Machine Learning Feature Selection for Predicting High Concentration Therapeutic Antibody Aggregation

Lai, Pin-Kuang; Fernando, Amendra; Cloutier, Theresa K.; Kingsbury, Jonathan S.; Gokarn, Yatin R.; Halloran, Kevin T.; Calero-Rubio, César; Trout, Bernhardt L.

doi:10.1016/j.xphs.2020.12.014

Cited by 34 publications

(43 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We applied a machine learning protocol developed from our previous work 24 to predict antibody aggregation. Thirty-five structural descriptors, including solvent-accessible surface area of hydrophobic residues (SASA_phobic), solvent-accessible surface area of hydrophilic residues (SASA_philic), SAP, spatial negative charge map (SCM_neg) and spatial positive charge map (SCM_pos) on the complementarity-determining region (CDR) loops and Fv region, were used for feature selection and model building ( Table 1 ).…”

Section: Resultsmentioning

confidence: 99%

“… 23 Moreover, a machine learning-based model that was trained on 21 mAbs was developed to predict therapeutic antibody aggregation rates at 150 mg/ml using structural-based features extracted from MD simulations. 24 …”

Section: Introductionmentioning

confidence: 99%

“…The molecular origin of antibody aggregation and viscosity remains unclear, but hydrophobicity and charge are considered to be the two major driving forces. 23 , 25 Recent studies that evaluated the aggregation and viscosity of 21 mAbs showed no overlap between those with high aggregation rates and those with high viscosity, 9 , 24 indicating that the underlying mechanisms of aggregation and viscosity are different. Machine learning provides a great tool to find the most relevant features for aggregation and viscosity, respectively.…”

Section: Introductionmentioning

confidence: 99%

“…Previous machine learning research on predicting antibody aggregation rates and viscosity used data derived from commercial mAbs, which may have gone through molecule and/or formulation optimization for stability. 9 , 24 Although predictive models could be applied to mAbs in early development, such studies have not been previously reported. In this work, we measured the aggregation rates and viscosity at 150 mg/ml of 20 preclinical and clinical stage mAbs.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

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

Lai

Gallegos

Mody

et al. 2022

mAbs

Self Cite

View full text Add to dashboard Cite

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.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

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

Lai

Gallegos

Mody

et al. 2022

mAbs

Self Cite

View full text Add to dashboard Cite

show abstract

“…While the current dataset of 260 mAbs is already larger than previous mAbs developability studies 6,22,23,[25][26][27][28][29] , it is still smaller than most machine learning projects in which millions of data points were used for training 30 . To overcome the data scarcity, we propose an end-to-end machine learning framework for solubility prediction with transfer learning from pretrained protein language model (ESM-1b) 20 (Figure 2).…”

Section: Pretrained Protein Language Model Embeddings Enable the Use Of Small Labeled Dataset And Simple Architecture For Mab Solubility mentioning

confidence: 99%

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

Deep learning framework for peak detection at the intact level of therapeutic proteins

Nikita,

Bhattacharya,

Manocha

et al. 2024

J of Separation Science

View full text Add to dashboard Cite

While automated peak detection functionalities are available in commercially accessible software, achieving optimal true positive rates frequently necessitates visual inspection and manual adjustments. In the initial phase of this study, hetero‐variants (glycoforms) of a monoclonal antibody were distinguished using liquid chromatography‐mass spectrometry, revealing discernible peaks at the intact level. To comprehensively identify each peak (hetero‐variant) in the intact‐level analysis, a deep learning approach utilizing convolutional neural networks (CNNs) was employed in the subsequent phase of the study. In the current case study, utilizing conventional software for peak identification, five peaks were detected using a 0.5 threshold, whereas seven peaks were identified using the CNN model. The model exhibited strong performance with a probability area under the curve (AUC) of 0.9949, surpassing that of partial least squares discriminant analysis (PLS‐DA) (probability AUC of 0.8041), and locally weighted regression (LWR) (probability AUC of 0.6885) on the data acquired during experimentation in real‐time. The AUC of the receiver operating characteristic curve also illustrated the superior performance of the CNN over PLS‐DA and LWR.

show abstract

Machine Learning Feature Selection for Predicting High Concentration Therapeutic Antibody Aggregation

Cited by 34 publications

References 43 publications

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

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

solPredict: Antibody apparent solubility prediction from sequence by transfer learning

Deep learning framework for peak detection at the intact level of therapeutic proteins

Contact Info

Product

Resources

About