Explore

Sabre Bio Lab

Antibody Design on AI-Lab Collaborative System

Sabre Platform

Sabre Platform

ROC-curves-of-deep-learning-models-CFD-score-and-three-traditional-machine-learning.png

0.1.2-5

Release Date

March 15, 2022

Property

Binding

Antigen

PD-1, PD-L1, TIGIT

Performance-POC

Lab

⁠

Publications

Publications

EpiBERTope: a sequence-based pre-trained BERT model improves linear and structural epitope prediction by learning long-distance protein interactions effectively

Author

Minjun Park, Seung-woo Seo, Eunyoung Park,

Jinhan Kim⁠

⁠

Publication

bioRxiv

Date Published

Mar 2022

doi

https://doi.org/10.1101/2022.02.27.481241

Abstract

Motivation Epitopes are the immunogenic regions of antigen that are recognized by antibodies in a highly specific manner to trigger an immune response. Predicting such regions is extremely difficult yet contains profound implications for complex mechanisms of humoral immunogenicity.

Results Here, we present a BERT-based epitope prediction model called EpiBERTope, a pre-trained model on the Swiss-Prot protein database, which can predict both linear and structural epitopes using protein sequences only. The model achieves an AUC of 0.922 and 0.667 for linear and structural epitope datasets respectively, outperforming all benchmark classification models including random forest, gradient boosting, naive Bayesian, and support vector machine models. In conclusion, EpiBERTope is a sequence-based model that captures content-based global interactions of antigen sequences, which will be transformative in epitope discovery with high specificity.

Download

https://www.biorxiv.org/content/10.1101/2022.02.27.481241v1.full.pdf

View Publication

https://www.biorxiv.org/content/10.1101/2022.02.27.481241v1

J-model: an open and social ensemble learning architecture for classification

Author

Jinhan Kim

Publication

PhD Thesis, School of Informatics, University of Edinburgh, UK

Date Published

Nov 2012

doi

Abstract

Ensemble learning is a promising direction of research in machine learning, in which an ensemble classifier gives better predictive and more robust performance for classification problems by combining other learners. Meanwhile agent-based systems provide frameworks to share knowledge from multiple agents in an open context. This thesis combines multi-agent knowledge sharing with ensemble methods to produce a new style of learning system for open environments. We now are surrounded by many smart objects such as wireless sensors, ambient communication devices, mobile medical devices and even information supplied via other humans. When we coordinate smart objects properly, we can produce a form of collective intelligence from their collaboration. Traditional ensemble methods and agent-based systems have complementary advantages and disadvantages in this context. Traditional ensemble methods show better classification performance, while agent-based systems might not guarantee their performance for classification. Traditional ensemble methods work as closed and centralised systems (so they cannot handle classifiers in an open context), while agent-based systems are natural vehicles for classifiers in an open context. We designed an open and social ensemble learning architecture, named J-model, to merge the conflicting benefits of the two research domains. The J-model architecture is based on a service choreography approach for coordinating classifiers. Coordination protocols are defined by interaction models that describe how classifiers will interact with one another in a peer-to-peer manner. The peer ranking algorithm recommends more appropriate classifiers to participate in an interaction model to boost the success rate of results of their interactions. Coordinated participant classifiers who are recommended by the peer ranking algorithm become an ensemble classifier within J-model. We evaluated J-model’s classification performance with 13 UCI machine learning benchmark data sets and a virtual screening problem as a realistic classification problem. J-model showed better performance of accuracy, for 9 benchmark sets out of 13 data sets, than 8 other representative traditional ensemble methods. J-model gave better results of specificity for 7 benchmark sets. In the virtual screening problem, J-model gave better results for 12 out of 16 bioassays than already published results. We defined different interaction models for each specific classification task and the peer ranking algorithm was used across all the interaction models. Our research contributions to knowledge are as follows. First, we showed that service choreography can be an effective ensemble coordination method for classifiers in an open context. Second, we used interaction models that implement task specific coordinations of classifiers to solve a variety of representative classification problems. Third, we designed the peer ranking algorithm which is generally and independently applicable to the task of recommending appropriate member classifiers from a classifier pool based on an open pool of interaction models and classifiers.

Download

https://era.ed.ac.uk/bitstream/handle/1842/7672/Kim2012.pdf?sequence=2&isAllowed=y

View Publication

https://era.ed.ac.uk/handle/1842/7672

⁠

News & Events

News & Events

BIO-Europe 2022 @ Leipzig, Germany