td>\n",
" <td id=\"T_3771a_row0_col1\" class=\"data row0 col1\" >942</td>\n",
" <td id=\"T_3771a_row0_col2\" class=\"data row0 col2\" >247</td>\n",
" <td id=\"T_3771a_row0_col3\" class=\"data row0 col3\" >12</td>\n",
" <th id=\"T_be752_level0_row0\" class=\"row_heading level0 row0\" >AP</th>\n",
" <td id=\"T_be752_row0_col0\" class=\"data row0 col0\" >1201</td>\n",
" <td id=\"T_be752_row0_col1\" class=\"data row0 col1\" >942</td>\n",
" <td id=\"T_be752_row0_col2\" class=\"data row0 col2\" >247</td>\n",
" <td id=\"T_be752_row0_col3\" class=\"data row0 col3\" >12</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_3771a_level0_row1\" class=\"row_heading level0 row1\" >FP</th>\n",
" <td id=\"T_3771a_row1_col0\" class=\"data row1 col0\" >1100</td>\n",
" <td id=\"T_3771a_row1_col1\" class=\"data row1 col1\" >895</td>\n",
" <td id=\"T_3771a_row1_col2\" class=\"data row1 col2\" >186</td>\n",
" <td id=\"T_3771a_row1_col3\" class=\"data row1 col3\" >19</td>\n",
" <th id=\"T_be752_level0_row1\" class=\"row_heading level0 row1\" >FP</th>\n",
" <td id=\"T_be752_row1_col0\" class=\"data row1 col0\" >1100</td>\n",
" <td id=\"T_be752_row1_col1\" class=\"data row1 col1\" >895</td>\n",
" <td id=\"T_be752_row1_col2\" class=\"data row1 col2\" >186</td>\n",
" <td id=\"T_be752_row1_col3\" class=\"data row1 col3\" >19</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_3771a_level0_row2\" class=\"row_heading level0 row2\" >SE</th>\n",
" <td id=\"T_3771a_row2_col0\" class=\"data row2 col0\" >743</td>\n",
" <td id=\"T_3771a_row2_col1\" class=\"data row2 col1\" >608</td>\n",
" <td id=\"T_3771a_row2_col2\" class=\"data row2 col2\" >129</td>\n",
" <td id=\"T_3771a_row2_col3\" class=\"data row2 col3\" >6</td>\n",
" <th id=\"T_be752_level0_row2\" class=\"row_heading level0 row2\" >SE</th>\n",
" <td id=\"T_be752_row2_col0\" class=\"data row2 col0\" >743</td>\n",
" <td id=\"T_be752_row2_col1\" class=\"data row2 col1\" >608</td>\n",
" <td id=\"T_be752_row2_col2\" class=\"data row2 col2\" >129</td>\n",
" <td id=\"T_be752_row2_col3\" class=\"data row2 col3\" >6</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_3771a_level0_row3\" class=\"row_heading level0 row3\" >GA</th>\n",
" <td id=\"T_3771a_row3_col0\" class=\"data row3 col0\" >355</td>\n",
" <td id=\"T_3771a_row3_col1\" class=\"data row3 col1\" >235</td>\n",
" <td id=\"T_3771a_row3_col2\" class=\"data row3 col2\" >113</td>\n",
" <td id=\"T_3771a_row3_col3\" class=\"data row3 col3\" >7</td>\n",
" <th id=\"T_be752_level0_row3\" class=\"row_heading level0 row3\" >GA</th>\n",
" <td id=\"T_be752_row3_col0\" class=\"data row3 col0\" >355</td>\n",
" <td id=\"T_be752_row3_col1\" class=\"data row3 col1\" >235</td>\n",
" <td id=\"T_be752_row3_col2\" class=\"data row3 col2\" >113</td>\n",
" <td id=\"T_be752_row3_col3\" class=\"data row3 col3\" >7</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_3771a_level0_row4\" class=\"row_heading level0 row4\" >B1</th>\n",
" <td id=\"T_3771a_row4_col0\" class=\"data row4 col0\" >47</td>\n",
" <td id=\"T_3771a_row4_col1\" class=\"data row4 col1\" >34</td>\n",
" <td id=\"T_3771a_row4_col2\" class=\"data row4 col2\" >13</td>\n",
" <td id=\"T_3771a_row4_col3\" class=\"data row4 col3\" >0</td>\n",
" <th id=\"T_be752_level0_row4\" class=\"row_heading level0 row4\" >B1</th>\n",
" <td id=\"T_be752_row4_col0\" class=\"data row4 col0\" >47</td>\n",
" <td id=\"T_be752_row4_col1\" class=\"data row4 col1\" >34</td>\n",
" <td id=\"T_be752_row4_col2\" class=\"data row4 col2\" >13</td>\n",
" <td id=\"T_be752_row4_col3\" class=\"data row4 col3\" >0</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_3771a_level0_row5\" class=\"row_heading level0 row5\" >B2</th>\n",
" <td id=\"T_3771a_row5_col0\" class=\"data row5 col0\" >59</td>\n",
" <td id=\"T_3771a_row5_col1\" class=\"data row5 col1\" >53</td>\n",
" <td id=\"T_3771a_row5_col2\" class=\"data row5 col2\" >6</td>\n",
" <td id=\"T_3771a_row5_col3\" class=\"data row5 col3\" >0</td>\n",
" <th id=\"T_be752_level0_row5\" class=\"row_heading level0 row5\" >B2</th>\n",
" <td id=\"T_be752_row5_col0\" class=\"data row5 col0\" >59</td>\n",
" <td id=\"T_be752_row5_col1\" class=\"data row5 col1\" >53</td>\n",
" <td id=\"T_be752_row5_col2\" class=\"data row5 col2\" >6</td>\n",
" <td id=\"T_be752_row5_col3\" class=\"data row5 col3\" >0</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_3771a_level0_row6\" class=\"row_heading level0 row6\" >Total</th>\n",
" <td id=\"T_3771a_row6_col0\" class=\"data row6 col0\" >3505</td>\n",
" <td id=\"T_3771a_row6_col1\" class=\"data row6 col1\" >2767</td>\n",
" <td id=\"T_3771a_row6_col2\" class=\"data row6 col2\" >694</td>\n",
" <td id=\"T_3771a_row6_col3\" class=\"data row6 col3\" >44</td>\n",
" <th id=\"T_be752_level0_row6\" class=\"row_heading level0 row6\" >Total</th>\n",
" <td id=\"T_be752_row6_col0\" class=\"data row6 col0\" >3505</td>\n",
" <td id=\"T_be752_row6_col1\" class=\"data row6 col1\" >2767</td>\n",
" <td id=\"T_be752_row6_col2\" class=\"data row6 col2\" >694</td>\n",
" <td id=\"T_be752_row6_col3\" class=\"data row6 col3\" >44</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n"
],
"text/plain": [
"<pandas.io.formats.style.Styler at 0x7f61869f14c0>"
"<pandas.io.formats.style.Styler at 0x7f3b193ff160>"
]
},
"execution_count": 22,
Expand Down
Loading
Loading