遗传证据强的药物靶点更易获批，尤其在癌症领域。
Human genetic evidence is associated with drug approval across therapeutic areas: an observational analysis of 26,278 target-disease pairs with temporal validation and feature ablation
- 分析2.6万对靶点-疾病关系，发现有遗传关联的靶点获批率高3.25倍。
- 剔除数据冗余后仍显著，但文献信息干扰了预测模型性能。
- 提供1433个潜在候选对，适合新药研发初期的靶点筛选。
在来自 Open Targets 和 ChEMBL 的 26,278 对靶点-疾病关系中，具有遗传关联的靶点获批率是无关联靶点的 3.25 倍（比值比 OR = 3.25，95% 置信区间 2.79–3.79，p = 1.91e-42）。考虑基因共享导致的非独立性后，靶点层面的 OR 为 2.79（自举法 95% 置信区间 2.22–3.53）；癌症领域的配对层面 OR 6.72 在靶点层面降至 2.71，显示非独立性会夸大特定领域的估计值。2015 年后的审批数据同样呈现显著富集（OR = 3.51，p = 1.72e-8）。六种证据类型消融分析表明，仅靠文献挖掘即可解释大部分分类器表现（AUPRC = 0.099 vs. 0.109 全特征），提示存在时间泄漏。剔除文献后，其余证据仍具高于基线信号（AUPRC = 0.084，为基线的 1.63 倍）。敏感性分析将配对层面的 OR 限定在 3.25 至 4.93 之间。仅依赖遗传证据仅带来 1.0 个百分点的绝对 AUPRC 提升，最佳模型校准性差，实际预测价值有限。研究整理出 1,433 个遗传支持的Ⅰ/Ⅱ期靶点-疾病对，作为假设生成资源。所有结论均为观察性结果。
原文摘要 · Abstract (English)
Genetic evidence is enriched among approved drug targets: in an observational analysis of 26,278 target-disease pairs from Open Targets and ChEMBL, targets with any genetic association had a 3.25-fold higher approval rate than those without (OR = 3.25, 95% CI 2.79-3.79, p = 1.91e-42). A target-level analysis accounting for non-independence of pairs sharing the same gene gave OR = 2.79 (bootstrap 95% CI 2.22-3.53); the oncology pair-level OR of 6.72 attenuates to 2.71 at the target level, illustrating how non-independence inflates area-specific estimates. The enrichment replicated in post-2015 approvals (OR = 3.51, p = 1.72e-8). Feature ablation across six evidence types revealed that literature mining alone accounts for most classifier performance (AUPRC = 0.099 versus 0.109 for all features), consistent with temporal leakage from post-approval publications. Excluding literature, remaining evidence types retain above-baseline signal (AUPRC = 0.084, 1.63x baseline). Sensitivity analyses bracket the pair-level OR between 3.25 and 4.93. Genetic evidence alone yields only a 1.0-percentage-point absolute AUPRC gain and the best model has poor calibration; the classifier has limited practical predictive value. We catalogue 1,433 genetically supported Phase 1/2 pairs as a hypothesis-generating resource. All findings are observational.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。