公开(公告)号：WO0063421A9

公开(公告)日：2002-06-06

申请号：PCT/US0010484

申请日：2000-04-19

Applicant: BIOS GROUP LP ,  KAUFFMAN STUART A ,  LEVITAN BENNETT S

Inventor： KAUFFMAN STUART A ,  LEVITAN BENNETT S

IPC: C07B61/00 ,  C40B30/02 ,  G01N33/68 ,  G06F19/00 ,  G06F19/16 ,  G06F19/24 ,  C12Q1/00 ,  C07H21/02 ,  C12P19/24 ,  C12P21/06 ,  C12Q1/68 ,  G01N33/48 ,  G01N33/50

CPC classification number: G06F19/16 ,  C40B30/02 ,  C40B50/02 ,  G01N33/6803 ,  G01N2500/00 ,  G06F19/24 ,  G06F19/704

Abstract: The present invention is directed to production of a molecule having a predetermined property. In accordance with one embodiment, a library of initial candidate molecules that are at least somewhat dissimilar to a chosen target molecule or "targetshape" is generated. Variants of the initial candidates are generated and screened to identify intermediate candidates from among those variants that are either more or less similar to the targetshape. Data mining techniques such as neural networks are used to extract information about the molecule structures and shapes which lead to the desired activity. Molecular data bases may be screened for candidates matching the preferred shape description or molecules matching the preferred shape description may be synthesized. The process may be iterated by generating variants of the intermediate candidates and screening these variants to identify molecules futher more or less similar to the targetshape.

Abstract translation: 本发明涉及具有预定特性的分子的制备。 根据一个实施方案，产生至少在某种程度上不同于所选择的靶分子或“靶标形状”的初始候选分子的文库。 生成和筛选初始候选人的变体，以从与目标形状大致相似的那些变体中识别中间候选。 使用诸如神经网络的数据挖掘技术来提取关于导致所需活动的分子结构和形状的信息。 可以筛选与优选形状描述匹配的候选物的分子数据库，或者可以合成优选形状描述匹配的分子。 可以通过产生中间候选物的变体并筛选这些变体来鉴定或多或少与靶标相似的分子来迭代该过程。

公开(公告)号：AU4469700A

公开(公告)日：2000-11-02

申请号：AU4469700

申请日：2000-04-19

Applicant: BIOS GROUP LP

Inventor： KAUFFMAN STUART A ,  LEVITAN BENNETT S

IPC: C07B61/00 ,  C40B30/02 ,  G01N33/68 ,  G06F19/00 ,  G06F19/16 ,  G06F19/24 ,  C12Q1/00 ,  C12Q1/68 ,  C12P19/24 ,  C12P21/06 ,  C07H21/02 ,  G01N33/48 ,  G01N33/50

Abstract: The present invention is directed to production of a molecule having a predetermined property. In accordance with one embodiment, a library of initial candidate molecules that are at least somewhat dissimilar to a chosen target molecule or "targetshape" is generated. Variants of the initial candidates are generated and screened to identify intermediate candidates from among those variants that are either more or less similar to the targetshape. Data mining techniques such as neural networks are used to extract information about the molecule structures and shapes which lead to the desired activity. Molecular data bases may be screened for candidates matching the preferred shape description or molecules matching the preferred shape description may be synthesized. The process may be iterated by generating variants of the intermediate candidates and screening these variants to identify molecules futher more or less similar to the targetshape.