{"id":2736,"date":"2025-09-11T12:53:08","date_gmt":"2025-09-11T03:53:08","guid":{"rendered":"https:\/\/www.insilico.jp\/blog\/?p=2736"},"modified":"2025-09-11T12:53:09","modified_gmt":"2025-09-11T03:53:09","slug":"chemprop","status":"publish","type":"post","link":"https:\/\/www.insilico.jp\/blog\/2025\/09\/11\/chemprop\/","title":{"rendered":"Chemprop\u3092\u6d3b\u7528\u3057\u305f\u6a5f\u68b0\u5b66\u7fd2\u306b\u3088\u308b\u5316\u5b66\u7279\u6027\u4e88\u6e2c"},"content":{"rendered":"\n

\u7406\u8ad6\u5275\u85ac\u7814\u7a76\u6240\u306e\u91d1\u5b50\u4fe1\u4eba\u3067\u3059\u3002
\u4eca\u56de\u306f\u5316\u5b66\u7279\u6027\u4e88\u6e2c\u306e\u305f\u3081\u306e\u6a5f\u68b0\u5b66\u7fd2\u30d1\u30c3\u30b1\u30fc\u30b8\u306e\u30aa\u30fc\u30d7\u30f3\u30bd\u30fc\u30b9\u30bd\u30d5\u30c8\u30a6\u30a7\u30a2\u3092\u7d39\u4ecb\u3057\u307e\u3059\u3002<\/p>\n\n\n\n

\u53c2\u8003\u6587\u732e
Chemprop: A Machine Learning Package for Chemical Property Prediction
(Esther HeidKevin P. GreenmanYunsie ChungShih-Cheng LiDavid E. GraffFlorence H. VermeireHaoyang WuWilliam H. Green and Charles J. McGill, Journal of Chemical Information and Modeling<\/em>, 2024<\/strong>, 64, 1<\/em>, 9-17.)
https:\/\/dx.doi.org\/10.1021\/acs.jcim.3c01250<\/a><\/p>\n\n\n\n

\u6a5f\u68b0\u5b66\u7fd2\u3068\u306f\u5b66\u7fd2\u30c7\u30fc\u30bf\u304b\u3089\u305d\u306e\u7279\u5fb4\u3092\u8aad\u307f\u53d6\u308a\u3001\u672a\u77e5\u30c7\u30fc\u30bf\u306e\u4e88\u6e2c\u3092\u884c\u3046\u30b3\u30f3\u30d4\u30e5\u30fc\u30bf\u30a2\u30eb\u30b4\u30ea\u30ba\u30e0\u306e\u4e00\u7a2e\u3067\u3001\u8fd1\u5e74\u306eAI\u30d6\u30fc\u30e0\u306e\u4e00\u7aef\u3092\u62c5\u3063\u3066\u3044\u308b\u6280\u8853\u306b\u306a\u308a\u307e\u3059\u3002\u5316\u5b66\u306b\u304a\u3044\u3066\u306f\u5206\u5b50\u69cb\u9020\u3084\u5316\u5b66\u7684\u6027\u8cea\u3092\u5b66\u7fd2\u30c7\u30fc\u30bf\u3068\u3057\u3066\u3001\u672a\u77e5\u306e\u5316\u5b66\u7269\u8cea\u306e\u7279\u6027\u3092\u4e88\u6e2c\u3059\u308b\u305f\u3081\u306b\u7528\u3044\u3089\u308c\u3066\u3044\u307e\u3059\u3002\u4eca\u56de\u7d39\u4ecb\u3059\u308bChemprop\u306f\u7269\u8cea\u306e\u69cb\u9020\u60c5\u5831\u3068\u305d\u306e\u30d7\u30ed\u30d1\u30c6\u30a3\u3092\u5b66\u7fd2\u3059\u308b\u30d1\u30c3\u30b1\u30fc\u30b8\u3067\u3001\u56de\u5e30\u5206\u6790\u3068\u5206\u985e\u5206\u6790\u306e\u6a5f\u80fd\u304c\u63d0\u4f9b\u3055\u308c\u3066\u3044\u307e\u3059\u3002<\/p>\n\n\n\n

\u52d5\u4f5c\u74b0\u5883
Intel Core i7-1265U
Windows 11 Pro
conda 25.3.1<\/p>\n\n\n\n

Chemprop\u306e\u30a4\u30f3\u30b9\u30c8\u30fc\u30eb<\/h2>\n\n\n\n

Python\u306e\u4eee\u60f3\u74b0\u5883\u3092\u4f5c\u6210\u3057\u3001PyPI\u304b\u3089Chemprop\u3092\u30a4\u30f3\u30b9\u30c8\u30fc\u30eb\u3057\u307e\u3059\u3002
\u4eca\u56de\u306fGPU\u74b0\u5883\u3067\u306f\u306a\u3044\u306e\u3067\u3042\u3089\u304b\u3058\u3081CPU\u306e\u307f\u306ePytorch\u3092\u30a4\u30f3\u30b9\u30c8\u30fc\u30eb\u3057\u3066\u304a\u304d\u307e\u3059\u3002<\/p>\n\n\n\n

$ conda create -n chemprop python=3.12 -y\n$ conda activate chemprop\n$ conda install pytorch cpuonly -c pytorch -y\n$ pip install chemprop<\/code><\/pre>\n\n\n\n
Chemprop\u306b\u3088\u308b\u6eb6\u89e3\u5ea6\u306e\u5b66\u7fd2\u3068\u4e88\u6e2c<\/h2>\n\n\n\n
\u30af\u30a4\u30c3\u30af\u30b9\u30bf\u30fc\u30c8\u304b\u3089\u30b5\u30f3\u30d7\u30eb\u3068\u3057\u3066\u914d\u5e03\u3055\u308c\u3066\u3044\u308b\u6eb6\u89e3\u5ea6\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u3092\u4f7f\u3063\u3066\u5b66\u7fd2\u3068\u4e88\u6e2c\u3092\u884c\u3063\u3066\u307f\u307e\u3057\u3087\u3046\u3002<\/p>\n\n\n\n
$ git clone https:\/\/github.com\/chemprop\/chemprop.git\n$ cd chemprop\n$ chemprop train --data-path tests\/data\/regression.csv --task-type regression --output-dir train_example\n$ chemprop predict --test-path tests\/data\/regression.csv --model-path train_example\/model_0\/best.pt --preds-path train_example\/predictions.csv<\/code><\/pre>\n\n\n\n
\u30e2\u30c7\u30eb\u306e\u5b66\u7fd2\u306f\u6570\u5206\u3067\u7d42\u4e86\u3057\u3001\u5b66\u7fd2\u30c7\u30fc\u30bf\u306ftrain_example\u306b\u4fdd\u5b58\u3055\u308c\u307e\u3059\u3002
\u3053\u3053\u3067\u306f\u5b66\u7fd2\u30c7\u30fc\u30bf\u3068\u540c\u3058\u30c7\u30fc\u30bf\u304b\u3089\u6eb6\u89e3\u5ea6\u306e\u4e88\u6e2c\u3092\u884c\u3063\u3066\u3044\u307e\u3059\u304c\u3001\u304a\u304a\u3088\u305d\u540c\u3058\u5024\u304c\u5f97\u3089\u308c\u307e\u3057\u305f\u3002<\/p>\n\n\n\n
smiles<\/td>logSolubility<\/td>Predicted logSolubility<\/td><\/tr>
OCC3OC(OCC2OC(OC(C#N)c1ccccc1)C(O)C(O)C2O)C(O)C(O)C3O<\/td>-0.77<\/td>-1.1173626<\/td><\/tr>
Cc1occc1C(=O)Nc2ccccc2<\/td>-3.3<\/td>-2.6342313<\/td><\/tr>
CC(C)=CCCC(C)=CC(=O)<\/td>-2.06<\/td>-2.546916<\/td><\/tr>
c1ccc2c(c1)ccc3c2ccc4c5ccccc5ccc43<\/td>-7.87<\/td>-8.481346<\/td><\/tr>
c1ccsc1<\/td>-1.33<\/td>-0.90503526<\/td><\/tr><\/tbody><\/table><\/figure>\n\n\n\n
RMSD\u306f0.7061\u3001R2<\/sup>\u306f0.8855\u3068\u7b97\u51fa\u3055\u308c\u307e\u3057\u305f\u3002\u8fd1\u5e74\u958b\u767a\u3055\u308c\u3066\u3044\u308b\u6eb6\u89e3\u5ea6\u4e88\u6e2c\u30bd\u30d5\u30c8\u30a6\u30a7\u30a2\u203b1<\/sup>\u306b\u306f\u53ca\u3073\u307e\u305b\u3093\u304c\u3001\u6c4e\u7528\u7684\u306a\u6a5f\u68b0\u5b66\u7fd2\u30d7\u30ed\u30b0\u30e9\u30e0\u3068\u3057\u3066\u306f\u975e\u5e38\u306b\u9ad8\u3044\u7cbe\u5ea6\u3067\u3042\u308b\u3068\u8a00\u3048\u307e\u3059\u3002<\/p>\n\n\n\n
Chemprop\u306b\u3088\u308b\u89aa\u6cb9\u6027\u306e\u5b66\u7fd2\u3068\u4e88\u6e2c<\/h2>\n\n\n\n
\u4f8b\u3068\u3057\u3066\u4f4e\u5206\u5b50\u5316\u5408\u7269\u306e\u89aa\u6cb9\u6027\u306e\u5b66\u7fd2\u3068\u4e88\u6e2c\u3092\u884c\u3063\u3066\u307f\u307e\u3057\u3087\u3046\u3002
MoleculeNet\uff08https:\/\/www.moleculenet.org\/<\/a>\uff09\u3067\u516c\u958b\u3055\u308c\u3066\u3044\u308bLipophilicity\u306e\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u3092\u4f7f\u7528\u3057\u307e\u3059\u3002
\u3053\u306e\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u306b\u306f4200\u5206\u5b50\u306e\u6c34-\u30aa\u30af\u30bf\u30ce\u30fc\u30eb\u5206\u914d\u4fc2\u6570\u304c\u8a18\u8f09\u3055\u308c\u3066\u3044\u307e\u3059\u3002\u4eca\u56de\u306f\u3053\u306e\u3046\u3061\u4e0a\u304b\u3089100\u5206\u5b50\u3092\u30c6\u30b9\u30c8\u30c7\u30fc\u30bf\u3068\u3057\u3001\u6b8b\u308a\u306e4100\u5206\u5b50\u3092\u5b66\u7fd2\u30c7\u30fc\u30bf\u3068\u3057\u3066\u4f5c\u6210\u3057\u305f\u30e2\u30c7\u30eb\u304b\u3089\u30c6\u30b9\u30c8\u30c7\u30fc\u30bf\u306e\u6c34-\u30aa\u30af\u30bf\u30ce\u30fc\u30eb\u5206\u914d\u4fc2\u6570\u3092\u4e88\u6e2c\u3055\u305b\u3066\u307f\u307e\u3057\u3087\u3046\u3002<\/p>\n\n\n\n
$ mkdir Lipophilicity\n$ cd Lipophilicity\n$ wget https:\/\/deepchemdata.s3-us-west-1.amazonaws.com\/datasets\/Lipophilicity.cs\nv\n$ awk 'BEGIN{FS=OFS=\",\"} {sub(\/\\r$\/,\"\")} NR==1{print \"smiles\",\"exp\"} NR>1 && NR<=101 {print $3,$2}' Lipophilicity.csv > Lipophilicity_test.csv\n$ awk 'BEGIN{FS=OFS=\",\"} {sub(\/\\r$\/,\"\")} NR==1{print \"smiles\",\"exp\"} NR>=102{print $3,$2}' Lipophilicity.csv > Lipophilicity_learn.csv\n$ mkdir train\n$ chemprop train --data-path Lipophilicity_learn.csv --task-type regression --output-dir train\n$ chemprop predict --test-path Lipophilicity_test.csv --model-path train\/model_0\/best.pt --preds-path Lipophilicity_predictions.csv<\/code><\/pre>\n\n\n\n
smiles<\/td>Lipophilicity<\/td>Predicted Lipophilicity<\/td><\/tr>
Cn1c(CN2CCN(CC2)c3ccc(Cl)cc3)nc4ccccc14<\/td>3.54<\/td>3.338566<\/td><\/tr>
COc1cc(OC)c(cc1NC(=O)CSCC(=O)O)S(=O)(=O)N2C(C)CCc3ccccc23<\/td>-1.18<\/td>-0.7544372<\/td><\/tr>
COC(=O)C@@Hc3ccccc3Cl<\/td>3.69<\/td>3.4061437<\/td><\/tr>
OCC@HCN1C(=O)C(Cc2ccccc12)NC(=O)c3cc4cc(Cl)sc4[nH]3<\/td>3.37<\/td>3.1107576<\/td><\/tr>
Cc1cccc(CC@HC(C)(C)C)C(=O)NCC#N)c1<\/td>3.1<\/td>3.1931968<\/td><\/tr><\/tbody><\/table><\/figure>\n\n\n\n
\u3053\u3061\u3089\u306fRMSD\u306f0.5724\u3001R2<\/sup>\u306f0.8120\u3068\u7b97\u51fa\u3055\u308c\u307e\u3057\u305f\u3002\u30c6\u30b9\u30c8\u30c7\u30fc\u30bf\u306f\u5b66\u7fd2\u30c7\u30fc\u30bf\u306b\u306f\u542b\u307e\u308c\u3066\u3044\u306a\u3044\u306b\u3082\u304b\u304b\u308f\u3089\u305a\u975e\u5e38\u306b\u9ad8\u3044\u7cbe\u5ea6\u3067\u306e\u4e88\u6e2c\u304c\u3067\u304d\u307e\u3057\u305f\u3002<\/p>\n\n\n\n
Chemprop\u306b\u3088\u308bBBB\u900f\u904e\u6027\u306e\u5b66\u7fd2\u3068\u4e88\u6e2c<\/h2>\n\n\n\n
\u3053\u3053\u307e\u3067\u56de\u5e30\u5206\u6790\u3092\u6271\u3044\u307e\u3057\u305f\u304c\u3001\u5206\u985e\u5206\u6790\u306b\u3064\u3044\u3066\u3082\u8a66\u3057\u3066\u307f\u307e\u3057\u3087\u3046\u3002
\u540c\u69d8\u306bMoleculeNet\u3067\u516c\u958b\u3055\u308c\u3066\u3044\u308bBBB\uff08\u8840\u6db2\u8133\u95a2\u9580\uff09\u900f\u904e\u6027\u306e\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u3092\u4f7f\u7528\u3057\u307e\u3059\u3002
\u5148\u307b\u3069\u3068\u540c\u3058\u3088\u3046\u306b\u4e0a\u304b\u3089100\u5206\u5b50\u3092\u30c6\u30b9\u30c8\u30c7\u30fc\u30bf\u3068\u3057\u3001\u6b8b\u308a\u3092\u5b66\u7fd2\u30c7\u30fc\u30bf\u3068\u3057\u3066\u4e88\u6e2c\u3092\u884c\u3063\u3066\u307f\u307e\u3059\u3002
\u5206\u985e\u5206\u6790\u306e\u5834\u5408\u306fclassification<\/code>\u3092\u6307\u5b9a\u3057\u307e\u3059\u3002\u3053\u3053\u3067\u306f\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u306e\u3046\u3061\u30a8\u30e9\u30fc\u306e\u3042\u3063\u305f\u90e8\u5206\u3092\u53d6\u308a\u9664\u3044\u3066\u3044\u307e\u3059\u3002<\/p>\n\n\n\n
$ mkdir BBB\n$ cd BBB\n$ wget https:\/\/deepchemdata.s3-us-west-1.amazonaws.com\/datasets\/BBBP.csv\n$ awk 'BEGIN{FS=OFS=\",\"; skip[61]; skip[63]; skip[96]} {sub(\/\\r$\/,\"\")} NR==1{print \"smiles\",\"p_np\"; next} NR>1 && NR<=101 && !(NR in skip){print $4,$3}' BBBP.csv > BBBP_test.csv\n$ awk 'BEGIN{FS=OFS=\",\"; skip[390]; skip[393]; skip[616]; skip[644]; skip[647]; skip[648]; skip[649]; skip[650]; skip[651]; skip[687]} {sub(\/\\r$\/,\"\")} NR==1{print \"smiles\",\"p_np\"; next} NR>=102 && !(NR in skip){print $4,$3}' BBBP.csv > BBBP_learn.csv\n$ mkdir train\n$ chemprop train --data-path BBBP_learn.csv --task-type classification --output-dir train\n$ chemprop predict --test-path BBBP_test.csv --model-path train\/model_0\/best.pt --preds-path BBBP_predictions.csv<\/code><\/pre>\n\n\n\n
smiles<\/td>p_np<\/td>predicted_p_np<\/td><\/tr>
[Cl].CC(C)NCC(O)COc1cccc2ccccc12<\/td>1<\/td>0.63125145<\/td><\/tr>
C(=O)(OC(C)(C)C)CCCc1ccc(cc1)N(CCCl)CCCl<\/td>1<\/td>0.8915068<\/td><\/tr>
c12c3c(N4CCN(C)CC4)c(F)cc1c(c(C(O)=O)cn2C(C)CO3)=O<\/td>1<\/td>0.17763571<\/td><\/tr>
C1CCN(CC1)Cc1cccc(c1)OCCCNC(=O)C<\/td>1<\/td>0.96214366<\/td><\/tr>
Cc1onc(c2ccccc2Cl)c1C(=O)N[C@H]3[C@H]4SC(C)(C)C@@HC(O)=O<\/td>1<\/td>0.019103616<\/td><\/tr><\/tbody><\/table><\/figure>\n\n\n\n
\u5206\u985e\u5206\u6790\u306e\u5834\u5408\u5165\u529b\u5024\u306f0,1\u306b\u306a\u3063\u3066\u3044\u307e\u3059\u304c\u3001\u51fa\u529b\u5024\u306f\u305d\u306e\u3042\u3044\u3060\u306e\u5024\u3092\u3068\u308a\u307e\u3059\u3002\u3053\u3053\u3067\u306f\u7c21\u6613\u7684\u306b\u56db\u6368\u4e94\u5165\u3057\u3066\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u3068\u306e\u4e00\u81f4\u3092\u8a55\u4fa1\u3059\u308b\u306871%\u306e\u6b63\u7b54\u7387\u3068\u306a\u308a\u307e\u3057\u305f\u3002<\/p>\n\n\n\n
\u304a\u308f\u308a\u306b<\/h2>\n\n\n\n
\u5206\u5b50\u306e\u69cb\u9020\u60c5\u5831\u3068\u305d\u306e\u30d7\u30ed\u30d1\u30c6\u30a3\u3092\u5b66\u7fd2\u3059\u308bChemprop\u3092\u7d39\u4ecb\u3057\u307e\u3057\u305f\u3002\u6628\u4eca\u306eAI\u30d6\u30fc\u30e0\u306e\u8981\u56e0\u3068\u3082\u306a\u3063\u305f\u6a5f\u68b0\u5b66\u7fd2\u3067\u3059\u304c\u3001\u521d\u5b66\u8005\u306b\u3068\u3063\u3066\u306f\u975e\u5e38\u306b\u96e3\u3057\u304f\u6271\u3044\u306b\u304f\u3044\u3082\u306e\u3067\u3057\u305f\u3002\u3053\u3046\u3044\u3063\u305f\u7c21\u4fbf\u306b\u5229\u7528\u3067\u304d\u308b\u30d1\u30c3\u30b1\u30fc\u30b8\u3092\u6d3b\u7528\u3059\u308b\u3053\u3068\u3067\u30c7\u30fc\u30bf\u30b5\u30a4\u30a8\u30f3\u30b9\u3092\u5c02\u9580\u3068\u3057\u306a\u3044\u5316\u5b66\u8005\u306b\u3068\u3063\u3066\u3082\u3088\u308a\u76f4\u63a5\u7684\u306b\u7814\u7a76\u3078\u6d3b\u7528\u3057\u3066\u3044\u304f\u3053\u3068\u304c\u3067\u304d\u308b\u306e\u3067\u306f\u306a\u3044\u304b\u3068\u601d\u3044\u307e\u3059\u3002<\/p>\n\n\n\n
\u203b1 Physics-Based Solubility Prediction for Organic Molecules (Daniel J. Fowles, Benedict J. Connaughton, James W. Carter, John B. O. Mitchell and David S. Palmer Chem. Rev.<\/em> 2025, 125, 15, 7057\u20137098)
https:\/\/doi.org\/10.1021\/acs.chemrev.4c00855<\/a><\/p>\n\n\n\n
\u524d\u56de\u8a18\u4e8b
Direct MaxFlux\u6cd5\u306b\u3088\u308b\u9077\u79fb\u72b6\u614b\u4e88\u6e2c
https:\/\/www.insilico.jp\/blog\/2025\/07\/10\/direct-maxflux\/<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"
\u7406\u8ad6\u5275\u85ac\u7814\u7a76\u6240\u306e\u91d1\u5b50\u4fe1\u4eba\u3067\u3059\u3002\u4eca\u56de\u306f\u5316\u5b66\u7279\u6027\u4e88\u6e2c\u306e\u305f\u3081\u306e\u6a5f\u68b0\u5b66\u7fd2\u30d1\u30c3\u30b1\u30fc\u30b8\u306e\u30aa\u30fc\u30d7\u30f3\u30bd\u30fc\u30b9\u30bd\u30d5\u30c8\u30a6\u30a7\u30a2\u3092\u7d39\u4ecb\u3057\u307e\u3059\u3002 \u53c2\u8003\u6587\u732eChemprop: A Machine Learning Package for Chemic…<\/p>\n","protected":false},"author":7,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[118],"tags":[97],"class_list":["post-2736","post","type-post","status-publish","format-standard","hentry","category-ai-drug-discovery","tag-python"],"yoast_head":"\nChemprop\u3092\u6d3b\u7528\u3057\u305f\u6a5f\u68b0\u5b66\u7fd2\u306b\u3088\u308b\u5316\u5b66\u7279\u6027\u4e88\u6e2c - In Silico \u5275\u85ac<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/www.insilico.jp\/blog\/2025\/09\/11\/chemprop\/\" \/>\n<meta property=\"og:locale\" content=\"ja_JP\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Chemprop\u3092\u6d3b\u7528\u3057\u305f\u6a5f\u68b0\u5b66\u7fd2\u306b\u3088\u308b\u5316\u5b66\u7279\u6027\u4e88\u6e2c - In Silico \u5275\u85ac\" \/>\n<meta property=\"og:description\" content=\"\u7406\u8ad6\u5275\u85ac\u7814\u7a76\u6240\u306e\u91d1\u5b50\u4fe1\u4eba\u3067\u3059\u3002\u4eca\u56de\u306f\u5316\u5b66\u7279\u6027\u4e88\u6e2c\u306e\u305f\u3081\u306e\u6a5f\u68b0\u5b66\u7fd2\u30d1\u30c3\u30b1\u30fc\u30b8\u306e\u30aa\u30fc\u30d7\u30f3\u30bd\u30fc\u30b9\u30bd\u30d5\u30c8\u30a6\u30a7\u30a2\u3092\u7d39\u4ecb\u3057\u307e\u3059\u3002 \u53c2\u8003\u6587\u732eChemprop: A Machine Learning Package for Chemic...\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.insilico.jp\/blog\/2025\/09\/11\/chemprop\/\" \/>\n<meta property=\"og:site_name\" content=\"In Silico \u5275\u85ac\" \/>\n<meta property=\"article:published_time\" content=\"2025-09-11T03:53:08+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2025-09-11T03:53:09+00:00\" \/>\n<meta name=\"author\" content=\"kaneko\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"\u57f7\u7b46\u8005\" \/>\n\t<meta name=\"twitter:data1\" content=\"kaneko\" \/>\n\t<meta name=\"twitter:label2\" content=\"\u63a8\u5b9a\u8aad\u307f\u53d6\u308a\u6642\u9593\" \/>\n\t<meta name=\"twitter:data2\" content=\"12\u5206\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\\\/\\\/www.insilico.jp\\\/blog\\\/2025\\\/09\\\/11\\\/chemprop\\\/#article\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/www.insilico.jp\\\/blog\\\/2025\\\/09\\\/11\\\/chemprop\\\/\"},\"author\":{\"name\":\"kaneko\",\"@id\":\"https:\\\/\\\/www.insilico.jp\\\/blog\\\/#\\\/schema\\\/person\\\/b0ca2eef6dece0def1eda9368533cdac\"},\"headline\":\"Chemprop\u3092\u6d3b\u7528\u3057\u305f\u6a5f\u68b0\u5b66\u7fd2\u306b\u3088\u308b\u5316\u5b66\u7279\u6027\u4e88\u6e2c\",\"datePublished\":\"2025-09-11T03:53:08+00:00\",\"dateModified\":\"2025-09-11T03:53:09+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/www.insilico.jp\\\/blog\\\/2025\\\/09\\\/11\\\/chemprop\\\/\"},\"wordCount\":320,\"keywords\":[\"Python\"],\"articleSection\":[\"AI\u5275\u85ac\u95a2\u9023\"],\"inLanguage\":\"ja\"},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/www.insilico.jp\\\/blog\\\/2025\\\/09\\\/11\\\/chemprop\\\/\",\"url\":\"https:\\\/\\\/www.insilico.jp\\\/blog\\\/2025\\\/09\\\/11\\\/chemprop\\\/\",\"name\":\"Chemprop\u3092\u6d3b\u7528\u3057\u305f\u6a5f\u68b0\u5b66\u7fd2\u306b\u3088\u308b\u5316\u5b66\u7279\u6027\u4e88\u6e2c - In Silico \u5275\u85ac\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/www.insilico.jp\\\/blog\\\/#website\"},\"datePublished\":\"2025-09-11T03:53:08+00:00\",\"dateModified\":\"2025-09-11T03:53:09+00:00\",\"author\":{\"@id\":\"https:\\\/\\\/www.insilico.jp\\\/blog\\\/#\\\/schema\\\/person\\\/b0ca2eef6dece0def1eda9368533cdac\"},\"breadcrumb\":{\"@id\":\"https:\\\/\\\/www.insilico.jp\\\/blog\\\/2025\\\/09\\\/11\\\/chemprop\\\/#breadcrumb\"},\"inLanguage\":\"ja\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/www.insilico.jp\\\/blog\\\/2025\\\/09\\\/11\\\/chemprop\\\/\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/www.insilico.jp\\\/blog\\\/2025\\\/09\\\/11\\\/chemprop\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"\u30db\u30fc\u30e0\",\"item\":\"https:\\\/\\\/www.insilico.jp\\\/blog\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Chemprop\u3092\u6d3b\u7528\u3057\u305f\u6a5f\u68b0\u5b66\u7fd2\u306b\u3088\u308b\u5316\u5b66\u7279\u6027\u4e88\u6e2c\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/www.insilico.jp\\\/blog\\\/#website\",\"url\":\"https:\\\/\\\/www.insilico.jp\\\/blog\\\/\",\"name\":\"In Silico \u5275\u85ac\",\"description\":\"\u3053\u306e\u30d6\u30ed\u30b0\u30b5\u30a4\u30c8\u306f\u3001In silico\u5275\u85ac\u306b\u95a2\u9023\u3059\u308b\u7814\u7a76\u8ad6\u6587\u3084\u30bd\u30d5\u30c8\u30a6\u30a7\u30a2\u30fb\u30c4\u30fc\u30eb\u306e\u5229\u7528\u3084\u30d7\u30ed\u30b0\u30e9\u30df\u30f3\u30b0\u306a\u3069\u306b\u3064\u3044\u3066\u3054\u7d39\u4ecb\u3057\u3066\u3044\u307e\u3059\u3002\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/www.insilico.jp\\\/blog\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"ja\"},{\"@type\":\"Person\",\"@id\":\"https:\\\/\\\/www.insilico.jp\\\/blog\\\/#\\\/schema\\\/person\\\/b0ca2eef6dece0def1eda9368533cdac\",\"name\":\"kaneko\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"ja\",\"@id\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/64295ac39d73574d855361ef8cb37a565cfa90b98aaac50012b6ca5665a37a38?s=96&d=mm&r=g\",\"url\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/64295ac39d73574d855361ef8cb37a565cfa90b98aaac50012b6ca5665a37a38?s=96&d=mm&r=g\",\"contentUrl\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/64295ac39d73574d855361ef8cb37a565cfa90b98aaac50012b6ca5665a37a38?s=96&d=mm&r=g\",\"caption\":\"kaneko\"},\"url\":\"https:\\\/\\\/www.insilico.jp\\\/blog\\\/author\\\/kaneko\\\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Chemprop\u3092\u6d3b\u7528\u3057\u305f\u6a5f\u68b0\u5b66\u7fd2\u306b\u3088\u308b\u5316\u5b66\u7279\u6027\u4e88\u6e2c - In Silico \u5275\u85ac","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/www.insilico.jp\/blog\/2025\/09\/11\/chemprop\/","og_locale":"ja_JP","og_type":"article","og_title":"Chemprop\u3092\u6d3b\u7528\u3057\u305f\u6a5f\u68b0\u5b66\u7fd2\u306b\u3088\u308b\u5316\u5b66\u7279\u6027\u4e88\u6e2c - In Silico \u5275\u85ac","og_description":"\u7406\u8ad6\u5275\u85ac\u7814\u7a76\u6240\u306e\u91d1\u5b50\u4fe1\u4eba\u3067\u3059\u3002\u4eca\u56de\u306f\u5316\u5b66\u7279\u6027\u4e88\u6e2c\u306e\u305f\u3081\u306e\u6a5f\u68b0\u5b66\u7fd2\u30d1\u30c3\u30b1\u30fc\u30b8\u306e\u30aa\u30fc\u30d7\u30f3\u30bd\u30fc\u30b9\u30bd\u30d5\u30c8\u30a6\u30a7\u30a2\u3092\u7d39\u4ecb\u3057\u307e\u3059\u3002 \u53c2\u8003\u6587\u732eChemprop: A Machine Learning Package for Chemic...","og_url":"https:\/\/www.insilico.jp\/blog\/2025\/09\/11\/chemprop\/","og_site_name":"In Silico \u5275\u85ac","article_published_time":"2025-09-11T03:53:08+00:00","article_modified_time":"2025-09-11T03:53:09+00:00","author":"kaneko","twitter_card":"summary_large_image","twitter_misc":{"\u57f7\u7b46\u8005":"kaneko","\u63a8\u5b9a\u8aad\u307f\u53d6\u308a\u6642\u9593":"12\u5206"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/www.insilico.jp\/blog\/2025\/09\/11\/chemprop\/#article","isPartOf":{"@id":"https:\/\/www.insilico.jp\/blog\/2025\/09\/11\/chemprop\/"},"author":{"name":"kaneko","@id":"https:\/\/www.insilico.jp\/blog\/#\/schema\/person\/b0ca2eef6dece0def1eda9368533cdac"},"headline":"Chemprop\u3092\u6d3b\u7528\u3057\u305f\u6a5f\u68b0\u5b66\u7fd2\u306b\u3088\u308b\u5316\u5b66\u7279\u6027\u4e88\u6e2c","datePublished":"2025-09-11T03:53:08+00:00","dateModified":"2025-09-11T03:53:09+00:00","mainEntityOfPage":{"@id":"https:\/\/www.insilico.jp\/blog\/2025\/09\/11\/chemprop\/"},"wordCount":320,"keywords":["Python"],"articleSection":["AI\u5275\u85ac\u95a2\u9023"],"inLanguage":"ja"},{"@type":"WebPage","@id":"https:\/\/www.insilico.jp\/blog\/2025\/09\/11\/chemprop\/","url":"https:\/\/www.insilico.jp\/blog\/2025\/09\/11\/chemprop\/","name":"Chemprop\u3092\u6d3b\u7528\u3057\u305f\u6a5f\u68b0\u5b66\u7fd2\u306b\u3088\u308b\u5316\u5b66\u7279\u6027\u4e88\u6e2c - In Silico \u5275\u85ac","isPartOf":{"@id":"https:\/\/www.insilico.jp\/blog\/#website"},"datePublished":"2025-09-11T03:53:08+00:00","dateModified":"2025-09-11T03:53:09+00:00","author":{"@id":"https:\/\/www.insilico.jp\/blog\/#\/schema\/person\/b0ca2eef6dece0def1eda9368533cdac"},"breadcrumb":{"@id":"https:\/\/www.insilico.jp\/blog\/2025\/09\/11\/chemprop\/#breadcrumb"},"inLanguage":"ja","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.insilico.jp\/blog\/2025\/09\/11\/chemprop\/"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/www.insilico.jp\/blog\/2025\/09\/11\/chemprop\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"\u30db\u30fc\u30e0","item":"https:\/\/www.insilico.jp\/blog\/"},{"@type":"ListItem","position":2,"name":"Chemprop\u3092\u6d3b\u7528\u3057\u305f\u6a5f\u68b0\u5b66\u7fd2\u306b\u3088\u308b\u5316\u5b66\u7279\u6027\u4e88\u6e2c"}]},{"@type":"WebSite","@id":"https:\/\/www.insilico.jp\/blog\/#website","url":"https:\/\/www.insilico.jp\/blog\/","name":"In Silico \u5275\u85ac","description":"\u3053\u306e\u30d6\u30ed\u30b0\u30b5\u30a4\u30c8\u306f\u3001In silico\u5275\u85ac\u306b\u95a2\u9023\u3059\u308b\u7814\u7a76\u8ad6\u6587\u3084\u30bd\u30d5\u30c8\u30a6\u30a7\u30a2\u30fb\u30c4\u30fc\u30eb\u306e\u5229\u7528\u3084\u30d7\u30ed\u30b0\u30e9\u30df\u30f3\u30b0\u306a\u3069\u306b\u3064\u3044\u3066\u3054\u7d39\u4ecb\u3057\u3066\u3044\u307e\u3059\u3002","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/www.insilico.jp\/blog\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"ja"},{"@type":"Person","@id":"https:\/\/www.insilico.jp\/blog\/#\/schema\/person\/b0ca2eef6dece0def1eda9368533cdac","name":"kaneko","image":{"@type":"ImageObject","inLanguage":"ja","@id":"https:\/\/secure.gravatar.com\/avatar\/64295ac39d73574d855361ef8cb37a565cfa90b98aaac50012b6ca5665a37a38?s=96&d=mm&r=g","url":"https:\/\/secure.gravatar.com\/avatar\/64295ac39d73574d855361ef8cb37a565cfa90b98aaac50012b6ca5665a37a38?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/64295ac39d73574d855361ef8cb37a565cfa90b98aaac50012b6ca5665a37a38?s=96&d=mm&r=g","caption":"kaneko"},"url":"https:\/\/www.insilico.jp\/blog\/author\/kaneko\/"}]}},"_links":{"self":[{"href":"https:\/\/www.insilico.jp\/blog\/wp-json\/wp\/v2\/posts\/2736","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.insilico.jp\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.insilico.jp\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.insilico.jp\/blog\/wp-json\/wp\/v2\/users\/7"}],"replies":[{"embeddable":true,"href":"https:\/\/www.insilico.jp\/blog\/wp-json\/wp\/v2\/comments?post=2736"}],"version-history":[{"count":7,"href":"https:\/\/www.insilico.jp\/blog\/wp-json\/wp\/v2\/posts\/2736\/revisions"}],"predecessor-version":[{"id":2774,"href":"https:\/\/www.insilico.jp\/blog\/wp-json\/wp\/v2\/posts\/2736\/revisions\/2774"}],"wp:attachment":[{"href":"https:\/\/www.insilico.jp\/blog\/wp-json\/wp\/v2\/media?parent=2736"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.insilico.jp\/blog\/wp-json\/wp\/v2\/categories?post=2736"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.insilico.jp\/blog\/wp-json\/wp\/v2\/tags?post=2736"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}