Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat

The DOI matches its Crossref record; 82 of the 85 references it cites were found in a registry or an index; 4 of the 17 sources its claims cite were checked for support.

Solubility-Weighted Index: fast and accurate prediction of protein solubility

Open access

Published version of a preprint

Abstract

Recombinant protein production is a widely used technique in the biotechnology and biomedical industries, yet only a quarter of target proteins are soluble and can therefore be purified. We have discovered that global structural flexibility, which can be modeled by normalized B-factors, accurately predicts the solubility of 12216 recombinant proteins expressed in Escherichia coli. We call this new predictor the 'Solubility-Weighted Index' (SWI). SWI outperforms many existing protein solubility prediction tools.

Overview

CoChat Summary

TL;DR

The paper introduces the Solubility-Weighted Index (SWI), a sequence-composition score derived from optimized normalized B-factors, to predict recombinant protein solubility in *E. coli*. On the PSI: Biology dataset of 12,216 proteins, SWI improved prediction over flexibility-based scoring and outperformed most compared tools, while also supporting a web server, SoDoPE, for region-level solubility prediction.

Key findings

  • Protein structural flexibility was the strongest among the tested sequence properties, with solubility prediction AUC = 0.67 on the PSI: Biology dataset.
  • Optimizing normalized B-factors yielded SWI, with training AUC = 0.72 ± 0.00 and test AUC = 0.71 ± 0.01, described as a 7.5% improvement over flexibility in solubility prediction.
  • On the independent eSOL dataset (N = 3,198), correlation with solubility improved from Spearman’s rho = 0.40 for the initial B-factors to 0.50 for the final weights; removing His-tags reduced it slightly to rho = 0.47.
  • SWI outperformed other compared solubility tools except Protein-Sol for *E. coli* solubility prediction, and the authors report that their SWI C program was the fastest algorithm tested.

Methods

  • The main dataset was 12,216 PSI: Biology recombinant proteins expressed in *E. coli* (from DNASU), with validation on the independent eSOL *E. coli* dataset (N = 3,198) and a stickiness dataset of 397 proteins.
  • The authors evaluated 9 standard and 9,920 miscellaneous sequence properties, then optimized normalized B-factors using 10-fold cross-validation, 10 clusters of roughly 1,200 sequences, 1,000 bootstrap resamplings per fold, and Nelder–Mead optimization targeting AUC.
  • They benchmarked SWI against scalable existing predictors and also fit a logistic regression to convert SWI into a solubility probability for the SoDoPE web server.

Limitations

  • The paper states that the SWI probability model should be used only when the protein is successfully expressed in *E. coli*.
  • The authors note a possible limitation that SWI may overfit to His-tag fusion proteins, based on the slight drop in eSOL correlation after His-tag removal.
  • Evident from the text: the study focuses on *E. coli* expression systems and the compared datasets, so the findings may not generalize to other hosts or solubility contexts without additional validation.

Model-written summary. Check it against the paper before relying on it.

Integrity signals

Registry

Crossref · 10.1093/bioinformatics/btaa578

Cites

82 of 82 references verified0 citation errors · 0 not checkable

Statistics

Nothing to recompute.

Figures

Fig. 1. Global structural flexibility outperforms other standard protein sequence properties in protein solubility prediction. ROC analysis of the standard protein sequence features for predicting the solubility of 12 216 recombinant proteins expressed in E.coli (the PSI: Biology dataset). The ROC curves are shown in two separate panels for clarity. AUC scores (perfect = 1.00, random = 0.50) are shown in parentheses. Dashed lines denote the performance of random classifiers. See also Supplementary Figure S2 and Table S2. AUC, Area Under the ROC Curve; GRAVY, Grand Average of Hydropathy; PSI: Biology, Protein Structure Initiative: Biology; ROC, Receiver Operating Characteristic
Fig. 1. Global structural flexibility outperforms other standard protein sequence properties in protein solubility prediction. ROC analysis of the standard protein sequence features for predicting the solubility of 12 216 recombinant proteins expressed in E.coli (the PSI: Biology dataset). The ROC curves are shown in two separate panels for clarity. AUC scores (perfect = 1.00, random = 0.50) are shown in parentheses. Dashed lines denote the performance of random classifiers. See also Supplementary Figure S2 and Table S2. AUC, Area Under the ROC Curve; GRAVY, Grand Average of Hydropathy; PSI: Biology, Protein Structure Initiative: Biology; ROC, Receiver Operating CharacteristicCC BY · PubMed Central
Fig. 2. Derivation of the SWI. (A) Flow chart shows an iterative refinement of the weights of amino acid residues for solubility prediction. Each cross-validation step used separate sequence similarity clusters for training and testing. Furthermore, bootstrapping was used to resample each training set, avoiding training and testing on similar sequences. The solubility scores of protein sequences were calculated using a sequence composition scoring approach. These scores were used to compute the AUC scores for training and test datasets. (B) Training and test performance of solubility prediction using optimized weights for 20 amino acid residues in a 10-fold cross-validation (mean AUC ± standard deviation). Related data and figures are available as Supplementary Table S3 and Figures S4 and S5. (C) Comparison between the 20 initial and final weights for amino acid residues. The final weights W=〈Vi〉,1≤i≤10 were used to calculate the solubility score of a protein sequence (SWI) in the four subsequent analyses. Filled circles, which represent amino acid residues, are colored by hydrophobicity (Kyte and Doolittle, 1982). Solid black circles denote aromatic residues phenylalanine (F), tyrosine (Y), tryptophan (W). Dotted diagonal line represents no change in weight. See also Supplementary Table S4. AUC, Area Under the ROC Curve; ROC, Receiver Operating Characteristic. (Color version of this figure is available at Bioinformatics online.)
Fig. 2. Derivation of the SWI. (A) Flow chart shows an iterative refinement of the weights of amino acid residues for solubility prediction. Each cross-validation step used separate sequence similarity clusters for training and testing. Furthermore, bootstrapping was used to resample each training set, avoiding training and testing on similar sequences. The solubility scores of protein sequences were calculated using a sequence composition scoring approach. These scores were used to compute the AUC scores for training and test datasets. (B) Training and test performance of solubility prediction using optimized weights for 20 amino acid residues in a 10-fold cross-validation (mean AUC ± standard deviation). Related data and figures are available as Supplementary Table S3 and Figures S4 and S5. (C) Comparison between the 20 initial and final weights for amino acid residues. The final weights W=〈Vi〉,1≤i≤10 were used to calculate the solubility score of a protein sequence (SWI) in the four subsequent analyses. Filled circles, which represent amino acid residues, are colored by hydrophobicity (Kyte and Doolittle, 1982). Solid black circles denote aromatic residues phenylalanine (F), tyrosine (Y), tryptophan (W). Dotted diagonal line represents no change in weight. See also Supplementary Table S4. AUC, Area Under the ROC Curve; ROC, Receiver Operating Characteristic. (Color version of this figure is available at Bioinformatics online.)CC BY · PubMed Central
Fig. 3. SWI strongly correlates with protein solubility. (A) Correlation matrix plot of the solubility of recombinant proteins expressed in E.coli and their standard protein sequence properties and SWI. These recombinant proteins are the PSI: Biology targets (N = 12 216) with a binary solubility status of ‘Protein_Soluble’ or ‘Tested_Not_Soluble’. Related data are available as Supplementary Table S5. (B) Correlation matrix plot of the solubility percentages of E.coli proteins and their standard protein sequence properties and SWI. The solubility percentages were previously determined using an E.coli cell-free system (eSOL, N = 3198). Related data are available as Supplementary Table S6. GRAVY, Grand Average of Hydropathy; PSI: Biology, Protein Structure Initiative: Biology; Rs, Spearman’s rho; SWI, Solubility-Weighted Index
Fig. 3. SWI strongly correlates with protein solubility. (A) Correlation matrix plot of the solubility of recombinant proteins expressed in E.coli and their standard protein sequence properties and SWI. These recombinant proteins are the PSI: Biology targets (N = 12 216) with a binary solubility status of ‘Protein_Soluble’ or ‘Tested_Not_Soluble’. Related data are available as Supplementary Table S5. (B) Correlation matrix plot of the solubility percentages of E.coli proteins and their standard protein sequence properties and SWI. The solubility percentages were previously determined using an E.coli cell-free system (eSOL, N = 3198). Related data are available as Supplementary Table S6. GRAVY, Grand Average of Hydropathy; PSI: Biology, Protein Structure Initiative: Biology; Rs, Spearman’s rho; SWI, Solubility-Weighted IndexCC BY · PubMed Central
Fig. 4. SWI outperforms existing protein solubility prediction tools. (A) Prediction accuracy of solubility prediction tools using the above cross-validation sets (Fig. 2A). For SWI, the test AUC scores were calculated from a 10-fold cross-validation (i.e. a boxplot representation of Fig. 2B). For other tools, no cross-validations were done as the AUC scores were calculated directly from the individual subsets used for cross-validation. CamSol and ccSOL omics are only available as web servers (no fill colors). (B) Wall time of protein solubility prediction tools per sequence (log scale). All command line tools were run three times using 10 sequences selected from the PSI: Biology and eSOL datasets. Related data are available as Supplementary Table S7. AUC, Area Under the ROC Curve; PSI: Biology, Protein Structure Initiative: Biology; ROC, Receiver Operating Characteristic; SWI, Solubility-Weighted Index; s, seconds. (Color version of this figure is available at Bioinformatics online.)
Fig. 4. SWI outperforms existing protein solubility prediction tools. (A) Prediction accuracy of solubility prediction tools using the above cross-validation sets (Fig. 2A). For SWI, the test AUC scores were calculated from a 10-fold cross-validation (i.e. a boxplot representation of Fig. 2B). For other tools, no cross-validations were done as the AUC scores were calculated directly from the individual subsets used for cross-validation. CamSol and ccSOL omics are only available as web servers (no fill colors). (B) Wall time of protein solubility prediction tools per sequence (log scale). All command line tools were run three times using 10 sequences selected from the PSI: Biology and eSOL datasets. Related data are available as Supplementary Table S7. AUC, Area Under the ROC Curve; PSI: Biology, Protein Structure Initiative: Biology; ROC, Receiver Operating Characteristic; SWI, Solubility-Weighted Index; s, seconds. (Color version of this figure is available at Bioinformatics online.)CC BY · PubMed Central

Verification

Claims the paper makes

3 Valid · 0 Not valid · 6 Not checked · 44 Own results and interpretations

38 more claims

Create a free account to see all 53 claims and to verify the 2 references still open.

See all claims — free account
  • Probably not a substantial claim. 6
  • It may state two separate claims as one. 4
  • The quote only partly states this claim. 1

Create a free account to see these claims.

Citations

Cites

Show all 85 references

Research works printed but not linked: 1

  1. Harrison, 2000, Expression of soluble heterologous proteins via fusion with NusA protein, Innovations, 11, 4

Cited by

See all 105

Metadata

Authors
Bhandari, B. K., Gardner, P. P., & Lim, C. S.
Affiliations
  • University of Otago (NZ)
  • University of Canterbury (NZ)
Corresponding author
Lim, Chun Shen
Venue
Bioinformatics
Published
2020-06-19
Volume
36
Issue
18
Pages
4691-4698
ISSN
  • 1367-4803 (ISSN-L)
  • 1367-4811
OpenAlex
W3036344389
Cited by
97
References
85
Citations by year
2026: 17 · 2025: 19 · 2024: 23 · 2023: 11 · 2022: 9 · 2021: 13 · 2020: 5
FWCI
3.16
Type
journal article
Language
en
Open access
Locations
  • Bioinformatics (publishedVersion, cc-by)
  • bioRxiv (Cold Spring Harbor Laboratory) (acceptedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
Funders
Ministry of Business, Innovation and Employment, New Zealand [MBIE (UOOX1709)
Topics
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Protein Structure and Dynamics
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Machine Learning in Bioinformatics
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Protein purification and stability
Keywords
protein solubility prediction, structural flexibility, recombinant protein expression, Escherichia coli expression, protein expression optimization, protein purification
MeSH terms
Computers, Escherichia coli, Proteins, Software, Solubility

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

A language model drew the claims from the paper on 2026-10-10, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).

A second model labelled each claim on 2026-10-10 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).

Cited sources are checked with a language model’s help (gpt-6-sol).

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Solubility-Weighted Index: fast and accurate prediction of protein solubility. https://app.cochat.ai/papers/10.1093/bioinformatics/btaa578
The paper
Bhandari, B. K., Gardner, P. P., & Lim, C. S. (2020). Solubility-Weighted Index: fast and accurate prediction of protein solubility. Bioinformatics. https://doi.org/10.1093/bioinformatics/btaa578

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.