# Addressing the Cold-Start Problem for Personalized Combination Drug Screening

arXiv: https://arxiv.org/abs/2509.07850 · HTML: https://mlsanity.com/paper/2509.07850/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 40 references that are in the map.
- First posted on arXiv 9 Sep 2025.

## Builds on (most cited first, 9 of 9)

- [Deep Bayesian Active Learning with Image Data](https://mlsanity.com/paper/1703.02910/) (2017)
- [MeLU: Meta-Learned User Preference Estimator for Cold-Start Recommendation](https://mlsanity.com/paper/1908.00413/) (2019)
- [Drug discovery with explainable artificial intelligence](https://mlsanity.com/paper/2007.00523/) (2020)
- [Accelerating high-throughput virtual screening through molecular pool-based active learning](https://mlsanity.com/paper/2012.07127/) (2020)
- [Faster k-Medoids Clustering: Improving the PAM, CLARA, and CLARANS Algorithms](https://mlsanity.com/paper/1810.05691/) (2018)
- [Discrepancy-Based Active Learning for Domain Adaptation](https://mlsanity.com/paper/2103.03757/) (2021)
- [Towards Explainable Anticancer Compound Sensitivity Prediction via Multimodal Attention-based Convolutional Encoders](https://mlsanity.com/paper/1904.11223/) (2019)
- [BanditPAM++: Faster k-medoids Clustering](https://mlsanity.com/paper/2310.18844/) (2023)
- [OneBatchPAM: A Fast and Frugal K-Medoids Algorithm](https://mlsanity.com/paper/2501.19285/) (2025)

## Built on by (most cited first, 1 of 1)

- [ScreenShot: A Foundation Model for Few-Shot Combination Drug Screening](https://mlsanity.com/paper/2608.12219/) (2026)

## Abstract (arXiv)

Personalizing combination therapies in oncology requires navigating an immense space of possible drug and dose combinations, a task that remains largely infeasible through exhaustive experimentation. Recent developments in patient-derived models have enabled high-throughput ex vivo screening, but the number of feasible experiments is limited. Further, a tight therapeutic window makes gathering molecular profiling information (e.g. RNA-seq) impractical as a means of guiding drug response prediction. This leads to a challenging cold-start problem: how do we select the most informative combinations to test early, when no prior information about the patient is available? We propose a strategy that leverages a pretrained deep learning model built on historical drug response data. The model provides both embeddings for drug combinations and dose-level importance scores, enabling a principled selection of initial experiments. We combine clustering of drug embeddings to ensure functional diversity with a dose-weighting mechanism that prioritizes doses based on their historical informativeness. Retrospective simulations on large-scale drug combination datasets show that our method substantially improves initial screening efficiency compared to baselines, offering a viable path for more effective early-phase decision-making in personalized combination drug screens.