藥物-疾病關(guān)系預(yù)測:一種推薦系統(tǒng)模型
發(fā)布時間:2019-02-11 16:07
【摘要】:目的藥物重定位是指發(fā)掘已有藥物新的治療作用,然而具有潛在治療作用的藥物-疾病往往隱藏在數(shù)以百萬計的關(guān)系對中。該研究基于醫(yī)療大數(shù)據(jù)分析,預(yù)測具有潛在治療關(guān)系的藥物-疾病關(guān)系對。方法將社交網(wǎng)絡(luò)中推薦系統(tǒng)模型應(yīng)用于藥物重定位研究,并假設(shè)具有相似化學(xué)結(jié)構(gòu)的藥物可能具有相似的適應(yīng)癥。從開源數(shù)據(jù)庫收集已知藥物-疾病的治療關(guān)系、副作用關(guān)系以及藥物和疾病特征描述符,計算得到藥物-藥物的相似度和疾病-疾病相似度,再構(gòu)建推薦模型將上述信息融合,并預(yù)測具有潛在治療關(guān)系的藥物-疾病,最終得到預(yù)測關(guān)系對的排序列表。結(jié)果列表排名前500的關(guān)系對中,有12.8%得到臨床實驗支持或綜述報道,20%得到模式生物實驗或細(xì)胞實驗支持。結(jié)論相比于已有分類模型和隨機(jī)抽樣結(jié)果,本模型可明顯提高具有潛在治療作用藥物-疾病的富集程度。
[Abstract]:Objective Drug relocalization refers to the discovery of new therapeutic effects of existing drugs. However, drug-disease with potential therapeutic effect is often hidden in millions of relation pairs. Based on the analysis of medical big data, this study predicts drug-disease relationships with potential therapeutic relationships. Methods the model of recommendation system in social network was applied to the study of drug relocalization, and it was assumed that drugs with similar chemical structure might have similar indications. From the open source database, we collect the treatment relation, side effect relation, drug and disease characteristic descriptor of known drug and disease, calculate the similarity between drug and disease, then construct the recommendation model to fuse the above information. The drug-disease with potential therapeutic relationship is predicted, and the ranking list of predictive relationship pairs is obtained. Results among the top 500 relationship pairs, 12. 8% were supported or reviewed in clinical trials, and 20% were supported by model biological or cell experiments. Conclusion compared with the existing classification model and random sampling results, this model can significantly improve the concentration of drug-disease with potential therapeutic effect.
【作者單位】: 合肥工業(yè)大學(xué)計算機(jī)與信息學(xué)院;佛蒙特大學(xué)計算機(jī)系;同濟(jì)大學(xué)生命科學(xué)與技術(shù)學(xué)院;
【基金】:國家自然科學(xué)基金資助項目(No 31100956,61173117) 國家高技術(shù)研究發(fā)展計劃(863計劃)資助項目(No2012AA020405)
【分類號】:TP391.3;R95
[Abstract]:Objective Drug relocalization refers to the discovery of new therapeutic effects of existing drugs. However, drug-disease with potential therapeutic effect is often hidden in millions of relation pairs. Based on the analysis of medical big data, this study predicts drug-disease relationships with potential therapeutic relationships. Methods the model of recommendation system in social network was applied to the study of drug relocalization, and it was assumed that drugs with similar chemical structure might have similar indications. From the open source database, we collect the treatment relation, side effect relation, drug and disease characteristic descriptor of known drug and disease, calculate the similarity between drug and disease, then construct the recommendation model to fuse the above information. The drug-disease with potential therapeutic relationship is predicted, and the ranking list of predictive relationship pairs is obtained. Results among the top 500 relationship pairs, 12. 8% were supported or reviewed in clinical trials, and 20% were supported by model biological or cell experiments. Conclusion compared with the existing classification model and random sampling results, this model can significantly improve the concentration of drug-disease with potential therapeutic effect.
【作者單位】: 合肥工業(yè)大學(xué)計算機(jī)與信息學(xué)院;佛蒙特大學(xué)計算機(jī)系;同濟(jì)大學(xué)生命科學(xué)與技術(shù)學(xué)院;
【基金】:國家自然科學(xué)基金資助項目(No 31100956,61173117) 國家高技術(shù)研究發(fā)展計劃(863計劃)資助項目(No2012AA020405)
【分類號】:TP391.3;R95
【參考文獻(xiàn)】
相關(guān)期刊論文 前1條
1 張永祥;程肖蕊;周文霞;;藥物重定位——網(wǎng)絡(luò)藥理學(xué)的重要應(yīng)用領(lǐng)域[J];中國藥理學(xué)與毒理學(xué)雜志;2012年06期
【共引文獻(xiàn)】
相關(guān)期刊論文 前6條
1 王可鑒;石樂明;賀林;張永祥;楊侖;;中國藥物研發(fā)的新機(jī)遇:基于醫(yī)藥大數(shù)據(jù)的系統(tǒng)性藥物重定位[J];科學(xué)通報;2014年18期
2 劉s,
本文編號:2419888
本文鏈接:http://sikaile.net/yixuelunwen/yiyaoxuelunwen/2419888.html
最近更新
教材專著