GP-DHT: A dual-head transformer with supervised contrastive learning for shared-gene pretraining and single-cell GRN prediction

Shuai Yan, Qingzhi Yu, Wenfeng Dai, Xiang Cheng · 2026

Read GP-DHT: A dual-head transformer with supervised contrastive learning for shared-gene pretraining and single-cell GRN prediction by Shuai Yan, Qingzhi Yu, Wenfeng Dai, Xiang Cheng (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/plos-pone-0359164.txt.

Description

Shuai Yan, Qingzhi Yu, Wenfeng Dai, and Xiang Cheng published this research article in PLOS ONE in 2026. It presents a dual-head transformer model, called GP-DHT, for single-cell gene regulatory network prediction, mapping which genes switch others on and off in individual cells. Pretraining uses shared genes and supervised contrastive learning.

Gene regulatory networks explain how the same DNA produces many cell types. Predicting them from single-cell data is a central problem in genomics, and pretraining on shared genes aims to make the model work across datasets. Computational biologists building cell atlases are the readers who would test this model's predictions.

Catalog record

CREATORShuai Yan, Qingzhi Yu, Wenfeng Dai, Xiang Cheng
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE62357
LICENSECC_BY
RIGHTSCC BY
SOURCEPLOS

Source: https://doi.org/10.1371/journal.pone.0359164

Browse the full library · About the Tower of Babel