Loading examples/notebooks/Explaining_Tox21.ipynb +12 −9 Original line number Diff line number Diff line Loading @@ -28006,8 +28006,7 @@ } ], "source": [ "# We can also see what fragments are missing by investigating the training \n", "# set activated fragments\n", "# We can also see what fragments are missing by investigating the training set \n", "# According to our explanation having one of these fragments would make our molecule more\n", "# likely to be toxic\n", "Chem.MolFromSmiles(list(all_train_fps[381])[0])" Loading @@ -28015,19 +28014,23 @@ }, { "cell_type": "code", "execution_count": 12, "execution_count": 17, "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "RDKit ERROR: [16:34:00] non-ring atom 0 marked aromatic\n" "data": { "image/png": "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\n", "text/plain": [ "<rdkit.Chem.rdchem.Mol at 0x7fe440782d50>" ] }, "execution_count": 17, "metadata": {}, "output_type": "execute_result" } ], "source": [ "Chem.MolFromSmiles(list(all_train_fps[381])[2])" "Chem.MolFromSmiles(list(all_train_fps[381])[1])" ] }, { Loading
examples/notebooks/Explaining_Tox21.ipynb +12 −9 Original line number Diff line number Diff line Loading @@ -28006,8 +28006,7 @@ } ], "source": [ "# We can also see what fragments are missing by investigating the training \n", "# set activated fragments\n", "# We can also see what fragments are missing by investigating the training set \n", "# According to our explanation having one of these fragments would make our molecule more\n", "# likely to be toxic\n", "Chem.MolFromSmiles(list(all_train_fps[381])[0])" Loading @@ -28015,19 +28014,23 @@ }, { "cell_type": "code", "execution_count": 12, "execution_count": 17, "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "RDKit ERROR: [16:34:00] non-ring atom 0 marked aromatic\n" "data": { "image/png": "iVBORw0KGgoAAAANSUhEUgAAAcIAAACWCAIAAADCEh9HAAAABmJLR0QA/wD/AP+gvaeTAAAMjklEQVR4nO3dT1RU5R/H8QuaKWmJQVEGWaCI+W8sFfNPZZ1TKp7TxuPGacmSLcvZzhKXLKeVx+Wk1TkTZVSKCv5DBDX/MEr+DUUEBWPmt3jq/m4zE+p878xzn3vfryXi8JzhzofnmXmezy1Jp9MWACBfpboHAABmI0YBQIQYBQARYhQARIhRABAhRgFAhBgFABFiFABEiFEAECFGAUCEGAUAEWIUAESIUQAQIUYBQIQYBQARYhQARIhRABAhRgFAhBgFABFiFABEiFEAECFGAUCEGAUAEWIUAESIUQAQIUYBQIQYBQARYhQARIhRABAhRgFAhBgFABFiFABEiFEAECFGAUCEGAUAEWIUAESIUQAQIUYBQIQYBQARYhQARIhRABAhRgFAhBgFABFitHhGRkaSyWRvb6/ugcDPent7k8nkyMiI7oEECDFaDKlU6uuvv66vr9+5c+fKlSt37tx59epV3YOC3wwNDX311VerVq368ssva2tr9+7dOzU1pXtQwZBGgXV2doZCIfVs19XVzZkzx7KssrKySCQyNjame3Twg7GxsUgkUlZWZlnWnDlz6urq1PUWCoU6Ozt1j87/iNECunbtWjgcLikpsSxr4cKFsVgslUpdv349+4u6RwqDxePxRYsWqdxsamq6cuWK+uI777xjf/Hy5cu6h+lnxGhBjI2NRaPRuXPnqolna2vr6Oio8xuOHj3a2NiorvJ169YdPnxY11Bhrp6ens2bN6uraM2aNRkTz/Hx8Wg0Om/ePDVFbW1tffDgga6h+hsx6r54PP72229nzA6ypVKpWCxWVVVlWVZJSUk4HL5x40ZxRwpT3b17t6WlZcaMGZZlvfrqq21tbX/99VfO73Suft58801WP4VAjLqpp6dn06ZN/zU7yOnhw4eRSOTFF1+0LOull16KRCKPHj0qwlBhqMnJyba2tldeecWyrBdeeKGlpeX+/ftP/V/Hjh3bsGGDujLXrl3L6sddxKg77ty5Y88OKioqppkd5HTx4sVdu3bZH0Pt37+/cEOFuRKJxLJly9R18tlnn/X19T37/2X1UzjEqJSaHbz88sv27GBkZCS/h+ro6FixYoV6kWzduvXMmTPuDhXmGhgY2L59u7o26uvrDx48mN/jqNXP7NmzWf24iBgVicfjtbW19uzg3Llzwgd88uRJe3t7ZWWlZVkzZ85sbm6+ffu2K0OFoYaHh1tbW2fNmmVZVnl5eTQanZiYED6mc/VTU1MTi8VcGWpgEaN5GhgY2LZtm3x2kNPw8HBLS8vMmTPVK6etre3JkycuPj6MMDU1FYvF1N/U0tLScDh869YtFx+/o6Nj5cqV6hr+5JNPTp8+7eKDBwox+twyMs6V2UFO/f39dlIvXbr022+/LcRPgTf9+OOPRcg45+pHJTWrnzwQo89By4rb+b5BU1PT77//XuifCL2SyWQ4HFa/8erq6iKsuAvxvkGgEKPPKuPzn2KugFz8FAtepvfzH7c+xQogYvTpPLIb6Y8//mhublZ7qt5444329vbn2lMFL0ulUvv376+urla7kXbt2pVMJrWMJJFINDQ05LenKrCI0el4cHdId3e3c4f/L7/8onc8kMvYG//bb7/pHU/26udZdvgHGTGam5f3KquZi/O86dWrV3UPCvkYGhpyntRsb2+fmprSPai/OU+UTH/eFMRoDkacnFPdaHbtXnb7CbzM2Rsya9aslpYWb/aGTN9+AoUY/RfjWuycXXxvvfWW9weMtIEtdjm7+GAjRv+mZgeq2s64VrGurq7169erq3z9+vVdXV26R4TcTpw4sWXLFvWbWr169c8//6x7RM/K2f2oXiCsfmzEaDqd9cfW+7ODbOrEy+uvv27vo75586buQeH/nNV2CxYsMPStRuOWa8UR9Bh1zg5CoZBBs4OcRkdH7dq9uXPnRiKRx48f6x5U0GVX2927d0/3oEQySsePHDmie0SaBTdGn7341jgXLlywN7ouXryY2j2NEonEe++9Z2/DPHv2rO4RucO5+vHaVpbiC2KM5ld8a5xEIrF8+XL1Av700097e3t1jyhYzp8/39TUpJ7/JUuWfPPNN7pH5L7s0vFgrn4CF6OS4lvjqBKAiooKuwTgzp07ugflf/fu3bOPqM+fPz8ajfo7XDxyzE+jAMXo+fPnd+zYYc8ODhw4oHtERfLnn3/64MMNI6il7muvvWYVptrOy3744Qfn6idQpeOBiFFngY2aHQSwwObcuXOff/65usobGhq+++473SPym59++mnVqlXqGf74449PnTqle0TFlr36CUjtns9jNMizg5zi8fi7775rb+26dOmS7hH5gbPajkMQavWjCnnV6sf3peN+jtGM4tsAzg5ympiYsIsn1DFEavfypo7kqvKasrIyL5TXeER/f/8XX3yhXn2+Lx33Z4wWv/jWOENDQ83NzaWlpdY/tXveKcUwgiqIqampsf6pthscHNQ9KM/JWP34tXTcbzHqrLZjdvBUx48f//DDD9VV/sEHH/z666+6R2SG48ePb9y4UT1v77//Ps/bNJyrH7+WjvsnRpkd5Ifn7bkwi8+PKh336/PmkxjNmFVpL741Du/xPRXvKct1d3c7Z/G+KR03PkadswOvFd8aJ/s95SB/4uzEDge3OEvH1erHB6XjBseomh14v/jWOOx/dHLut126dCn7bV2RUToeiUTGx8d1Dyp/psZoRvEtswN3sd82nev0l+/3PxaZb0rHzYvRjNM433//ve4R+VbQzobb6CIopkOHDq1evVq9oj/66KOTJ0/qHtFzMylGORuuRUYXgS+bipwyzobTjFUEppeOmxGjqtpu/vz5ausZs4Pi82tvphM9rXqp1Y+JpeMGxGgQXsBG8HFPK3cN8I4LFy7YPa2m/DHzdIw6i29NeUJ9z2d3DTB9OelXGZMnj7+14tEYdU7vA/XhhinMvcOlE3dU9bLJyUn7gz6Pv5XnuRhldmAQ4+63bvPNVhvfM+KDZW/FqA+2PgTN+Ph4NBpVhyDU7cs9fgjCeb/1srIy7rduBI9vc/RKjDI7MNrQ0JD96/PskVznMUQ1ffbBMcRA8eyhG/0x6rNjYUF27NixDRs2qKt87dq1niqI6e7u3rRpkxrbmjVrfFOKETTePAKuM0Z9WVIQcKlUKhaLVVVV2b/TZDKpd0iqok29uVZRUeHNN9fwXLxWSKQtRv1amYX0v8uz1e3LtdTuqY2u/i4MDjLv1GNqiFF/F7jCNjg4qPFWLvF4vLa21n4fza+3rwg4j5SOFzVGg3A7AWTIuLHg6dOnC/0T+/v7t23bpn5ifX29v2+mhrQHbh1UvBgNyM2tkE3tBa6srLQKXLs3PDxs39q3vLycartA0Xgjy2LEaMatVim+Dabh4WG7dq+8vDwajU5MTLj14KraTiW1qra7ffu2Ww8OgzhXP0UrHS9sjKoTCGp2QPEt0un0wMDA9u3b7RX3wYMH5Y/Z0dGxYsUK9Zhbt249c+aM/DFhruKXjhcqRim+xTQSicSyZcvs4om+vr78HufixYt2tV1dXR3lNbBll467uPrJUJAYzSi+ZXaAbMLaPfWpgiqv0binCh6XUTp+4MCBQvwUl2PUWXzL7ABPlUftXsYO/3A4fOPGjeKMFobKWP243lnsWoxmzw6otsMz6unp2bx5s31Ss7Oz87++8+jRo42NjfZ508OHDxdznDBXQUvHXYjR7Go7ZgfIQzweX7Rokb0l7sqVK85/vX79ut1+snDhQsprkIcClY5LY9Q5O1i3bt2RI0fkY0Jgqdo91WKnavdGR0dzflH3SGEwZ+l4KBSSl47nH6OpVGrPnj1qdlBTU7Nv3z5mB3DF4ODg7t271aVVVVVlvw26e/duLUf94D+pVGrfvn32KdI9e/ZI4qvUyldJSUlFRYWaHfT19dnXPSCk/ip3dXU1NjY+fvx4cnIyFAodOnTIvu4BIfVXeWBgQC10KisrJfFVkk6n8/7P9+/fHx0dra6uzvsRgGmkUqn+/n7LshoaGlSXDeC6a9euzZs3T92/PT+iGAUA8BceAESIUQAQIUYBQIQYBQARYhQARIhRABAhRgFAhBgFABFiFABEiFEAECFGAUCEGAUAEWIUAESIUQAQIUYBQIQYBQARYhQARIhRABAhRgFAhBgFABFiFABEiFEAECFGAUCEGAUAEWIUAESIUQAQIUYBQIQYBQARYhQARIhRABAhRgFAhBgFABFiFABEiFEAECFGAUCEGAUAEWIUAESIUQAQIUYBQIQYBQARYhQARIhRABAhRgFA5H8N0UDoK75ZegAAAABJRU5ErkJggg==\n", "text/plain": [ "<rdkit.Chem.rdchem.Mol at 0x7fe440782d50>" ] }, "execution_count": 17, "metadata": {}, "output_type": "execute_result" } ], "source": [ "Chem.MolFromSmiles(list(all_train_fps[381])[2])" "Chem.MolFromSmiles(list(all_train_fps[381])[1])" ] }, {
