D3EGFR: a webserver for deep learning-guided drug sensitivity prediction and drug response information retrieval of EGFR mutation-driven lung cancer

As key oncogenic drivers in non-small cell lung cancer (NSCLC), various mutations of epidermal growth factor receptor (EGFR) with variable drug sensitivities have been the major obstacle for precision medicine. For the purpose, we built a database, namely D3EGFRdb, with the clinicopathologic characteristics and drug responses of 1,339 patients harboring EGFR mutations via literature mining. Besides, we developed a deep learning-based prediction model, namely D3EGFRAI, for drug sensitivity prediction of new EGFR mutation-driven NSCLC. The D3EGFR contained functions above is freely accessible at https://www.d3pharma.com/D3EGFR/index.php.作为非小细胞肺癌（non-small cell lung cancer, NSCLC）的关键致癌驱动因子，表皮生长因子受体（epidermal growth factor receptor, EGFR）的各类突变具有各异的药物敏感性，这也是当前精准医学面临的主要阻碍。为此，我们通过文献挖掘构建了名为D3EGFRdb的数据库，收录了1339例携带EGFR突变患者的临床病理特征与药物应答数据。此外，我们还开发了一款基于深度学习的预测模型D3EGFRAI，用于新型EGFR突变驱动型非小细胞肺癌的药物敏感性预测。具备上述功能的D3EGFRdb可通过https://www.d3pharma.com/D3EGFR/index.php免费访问。