Ultradilute Measurements of Self-Association for the Identification of Antibodies with Favorable High-Concentration Solution Properties

Starr, Charles G.; Makowski, Emily K.; Wu, Lina; Berg, Brendan; Kingsbury, Jonathan S.; Gokarn, Yatin R.; Tessier, Peter M.

doi:10.1021/acs.molpharmaceut.1c00280

Cited by 28 publications

(46 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A broad range of solubility was observed in IgG4 molecules, whereas IgG1 mAbs tend to be highly soluble under H6 condition. Similarly, previous study reports that IgG1 and IgG4 mAbs show totally different behavior in terms of viscosity, opalescence, and thermostability 6,24,25 . Therefore, a dataset consisting of different subclasses is critical to the development of computational predictors that can be generalizable to diverse mAbs.…”

Section: Dataset Constructionsupporting

confidence: 74%

solPredict: Antibody apparent solubility prediction from sequence by transfer learning

Feng

Jiang

Shih

et al. 2021

Preprint

View full text Add to dashboard Cite

There is growing interest in developing therapeutic mAbs for the route of subcutaneous administration for several reasons, including patient convenience and compliance. This requires identifying mAbs with superior solubility that are amenable for high-concentration formulation development. However, early selection of developable antibodies with optimal high-concentration attributes remains challenging. Since experimental screening is often material and labor intensive, there is significant interest in developing robust in silico tools capable of screening thousands of molecules based on sequence information alone. In this paper, we present a strategy applying protein language modeling, named solPredict, to predict the apparent solubility of mAbs in histidine (pH 6.0) buffer condition. solPredict inputs embeddings extracted from pretrained protein language model from single sequences into a shallow neutral network. A dataset of 220 diverse, in-house mAbs, with extrapolated protein solubility data obtained from PEG-induced precipitation method, were used for model training and hyperparameter tuning through five-fold cross validation. An independent test set of 40 mAbs were used for model evaluation. solPredict achieves high correlation with experimental data (Spearman correlation coefficient = 0.86, Pearson correlation coefficient = 0.84, R2 = 0.69, and RMSE = 4.40). The output from solPredict directly corresponds to experimental solubility measurements (PEG %) and enables quantitative interpretation of results. This approach eliminates the need of 3D structure modeling of mAbs, descriptor computation, and expert-crafted input features. The minimal computational expense of solPredict enables rapid, large-scale, and high-throughput screening of mAbs during early antibody discovery.

show abstract

Section: Dataset Constructionsupporting

confidence: 74%

solPredict: Antibody apparent solubility prediction from sequence by transfer learning

Feng

Jiang

Shih

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…EM1 and EM2 also have attractive, drug-like biophysical properties, as they display low levels of self-association (CS-SINS scores <0.35) in a standard antibody formulation (pH 6 and 10 mM histidine), which suggests the antibody mutants will display low viscosity and opalescence in concentrated antibody formulations (150 mg/mL; Fig. 6E ) 47 . Moreover, these antibody variants display high thermal stability with melting temperatures >75 °C (Fig.…”

Section: Resultsmentioning

confidence: 99%

“…CS-SINS was measured as reported previously 47 . Briefly, capture antibody (Jackson ImmunoResearch, 109-005-008) and polylysine (90%:10% w/w ratio respectively; Fisher Scientific, ICN19454405) were immobilized on concentrated gold nanoparticles and incubated overnight.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Co-optimization of therapeutic antibody affinity and specificity using machine learning models that generalize to novel mutational space

et al. 2022

Self Cite

View full text Add to dashboard Cite

Therapeutic antibody development requires selection and engineering of molecules with high affinity and other drug-like biophysical properties. Co-optimization of multiple antibody properties remains a difficult and time-consuming process that impedes drug development. Here we evaluate the use of machine learning to simplify antibody co-optimization for a clinical-stage antibody (emibetuzumab) that displays high levels of both on-target (antigen) and off-target (non-specific) binding. We mutate sites in the antibody complementarity-determining regions, sort the antibody libraries for high and low levels of affinity and non-specific binding, and deep sequence the enriched libraries. Interestingly, machine learning models trained on datasets with binary labels enable predictions of continuous metrics that are strongly correlated with antibody affinity and non-specific binding. These models illustrate strong tradeoffs between these two properties, as increases in affinity along the co-optimal (Pareto) frontier require progressive reductions in specificity. Notably, models trained with deep learning features enable prediction of novel antibody mutations that co-optimize affinity and specificity beyond what is possible for the original antibody library. These findings demonstrate the power of machine learning models to greatly expand the exploration of novel antibody sequence space and accelerate the development of highly potent, drug-like antibodies.

show abstract

“…The training dataset can be augmented by a combinatorial design of different antibody regions to improve the deep learning model. In addition, biophysical properties from experiments such as melting temperature, retention time from hydrophobic interaction chromatography, and self-interaction from charge-stabilized self-interaction nanoparticle spectroscopy 43 could be trained by the CNN model if combined with high throughput screening to generate larger datasets. These are potential future research topics.…”

Section: Discussionmentioning

confidence: 99%

DeepSCM: an efficient convolutional neural network surrogate model for the screening of therapeutic antibody viscosity

Lai

2022

Preprint

View full text Add to dashboard Cite

Predicting high concentration antibody viscosity is essential for developing subcutaneous administration. Computer simulations provide promising tools to reach this aim. One such model is the spatial charge map (SCM) proposed by Agrawal and coworkers (mAbs. 2015, 8(1):43–48). SCM applies molecular dynamics simulations to calculate a score for the screening of antibody viscosity at high concentrations. However, molecular dynamics simulations are computationally costly and require structural information, a significant application bottleneck. In this work, high throughput computing was performed to calculate the SCM scores for 6596 nonredundant antibody variable regions. A convolutional neural network surrogate model, DeepSCM, requiring only sequence information, was then developed based on this dataset. The linear correlation coefficient of the DeepSCM and SCM scores achieved 0.9 on the test set (N=1320). The DeepSCM model was applied to screen the viscosity of 38 therapeutic antibodies that SCM correctly classified and resulted in only one misclassification. The DeepSCM model will facilitate high concentration antibody viscosity screening. The code and parameters are freely available at https://github.com/Lailabcode/DeepSCM.

show abstract

Ultradilute Measurements of Self-Association for the Identification of Antibodies with Favorable High-Concentration Solution Properties

Cited by 28 publications

References 34 publications

solPredict: Antibody apparent solubility prediction from sequence by transfer learning

solPredict: Antibody apparent solubility prediction from sequence by transfer learning

Co-optimization of therapeutic antibody affinity and specificity using machine learning models that generalize to novel mutational space

DeepSCM: an efficient convolutional neural network surrogate model for the screening of therapeutic antibody viscosity

Contact Info

Product

Resources

About