CoChat
Sign Up
Cited by 103Protein purification and stabilityMonoclonal and Polyclonal Antibodies ResearchProtein Structure and Dynamics

The DOI matches its Crossref record; 50 of the 50 references it cites were found in a registry or an index.

Machine learning prediction of antibody aggregation and viscosity for high concentration formulation development of protein therapeutics

Open access
Lai, Pin-Kuang, Gallegos, Austin, Mody, Neil, Sathish, Hasige A., Trout, Bernhardt L.·2022·mAbs
DOI 10.1080/19420862.2022.2026208PMC PMC8794240
Open this paper in CoChat — free account

Abstract

Machine learning has been recently used to predict therapeutic antibody aggregation rates and viscosity at high concentrations (150 mg/ml). These works focused on commercially available antibodies, which may have been optimized for stability. In this study, we measured accelerated aggregation rates at 45°C and viscosity at 150 mg/ml for 20 preclinical and clinical-stage antibodies. Features obtained from molecular dynamics simulations of the full-length antibody and sequences were used for machine learning model construction. We found a k-nearest neighbors regression model with two features, spatial positive charge map on the CDRH2 and solvent-accessible surface area of hydrophobic residues on the variable fragment, gives the best performance for predicting antibody aggregation rates (r = 0.89). For the viscosity classification model, the model with the highest accuracy is a logistic regression model with two features, spatial negative charge map on the heavy chain variable region and spatial negative charge map on the light chain variable region. The accuracy and the area under precision recall curve of the classification model from validation tests are 0.86 and 0.70, respectively. In addition, we combined data from another 27 commercial mAbs to develop a viscosity predictive model. The best model is a logistic regression model with two features, number of hydrophobic residues on the light chain variable region and net charges on the light chain variable region. The accuracy and the area under precision recall curve of the classification model are 0.85 and 0.6, respectively. The aggregation rates and viscosity models can be used to predict antibody stability to facilitate pharmaceutical development.

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1080/19420862.2022.2026208

Cites

50 of 50 references verified0 citation errors · 0 not checkable

Statistics

Figures

Figure 1. Aggregation rates of all 20 mAbs studied in this work.
Figure 1. Aggregation rates of all 20 mAbs studied in this work.CC BY-NC · PubMed Central
Figure 2. Correlation coefficients for the best two-feature linear, support vector regression (SVR) and k-nearest neighbors (KNN) regression models trained using all 20 data and LOOCV. The features for the linear regression model are SCM_neg_H2 and SASA_phobic_H3. The features for the SVR and KNN models are both SCM_pos_H2 and SASA_phobic_Fv.
Figure 2. Correlation coefficients for the best two-feature linear, support vector regression (SVR) and k-nearest neighbors (KNN) regression models trained using all 20 data and LOOCV. The features for the linear regression model are SCM_neg_H2 and SASA_phobic_H3. The features for the SVR and KNN models are both SCM_pos_H2 and SASA_phobic_Fv.CC BY-NC · PubMed Central
Figure 3. Viscosity at 150 mg/mL at pH 6.0 in histidine buffer of all 20 mAbs studied in this work. The red dashed line indicates the low/high viscosity cutoff (30 cP). A histogram showing the experimental viscosity at 150 mg/ml of 20 mAbs. The viscosity of mAb10, mAb12, mAb13, mAb14, mAb16 and mAb20 are above the high viscosity threshold 30 cP.
Figure 3. Viscosity at 150 mg/mL at pH 6.0 in histidine buffer of all 20 mAbs studied in this work. The red dashed line indicates the low/high viscosity cutoff (30 cP). A histogram showing the experimental viscosity at 150 mg/ml of 20 mAbs. The viscosity of mAb10, mAb12, mAb13, mAb14, mAb16 and mAb20 are above the high viscosity threshold 30 cP.CC BY-NC · PubMed Central
Figure 4. The relationship of viscosity at 150 mg/ml with the diffusion interaction coefficients (kD) for the 20 mAbs in this study. Open circles showing the viscosity on the y-axis and kD on the x-axis. Five high viscosity mAbs have kD values < −5 mL/g (mAb10, mAb12, mAb13, mAb16 and mAb20).
Figure 4. The relationship of viscosity at 150 mg/ml with the diffusion interaction coefficients (kD) for the 20 mAbs in this study. Open circles showing the viscosity on the y-axis and kD on the x-axis. Five high viscosity mAbs have kD values < −5 mL/g (mAb10, mAb12, mAb13, mAb16 and mAb20).CC BY-NC · PubMed Central

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 50 references

Cited by

Sorted by citations

See all 103

Related

Metadata

Authors
Lai, P.-K., Gallegos, A., Mody, N., Sathish, H. A., & Trout, B. L.
Affiliations
  • Stevens Institute of Technology (US)
  • AstraZeneca (United States) (US)
  • Massachusetts Institute of Technology (US)
Corresponding author
Trout, Bernhardt L.
ORCID
Venue
mAbs
Publisher
Informa UK Limited
Published
2022-01-25
Volume
14
Issue
1
Pages
2026208-2026208
ISSN
  • 1942-0862 (ISSN-L)
  • 1942-0870
DOI
10.1080/19420862.2022.2026208
PMC
PMC8794240
OpenAlex
W4207044828
Cited by
103
References
50
Citations by year
2026: 34 · 2025: 22 · 2024: 28 · 2023: 13 · 2022: 6
FWCI
5.63
Type
journal article
Language
en
Open access
Licence
Locations
  • mAbs (publishedVersion, cc-by-nc)
  • PubMed Central (publishedVersion, cc-by-nc)
  • PubMed (publishedVersion)
  • DSpace@MIT (Massachusetts Institute of Technology) (submittedVersion, cc-by-nc)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Funders
The author(s) reported there is no funding associated with the work featured in this article
Topics
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Protein purification and stability
  • Life Sciences › Immunology and Microbiology › Immunology › Monoclonal and Polyclonal Antibodies Research
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Protein Structure and Dynamics
Keywords
antibody aggregation, viscosity prediction, high-concentration formulations, therapeutic proteins, monoclonal antibodies, k-nearest neighbors regression, logistic regression, hydrophobic residues, solvent accessible surface area, antibody stability, drug formulation development
MeSH terms
Machine Learning, Antibodies, Monoclonal, Humans, Viscosity, Molecular Dynamics Simulation, Protein Aggregates

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.

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