update

test/SIME_chemplot_tSNE.ipynb

@@ -1,5 +1,12 @@
 {
  "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "micromamba create -n qsar -c rdkit -c mordred-descriptor -c conda-forge rdkit numpy mordred scikit-learn pandas matplotlib padelpy fuzzywuzzy optuna hydra-core ipykernel loguru ipython joblib openbabel mopac rdkit jupyter ipykernel chemplot joblib -y"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 1,
@@ -94,7 +101,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 5,
    "metadata": {},
    "outputs": [
     {
@@ -6091,6 +6098,17 @@
       "[15:20:17] Explicit valence for atom # 29 C, 5, is greater than permitted\n",
       "[15:20:17] Explicit valence for atom # 29 C, 5, is greater than permitted\n"
      ]
+    },
+    {
+     "ename": "",
+     "evalue": "",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[1;31m在当前单元格或上一个单元格中执行代码时 Kernel 崩溃。\n",
+      "\u001b[1;31m请查看单元格中的代码，以确定故障的可能原因。\n",
+      "\u001b[1;31m单击<a href='https://aka.ms/vscodeJupyterKernelCrash'>此处</a>了解详细信息。\n",
+      "\u001b[1;31m有关更多详细信息，请查看 Jupyter <a href='command:jupyter.viewOutput'>log</a>。"
+     ]
     }
    ],
    "source": [

test/macrocycles_core.ipynb

@@ -0,0 +1,88 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "{'H': 1, 'F': 1, 'Cl': 1, 'Br': 1, 'I': 1, 'B': 3, 'B+1': 2, 'B-1': 4, 'O': 2, 'O+1': 3, 'O-1': 1, 'N': 3, 'N+1': 4, 'N-1': 2, 'C': 4, 'C+1': 5, 'C-1': 3, 'P': 5, 'P+1': 6, 'P-1': 4, 'S': 6, 'S+1': 7, 'S-1': 5, '?': 8}\n"
+     ]
+    }
+   ],
+   "source": [
+    "import selfies as sf\n",
+    "\n",
+    "# 获取默认的语义约束字典\n",
+    "constraints = sf.get_preset_constraints(\"default\")\n",
+    "print(constraints)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import selfies as sf\n",
+    "new_constraints = sf.get_preset_constraints(\"default\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "sf.set_semantic_constraints(new_constraints)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "smiles_dataset = [\"COC\", \"FCF\", \"O=O\", \"O=Cc1ccccc1\"]\n",
+    "selfies_dataset = list(map(sf.encoder, smiles_dataset))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "alphabet = sf.get_alphabet_from_selfies(selfies_dataset)\n",
+    "alphabet.add(\"[nop]\")\n",
+    "\n",
+    "alphabet = list(sorted(alphabet))\n",
+    "alphabet"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "frage",
+   "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": "3.10.16"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

test/tutorial.ipynb

@@ -0,0 +1,668 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Tutorial"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "colab_type": "text",
+    "id": "tM3wFk1e_COd",
+    "tags": []
+   },
+   "source": [
+    "## The Basics\n",
+    "We begin by importing `selfies`. "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 89
+    },
+    "colab_type": "code",
+    "id": "GH0DQxBN_Fei",
+    "outputId": "56aa043e-df48-4081-f938-49711a166d33"
+   },
+   "outputs": [],
+   "source": [
+    "import selfies as sf"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "First, let's try translating between SMILES and SELFIES - as an example, we will use benzaldehyde. To translate from SMILES to SELFIES, use the `selfies.encoder` function, and to translate from SMILES back to SELFIES, use the `selfies.decoder` function."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "original_smiles = \"O=Cc1ccccc1\"  # benzaldehyde\n",
+    "\n",
+    "try:\n",
+    "    encoded_selfies = sf.encoder(original_smiles)  # SMILES  -> SELFIES\n",
+    "    decoded_smiles = sf.decoder(encoded_selfies)   # SELFIES -> SMILES\n",
+    "except sf.EncoderError as err: \n",
+    "    pass  # sf.encoder error...\n",
+    "except sf.DecoderError as err: \n",
+    "    pass  # sf.decoder error..."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'[O][=C][C][=C][C][=C][C][=C][Ring1][=Branch1]'"
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "encoded_selfies"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'O=CC1=CC=CC=C1'"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "decoded_smiles"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "colab_type": "text",
+    "id": "Ng8PmMiB_RvJ"
+   },
+   "source": [
+    "Note that `original_smiles` and `decoded_smiles` are different strings, but they both represent benzaldehyde. Thus, when comparing the two SMILES strings, string equality should _not_ be used. Insead, use RDKit to check whether the SMILES strings represent the same molecule."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 34
+    },
+    "colab_type": "code",
+    "id": "iAc5FVrP_XV6",
+    "outputId": "b503f896-a2a0-46a6-fc5b-9c474c01ba62"
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "True"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from rdkit import Chem\n",
+    "\n",
+    "Chem.CanonSmiles(original_smiles) == Chem.CanonSmiles(decoded_smiles)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "colab_type": "text",
+    "id": "IKfNr5m6_h4f",
+    "tags": []
+   },
+   "source": [
+    "## Customizing SELFIES\n",
+    "The SELFIES grammar is derived dynamically from a set of semantic constraints, which assign bonding capacities to various atoms. Let's customize the semantic constraints that `selfies` operates on. By default, the following constraints are used:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 200
+    },
+    "colab_type": "code",
+    "id": "Xmce7wvV_t4Y",
+    "outputId": "8b10af2f-486e-4910-8a71-055b59a09746"
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'H': 1,\n",
+       " 'F': 1,\n",
+       " 'Cl': 1,\n",
+       " 'Br': 1,\n",
+       " 'I': 1,\n",
+       " 'O': 2,\n",
+       " 'O+1': 3,\n",
+       " 'O-1': 1,\n",
+       " 'N': 3,\n",
+       " 'N+1': 4,\n",
+       " 'N-1': 2,\n",
+       " 'C': 4,\n",
+       " 'C+1': 5,\n",
+       " 'C-1': 3,\n",
+       " 'P': 5,\n",
+       " 'P+1': 6,\n",
+       " 'P-1': 4,\n",
+       " 'S': 6,\n",
+       " 'S+1': 7,\n",
+       " 'S-1': 5,\n",
+       " '?': 8}"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "sf.get_preset_constraints(\"default\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "These constraints map atoms (they keys) to their bonding capacities (the values). The special `?` key maps to the bonding capacity for all atoms that are not explicitly listed in the constraints. For example, S and Li are constrained to a maximum of 6 and 8 bonds, respectively. Every SELFIES string can be decoded into a molecule that obeys the current constraints."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'[Li]=CCS=CC#S'"
+      ]
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "sf.decoder(\"[Li][=C][C][S][=C][C][#S]\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "colab_type": "text",
+    "id": "KevVGyIEAVlu"
+   },
+   "source": [
+    "But suppose that we instead wanted to constrain S and Li to a maximum of 2 and 1 bond(s), respectively. To do so, we create a new set of constraints, and tell `selfies` to operate on them using `selfies.set_semantic_constraints`."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {
+    "colab": {},
+    "colab_type": "code",
+    "id": "y5EbmzkKATkD"
+   },
+   "outputs": [],
+   "source": [
+    "new_constraints = sf.get_preset_constraints(\"default\")\n",
+    "new_constraints['Li'] = 1\n",
+    "new_constraints['S'] = 2\n",
+    "\n",
+    "sf.set_semantic_constraints(new_constraints)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "To check that the update was succesful, we can use `selfies.get_semantic_constraints`, which returns the semantic constraints that `selfies` is currently operating on."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'H': 1,\n",
+       " 'F': 1,\n",
+       " 'Cl': 1,\n",
+       " 'Br': 1,\n",
+       " 'I': 1,\n",
+       " 'O': 2,\n",
+       " 'O+1': 3,\n",
+       " 'O-1': 1,\n",
+       " 'N': 3,\n",
+       " 'N+1': 4,\n",
+       " 'N-1': 2,\n",
+       " 'C': 4,\n",
+       " 'C+1': 5,\n",
+       " 'C-1': 3,\n",
+       " 'P': 5,\n",
+       " 'P+1': 6,\n",
+       " 'P-1': 4,\n",
+       " 'S': 2,\n",
+       " 'S+1': 7,\n",
+       " 'S-1': 5,\n",
+       " '?': 8,\n",
+       " 'Li': 1}"
+      ]
+     },
+     "execution_count": 9,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "sf.get_semantic_constraints()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "colab_type": "text",
+    "id": "e_djGmr_AvM7"
+   },
+   "source": [
+    "Our previous SELFIES string is now decoded like so. Notice that the specified bonding capacities are met, with every S and Li making only 2 and 1 bonds, respectively."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {
+    "colab": {},
+    "colab_type": "code",
+    "id": "TCzbjZMAAxpo"
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'[Li]CCSCC=S'"
+      ]
+     },
+     "execution_count": 10,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "sf.decoder(\"[Li][=C][C][S][=C][C][#S]\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "colab_type": "text",
+    "id": "Ng1Lr_e6A3cB"
+   },
+   "source": [
+    "Finally, to revert back to the default constraints, simply call: "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {
+    "colab": {},
+    "colab_type": "code",
+    "id": "zwC00Rx5A6eQ"
+   },
+   "outputs": [],
+   "source": [
+    "sf.set_semantic_constraints()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    " Please refer to the API reference for more details and more preset constraints.\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## SELFIES in Practice \n",
+    "\n",
+    "Let's use a simple example to show how `selfies` can be used in practice, as well as highlight some convenient utility functions from the library. We start with a toy dataset of SMILES strings. As before, we can use `selfies.encoder` to convert the dataset into SELFIES form."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "['[C][O][C]',\n",
+       " '[F][C][F]',\n",
+       " '[O][=O]',\n",
+       " '[O][=C][C][=C][C][=C][C][=C][Ring1][=Branch1]']"
+      ]
+     },
+     "execution_count": 12,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "smiles_dataset = [\"COC\", \"FCF\", \"O=O\", \"O=Cc1ccccc1\"]\n",
+    "selfies_dataset = list(map(sf.encoder, smiles_dataset))\n",
+    "\n",
+    "selfies_dataset"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "The function `selfies.len_selfies` computes the symbol length of a SELFIES string. We can use it to find the maximum symbol length of the SELFIES strings in the dataset.      "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "10"
+      ]
+     },
+     "execution_count": 13,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "max_len = max(sf.len_selfies(s) for s in selfies_dataset)\n",
+    "max_len"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "To extract the SELFIES symbols that form the dataset, use `selfies.get_alphabet_from_selfies`. Here, we add `[nop]` to the alphabet, which is a special padding character that `selfies` recognizes."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "['[=Branch1]', '[=C]', '[=O]', '[C]', '[F]', '[O]', '[Ring1]', '[nop]']"
+      ]
+     },
+     "execution_count": 14,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "alphabet = sf.get_alphabet_from_selfies(selfies_dataset)\n",
+    "alphabet.add(\"[nop]\")\n",
+    "\n",
+    "alphabet = list(sorted(alphabet))\n",
+    "alphabet"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Then, create a mapping between the alphabet SELFIES symbols and indices."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'[=Branch1]': 0,\n",
+       " '[=C]': 1,\n",
+       " '[=O]': 2,\n",
+       " '[C]': 3,\n",
+       " '[F]': 4,\n",
+       " '[O]': 5,\n",
+       " '[Ring1]': 6,\n",
+       " '[nop]': 7}"
+      ]
+     },
+     "execution_count": 15,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "vocab_stoi = {symbol: idx for idx, symbol in enumerate(alphabet)}\n",
+    "vocab_itos = {idx: symbol for symbol, idx in vocab_stoi.items()}\n",
+    "\n",
+    "vocab_stoi"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "SELFIES provides some convenience methods to convert between SELFIES strings and label (integer) and one-hot encodings. Using the first entry of the dataset (dimethyl ether) as an example:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "dimethyl_ether = selfies_dataset[0]\n",
+    "label, one_hot = sf.selfies_to_encoding(dimethyl_ether, vocab_stoi, pad_to_len=max_len)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[3, 5, 3, 7, 7, 7, 7, 7, 7, 7]"
+      ]
+     },
+     "execution_count": 17,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "label"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[[0, 0, 0, 1, 0, 0, 0, 0],\n",
+       " [0, 0, 0, 0, 0, 1, 0, 0],\n",
+       " [0, 0, 0, 1, 0, 0, 0, 0],\n",
+       " [0, 0, 0, 0, 0, 0, 0, 1],\n",
+       " [0, 0, 0, 0, 0, 0, 0, 1],\n",
+       " [0, 0, 0, 0, 0, 0, 0, 1],\n",
+       " [0, 0, 0, 0, 0, 0, 0, 1],\n",
+       " [0, 0, 0, 0, 0, 0, 0, 1],\n",
+       " [0, 0, 0, 0, 0, 0, 0, 1],\n",
+       " [0, 0, 0, 0, 0, 0, 0, 1]]"
+      ]
+     },
+     "execution_count": 18,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "one_hot"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'[C][O][C][nop][nop][nop][nop][nop][nop][nop]'"
+      ]
+     },
+     "execution_count": 21,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "dimethyl_ether = sf.encoding_to_selfies(one_hot, vocab_itos, enc_type=\"one_hot\")\n",
+    "dimethyl_ether"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'COC'"
+      ]
+     },
+     "execution_count": 22,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "sf.decoder(dimethyl_ether)  # sf.decoder ignores [nop]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "If different encoding strategies are desired, `selfies.split_selfies` can be used to tokenize a SELFIES string into its individual symbols."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 24,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "['[C]', '[O]', '[C]']"
+      ]
+     },
+     "execution_count": 24,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "list(sf.split_selfies(\"[C][O][C]\"))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Please refer to the API reference for more details and utility functions."
+   ]
+  }
+ ],
+ "metadata": {
+  "colab": {
+   "collapsed_sections": [],
+   "name": "selfies_example.ipynb",
+   "provenance": []
+  },
+  "kernelspec": {
+   "display_name": "Python 3",
+   "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": "3.6.13"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}