Page 305 - ebook

[F. Others] F-9

Deep Y: AI-based biosimilarity assessment platform for

antibody drugs using intact glycoproteins analysis

Dae Sik Cho¹,², Hee Youn Hwang³, Myung Jin Oh¹,², Hyun Joo An¹,²*

¹Graduate School of Analytical Science and Technology, Chungnam National University, Daejeon 34134, Korea,

²Asia-Pacific Glycomics Reference Site, Chungnam National University, Daejeon 34134, Korea, ³Division of

Bioconvergence Analysis, Korea Basic Science Institute, Ochang 28119, Korea

A biosimilar is a biological drug that is nearly identical to the original product. Glycosylation on antibody drugs
typically exhibits a high degree of complexity and can be very sensitive to changes in the manufacturing process.

This glycosylation has the greatest impact on maintaining consistent quality and clinical performance throughout
the biosimilar lifecycle. Nevertheless, the objective criteria for evaluating similarity in terms of glycosylation in

biosimilar development are still ambiguous and difficult. Therefore, we developed DeepY, a deep learning platform
for assessing the biosimilarity of mAbs using intact glycoprotein analysis by LC-Q-TOF MS. A total of six original

and biosimilar were secured, including Trastuzumab, Infliximab, Adalimumab, and Bevacizumab, and the
glycoproteome forms were analyzed for biosimilarity evaluation. A total 2,880 spectra and 86,400 glycoform data

including test set, training set, and validation set were generated for development of an artificial intelligence
algorithm using convolutional and fully connected neural network. Decoy data also was created to improve a data

extraction algorithm. Deep Y can now determine the biosimilarity of mAbs with about 99% accuracy and is available
on the website (http://Deepy.kr). There is no doubt that DeepY will be a groundbreaking scientific assistant for the
development of antibody biosimilars.