Reverse Item Response Theory for Sparsity-Robust Ranking in Fragmented Cancer Drug-Response Matrices

用于碎片化癌症药物反应矩阵中稀疏鲁棒排序的反向项目反应理论

Abstract: We introduce reverse Item Response Theory (IRT) to pharmacogenomic drug-response analysis by treating cancer types as latent “subjects” with resistance ability and drugs as “items” with evasion difficulty. 摘要： 我们将反向项目反应理论（IRT）引入药物基因组学药物反应分析中，将癌症类型视为具有耐药能力的潜在“受试者”，将药物视为具有逃避难度的“项目”。

Applied to 242,036 drug sensitivity measurements from the Genomics of Drug Sensitivity in Cancer (GDSC2) database, the model estimates cancer-type-level in-vitro resistance and drug-level broad activity on a shared latent scale. 该模型应用于来自癌症药物敏感性基因组学（GDSC2）数据库的 242,036 项药物敏感性测量数据，在共享的潜在尺度上估计了癌症类型层面的体外耐药性和药物层面的广泛活性。

Validation across four missingness regimes demonstrates that reverse IRT better recovers the full-data latent ranking than simple averaging, with advantages of Delta-rho = +0.089 to +0.095 at 60% missingness under MCAR, cancer-biased, and drug-biased sparsity. 在四种缺失机制下的验证表明，与简单平均法相比，反向 IRT 能更好地恢复全数据的潜在排序；在 MCAR（完全随机缺失）、癌症偏向和药物偏向的稀疏性条件下，当缺失率为 60% 时，其优势（Delta-rho）达到 +0.089 至 +0.095。

Held-out prediction confirms IRT achieves the best Brier score among five evaluated methods. Bootstrap confidence intervals show 19 of 28 cancer types have stable resistant/sensitive classifications. 留出法预测证实，IRT 在五种评估方法中取得了最佳的 Brier 分数。自助法（Bootstrap）置信区间显示，28 种癌症类型中有 19 种具有稳定的耐药/敏感分类。

Cross-platform PRISM replication shows 82% directional agreement but weak rank-order correlation (rho = 0.25), indicating the contribution is methodological robustness under fragmented evaluation, not a universal clinical resistance leaderboard. 跨平台 PRISM 的重复实验显示出 82% 的方向一致性，但秩相关性较弱（rho = 0.25），这表明该研究的贡献在于碎片化评估下的方法论鲁棒性，而非提供一个通用的临床耐药性排行榜。