LPItabformer: Enhancing generalization in predicting lncRNA-protein interactions via a tabular Transformer

Long-noncoding RNAs (LncRNAs) play important roles in physiological and pathological processes. Accurately predicting lncRNA-protein interactions (LPIs) is vital strategy for clarify functions and pathogenic mechanisms of lncRNAs. Current computational methods for evaluating LPIs with their utility...

Full description

Saved in:
Bibliographic Details
Main Authors: Qin Lin, Jie Sheng, Chang Zhou, Tao Xiao, Yilei Meng, Mingxin Lu, Junfang Zhang, Xueyun Yan, Luying Peng, Huaming Cao, Li Li
Format: Article
Language:English
Published: Elsevier 2025-01-01
Series:Computational and Structural Biotechnology Journal
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2001037025002132
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849735944366718976
author Qin Lin
Jie Sheng
Chang Zhou
Tao Xiao
Yilei Meng
Mingxin Lu
Junfang Zhang
Xueyun Yan
Luying Peng
Huaming Cao
Li Li
author_facet Qin Lin
Jie Sheng
Chang Zhou
Tao Xiao
Yilei Meng
Mingxin Lu
Junfang Zhang
Xueyun Yan
Luying Peng
Huaming Cao
Li Li
author_sort Qin Lin
collection DOAJ
description Long-noncoding RNAs (LncRNAs) play important roles in physiological and pathological processes. Accurately predicting lncRNA-protein interactions (LPIs) is vital strategy for clarify functions and pathogenic mechanisms of lncRNAs. Current computational methods for evaluating LPIs with their utility and generalization have significant room for improvement. In this study, data splitting by incorporating protein clusters as group information reveals that lots of LPI prediction methods suffer from generalization flaws due to data leakage caused by ignoring LPI biological properties. To address the issue, we present LPItabformer, a tabular Transformer framework for predicting LPIs, that incorporates a domain shifts with uncertainty (DSU) module for generalization enhancement. The LPItabformer demonstrates a capacity to alleviate the generalization challenges associated with biases in LPI data and preferences in protein binding patterns. In addition, LPItabformer shows greater robustness and generalization on human and mouse LPI datasets compared to state-of-the-art methods. Ultimately, we have verified that the LPItabformer is capable of predicting novel LPIs. Code is available at https://github.com/Ci-TJ/LPItabformer.
format Article
id doaj-art-304c45ca1abe4e0cbba2e23cd1a58cb8
institution DOAJ
issn 2001-0370
language English
publishDate 2025-01-01
publisher Elsevier
record_format Article
series Computational and Structural Biotechnology Journal
spelling doaj-art-304c45ca1abe4e0cbba2e23cd1a58cb82025-08-20T03:07:24ZengElsevierComputational and Structural Biotechnology Journal2001-03702025-01-01272323233510.1016/j.csbj.2025.05.050LPItabformer: Enhancing generalization in predicting lncRNA-protein interactions via a tabular TransformerQin Lin0Jie Sheng1Chang Zhou2Tao Xiao3Yilei Meng4Mingxin Lu5Junfang Zhang6Xueyun Yan7Luying Peng8Huaming Cao9Li Li10State Key Laboratory of Cardiovascular Diseases and Medical Innovation Center, Shanghai East Hospital, School of Medicine, Tongji University, Shanghai 200120, China; Shanghai Arrhythmias Research Center, Shanghai East Hospital, Tongji University School of Medicine, Shanghai 200120, China; Stem Cell Research Center, Medical School, Tongji University, Shanghai 200120, ChinaState Key Laboratory of Cardiovascular Diseases and Medical Innovation Center, Shanghai East Hospital, School of Medicine, Tongji University, Shanghai 200120, China; Shanghai Arrhythmias Research Center, Shanghai East Hospital, Tongji University School of Medicine, Shanghai 200120, China; Stem Cell Research Center, Medical School, Tongji University, Shanghai 200120, ChinaState Key Laboratory of Cardiovascular Diseases and Medical Innovation Center, Shanghai East Hospital, School of Medicine, Tongji University, Shanghai 200120, China; Shanghai Arrhythmias Research Center, Shanghai East Hospital, Tongji University School of Medicine, Shanghai 200120, China; Stem Cell Research Center, Medical School, Tongji University, Shanghai 200120, ChinaState Key Laboratory of Cardiovascular Diseases and Medical Innovation Center, Shanghai East Hospital, School of Medicine, Tongji University, Shanghai 200120, China; Shanghai Arrhythmias Research Center, Shanghai East Hospital, Tongji University School of Medicine, Shanghai 200120, China; Stem Cell Research Center, Medical School, Tongji University, Shanghai 200120, ChinaState Key Laboratory of Cardiovascular Diseases and Medical Innovation Center, Shanghai East Hospital, School of Medicine, Tongji University, Shanghai 200120, China; Shanghai Arrhythmias Research Center, Shanghai East Hospital, Tongji University School of Medicine, Shanghai 200120, China; Stem Cell Research Center, Medical School, Tongji University, Shanghai 200120, ChinaState Key Laboratory of Cardiovascular Diseases and Medical Innovation Center, Shanghai East Hospital, School of Medicine, Tongji University, Shanghai 200120, China; Shanghai Arrhythmias Research Center, Shanghai East Hospital, Tongji University School of Medicine, Shanghai 200120, China; Stem Cell Research Center, Medical School, Tongji University, Shanghai 200120, ChinaTeaching Laboratory Center, Tongji University School of Medicine, Shanghai 200331, ChinaDepartment of Cardiology, Shibei Hospital, Shanghai 200435, ChinaState Key Laboratory of Cardiovascular Diseases and Medical Innovation Center, Shanghai East Hospital, School of Medicine, Tongji University, Shanghai 200120, China; Shanghai Arrhythmias Research Center, Shanghai East Hospital, Tongji University School of Medicine, Shanghai 200120, China; Stem Cell Research Center, Medical School, Tongji University, Shanghai 200120, ChinaDepartment of Cardiology, Shibei Hospital, Shanghai 200435, China; Correspondence author.State Key Laboratory of Cardiovascular Diseases and Medical Innovation Center, Shanghai East Hospital, School of Medicine, Tongji University, Shanghai 200120, China; Shanghai Arrhythmias Research Center, Shanghai East Hospital, Tongji University School of Medicine, Shanghai 200120, China; Stem Cell Research Center, Medical School, Tongji University, Shanghai 200120, China; Corresponding author at: State Key Laboratory of Cardiovascular Diseases and Medical Innovation Center, Shanghai East Hospital, School of Medicine, Tongji University, Shanghai 200120, ChinaLong-noncoding RNAs (LncRNAs) play important roles in physiological and pathological processes. Accurately predicting lncRNA-protein interactions (LPIs) is vital strategy for clarify functions and pathogenic mechanisms of lncRNAs. Current computational methods for evaluating LPIs with their utility and generalization have significant room for improvement. In this study, data splitting by incorporating protein clusters as group information reveals that lots of LPI prediction methods suffer from generalization flaws due to data leakage caused by ignoring LPI biological properties. To address the issue, we present LPItabformer, a tabular Transformer framework for predicting LPIs, that incorporates a domain shifts with uncertainty (DSU) module for generalization enhancement. The LPItabformer demonstrates a capacity to alleviate the generalization challenges associated with biases in LPI data and preferences in protein binding patterns. In addition, LPItabformer shows greater robustness and generalization on human and mouse LPI datasets compared to state-of-the-art methods. Ultimately, we have verified that the LPItabformer is capable of predicting novel LPIs. Code is available at https://github.com/Ci-TJ/LPItabformer.http://www.sciencedirect.com/science/article/pii/S2001037025002132Long non-coding RNALncRNA-protein interactionsTabular TransformerGeneralizationDeep learning
spellingShingle Qin Lin
Jie Sheng
Chang Zhou
Tao Xiao
Yilei Meng
Mingxin Lu
Junfang Zhang
Xueyun Yan
Luying Peng
Huaming Cao
Li Li
LPItabformer: Enhancing generalization in predicting lncRNA-protein interactions via a tabular Transformer
Computational and Structural Biotechnology Journal
Long non-coding RNA
LncRNA-protein interactions
Tabular Transformer
Generalization
Deep learning
title LPItabformer: Enhancing generalization in predicting lncRNA-protein interactions via a tabular Transformer
title_full LPItabformer: Enhancing generalization in predicting lncRNA-protein interactions via a tabular Transformer
title_fullStr LPItabformer: Enhancing generalization in predicting lncRNA-protein interactions via a tabular Transformer
title_full_unstemmed LPItabformer: Enhancing generalization in predicting lncRNA-protein interactions via a tabular Transformer
title_short LPItabformer: Enhancing generalization in predicting lncRNA-protein interactions via a tabular Transformer
title_sort lpitabformer enhancing generalization in predicting lncrna protein interactions via a tabular transformer
topic Long non-coding RNA
LncRNA-protein interactions
Tabular Transformer
Generalization
Deep learning
url http://www.sciencedirect.com/science/article/pii/S2001037025002132
work_keys_str_mv AT qinlin lpitabformerenhancinggeneralizationinpredictinglncrnaproteininteractionsviaatabulartransformer
AT jiesheng lpitabformerenhancinggeneralizationinpredictinglncrnaproteininteractionsviaatabulartransformer
AT changzhou lpitabformerenhancinggeneralizationinpredictinglncrnaproteininteractionsviaatabulartransformer
AT taoxiao lpitabformerenhancinggeneralizationinpredictinglncrnaproteininteractionsviaatabulartransformer
AT yileimeng lpitabformerenhancinggeneralizationinpredictinglncrnaproteininteractionsviaatabulartransformer
AT mingxinlu lpitabformerenhancinggeneralizationinpredictinglncrnaproteininteractionsviaatabulartransformer
AT junfangzhang lpitabformerenhancinggeneralizationinpredictinglncrnaproteininteractionsviaatabulartransformer
AT xueyunyan lpitabformerenhancinggeneralizationinpredictinglncrnaproteininteractionsviaatabulartransformer
AT luyingpeng lpitabformerenhancinggeneralizationinpredictinglncrnaproteininteractionsviaatabulartransformer
AT huamingcao lpitabformerenhancinggeneralizationinpredictinglncrnaproteininteractionsviaatabulartransformer
AT lili lpitabformerenhancinggeneralizationinpredictinglncrnaproteininteractionsviaatabulartransformer