Decoding the effects of mutation on protein interactions using machine learning DOI
Xu Wang, Anbang Li, Yunjie Zhao

и другие.

Biophysics Reviews, Год журнала: 2025, Номер 6(1)

Опубликована: Фев. 21, 2025

Accurately predicting mutation-caused binding free energy changes (ΔΔGs) on protein interactions is crucial for understanding how genetic variations affect between proteins and other biomolecules, such as proteins, DNA/RNA, ligands, which are vital regulating numerous biological processes. Developing computational approaches with high accuracy efficiency critical elucidating the mechanisms underlying various diseases, identifying potential biomarkers early diagnosis, developing targeted therapies. This review provides a comprehensive overview of recent advancements in impact mutations across different interaction types, central to processes disease mechanisms, including cancer. We summarize progress predictive approaches, physicochemical-based, machine learning, deep learning methods, evaluating strengths limitations each. Additionally, we discuss challenges related mutational data, biases, data quality, dataset size, explore difficulties accurate prediction tools mutation-induced effects interactions. Finally, future directions advancing these tools, highlighting capabilities technologies, artificial intelligence drive significant improvements prediction.

Язык: Английский

Advances and Mechanisms of RNA–Ligand Interaction Predictions DOI Creative Commons
Zhuo Chen, Chengwei Zeng,

Haoquan Liu

и другие.

Life, Год журнала: 2025, Номер 15(1), С. 104 - 104

Опубликована: Янв. 15, 2025

The diversity and complexity of RNA include sequence, secondary structure, tertiary structure characteristics. These elements are crucial for RNA's specific recognition other molecules. With advancements in biotechnology, RNA-ligand structures allow researchers to utilize experimental data uncover the mechanisms complex interactions. However, determining these complexes experimentally can be technically challenging often results low-resolution data. Many machine learning computational approaches have recently emerged learn multiscale-level features predict Predicting interactions remains an unexplored area. Therefore, studying is essential understanding biological processes. In this review, we analyze interaction characteristics by examining structure. Our goal clarify how specifically recognizes ligands. Additionally, systematically discuss methods predicting guide future research directions. We aim inspire creation more reliable prediction tools.

Язык: Английский

Процитировано

0
Molecular Dynamics of Apolipoprotein Genotypes APOE4 and SNARE Family Proteins and Their Impact on Alzheimer’s Disease DOI Creative Commons
Yuqing Wang, Xuefeng Liu,

Pengtao Zheng

и другие.

Life, Год журнала: 2025, Номер 15(2), С. 223 - 223

Опубликована: Фев. 2, 2025

Alzheimer's disease is a chronic neurodegenerative disorder characterized by progressive memory loss and significant impact on quality of life. The APOE ε4 allele major genetic contributor to AD pathogenesis, with synaptic dysfunction being central hallmark in its pathophysiology. While the role APOE4 reducing SNARE protein levels has been established, underlying molecular mechanisms this interaction remain obscure. Our research employs dynamics simulations analyze interactions between APOE3 isoforms proteins VAMP2, SNAP25, SYNTAXIN1, which play crucial roles presynaptic membrane. findings reveal that significantly destabilizes complex, suppresses structural dynamics, reduces hydrogen bonding, consequently partially hindering neurotransmitter release-a very likely discovery for elucidating disease. We identified exhibits diminished affinity complex comparison APOE3. This observation suggests may modulating stability potentially impacting progression occurrence through free energy analysis. work highlights perturbations function mediated APOE4, offer novel insights into underpinnings AD. By interplay our study not only enhances comprehension AD's pathology but also paves way devising innovative therapeutic interventions, such as targeting APOE4-SNARE or restore release.

Язык: Английский

Процитировано

0
RNA-protein interaction prediction using network-guided deep learning DOI Creative Commons
Haoquan Liu, Yiren Jian, Chen Zeng

и другие.

Communications Biology, Год журнала: 2025, Номер 8(1)

Опубликована: Фев. 16, 2025

Accurate computational determination of RNA-protein interactions remains challenging, particularly when encountering unknown RNAs and proteins. The limited number their flexibility constrained the effectiveness deep-learning models for interaction prediction. Here, we introduce ZHMolGraph, which integrates graph neural network unsupervised large language to predict interaction. We validate ZHMolGraph predictions on two benchmark datasets outperform current best methods. For dataset entirely proteins, shows an improvement in achieving high AUROC 79.8% AUPRC 82.0%. This represents a substantial 7.1%–28.7% 4.6%–30.0% over other utilize enhance challenging SARS-CoV-2 RPI unbound complex predictions. Such enhancements make reliable option genome-wide holds broad potential modeling designing complexes. study has developed new method by combining networks models. model showed superior performances tests, especially previously unseen

Язык: Английский

Процитировано

0
Decoding the effects of mutation on protein interactions using machine learning DOI
Xu Wang, Anbang Li, Yunjie Zhao

и другие.

Biophysics Reviews, Год журнала: 2025, Номер 6(1)

Опубликована: Фев. 21, 2025

Accurately predicting mutation-caused binding free energy changes (ΔΔGs) on protein interactions is crucial for understanding how genetic variations affect between proteins and other biomolecules, such as proteins, DNA/RNA, ligands, which are vital regulating numerous biological processes. Developing computational approaches with high accuracy efficiency critical elucidating the mechanisms underlying various diseases, identifying potential biomarkers early diagnosis, developing targeted therapies. This review provides a comprehensive overview of recent advancements in impact mutations across different interaction types, central to processes disease mechanisms, including cancer. We summarize progress predictive approaches, physicochemical-based, machine learning, deep learning methods, evaluating strengths limitations each. Additionally, we discuss challenges related mutational data, biases, data quality, dataset size, explore difficulties accurate prediction tools mutation-induced effects interactions. Finally, future directions advancing these tools, highlighting capabilities technologies, artificial intelligence drive significant improvements prediction.

Язык: Английский

Процитировано

0