bioRxiv · 20 Nov 2026
Modelling Phenotypic Assay Noise for Multivariable Biomarker Discovery using Deep Neural Networks
James J Bannon, Katy L Scott L Scott, Marc Delgado Sanchez, Farnoosh Khodakarami, Robert F Gruener, R. Stephanie Huang, Benjamin Haibe-Kains
Citations by database
Each database indexes a different set of journals, preprints and books, so they are shown side by side rather than blended.
- OpenCitations0
- Crossref0
- Europe PMC0
Citations per year
The current year is still counting.
- 2026 so far0
Abstract
Accurately predicting cancer drug response remains a major challenge in precision oncology. Although some therapies are guided by clinically-approved biomarkers, these markers often yield limited predictive value and are unavailable for many drugs. Artificial Intelligence and Machine Learning approaches trained on large-scale cancer cell line pharmacogenomic screens offer a promising route to more comprehensive response prediction, yet they generally assume that phenotypic readouts are measured without error. This assumption is problematic because viability-based drug response assays are inherently noisy, potentially causing models to learn experimental artefacts rather than biologically meaningful determinants of sensitivity. Here, we show that phenotypic measurement noise is present in four widely used cancer cell line screening datasets and introduce Deep Concordance Index Networks (DeepCINET), a deep learning framework that explicitly accounts for this noise. Across datasets, incorporating this noise-aware ranking strategy improves generalization across experimental conditions and to previously unseen samples. DeepCINET outperforms baseline models in multiple settings, with particularly notable gains in prioritizing the most drug-sensitive cell lines. Together, these results establish phenotypic assay noise as a critical and previously overlooked source of error in drug response modelling and provide a principled framework for noise-aware multivariable biomarker discovery.
What the data shows
- No database records a citation yet, as is usual for a paper this new.
Graph
This paper in the middle, its authors and their most-cited papers below, the papers it cites to the left and the papers citing it to the right. The timeline lays every paper out by year.
Select a node for its details. Drag to pan, scroll to zoom, drag a node to move it.
Start with
Cited by 0 papers
Who cites this paper, from open citation data, with Crossref's record of each; the 100 newest when there are more.
References (0)
What it cites, from open citation data, with Crossref's record of each.