Hit Selection Using SSMD-Based Machine Learning Performance Metrics in High-Throughput Screening Assays
Abstract
High-throughput screening (HTS) assays are central to early-stage drug discovery but are often limited by extreme data sparsity, as primary screens typically use only a single replicate per test substance. This sparsity makes conventional machine-learning performance metrics, such as sensitivity, specificity, and area under the receiver operating characteristic curve (AUROC), difficult to estimate empirically because they require adequately sized labeled samples. Here, we introduce a model-based framework that derives these classification metrics from the strictly standardized mean difference (SSMD), a well-established HTS effect-size parameter. Under a Gaussian equal-variance assumption, we derive closed-form relationships linking SSMD to Youden-optimal sensitivity and specificity, and sensitivity at a preset specificity, yielding explicit estimators and exact confidence intervals from the noncentral t-distribution, even under single-replicate designs. Unlike classical statistical power, which approaches 1 as sample size grows regardless of how small the true non-zero difference between group means is, the SSMD-derived sensitivity converges to a finite population value that reflects the true degree of separation between two groups, making it a more meaningful and stable performance measure for hit selection. We demonstrate the utility of this framework in a hepatitis C virus primary siRNA screen comprising approximately 22,000 single-replicate measurements, showing that SSMD, AUROC, and sensitivity-based thresholds yield equivalent and interpretable hit sets. This work bridges classical HTS statistics and machine-learning evaluation theory, providing a statistically principled, reproducible way to estimate classification performance in ultra-low-replication screening workflows.
Versions
Related
- High-throughput variant libraries and machine learning enable robust target-site selection for toehold-switch design in Detectrons
- Improving sport horse selection using machine learning: Early prediction of elite-level show jumping performance
- A Unified Structure-Based Deep-Learning Framework for High-Throughput Screening of Protein-Binding RNAs
- Phenomic selection enables nursery screening for field performance in maize and pea
- ML4SD: Leveraging Machine Learning and High-Throughput Search Algorithms for an Iterative Growth-Coupled Design Innovation
BibTeX
@misc{zhang2026selection,
title = {{Hit Selection Using SSMD-Based Machine Learning Performance Metrics in High-Throughput Screening Assays}},
author = {Xiaohua Douglas Zhang},
howpublished = {arXiv},
year = {2026},
month = aug,
doi = {10.48550/arxiv.2608.07609},
eprint = {2608.07609},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2608.07609},
}
RIS
TY - UNPB
TI - Hit Selection Using SSMD-Based Machine Learning Performance Metrics in High-Throughput Screening Assays
AU - Xiaohua Douglas Zhang
PY - 2026
DA - 2026/08/06
PB - arXiv
DO - 10.48550/arxiv.2608.07609
UR - https://arxiv.org/abs/2608.07609
AB - High-throughput screening (HTS) assays are central to early-stage drug discovery but are often limited by extreme data sparsity, as primary screens typically use only a single replicate per test substance. This sparsity makes conventional machine-learning performance metrics, such as sensitivity, specificity, and area under the receiver operating characteristic curve (AUROC), difficult to estimate empirically because they require adequately sized labeled samples. Here, we introduce a model-based framework that derives these classification metrics from the strictly standardized mean difference (SSMD), a well-established HTS effect-size parameter. Under a Gaussian equal-variance assumption, we derive closed-form relationships linking SSMD to Youden-optimal sensitivity and specificity, and sensitivity at a preset specificity, yielding explicit estimators and exact confidence intervals from the noncentral t-distribution, even under single-replicate designs. Unlike classical statistical power, which approaches 1 as sample size grows regardless of how small the true non-zero difference between group means is, the SSMD-derived sensitivity converges to a finite population value that reflects the true degree of separation between two groups, making it a more meaningful and stable performance measure for hit selection. We demonstrate the utility of this framework in a hepatitis C virus primary siRNA screen comprising approximately 22,000 single-replicate measurements, showing that SSMD, AUROC, and sensitivity-based thresholds yield equivalent and interpretable hit sets. This work bridges classical HTS statistics and machine-learning evaluation theory, providing a statistically principled, reproducible way to estimate classification performance in ultra-low-replication screening workflows.
ER -