SaltyMeta: a curated benchmark and protein language model-informed web tool for salty peptide prediction

Abstract

Excess sodium intake remains a major public health challenge, while salty and saltiness-enhancing peptides offer a potential route to preserve sensory saltiness in reduced-sodium foods. Machine-learning studies of salty peptides, however, are constrained by small datasets, heterogeneous evidence standards, uncertain negative labels, and sequence similarity leakage. Here we present SaltyMeta, a curated benchmark and web-accessible screening framework for salty or saltiness-enhancing short peptides. The benchmark contains 580 peptides, including 280 positive peptides and 300 negative peptides, all standardized to 2-15 residue one-letter amino-acid sequences. Quality control found no non-standard residues, exact duplicates, or positive-negative overlaps. A similarity-grouped split retained 456 peptides for training and 124 for held-out testing. We evaluated 548 interpretable peptide descriptors, frozen ESM2 embeddings at 8M, 35M, and 150M parameter scales, and descriptor-embedding fusion models under grouped cross-validation. The traditional ExtraTrees baseline selected by training-set grouped cross-validation achieved ROC-AUC=0.693 in cross-validation and ROC-AUC=0.704, PR-AUC=0.702, F1=0.626, and MCC=0.304 on the held-out test set. The best initial protein-language-model fusion was traditional descriptors plus ESM2-8M embeddings, with grouped CV ROC-AUC=0.696 and test ROC-AUC=0.700. Advanced optimization using PCA95 dimensionality reduction and ExtraTrees feature-importance filtering yielded a practical ESM2-8M PCA95 top-300 model with test ROC-AUC=0.715 and PR-AUC=0.703, although repeated-CV gains remained modest. SaltyMeta is a transparent prioritization tool, not a sensory validation substitute. We provide benchmark, models, scripts, GitHub, and Streamlit for reproducible screening of food-derived peptides.

CEM 2.0: Co-evolution-guided mining of superior extremophilic proteins via a curated proteome database and protein language model.
Zhendong Zhang, Lina Ma, Mingyang Ding +2
Engineering microbiology21 Aug 2026Peer-reviewedCC BY-NC-NDFull textMolecular biology & gene regulationEurope PMC
DICD-IE: an expert-annotated benchmark for evaluating pretrained biomedical language models in dental implant literature and clinical knowledge extraction
Almonzer Salah Nooraldaim, Azza A. Abushama, Hiba Ahmed +7
Scientific Reports30 Sep 2026Peer-reviewedCC BY-NC-ND 4.0Full textMolecular biology & gene regulationCrossref
LEMON-ZEST: Evolution-Informed Tokenization for Efficient Protein Language Modeling
Biswajit Banerjee, Claudia Alvarez Carreno, Anton S. Petrov
arXiv29 Sep 2026PreprintCC BY 4.0Full textBiophysicsarXiv
PLANTMETBENCH: A MULTIMODAL KNOWLEDGE GRAPH BENCHMARK FOR BIOSYNTHESIS PREDICTION
Elena Del Pup, Berfin Inal, Joana Tirana +6
ChemRxiv27 Oct 2026PreprintCC BYFull textMolecular biology & gene regulationChemRxiv
Understanding language model scaling for protein fitness prediction
Chao Hou, Ди Лю, Aziz Zafar +1
Nature Computational Science13 Jul 2026Peer-reviewedLicence not statedFull text22 citedMolecular biology & gene regulationOpenAlex

Cite

BibTeX RIS

BibTeX

@misc{chen2026saltymeta,
  title = {{SaltyMeta: a curated benchmark and protein language model-informed web tool for salty peptide prediction}},
  author = {Wanchao Chen and Wen Li and Yanan He and Yan Yang},
  howpublished = {arXiv},
  year = {2026},
  month = sep,
  doi = {10.48550/arxiv.2609.16809},
  eprint = {2609.16809},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.16809},
  note = {CC BY-SA 4.0},
}

RIS

TY  - UNPB
TI  - SaltyMeta: a curated benchmark and protein language model-informed web tool for salty peptide prediction
AU  - Wanchao Chen
AU  - Wen Li
AU  - Yanan He
AU  - Yan Yang
PY  - 2026
DA  - 2026/09/15
PB  - arXiv
DO  - 10.48550/arxiv.2609.16809
UR  - https://arxiv.org/abs/2609.16809
AB  - Excess sodium intake remains a major public health challenge, while salty and saltiness-enhancing peptides offer a potential route to preserve sensory saltiness in reduced-sodium foods. Machine-learning studies of salty peptides, however, are constrained by small datasets, heterogeneous evidence standards, uncertain negative labels, and sequence similarity leakage. Here we present SaltyMeta, a curated benchmark and web-accessible screening framework for salty or saltiness-enhancing short peptides. The benchmark contains 580 peptides, including 280 positive peptides and 300 negative peptides, all standardized to 2-15 residue one-letter amino-acid sequences. Quality control found no non-standard residues, exact duplicates, or positive-negative overlaps. A similarity-grouped split retained 456 peptides for training and 124 for held-out testing. We evaluated 548 interpretable peptide descriptors, frozen ESM2 embeddings at 8M, 35M, and 150M parameter scales, and descriptor-embedding fusion models under grouped cross-validation. The traditional ExtraTrees baseline selected by training-set grouped cross-validation achieved ROC-AUC=0.693 in cross-validation and ROC-AUC=0.704, PR-AUC=0.702, F1=0.626, and MCC=0.304 on the held-out test set. The best initial protein-language-model fusion was traditional descriptors plus ESM2-8M embeddings, with grouped CV ROC-AUC=0.696 and test ROC-AUC=0.700. Advanced optimization using PCA95 dimensionality reduction and ExtraTrees feature-importance filtering yielded a practical ESM2-8M PCA95 top-300 model with test ROC-AUC=0.715 and PR-AUC=0.703, although repeated-CV gains remained modest. SaltyMeta is a transparent prioritization tool, not a sensory validation substitute. We provide benchmark, models, scripts, GitHub, and Streamlit for reproducible screening of food-derived peptides.
ER  -

Abstract

Related

Cite