| 查看: 501 | 回复: 3 | |||
| 当前主题已经存档。 | |||
| 当前只显示满足指定条件的回帖，点击这里查看本话题的所有回帖 | |||
cloudsea163金虫 (著名写手)
|
[交流]
【求助】QSAR的计算问题
|
||
|
在QSAR的计算中，描述符计算出来后，我看文献中报道采用启发式算法对描述符进行筛选，请问启发式筛选描述符是如何进行，求各位指点一下 [ Last edited by lei0736 on 2009-11-25 at 14:09 ] |
回复此楼» 猜你喜欢
售SCI一区T0P文章，我:8O.55.1.O.54,科目全,可伽急
已经有9人回复
-
售SCI一区T0P文章，我:8O.55.1.O.5.4,科目齐全,可+急
已经有5人回复
-
售SCI一区T0P文章，我:8.O.55.1.O54,科目全,可伽急
已经有6人回复
-
售SCI一区T0P文章，我:8.O.55.1.O54,科目全,可伽急
已经有5人回复
-
售SCI一区文章，我:8O5.5.1.O5.4,科目全,可伽急
已经有5人回复
-
售SCI一区T0P文章，我:8O.55.1.O.5.4,科目齐全,可+急
已经有7人回复
-
售SCI一区文章，我:8O5.5.1.O5.4,科目全,可伽急
已经有6人回复
-
售SCI一区T0P文章，我:8.O.55.1.O.5.4,科目全,可+急
已经有6人回复
-
售SCI文章，我:8O.5.5.1O.54,科目全,可十急
已经有6人回复
-
售SCI-T0P文章，我:8O.5.5.1.O.54,科目齐全,可+急
已经有5人回复
cloudsea163
金虫 (著名写手)
- 应助: 1 (幼儿园)
- 金币: 22.2
- 散金: 847
- 红花: 2
- 帖子: 1539
- 在线: 129.5小时
- 虫号: 508812
- 注册: 2008-02-22
- 性别: GG
- 专业: 能源化工
4楼2009-06-14 19:02:49
niliu
铁杆木虫 (著名写手)
- 模拟EPI: 2
- 应助: 8 (幼儿园)
- 贵宾: 1
- 金币: 9755.1
- 红花: 10
- 帖子: 1263
- 在线: 467小时
- 虫号: 78849
- 注册: 2005-07-07
- 专业: 理论和计算化学
2楼2009-06-13 18:50:27
niliu
铁杆木虫 (著名写手)
- 模拟EPI: 2
- 应助: 8 (幼儿园)
- 贵宾: 1
- 金币: 9755.1
- 红花: 10
- 帖子: 1263
- 在线: 467小时
- 虫号: 78849
- 注册: 2005-07-07
- 专业: 理论和计算化学
★ ★ ★ ★
xuefei06(金币+2,VIP+0):3Q！ 6-13 18:57
cloudsea163(金币+2,VIP+0): 6-14 19:02
cloudsea163(金币+2):谢谢 2010-02-27 15:22
xuefei06(金币+2,VIP+0):3Q！ 6-13 18:57
cloudsea163(金币+2,VIP+0): 6-14 19:02
cloudsea163(金币+2):谢谢 2010-02-27 15:22
|
CODESSA网站找到的： The heuristic method for descriptor selection proceeds with a pre-selection of descriptors by sequentially eliminating descriptors that do not match any of the following criteria: (i) Fisher F-criteria greater than 1.0; (ii) R2 value less than a value defined at the start; (iii) Student’s t-criterion less than a defined value; (iv) duplicate descriptors having a higher squared intercorrelation coefficient than a predetermined level (retaining the descriptor with higher R2 with reference to the property). The descriptors that remain are then listed in decreasing order of correlation coefficients when used in global search for 2-parameter correlations. Each significant 2-parameter correlation by F-criteria is recursively expanded to an n-parameter correlation till the normalized F-criteria remains greater than the startup value. The best N correlations by R2, as well as by F-criterion, are saved. |
3楼2009-06-13 18:56:31
