Skip to content
DraconiticResearch
Search Sources API
197,768 studies31 sourcesUpdated 29 min ago
Peer-reviewedCC BYNucleic Acids Research

DeepAden: an explainable machine learning method for predicting the substrate specificity of nonribosomal peptide synthetases

  • Jiaquan Huang1
  • Liangjun Ge1
  • Y J Wu1
  • Yi Tian1
  • Jianmin Wu1
  • Qiandi Gao1
  • Li Pan1
  • Song Meng2,3,4
  • Heqian Zhang1
  • Zhiwei Qin1
4 affiliations
  1. 1Center for Biological Science and Technology, Advanced Institute of Natural Sciences, Beijing Normal University , Zhuhai, Guangdong 519087 ,
  2. 2State Key Laboratory of Drug Research & Natural Products Research Center, Shanghai Institute of Materia Medica, Chinese Academy of Sciences , Shanghai 201203 ,
  3. 3University of Chinese Academy of Sciences , Beijing 100049 ,
  4. 4Zhongshan Institute for Drug Discovery, Shanghai Institute of Materia Medica, Chinese Academy of Sciences , Zhongshan 528400 ,
Open at sourceDOICite

Abstract

Microbial nonribosomal peptides (NRPs) exhibit remarkable structural diversity and are important sources of lead compounds for clinical drug development. The biosynthesis of NRPs relies on nonribosomal peptide synthetases (NRPSs), in which adenylation (A) domains define the core structure by selectively recognizing and activating amino acid substrates. Accurately predicting the substrate specificities of A-domains is thus essential for understanding the core structural and biosynthetic logic of NRPs. Here, we present DeepAden, a two-stage deep learning model. In the first stage, a graph attention network (GAT)-based model localizes 27-residue binding pockets within 6 Å of bound substrates and converts these into pocket representations. In the second stage, pocket representations are encoded alongside substrate information using pretrained language models and aligned using contrastive learning. We also applied a SHapley Additive exPlanations (SHAP)-guided data augmentation strategy to mitigate class imbalance, particularly focusing on nonproteinogenic substrates. DeepAden achieved competitive performance compared with state-of-the-art tools on a benchmark dataset and facilitated the annotation of two Streptomyces NRPS gene clusters by providing supportive A-domain substrate-specificity predictions. DeepAden provides a practical approach for pocket localization and substrate prediction and may facilitate the discovery and characterization of new NRP natural products. The DeepAden web server is available at https://deepnp.site/.

Related

  1. MINT: Predicting Enzyme-Cofactor Specificity by Multimodal Knowledge Transfer from Protein-Ligand Interactions
    Y. Ye, X. Li, H. Duan +2
    bioRxivPreprintAll rights reservedFull textSystems & synthetic biologybioRxiv
  2. Physics-guided explainable machine learning for predicting temporal scour evolution around hybrid spur dikes under unsteady flood hydrographs
    Mehdi Daryaee, Laleh Divband Hafshejani, Seyed Mahmood Kashefipour +1
    Scientific ReportsPeer-reviewedCC BY-NC-ND 4.0Full textEcologyCrossref
  3. Predicting driving performance from resting-state EEG using explainable gradient boosting
    Khadidjeh Sadatnejad, Christian Berthomier, Chloe Boitard +5
    Scientific ReportsPeer-reviewedCC BY 4.0Full textNeuroscienceHAL
  4. Structural and mechanistic divergence of the small (p)ppGpp synthetases RelP and RelQ.
    Steinchen W, Vogt Ms, Altegoer F +4
    Scientific ReportsPeer-reviewedCC BYFull text54 citedStructural biologyGeneral biologyHAL
  5. Limitations of general protein language models and public TCRpMHC data in training specificity prediction models
    B. Rai, S. Hall-Swan
    bioRxivPreprintAll rights reservedFull textBioinformatics & computational biologybioRxiv

Cite

BibTeXRIS
BibTeX
@article{huang2026deepaden,
  title = {{DeepAden: an explainable machine learning method for predicting the substrate specificity of nonribosomal peptide synthetases}},
  author = {Jiaquan Huang and Liangjun Ge and Y J Wu and Yi Tian and Jianmin Wu and Qiandi Gao and Li Pan and Song Meng and Heqian Zhang and Zhiwei Qin},
  journal = {Nucleic Acids Research},
  year = {2026},
  month = jul,
  doi = {10.1093/nar/gkag656},
  url = {https://doi.org/10.1093/nar/gkag656},
  note = {CC BY},
}
RIS
TY  - JOUR
TI  - DeepAden: an explainable machine learning method for predicting the substrate specificity of nonribosomal peptide synthetases
AU  - Jiaquan Huang
AU  - Liangjun Ge
AU  - Y J Wu
AU  - Yi Tian
AU  - Jianmin Wu
AU  - Qiandi Gao
AU  - Li Pan
AU  - Song Meng
AU  - Heqian Zhang
AU  - Zhiwei Qin
PY  - 2026
DA  - 2026/07/03
JO  - Nucleic Acids Research
DO  - 10.1093/nar/gkag656
UR  - https://doi.org/10.1093/nar/gkag656
AB  - Microbial nonribosomal peptides (NRPs) exhibit remarkable structural diversity and are important sources of lead compounds for clinical drug development. The biosynthesis of NRPs relies on nonribosomal peptide synthetases (NRPSs), in which adenylation (A) domains define the core structure by selectively recognizing and activating amino acid substrates. Accurately predicting the substrate specificities of A-domains is thus essential for understanding the core structural and biosynthetic logic of NRPs. Here, we present DeepAden, a two-stage deep learning model. In the first stage, a graph attention network (GAT)-based model localizes 27-residue binding pockets within 6 Å of bound substrates and converts these into pocket representations. In the second stage, pocket representations are encoded alongside substrate information using pretrained language models and aligned using contrastive learning. We also applied a SHapley Additive exPlanations (SHAP)-guided data augmentation strategy to mitigate class imbalance, particularly focusing on nonproteinogenic substrates. DeepAden achieved competitive performance compared with state-of-the-art tools on a benchmark dataset and facilitated the annotation of two Streptomyces NRPS gene clusters by providing supportive A-domain substrate-specificity predictions. DeepAden provides a practical approach for pocket localization and substrate prediction and may facilitate the discovery and characterization of new NRP natural products. The DeepAden web server is available at https://deepnp.site/.
SN  - 0305-1048
SN  - 1362-4954
SN  - 1362-4962
ER  -