TY - JOUR
T1 - DeepSCM
T2 - An efficient convolutional neural network surrogate model for the screening of therapeutic antibody viscosity
AU - Lai, Pin Kuang
N1 - Publisher Copyright:
© 2022 The Author(s)
PY - 2022/1
Y1 - 2022/1
N2 - 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.
AB - 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.
KW - Antibody viscosity
KW - Convolutional neural network
KW - Deep learning
KW - Developability
KW - Molecular dynamics simulations
KW - Spatial charge map
UR - http://www.scopus.com/inward/record.url?scp=85129849783&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85129849783&partnerID=8YFLogxK
U2 - 10.1016/j.csbj.2022.04.035
DO - 10.1016/j.csbj.2022.04.035
M3 - Article
AN - SCOPUS:85129849783
VL - 20
SP - 2143
EP - 2152
JO - Computational and Structural Biotechnology Journal
JF - Computational and Structural Biotechnology Journal
ER -