EUVIMEDEUVIMED entdecken
Open Access

Pro4S : Prediction of protein solubility by fusing sequence, structure, and surface

Jie Qian iD, Lin Yang iD, Renxiao Wang iD, Yifei Qi iD

Protein Science · 2026-09 · 35 (9)

DOI: 10.1002/pro.70749 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Protein Science, online erschienen am 12.08.2026. Verfasst von Jie Qian und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Medicinal Chemistry, School of Pharmaceutical Sciences, Fudan University, Shanghai, People's Republic of China. Hauptthemen laut MEDLINE: Proteins, Computational Biology. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 59 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: National Natural Science Foundation of China, Open Project of State Key Laboratory of Synergistic Chem-Bio Synthesis, Science and Technology Commission of Shanghai Municipality.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Protein solubility is a critical physicochemical property influencing protein stability, therapeutic efficacy, and overall developability in drug discovery. However, traditional experimental methods for assessing solubility are often resource‐intensive and time‐consuming. To address these limitations, computational approaches leveraging artificial intelligence have emerged. However, few existing frameworks are designed to effectively support both qualitative classification and quantitative regression tasks, which predominantly rely on sequence‐based information. Although several recent methods have incorporated structural features, protein surface characteristics remain relatively underexplored and are not yet systematically integrated with sequence and structural representations. Here, we introduce Pro4S, a novel multimodal Protein Solubility predictive model that integrates Sequence feature, Structural feature, and Surface descriptors using advanced contrastive learning techniques. Our framework achieves significant improvements in prediction accuracy, robustness, and generalizability for both qualitative and quantitative solubility assessments. Benchmark comparisons demonstrate that Pro4S consistently outperforms existing state‐of‐the‐art predictors across diverse datasets. Furthermore, by applying Pro4S to the emerging area of de novo protein design, we validated a strong correlation between predicted solubility and experimental expression levels, reducing the proportion of non‐expressed proteins by 52.7% while retaining 96.7% of highly expressed proteins. This highlights Pro4S's potential to serve as a reliable upfront screening tool for increasing expression success rates and accelerating rational protein engineering.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

ProteinsComputational BiologySolubilityProtein ConformationPrediction AlgorithmsSurface PropertiesModels, MolecularAmino Acid Sequence

Stichwörter der Autor:innen

contrastive learningdeep learningprotein solubility

Substanzen

Proteins

Autor:innen und Institutionen

  • Department of Medicinal Chemistry, School of Pharmaceutical Sciences, Fudan University, Shanghai, People's Republic of China.

ORCID-Profile: Jie Qian, Lin Yang, Renxiao Wang, Yifei Qi

Förderung

  • National Natural Science Foundation of China
  • Open Project of State Key Laboratory of Synergistic Chem-Bio Synthesis
  • Science and Technology Commission of Shanghai Municipality

Zitieren

APA

Qian, J., Yang, L., Wang, R., & Qi, Y. (2026). Pro4S : Prediction of protein solubility by fusing sequence, structure, and surface. Protein Science, 35(9). https://doi.org/10.1002/pro.70749

Vancouver

Qian J, Yang L, Wang R, Qi Y. Pro4S : Prediction of protein solubility by fusing sequence, structure, and surface. Protein Science. 2026;35(9). doi:10.1002/pro.70749

BibTeX
@article{Qian2026,
  author = {Qian, Jie and Yang, Lin and Wang, Renxiao and Qi, Yifei},
  title = {Pro4S : Prediction of protein solubility by fusing sequence, structure, and surface},
  journal = {Protein Science},
  year = {2026},
  volume = {35},
  number = {9},
  doi = {10.1002/pro.70749}
}
Kostenlos starten →