Training distribution determines the ceiling of drug-blind cancer sensitivity prediction
Precision oncology requires predicting which drugs will suppress a specific tumor from its molecular profile, but drug-blind sensitivity prediction has plateaued despite increasingly complex drug representations. Here we show that this stagnation reflects a metric artifact rather than a representational bottleneck. The standard benchmark, global Pearson r, is dominated by between-drug potency differences that a trivial drug-mean predictor captures without any cell-specific learning. Per-drug Pearson r, which isolates within-drug cell ranking, reveals that no drug encoding improves over cell-only features across four independent datasets. A controlled experiment channeling mechanism-of-action identity as either a drug feature or a training-distribution constraint identifies the cause. Supplying MoA as a feature yields negligible benefit, whereas using it to stratify training raises per-drug r substantially for targeted kinase inhibitors, because pan-cancer co-training suppresses pathway-specific sensitivity signals. Mechanism-stratified training and response matching from pilot observations provide two deployable strategies that together recover the principal sources of predictive gain in drug-blind sensitivity prediction.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Pharmacogenomic Knowledge Graph Augmentation for Graph Neural Network-Based Drug-Drug Interaction Prediction
Graph neural networks (GNNs) applied to drug-drug interaction (DDI) prediction rely exclusively on molecular structure encoded as SMILES-derived graphs. Prior work in this series demonstrated that model performance is bo…
Graph Neural NetworkBlind-Spot Mass: A Good-Turing Framework for Quantifying Deployment Coverage Risk in Machine Learning Systems
Blind-spot mass is a Good-Turing framework for quantifying deployment coverage risk in machine learning. In modern ML systems, operational state distributions are often heavy-tailed, implying that a long tail of valid bu…
Human Activity RecognitionRethinking Expert Trajectory Utilization in LLM Post-training for Mathematical Reasoning
Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL) dominate the post-training landscape for mathematical reasoning, yet differ fundamentally in their reliance on expert trajectories. To understand the optimal w…
Reinforcement LearningMathematical ReasoningLiterary Narrative as Moral Probe : A Cross-System Framework for Evaluating AI Ethical Reasoning and Refusal Behavior
Existing AI moral evaluation frameworks test for the production of correct-sounding ethical responses rather than the presence of genuine moral reasoning capacity. This paper introduces a novel probe methodology using li…
Moral ScenariosAI Scientists Are Only as Good as Their Evidence: A Stratified Ablation of Proprietary Data and Reasoning Skills in Drug-Asset Valuation
AI Scientist agents are often evaluated as if capability were mainly a function of model quality, prompting, or reasoning scaffolds. We test a different hypothesis in drug-asset valuation: for knowledge-intensive scienti…