{"id":1234,"date":"2024-01-22T16:54:04","date_gmt":"2024-01-22T08:54:04","guid":{"rendered":"https:\/\/www.huanglab.org.cn\/wordpress\/?p=1234"},"modified":"2024-01-26T15:03:21","modified_gmt":"2024-01-26T07:03:21","slug":"from-big-data-to-good-data-%e5%88%a9%e7%94%a8%e6%a8%a1%e6%9d%bf%e5%8c%b9%e9%85%8d%e6%96%b9%e6%b3%95%e6%9e%84%e5%bb%ba%e9%ab%98%e8%b4%a8%e9%87%8f%e7%9a%84%e8%9b%8b%e7%99%bd-%e9%85%8d%e4%bd%93%e5%a4%8d","status":"publish","type":"post","link":"https:\/\/www.huanglab.org.cn\/wordpress\/?p=1234","title":{"rendered":"From Big Data to Good Data: \u5229\u7528\u6a21\u677f\u5339\u914d\u65b9\u6cd5\u6784\u5efa\u9ad8\u8d28\u91cf\u7684\u86cb\u767d-\u914d\u4f53\u590d\u5408\u7269\u7ed3\u6784\u6a21\u578b\u6570\u636e\u96c6BindingNet"},"content":{"rendered":"\n<figure class=\"wp-block-image size-large is-resized\"><a href=\"http:\/\/www.huanglab.org.cn\/wordpress\/wp-content\/uploads\/2024\/01\/lxl24.jpg\"><img loading=\"lazy\" decoding=\"async\" src=\"http:\/\/www.huanglab.org.cn\/wordpress\/wp-content\/uploads\/2024\/01\/lxl24-1024x683.jpg\" alt=\"\" class=\"wp-image-1304\" width=\"463\" height=\"309\" srcset=\"https:\/\/www.huanglab.org.cn\/wordpress\/wp-content\/uploads\/2024\/01\/lxl24-1024x683.jpg 1024w, https:\/\/www.huanglab.org.cn\/wordpress\/wp-content\/uploads\/2024\/01\/lxl24-300x200.jpg 300w, https:\/\/www.huanglab.org.cn\/wordpress\/wp-content\/uploads\/2024\/01\/lxl24-768x512.jpg 768w, https:\/\/www.huanglab.org.cn\/wordpress\/wp-content\/uploads\/2024\/01\/lxl24-1536x1024.jpg 1536w, https:\/\/www.huanglab.org.cn\/wordpress\/wp-content\/uploads\/2024\/01\/lxl24.jpg 1920w\" sizes=\"auto, (max-width: 463px) 100vw, 463px\" \/><\/a><figcaption>\u672c\u6587\u7684\u7b2c\u4e00\u4f5c\u8005\uff0c\u674e\u96ea\u83b2\u535a\u58eb\u751f<\/figcaption><\/figure>\n\n\n\n<figure class=\"wp-block-image size-large is-resized\"><a href=\"http:\/\/www.huanglab.org.cn\/wordpress\/wp-content\/uploads\/2024\/01\/lxl01.png\"><img loading=\"lazy\" decoding=\"async\" src=\"http:\/\/www.huanglab.org.cn\/wordpress\/wp-content\/uploads\/2024\/01\/lxl01-1024x393.png\" alt=\"\" class=\"wp-image-1231\" width=\"791\" height=\"303\" srcset=\"https:\/\/www.huanglab.org.cn\/wordpress\/wp-content\/uploads\/2024\/01\/lxl01-1024x393.png 1024w, https:\/\/www.huanglab.org.cn\/wordpress\/wp-content\/uploads\/2024\/01\/lxl01-300x115.png 300w, https:\/\/www.huanglab.org.cn\/wordpress\/wp-content\/uploads\/2024\/01\/lxl01-768x295.png 768w, https:\/\/www.huanglab.org.cn\/wordpress\/wp-content\/uploads\/2024\/01\/lxl01-1536x590.png 1536w, https:\/\/www.huanglab.org.cn\/wordpress\/wp-content\/uploads\/2024\/01\/lxl01-2048x786.png 2048w\" sizes=\"auto, (max-width: 791px) 100vw, 791px\" \/><\/a><\/figure>\n\n\n\n<p>From Big Data to Good Data: \u5229\u7528\u6a21\u677f\u5339\u914d\u65b9\u6cd5\u6784\u5efa\u9ad8\u8d28\u91cf\u7684\u86cb\u767d-\u914d\u4f53\u590d\u5408\u7269\u7ed3\u6784\u6a21\u578b\u6570\u636e\u96c6BindingNet<\/p>\n\n\n\n<p>\u201cContent without method leads to fantasy; method without content to empty sophistry.\u201d\u2014 Goethe<\/p>\n\n\n\n<p>2024\u5e74\u70ed\u95f9\u975e\u51e1\u7684JPM\u5927\u4f1a\u5df2\u7ecf\u7ed3\u675f\uff0c\u524d\u51e0\u5e74\u9523\u9f13\u55a7\u5929\u7684AI\u5236\u836f\u516c\u53f8\u663e\u5f97\u51b7\u6e05\u4e86\u8bb8\u591a\u3002AI\u52a0\u901f\u65b0\u836f\u53d1\u73b0\u63d0\u9ad8\u65b0\u836f\u7814\u53d1\u6210\u529f\u7387\uff0c\u662f\u5564\u9152\u82b1\u8fd8\u662f\u6ce1\u6cab\uff0c\u6b63\u5728\u7ecf\u5386Hype Cycle\u4f4e \u8c37\u671f\u7684\u884c\u4e1a\u4e2d\u4eba\uff0c\u53ef\u80fd\u5bf9\u8fd9\u4e2a\u95ee\u9898\u4f1a\u6709\u66f4\u6df1\u523b\u7684\u8ba4\u8bc6\u3002\u662fAI\u672c\u8eab\u4e0d\u884c\u5417\uff1f\u4e0d\u662f\u7684\uff0c\u4f17\u6240\u5468\u77e5\uff0cAI\u5728\u56fe\u50cf\u8bc6\u522b\u548c\u751f\u6210\u9886\u57df\u975e\u5e38\u6210\u529f\u3002\u56de\u987e\u5176\u53d1\u5c55\u5386\u7a0b\uff0c\u4f1a\u53d1\u73b02009\u5e74\u662f\u4e00\u4e2a\u7279\u522b\u7684\u5e74\u4efd\uff0c\u8fd9\u4e00\u5e74ImageNet\u6a2a\u7a7a\u51fa\u4e16\uff0c&#8221;ImageNet\u6539\u53d8\u4e86AI\u9886\u57df\u4eba\u4eec\u5bf9\u6570\u636e\u96c6\u7684\u8ba4\u8bc6\uff0c\u4eba\u4eec\u771f\u6b63\u5f00\u59cb\u610f\u8bc6\u5230\u5b83\u5728\u7814\u7a76\u4e2d\u7684\u5730\u4f4d\uff0c\u5c31\u50cf\u7b97\u6cd5\u4e00\u6837\u91cd\u8981&#8221;\uff0c\u674e\u98de\u98de\u6559\u6388\u8bf4\u3002\u5982\u4eca\u5927\u5bb6\u610f\u8bc6\u5230\uff0c\u5728AI\u843d\u5730\u5177\u4f53\u573a\u666f\u65f6\uff0c\u6570\u636e\u53ef\u80fd\u6bd4\u7b97\u6cd5\u66f4\u52a0\u91cd\u8981\u3002<\/p>\n\n\n\n<p>AI\u52a0\u901f\u65b0\u836f\u53d1\u73b0\u7684\u4e00\u4e2a\u57fa\u77f3\u95ee\u9898\u662f\uff0cAI\u80fd\u5426\u51c6\u786e\u9884\u6d4b\u86cb\u767d-\u914d\u4f53\u7ed3\u5408\u4eb2\u548c\u529b\uff1f\u7136\u800c\uff0c\u73b0\u6709\u7684\u86cb\u767d-\u914d\u4f53\u590d\u5408\u7269\u5b9e\u9a8c\u7ed3\u6784\u6570\u91cf\u548c\u7c7b\u578b\u975e\u5e38\u6709\u9650\uff0c\u4e0d\u8db3\u4ee5\u7528\u4e8e\u8bad\u7ec3\u6709\u6cdb\u5316\u80fd\u529b\u7684AI\u6a21\u578b\u3002\u800cunfair datasets\u53c8\u8ba9\u6211\u4eec\u9ad8\u4f30AI\u6a21\u578b\u7684\u9884\u6d4b\u80fd\u529b\uff0c\u4ee5\u81f3\u4e8e\u5728\u524d\u77bb\u6027\u7684\u65b0\u836f\u5f00\u53d1\u5b9e\u8df5\u4e2d\u5931\u53bb\u4f5c\u7528\u3002\u5de5\u6b32\u5584\u5176\u4e8b\uff0c\u5fc5\u5148\u5229\u5176\u5668\u3002Pat Walters\u751a\u81f3\u76f4\u63a5\u547c\u5401\u201cAs a field, we must reach a consensus on appropriate datasets and statistical tests for method comparisons\u201d\u3002\u7c7b\u6bd4ImageNet\uff0cAI\u5236\u836f\u9886\u57df\u9700\u8981\u6784\u5efa\u6570\u91cf\u8db3\u591f\u3001\u6570\u636e\u6e05\u6670\u3001\u7c7b\u578b\u591a\u6837\u5316\u7684\u6570\u636e\u96c6\uff0c\u5bf9\u4e8e\u6b63\u786e\u8bc4\u4f30\u548c\u4f18\u5316\u63d0\u9ad8AI\u6a21\u578b\u5177\u6709\u91cd\u8981\u610f\u4e49\u3002\u4e3a\u6b64\uff0c\u5317\u4eac\u751f\u547d\u79d1\u5b66\u7814\u7a76\u6240\/\u6e05\u534e\u5927\u5b66\u751f\u7269\u533b\u5b66\u4ea4\u53c9\u7814\u7a76\u9662\u7684\u9ec4\u725b\u5b9e\u9a8c\u5ba4\u5229\u7528\u6a21\u677f\u5339\u914d\u65b9\u6cd5\u6784\u5efa\u4e86\u4e00\u4e2a\u5305\u542b69,816\u4e2a\u9ad8\u8d28\u91cf\u86cb\u767d-\u914d\u4f53\u590d\u5408\u7269\u6a21\u578b\u548c\u76f8\u5e94\u7684\u5b9e\u9a8c\u7ed3\u5408\u6d3b\u6027\u6570\u636e\u7684BindingNet\u6570\u636e\u96c6\uff0c\u4f5c\u4e3a\u9886\u57df\u5185\u6700\u5e38\u7528\u6570\u636e\u96c6PDBbind\u7684\u8865\u5145\u3002\u4f5c\u8005\u63a2\u7d22\u4e86\u5229\u7528BindingNet\u6570\u636e\u96c6\u8fdb\u884c\u7ed3\u6784\u6d3b\u6027\u5173\u7cfb\uff08SAR\uff09\u5206\u6790\u7684\u6f5c\u5728\u5e94\u7528\uff0c\u7814\u7a76\u4e86\u57fa\u4e8eBindingNet\u8bad\u7ec3\u7684\u6df1\u5ea6\u5b66\u4e60\u6a21\u578b\u5728\u9884\u6d4b\u86cb\u767d-\u914d\u4f53\u7ed3\u5408\u4eb2\u548c\u529b\u65b9\u9762\u7684\u6027\u80fd\u3002\u53d1\u73b0\u57fa\u4e8eBindingNet\u8bad\u7ec3\u7684\u6df1\u5ea6\u5b66\u4e60\u6a21\u578b\u53ef\u4ee5\u51cf\u8f7b\u7531\u5305\u57cb\u7684\u6eb6\u5242\u53ef\u53ca\u8868\u9762\u79ef\uff08buried SASA\uff09\u5f15\u8d77\u7684\u504f\u89c1\u3002 \u201c\u4e0d\u79ef\u8dec\u6b65\uff0c\u65e0\u4ee5\u81f3\u5343\u91cc\u201d\uff0c\u5982\u4f55\u8fdb\u4e00\u6b65\u5b8c\u5584BindingNet\u6570\u636e\u96c6\uff0c\u6269\u5927\u5176\u8986\u76d6\u7684\u5316\u5b66\u7a7a\u95f4\u548c\u86cb\u767d-\u914d\u4f53\u5bf9\u7684\u79cd\u7c7b\u5c06\u662f\u4e0b\u4e00\u6b65\u5de5\u4f5c\u7684\u91cd\u70b9\u3002\u8fd1\u65e5\uff0c\u8be5\u9879\u7814\u7a76\u5de5\u4f5c\u53d1\u8868\u5728J. Chem. Inf. Model \u7684Machine Learning in Bio-cheminformatics\u4e13\u520a\u4e2d\u30101\u3011\u3002<\/p>\n\n\n\n<p><a><strong>BindingNet<\/strong><\/a><strong>\u7684\u6784\u5efa\u65b9\u5f0f\uff1a<\/strong><\/p>\n\n\n\n<ul class=\"wp-block-list\"><li>\u4ee5PDBbind v2019\u6570\u636e\u96c6\u4e2d\u7684\u5c0f\u5206\u5b50\u914d\u4f53\u4e3a\u6a21\u677f\uff0c\u4eceChEMBL\u6570\u636e\u5e93\u4e2d\u641c\u5bfb\u4e0e\u5176\u540c\u4e00\u9776\u6807\u7684\u7ed3\u6784\u7c7b\u4f3c\u7684\u7cfb\u5217\u6d3b\u6027\u5206\u5b50\uff08\u76f8\u4f3c\u5ea6\u5927\u4e8e70%\uff09\uff0c\u5171\u627e\u52305907\u4e2aPDBbind\u6a21\u677f\u7ed3\u6784\u4f5c\u4e3a\u5019\u9009\u7684\u5339\u914d\u5bf9\u8c61\u3002<\/li><li>\u5229\u7528\u6700\u5927\u516c\u5171\u5b50\u7ed3\u6784\uff08MCS\uff09\u6a21\u677f\u5339\u914d\u7684\u65b9\u5f0f\u6784\u5efa\u521d\u59cb\u7684\u590d\u5408\u7269\u7ed3\u6784\uff0c\u5e76\u901a\u8fc7\u5bf9\u975e\u516c\u5171\u90e8\u5206\u7684\u6784\u8c61\u641c\u7d22\u548c\u914d\u4f53\u5206\u5b50\u7ed3\u5408\u6784\u8c61\u7684MM\/GB-SA\u4f18\u5316\u548c\u6253\u5206\uff0c\u6765\u4fdd\u8bc1\u590d\u5408\u7269\u7ed3\u6784\u6a21\u578b\u7684\u53ef\u9760\u6027\uff0c\u5171\u751f\u6210\u5408\u683c\u7684\u9ad8\u8d28\u91cf\u86cb\u767d-\u914d\u4f53\u590d\u5408\u7269\u7ed3\u6784\u6a21\u578b69,816\u5957\u3002<\/li><\/ul>\n\n\n\n<p><strong>SAR<\/strong><strong>\u5206\u6790\u548c\u6d3b\u6027\u60ac\u5d16\u5206\u5b50\u5bf9\u6570\u636e<\/strong><strong>\uff1a<\/strong><\/p>\n\n\n\n<p>\u5229\u7528\u8fd9\u79cd\u65b9\u5f0f\u6784\u5efa\u7684BindingNet\u5305\u542b\u4e86\u4e30\u5bcc\u7684\u7ed3\u6784\u6d3b\u6027\u5173\u7cfb\uff08SAR\uff09\u4fe1\u606f\uff0c\u5373\u540c\u4e00\u86cb\u767d\u9776\u6807\u4e0e\u4e0d\u540c\u5c0f\u5206\u5b50\u7684\u7ed3\u5408\u6784\u8c61\u548c\u6d3b\u6027\u7684\u53d8\u5316\u3002\u5176\u4e2d\u8fd8\u5305\u542b\u4e86\u8bb8\u591a\u6d3b\u6027\u60ac\u5d16\u5206\u5b50\u5bf9\uff08MMP-cliffs\uff09\uff0c\u5373\u7ed3\u6784\u53d8\u5316\u5fae\u5c0f\u4f46\u6d3b\u6027\u5dee\u5f02\u663e\u8457\u7684\u5206\u5b50\u5bf9\uff0c\u8fd9\u4e9b\u5206\u5b50\u5bf9\u6709\u52a9\u4e8e\u7406\u89e3\u86cb\u767d-\u914d\u4f53\u76f8\u4e92\u4f5c\u7528\u7684\u5173\u952e\u56e0\u7d20\u3002\u4f8b\u5982\uff0c\u901a\u8fc7\u5206\u6790BindingNet\u63d0\u4f9b\u7684CDK2-\u6291\u5236\u5242\u590d\u5408\u7269\u7684\u6a21\u578b\uff0c\u53ef\u4ee5\u5408\u7406\u5730\u89e3\u91ca\u6d3b\u6027\u53d8\u5316\u7684\u5177\u4f53\u539f\u56e0\uff0c\u5982\u5728R2\u4f4d\u70b9\u5f15\u5165F\u539f\u5b50\u4f1a\u589e\u52a0\u5176\u4e0eAsn132\u7fb0\u57fa\u6c27\u4e4b\u95f4\u7684\u9759\u7535\u6392\u65a5\uff0c\u5bfc\u81f4\u6d3b\u6027\u4e0b\u964d\u8fd1100\u500d\u3002\u4e3a\u4e86\u65b9\u4fbf\u7528\u6237\u67e5\u8be2\u3001\u5206\u6790\u548c\u4e0b\u8f7dBindingNet\u6570\u636e\u96c6\uff0c\u4f5c\u8005\u63d0\u4f9b\u4e86\u514d\u8d39\u516c\u5f00\u7684\u7f51\u7ad9<a href=\"http:\/\/bindingnet.huanglab.org.cn\/\">http:\/\/bindingnet.huanglab.org.cn<\/a>\u3002<\/p>\n\n\n\n<figure class=\"wp-block-image size-large is-resized\"><a href=\"http:\/\/www.huanglab.org.cn\/wordpress\/wp-content\/uploads\/2024\/01\/lxl02.png\"><img loading=\"lazy\" decoding=\"async\" src=\"http:\/\/www.huanglab.org.cn\/wordpress\/wp-content\/uploads\/2024\/01\/lxl02-1024x513.png\" alt=\"\" class=\"wp-image-1232\" width=\"725\" height=\"363\" srcset=\"https:\/\/www.huanglab.org.cn\/wordpress\/wp-content\/uploads\/2024\/01\/lxl02-1024x513.png 1024w, https:\/\/www.huanglab.org.cn\/wordpress\/wp-content\/uploads\/2024\/01\/lxl02-300x150.png 300w, https:\/\/www.huanglab.org.cn\/wordpress\/wp-content\/uploads\/2024\/01\/lxl02-768x385.png 768w, https:\/\/www.huanglab.org.cn\/wordpress\/wp-content\/uploads\/2024\/01\/lxl02-1536x770.png 1536w, https:\/\/www.huanglab.org.cn\/wordpress\/wp-content\/uploads\/2024\/01\/lxl02-2048x1027.png 2048w\" sizes=\"auto, (max-width: 725px) 100vw, 725px\" \/><\/a><\/figure>\n\n\n\n<h3 class=\"wp-block-heading\">\u673a\u5668\u5b66\u4e60\u6a21\u578b\u5f00\u53d1\u548c\u8bc4\u4f30\uff1a<\/h3>\n\n\n\n<p>BindingNet\u6570\u636e\u96c6\u53ef\u7528\u4e8e\u5f00\u53d1\u548c\u8bc4\u4f30\u673a\u5668\u5b66\u4e60\u6a21\u578b\uff0c\u9884\u6d4b\u86cb\u767d\u8d28-\u914d\u4f53\u590d\u5408\u7269\u7ed3\u5408\u6d3b\u6027\u3001\u7ed3\u5408\u4f4d\u7f6e\u4ee5\u53ca\u5206\u5b50\u751f\u6210\u7b49\u4efb\u52a1\u3002\u5728\u86cb\u767d-\u914d\u4f53\u76f8\u4e92\u4f5c\u7528\u9884\u6d4b\u65b9\u9762\uff0c PDBbind\u662f\u6700\u5e38\u7528\u7684\u8bad\u7ec3\u96c6\u3002\u4f46\u6709\u7814\u7a76\u6307\u51faPDBbind\u4f5c\u4e3a\u8bad\u7ec3\u96c6\u5b58\u5728\u7684\u4e00\u4e9b\u95ee\u9898\uff0c\u5982\u6570\u636e\u91cf\u4e0d\u8db3\u3001\u8fc7\u4e8e\u7a00\u758f\u7b49\u30102\u3011\u3002\u6b64\u5916\uff0c\u8be5\u7814\u7a76\u5c0f\u7ec4\u8fd8\u66fe\u62a5\u9053\uff0c\u7531PDBbind\u8bad\u7ec3\u7684\u673a\u5668\u5b66\u4e60\u6a21\u578b\u5bf9\u5305\u57cb\u6eb6\u5242\u53ef\u53ca\u8868\u9762\u79ef\uff08buried SASA\uff09\u5b58\u5728\u4e00\u5b9a\u7684\u504f\u89c1\uff0c\u5373buried SASA \u8d8a\u5927\uff0c\u6a21\u578b\u9884\u6d4b\u7684\u86cb\u767d-\u5c0f\u5206\u5b50\u7ed3\u5408\u6d3b\u6027\u8d8a\u597d\u30103\u3011\u3002\u7531\u4e8eBindingNet\u5305\u542b\u5927\u91cf\u7ed3\u6784\u76f8\u4f3c\uff0c\u4f46\u7ed3\u5408\u6d3b\u6027\u5dee\u5f02\u663e\u8457\u7684\u5c0f\u5206\u5b50\uff0c\u4f5c\u8005\u63a8\u6d4b\u57fa\u4e8eBindingNet\u8bad\u7ec3\u7684\u673a\u5668\u5b66\u4e60\u6a21\u578b\u80fd\u51cf\u8f7b\u5148\u524d\u5728PDBbind\u8bad\u7ec3\u7684\u6a21\u578b\u4e2d\u53d1\u73b0\u7684buried SASA\u504f\u89c1\u3002\u56e0\u6b64\u5728PDBbind_hold_out_2019 set\u4e0a\u8fdb\u884c\u6d4b\u8bd5\uff0c\u53d1\u73b0\u57fa\u4e8eBindingNet_v18\u8bad\u7ec3\u7684\u6a21\u578b\u786e\u5b9e\u6bd4\u57fa\u4e8ePDBbind_v18_subset\u8bad\u7ec3\u7684\u6a21\u578b\u8868\u73b0\u5dee\uff0c\u4e14PDBbind_v18_subset\u7684\u590d\u5408\u7269\u6a21\u578b\u9884\u6d4b\u7684\u7ed3\u5408\u6d3b\u6027\u4e0eburied SASA\u76f8\u5173\u6027\u66f4\u597d\uff0cRp\u8fbe\u5230\u4e860.623\u3002\u8fdb\u4e00\u6b65\u7684\u5206\u6790\u53d1\u73b0\u8bad\u7ec3\u96c6PDBbind_v18_subset\u548c\u6d4b\u8bd5\u96c6PDBbind_hold_out_2019\u6570\u636e\u96c6\u4e2d\u7684\u590d\u5408\u7269\u7ed3\u5408\u6d3b\u6027\u4e0eburied SASA\u672c\u8eab\u5c31\u5177\u6709\u4e00\u5b9a\u7684\u76f8\u5173\u6027\uff0c\u800c BindingNet_v18\u6570\u636e\u96c6\u4e2d\u8be5\u76f8\u5173\u6027\u66f4\u5f31\u3002\u4f5c\u8005\u7edf\u8ba1\u4e86PDBbind_subset\u548cBindingNet\u4e2d\u6bcf\u4e2a\u86cb\u767d\u5bb6\u65cf\u5185\u7684Rp(SASA,pAffi)\uff0c\u8bc1\u5b9e\u4e86BindingNet\u6570\u636e\u96c6\u4e2d\u7684Rp(SASA,pAffi)\u660e\u663e\u4f4e\u4e8ePDBbind_subset\u3002<\/p>\n\n\n\n<figure class=\"wp-block-image size-large is-resized\"><a href=\"http:\/\/www.huanglab.org.cn\/wordpress\/wp-content\/uploads\/2024\/01\/lxl03.png\"><img loading=\"lazy\" decoding=\"async\" src=\"http:\/\/www.huanglab.org.cn\/wordpress\/wp-content\/uploads\/2024\/01\/lxl03-1024x555.png\" alt=\"\" class=\"wp-image-1235\" width=\"722\" height=\"392\" srcset=\"https:\/\/www.huanglab.org.cn\/wordpress\/wp-content\/uploads\/2024\/01\/lxl03-1024x555.png 1024w, https:\/\/www.huanglab.org.cn\/wordpress\/wp-content\/uploads\/2024\/01\/lxl03-300x163.png 300w, https:\/\/www.huanglab.org.cn\/wordpress\/wp-content\/uploads\/2024\/01\/lxl03-768x416.png 768w, https:\/\/www.huanglab.org.cn\/wordpress\/wp-content\/uploads\/2024\/01\/lxl03-1536x832.png 1536w, https:\/\/www.huanglab.org.cn\/wordpress\/wp-content\/uploads\/2024\/01\/lxl03-2048x1110.png 2048w\" sizes=\"auto, (max-width: 722px) 100vw, 722px\" \/><\/a><\/figure>\n\n\n\n<h2 class=\"wp-block-heading\">\u603b\u7ed3\u4e0e\u5c55\u671b\uff1a<\/h2>\n\n\n\n<p>\u7efc\u4e0a\u6240\u8ff0\uff0c\u5229\u7528\u914d\u4f53\u6a21\u677f\u5339\u914d\u7684\u65b9\u6cd5\u6269\u5145PDBbind\u6570\u636e\u96c6\uff0c\u662f\u4e2a\u5728\u5b9e\u9a8c\u7ed3\u6784\u6570\u636e\u7a00\u758f\u7684\u60c5\u51b5\u4e0b\u7684\u53ef\u884c\u65b9\u6848\u3002BindingNet\u53ef\u4ee5\u4e3a\u836f\u7269\u5316\u5b66\u5bb6\u5728\u7cfb\u5217\u7c7b\u4f3c\u7269\u7684\u6676\u4f53\u7ed3\u6784\u5c1a\u672a\u786e\u5b9a\u7684\u60c5\u51b5\u4e0b\uff0c\u5728\u539f\u5b50\u6c34\u5e73\u4e0a\u7814\u7a76\u86cb\u767d-\u914d\u4f53\u76f8\u4e92\u4f5c\u7528\u63d0\u4f9b\u6709\u76ca\u7684\u89c1\u89e3\u3002\u4f5c\u8005\u53d1\u73b0\u57fa\u4e8eBindingNet\u8bad\u7ec3\u7684\u673a\u5668\u5b66\u4e60\u6a21\u578b\u53ef\u4ee5\u51cf\u8f7b\u5148\u524d\u5728PDBbind\u4e0a\u53d1\u73b0\u7684buried SASA\u504f\u89c1\uff0c\u8fd9\u5f97\u76ca\u4e8eBindingNet\u89c4\u6a21\u66f4\u5927\u4e14\u5305\u542b\u4e86\u5927\u91cf\u7684buried SASA\u76f8\u4f3c\u4f46\u7ed3\u5408\u6d3b\u6027\u4e0d\u540c\u7684\u590d\u5408\u7269\u7ed3\u6784\u6570\u636e\u3002BindingNet\u6570\u636e\u96c6\u4e5f\u53ef\u7528\u4e8e\u5f00\u53d1\u548c\u8bc4\u4f30\u7ed3\u5408\u4f4d\u7f6e\u9884\u6d4b\u3001\u914d\u4f53\u7ed3\u5408\u81ea\u7531\u80fd\u8ba1\u7b97\u548c\u6d3b\u6027\u60ac\u5d16\u9884\u6d4b\u7b49\u65b9\u6cd5\u3002\u4f5c\u8005\u63d0\u51fa\u8fd8\u9700\u8981\u8fdb\u4e00\u6b65\u52aa\u529b\u6765\u5b8c\u5584BindingNet\u6570\u636e\u96c6\u7684\u6784\u5efa\uff0c\u4ee5\u6269\u5927\u5176\u8986\u76d6\u7684\u5316\u5b66\u7a7a\u95f4\u548c\u86cb\u767d-\u914d\u4f53\u5bf9\u7684\u79cd\u7c7b\u3002\u53ef\u4ee5\u8003\u8651\u6574\u5408\u591a\u79cd\u65b9\u6cd5\uff0c\u5982\u5206\u5b50\u5bf9\u63a5\u548c\u57fa\u4e8e\u673a\u5668\u5b66\u4e60\u7684\u65b9\u6cd5\uff0c\u6765\u9884\u6d4b\u4e0d\u540c\u9776\u6807\u7684\u86cb\u767d-\u914d\u4f53\u590d\u5408\u7269\u7684\u7ed3\u5408\u4f4d\u7f6e\u548c\u589e\u52a0\u5c0f\u5206\u5b50\u591a\u6837\u6027\u3002\u4e3a\u4e86\u6269\u5927\u8986\u76d6\u8303\u56f4\uff0c\u8fd8\u53ef\u4ee5\u8003\u8651\u5305\u62ec\u4e0d\u540c\u7684\u751f\u7269\u6d3b\u6027\u6570\u636e\u5e93\uff0c\u5982BindingDB\u548cBinding MOAD\uff0c\u4ee5\u53caPDBbind\u672a\u6536\u5f55\u7684\u590d\u5408\u7269\u5b9e\u9a8c\u7ed3\u6784\u3002\u5728AI\u5236\u836f\u9886\u57df\u6784\u5efa\u51fa\u884c\u4e1a\u8ba4\u53ef\u548c\u9002\u7528\u7684\u201cImageNet\u201d\uff0cBindingNet\u53ea\u662f\u4e00\u4e2a\u8d77\u70b9\uff0c\u4f46\u5e0c\u671b\u4e5f\u80fd\u6210\u4e3aAI\u5236\u836f\u8fdb\u5165Hype Cycle\u53e6\u4e00\u4e2a\u9636\u6bb5\u7684\u8d77\u70b9\u3002<\/p>\n\n\n\n<p><a><strong>\u53c2\u8003\u6587\u732e<\/strong><\/a><\/p>\n\n\n\n<p>\u30101\u3011Li, X.; Shen, C.; Zhu, H.; Yang, Y.; Wang, Q.; Yang, J.*; Huang, N*. A High-Quality Data Set of Protein\u2013Ligand Binding Interactions Via Comparative Complex Structure Modeling. <a rel=\"noreferrer noopener\" href=\"https:\/\/doi.org\/10.1021\/acs.jcim.3c01170\" target=\"_blank\"><em>J. Chem. Inf. Model.<\/em> 2024. <\/a><\/p>\n\n\n\n<p>\u30102\u3011Yang, J.; Shen, C.; Huang, N*. Predicting or Pretending: Artificial Intelligence for Protein-Ligand Interactions Lack of Sufficiently Large and Unbiased Datasets. <a rel=\"noreferrer noopener\" href=\"https:\/\/doi.org\/10.3389\/fphar.2020.00069\" target=\"_blank\"><em>Front. Pharmacol.<\/em> <strong>2020<\/strong>, <em>11<\/em>, 69. <\/a><\/p>\n\n\n\n<p>\u30103\u3011Zhu, H.; Yang, J.*; Huang, N*. Assessment of the Generalization Abilities of Machine-Learning Scoring Functions for Structure-Based Virtual Screening. <a rel=\"noreferrer noopener\" href=\"https:\/\/doi.org\/10.1021\/acs.jcim.2c01149\" target=\"_blank\"><em>J. Chem. Inf. Model.<\/em> <strong>2022<\/strong>, <em>62<\/em> (22), 5485\u20135502. <\/a><\/p>\n","protected":false},"excerpt":{"rendered":"<p>From Big Data to Good Data: \u5229\u7528\u6a21\u677f\u5339\u914d\u65b9\u6cd5\u6784\u5efa\u9ad8\u8d28\u91cf\u7684\u86cb\u767d-\u914d\u4f53\u590d\u5408\u7269\u7ed3\u6784\u6a21\u578b\u6570\u636e\u96c6BindingNet \u201cContent without method leads to fantasy; method without content to empty sophistry.\u201d\u2014 Goethe 2024\u5e74\u70ed\u95f9\u975e\u51e1\u7684JPM\u5927\u4f1a\u5df2\u7ecf\u7ed3\u675f\uff0c\u524d\u51e0\u5e74\u9523\u9f13\u55a7\u5929\u7684AI\u5236\u836f\u516c\u53f8\u663e\u5f97\u51b7\u6e05\u4e86\u8bb8\u591a\u3002AI\u52a0\u901f\u65b0\u836f\u53d1\u73b0\u63d0\u9ad8\u65b0\u836f\u7814\u53d1\u6210\u529f\u7387\uff0c\u662f\u5564\u9152\u82b1\u8fd8\u662f\u6ce1\u6cab\uff0c\u6b63\u5728\u7ecf\u5386Hype Cycle\u4f4e \u8c37\u671f\u7684\u884c\u4e1a\u4e2d\u4eba\uff0c\u53ef\u80fd\u5bf9\u8fd9\u4e2a\u95ee\u9898\u4f1a\u6709\u66f4\u6df1\u523b\u7684\u8ba4\u8bc6\u3002\u662fAI\u672c\u8eab\u4e0d\u884c\u5417\uff1f\u4e0d\u662f\u7684\uff0c\u4f17\u6240\u5468\u77e5\uff0cAI\u5728\u56fe\u50cf\u8bc6\u522b\u548c\u751f\u6210\u9886\u57df\u975e\u5e38\u6210\u529f\u3002\u56de\u987e\u5176\u53d1\u5c55\u5386\u7a0b\uff0c\u4f1a\u53d1\u73b02009\u5e74\u662f\u4e00\u4e2a\u7279\u522b\u7684\u5e74\u4efd\uff0c\u8fd9\u4e00\u5e74ImageNet\u6a2a\u7a7a\u51fa\u4e16\uff0c&#8221;ImageNet\u6539\u53d8\u4e86AI\u9886\u57df\u4eba\u4eec\u5bf9\u6570\u636e\u96c6\u7684\u8ba4\u8bc6\uff0c\u4eba\u4eec\u771f\u6b63\u5f00\u59cb\u610f\u8bc6\u5230\u5b83\u5728\u7814\u7a76\u4e2d\u7684\u5730\u4f4d\uff0c\u5c31\u50cf\u7b97\u6cd5\u4e00\u6837\u91cd\u8981&#8221;\uff0c\u674e\u98de\u98de\u6559\u6388\u8bf4\u3002\u5982\u4eca\u5927\u5bb6\u610f\u8bc6\u5230\uff0c\u5728AI\u843d\u5730\u5177\u4f53\u573a\u666f\u65f6\uff0c\u6570\u636e\u53ef\u80fd\u6bd4\u7b97\u6cd5\u66f4\u52a0\u91cd\u8981\u3002 AI\u52a0\u901f\u65b0\u836f\u53d1\u73b0\u7684\u4e00\u4e2a\u57fa\u77f3\u95ee\u9898\u662f\uff0cAI\u80fd\u5426\u51c6\u786e\u9884\u6d4b\u86cb\u767d-\u914d\u4f53\u7ed3\u5408\u4eb2\u548c\u529b\uff1f\u7136\u800c\uff0c\u73b0\u6709\u7684\u86cb\u767d-\u914d\u4f53\u590d\u5408\u7269\u5b9e\u9a8c\u7ed3\u6784\u6570\u91cf\u548c\u7c7b\u578b\u975e\u5e38\u6709\u9650\uff0c\u4e0d\u8db3\u4ee5\u7528\u4e8e\u8bad\u7ec3\u6709\u6cdb\u5316\u80fd\u529b\u7684AI\u6a21\u578b\u3002\u800cunfair datasets\u53c8\u8ba9\u6211\u4eec\u9ad8\u4f30AI\u6a21\u578b\u7684\u9884\u6d4b\u80fd\u529b\uff0c\u4ee5\u81f3\u4e8e\u5728\u524d\u77bb\u6027\u7684\u65b0\u836f\u5f00\u53d1\u5b9e\u8df5\u4e2d\u5931\u53bb\u4f5c\u7528\u3002\u5de5\u6b32\u5584\u5176\u4e8b\uff0c\u5fc5\u5148\u5229\u5176\u5668\u3002Pat Walters\u751a\u81f3\u76f4\u63a5\u547c\u5401\u201cAs a field, we must reach a consensus on appropriate datasets and statistical tests for method comparisons\u201d\u3002\u7c7b\u6bd4ImageNet\uff0cAI\u5236\u836f\u9886\u57df\u9700\u8981\u6784\u5efa\u6570\u91cf\u8db3\u591f\u3001\u6570\u636e\u6e05\u6670\u3001\u7c7b\u578b\u591a\u6837\u5316\u7684\u6570\u636e\u96c6\uff0c\u5bf9\u4e8e\u6b63\u786e\u8bc4\u4f30\u548c\u4f18\u5316\u63d0\u9ad8AI\u6a21\u578b\u5177\u6709\u91cd\u8981\u610f\u4e49\u3002\u4e3a\u6b64\uff0c\u5317\u4eac\u751f\u547d\u79d1\u5b66\u7814\u7a76\u6240\/\u6e05\u534e\u5927\u5b66\u751f\u7269\u533b\u5b66\u4ea4\u53c9\u7814\u7a76\u9662\u7684\u9ec4\u725b\u5b9e\u9a8c\u5ba4\u5229\u7528\u6a21\u677f\u5339\u914d\u65b9\u6cd5\u6784\u5efa\u4e86\u4e00\u4e2a\u5305\u542b69,816\u4e2a\u9ad8\u8d28\u91cf\u86cb\u767d-\u914d\u4f53\u590d\u5408\u7269\u6a21\u578b\u548c\u76f8\u5e94\u7684\u5b9e\u9a8c\u7ed3\u5408\u6d3b\u6027\u6570\u636e\u7684BindingNet\u6570\u636e\u96c6\uff0c\u4f5c\u4e3a\u9886\u57df\u5185\u6700\u5e38\u7528\u6570\u636e\u96c6PDBbind\u7684\u8865\u5145\u3002\u4f5c\u8005\u63a2\u7d22\u4e86\u5229\u7528BindingNet\u6570\u636e\u96c6\u8fdb\u884c\u7ed3\u6784\u6d3b\u6027\u5173\u7cfb\uff08SAR\uff09\u5206\u6790\u7684\u6f5c\u5728\u5e94\u7528\uff0c\u7814\u7a76\u4e86\u57fa\u4e8eBindingNet\u8bad\u7ec3\u7684\u6df1\u5ea6\u5b66\u4e60\u6a21\u578b\u5728\u9884\u6d4b\u86cb\u767d-\u914d\u4f53\u7ed3\u5408\u4eb2\u548c\u529b\u65b9\u9762\u7684\u6027\u80fd\u3002\u53d1\u73b0\u57fa\u4e8eBindingNet\u8bad\u7ec3\u7684\u6df1\u5ea6\u5b66\u4e60\u6a21\u578b\u53ef\u4ee5\u51cf\u8f7b\u7531\u5305\u57cb\u7684\u6eb6\u5242\u53ef\u53ca\u8868\u9762\u79ef\uff08buried SASA\uff09\u5f15\u8d77\u7684\u504f\u89c1\u3002 \u201c\u4e0d\u79ef\u8dec\u6b65\uff0c\u65e0\u4ee5\u81f3\u5343\u91cc\u201d\uff0c\u5982\u4f55\u8fdb\u4e00\u6b65\u5b8c\u5584BindingNet\u6570\u636e\u96c6\uff0c\u6269\u5927\u5176\u8986\u76d6\u7684\u5316\u5b66\u7a7a\u95f4\u548c\u86cb\u767d-\u914d\u4f53\u5bf9\u7684\u79cd\u7c7b\u5c06\u662f\u4e0b\u4e00\u6b65\u5de5\u4f5c\u7684\u91cd\u70b9\u3002\u8fd1\u65e5\uff0c\u8be5\u9879\u7814\u7a76\u5de5\u4f5c\u53d1\u8868\u5728J. Chem. Inf. Model \u7684Machine Learning in Bio-cheminformatics\u4e13\u520a\u4e2d\u30101\u3011\u3002 BindingNet\u7684\u6784\u5efa\u65b9\u5f0f\uff1a \u4ee5PDBbind v2019\u6570\u636e\u96c6\u4e2d\u7684\u5c0f\u5206\u5b50\u914d\u4f53\u4e3a\u6a21\u677f\uff0c\u4eceChEMBL\u6570\u636e\u5e93\u4e2d\u641c\u5bfb\u4e0e\u5176\u540c\u4e00\u9776\u6807\u7684\u7ed3\u6784\u7c7b\u4f3c\u7684\u7cfb\u5217\u6d3b\u6027\u5206\u5b50\uff08\u76f8\u4f3c\u5ea6\u5927\u4e8e70%\uff09\uff0c\u5171\u627e\u52305907\u4e2aPDBbind\u6a21\u677f\u7ed3\u6784\u4f5c\u4e3a\u5019\u9009\u7684\u5339\u914d\u5bf9\u8c61\u3002 \u5229\u7528\u6700\u5927\u516c\u5171\u5b50\u7ed3\u6784\uff08MCS\uff09\u6a21\u677f\u5339\u914d\u7684\u65b9\u5f0f\u6784\u5efa\u521d\u59cb\u7684\u590d\u5408\u7269\u7ed3\u6784\uff0c\u5e76\u901a\u8fc7\u5bf9\u975e\u516c\u5171\u90e8\u5206\u7684\u6784\u8c61\u641c\u7d22\u548c\u914d\u4f53\u5206\u5b50\u7ed3\u5408\u6784\u8c61\u7684MM\/GB-SA\u4f18\u5316\u548c\u6253\u5206\uff0c\u6765\u4fdd\u8bc1\u590d\u5408\u7269\u7ed3\u6784\u6a21\u578b\u7684\u53ef\u9760\u6027\uff0c\u5171\u751f\u6210\u5408\u683c\u7684\u9ad8\u8d28\u91cf\u86cb\u767d-\u914d\u4f53\u590d\u5408\u7269\u7ed3\u6784\u6a21\u578b69,816\u5957\u3002 [&hellip;]<\/p>\n","protected":false},"author":2,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"ngg_post_thumbnail":0,"footnotes":""},"categories":[10],"tags":[],"class_list":["post-1234","post","type-post","status-publish","format-standard","hentry","category-news"],"_links":{"self":[{"href":"https:\/\/www.huanglab.org.cn\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/1234","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.huanglab.org.cn\/wordpress\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.huanglab.org.cn\/wordpress\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.huanglab.org.cn\/wordpress\/index.php?rest_route=\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.huanglab.org.cn\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=1234"}],"version-history":[{"count":6,"href":"https:\/\/www.huanglab.org.cn\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/1234\/revisions"}],"predecessor-version":[{"id":1307,"href":"https:\/\/www.huanglab.org.cn\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/1234\/revisions\/1307"}],"wp:attachment":[{"href":"https:\/\/www.huanglab.org.cn\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=1234"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.huanglab.org.cn\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=1234"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.huanglab.org.cn\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=1234"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}