Development of NEural network simulator for structure-activity COrrelation of molecules: Neco.
スポンサーリンク
概要
- 論文の詳細を見る
A perceptron type neural network simulator for structure-activity correlation of molecules, <B>Neco</B>, has been developed with two different pre-education methods : back propagation method and reconstruction of weight matrix method.<BR>Since the program was written in C, it is executable on popular Unix workstations. The number of intermediate layered units in intermediate layer and intermediate layer itself can be set arbitrarily by the user.<BR>As an example of application, conformations of norbornene isomers were predicted using <SUP>13</SUP><I>C</I>-NMR data. The predicted conformations are in excellent agreement with experiments.<BR>By reconstructing the weight matrix, it was suggested that <SUP>13</SUP><I>C</I> -NMR data of only two specified carbons in the norbornene skeleton have strong correlation with the conformation (exo and endo) of the main branch. This was verified by the parameter scan method.
- 日本コンピュータ化学会の論文
日本コンピュータ化学会 | 論文
- 計算機シミュレーションを用いたRNA結合タンパク質PumilioのRNA結合様式の研究
- エストロゲン受容体のアミノ酸変異によるエストラジオール結合エネルギーの変化
- 分割法による大規模共役系のケクレ構造の総数とPauling Bond Orderの計算
- SrTiO_3とCaTiO_3のTi-K XANESスペクトルにおける低エネルギーピークの起源
- 分子骨格操作に伴う分子軌道変化の等値面リアルタイム描画システム