Scholarlink

Background <p>Transcriptomic profiling technologies have advanced the analysis of biological and toxicological responses. However, substantial differences in probe design, dynamic range, gene coverage, and preprocessing pipelines across platforms introduce artifacts that limit cross-study integration and hinder the reuse of historical datasets. We aim to develop computational methods for accurate cross-platform translation to maximize the value of legacy resources.</p> Results <p>We present <i>TransPlatformer</i> a deep learning framework for translating gene expression profiles across heterogeneous toxicogenomics platforms. <i>TransPlatformer</i> employs a novel attention-based architecture to map high-dimensional fold-change vectors from legacy microarray technologies to current platforms. Models are trained and evaluated using DrugMatrix, spanning three technological generations. We investigate mixed-tissue, single-tissue, and cross-tissue training paradigms and benchmark performance against multilayer perceptron and matrix-completion baselines. In mixed-tissue training, <i>TransPlatformer</i> achieves a greater than 50% reduction in mean absolute error (0.043 vs. 0.09) and nearly doubles Pearson correlation (<InlineEquation ID="IEq1"> <EquationSource Format="TEX">\(\approx \)</EquationSource> </InlineEquation> 0.71 vs. 0.37) relative to baseline methods. Importantly, <i>TransPlatformer</i> preserves rare but biologically meaningful over- and under-expressed signals, with mean absolute error below 0.22. Single-tissue models yield further improvements for well-represented organs, such as a 10% reduction in liver mean absolute error, while underscoring the need for data augmentation strategies in low-sample tissues.ra</p> Conclusions <p><i>TransPlatformer</i> provides an effective and scalable computational solution for cross-platform transcriptomic translation. By enabling biologically faithful harmonization of gene expression data, the proposed approach facilitates the reuse of legacy toxicogenomics datasets, enhances downstream biomarker discovery, and supports more reproducible predictive modeling in toxicology.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Transplatformer: translating toxicogenomic profiles between generations of platforms

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年1月30日

查看全文
  • Guojing Cong,
  • Robert Patton,
  • Frank Chao,
  • Daniel L. Svoboda,
  • Jeremy N. Erickson,
  • Michele R. Balik-Meisner,
  • Deepak Mav,
  • Dhiral P. Phadke,
  • Elizabeth H. Scholl,
  • Ruchir R. Shah,
  • Scott S. Auerbach

摘要

Background

Transcriptomic profiling technologies have advanced the analysis of biological and toxicological responses. However, substantial differences in probe design, dynamic range, gene coverage, and preprocessing pipelines across platforms introduce artifacts that limit cross-study integration and hinder the reuse of historical datasets. We aim to develop computational methods for accurate cross-platform translation to maximize the value of legacy resources.

Results

We present TransPlatformer a deep learning framework for translating gene expression profiles across heterogeneous toxicogenomics platforms. TransPlatformer employs a novel attention-based architecture to map high-dimensional fold-change vectors from legacy microarray technologies to current platforms. Models are trained and evaluated using DrugMatrix, spanning three technological generations. We investigate mixed-tissue, single-tissue, and cross-tissue training paradigms and benchmark performance against multilayer perceptron and matrix-completion baselines. In mixed-tissue training, TransPlatformer achieves a greater than 50% reduction in mean absolute error (0.043 vs. 0.09) and nearly doubles Pearson correlation ( \(\approx \) 0.71 vs. 0.37) relative to baseline methods. Importantly, TransPlatformer preserves rare but biologically meaningful over- and under-expressed signals, with mean absolute error below 0.22. Single-tissue models yield further improvements for well-represented organs, such as a 10% reduction in liver mean absolute error, while underscoring the need for data augmentation strategies in low-sample tissues.ra

Conclusions

TransPlatformer provides an effective and scalable computational solution for cross-platform transcriptomic translation. By enabling biologically faithful harmonization of gene expression data, the proposed approach facilitates the reuse of legacy toxicogenomics datasets, enhances downstream biomarker discovery, and supports more reproducible predictive modeling in toxicology.