Author: Brandon Malone; Boris Simovski; Clement Moline; Jun Cheng; Marius Gheorghe; Hugues Fontenelle; Ioannis Vardaxis; Simen Tennoe; Jenny-Ann Malmberg; Richard Stratford; Trevor Clancy
Title: Artificial intelligence predicts the immunogenic landscape of SARS-CoV-2: toward universal blueprints for vaccine designs Document date: 2020_4_21
ID: cm30gyd8_56
Snippet: The raw input datasets are first transformed into binary tracks. For each class I HLA dataset, the epitope scores are transformed to binary (0 and 1) values, such that amino-acid positions with predicted epitope scores larger than 0.7 (for AP) and larger than 0.5 (for IP) are assigned the value 1 (positively predicted epitope), and the rest are assigned the value 0. Similarly, for class II HLA datasets, amino-acid positions with predicted epitope.....
Document: The raw input datasets are first transformed into binary tracks. For each class I HLA dataset, the epitope scores are transformed to binary (0 and 1) values, such that amino-acid positions with predicted epitope scores larger than 0.7 (for AP) and larger than 0.5 (for IP) are assigned the value 1 (positively predicted epitope), and the rest are assigned the value 0. Similarly, for class II HLA datasets, amino-acid positions with predicted epitope scores smaller than 10 are assigned the value 1, otherwise 0. These thresholds were relatively conservative. Each binary track can effectively be presented as a list of intervals of consecutive ones -segments, with consecutive zeros in between, forming inter-segments or gaps.
Search related documents:
Co phrase search for related documents- amino acid and class ii HLA dataset: 1
- amino acid and epitope score: 1, 2, 3
- amino acid and HLA dataset: 1, 2
- amino acid position and class HLA dataset: 1
- amino acid position and class ii HLA dataset: 1
- amino acid position and HLA dataset: 1
- class HLA dataset and HLA dataset: 1
- class ii HLA dataset and HLA dataset: 1
Co phrase search for related documents, hyperlinks ordered by date