2021
DOI: 10.1101/2021.02.12.430941
|View full text |Cite
Preprint
|
Sign up to set email alerts
|

DLAB - Deep learning methods for structure-based virtual screening of antibodies

Abstract: Antibodies are one of the most important classes of pharmaceuticals, with over 80 approved molecules currently in use against a wide variety of diseases. The drug discovery process for antibody therapeutic candidates however is time- and cost-intensive and heavily reliant on in-vivo and in-vitro high throughput screens. Here, we introduce a framework for structure-based deep learning for antibodies (DLAB) which can virtually screen putative binding antibodies against antigen targets of interest. DLAB is built … Show more

Help me understand this report
View published versions

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

3
27
0

Year Published

2021
2021
2023
2023

Publication Types

Select...
6
2
1

Relationship

1
8

Authors

Journals

citations
Cited by 15 publications
(30 citation statements)
references
References 47 publications
(59 reference statements)
3
27
0
Order By: Relevance
“…The authors included the spatial arrangement of the paratope in these known complexes as multi-dimensional features for training a CNN followed by a geometric neural network. Schneider et al (67) used Abodybuilder (87) to model the 3D structure of the antibody alone, using threading from known antibody structures, followed by a docking step to generate multiple binding poses and used an ML approach to provide a better ranking of the binding poses (as compared to the ranking provided by the docking scoring function). Interestingly, in both methods, including structures from alignment or threading to other known antibody-antigen binding structures was necessary to achieve high accuracy.…”
Section: Structural Information Improves Sequence-based Conformational Paratope-epitope Predictionmentioning
confidence: 99%
“…The authors included the spatial arrangement of the paratope in these known complexes as multi-dimensional features for training a CNN followed by a geometric neural network. Schneider et al (67) used Abodybuilder (87) to model the 3D structure of the antibody alone, using threading from known antibody structures, followed by a docking step to generate multiple binding poses and used an ML approach to provide a better ranking of the binding poses (as compared to the ranking provided by the docking scoring function). Interestingly, in both methods, including structures from alignment or threading to other known antibody-antigen binding structures was necessary to achieve high accuracy.…”
Section: Structural Information Improves Sequence-based Conformational Paratope-epitope Predictionmentioning
confidence: 99%
“…Computational modelling tools have allowed researchers to bridge this gap by predicting large numbers of antibody structures to a high level of accuracy [3, 4]. For example, models of antibody structures have recently been used for virtual screening [5] and to identify coronavirus-binding antibodies that bind the same epitope with very different sequences [6].…”
Section: Introductionmentioning
confidence: 99%
“…For instance, EpiPred 130 measures the conformational matching of an input pair of antibody and antigen structures. DLAB-Re 131 models the antibody structure from its sequence, 132 generates docking to the antigen structure and uses a convolutional neural network (CNN) to predict the paratope-epitope complementarity of a pose as a re-ranking score, therefore predicting both epitope and paratope.…”
Section: Learnability Of Antibody–antigen Bindingmentioning
confidence: 99%