Back

Epi4Ab: A data-driven prediction model of conformational epitopes for specific antibody VH/VL families and CDR H3/L1 sequences.

Tran, N. D.; Subramani, K.; Su, C. T.-T.

2025-03-15 bioinformatics
10.1101/2025.03.13.642979 bioRxiv
Show abstract

Antibodies recognize antigens via complementary and structurally dependent mechanisms. Therefore, inclusion of antibody inputs is crucial for accurate epitope prediction. Given limited availability of antibody-antigen complex structures, it is necessary that any epitope prediction model requires minimal yet sufficient antibody inputs to ensure precise epitope identification. To address this need, we introduce Epi4Ab, an antibody-specific epitope prediction model, which focuses on identifying unique in-contact antigen residues for a given antibody. Epi4Ab requires minimal antibody inputs, specifically VH/VL families and CDR H3/L1 sequences.

Published in mAbs (predicted rank #1) · training set

Matching journals

The top 5 journals account for 50% of the predicted probability mass.

mAbs · published here
○ 32 papers in training set
Top 0.1%
18.2%
Similar papers in this journal
2
Computational and Structural Biotechnology Journal
● 242 papers in training set
Top 0.1%
12.6%
Similar papers in this journal
3
Scientific Reports
○ 3612 papers in training set
Top 5%
9.6%
Similar papers in this journal
4
Briefings in Bioinformatics
◐ 354 papers in training set
Top 1%
6.6%
Similar papers in this journal
5
Frontiers in Immunology
○ 638 papers in training set
Top 3%
4.2%
Similar papers in this journal
50% of probability mass above
6
iScience
○ 1154 papers in training set
Top 5%
4.0%
7
Journal of Chemical Information and Modeling
● 238 papers in training set
Top 1%
4.0%
8
Bioinformatics
◐ 1204 papers in training set
Top 5%
4.0%
9
Antibody Therapeutics
◐ 16 papers in training set
Top 0.1%
3.2%
10
PLOS Computational Biology
● 1863 papers in training set
Top 10%
3.2%
11
Nature Communications
○ 5641 papers in training set
Top 37%
3.1%
12
ImmunoInformatics
○ 12 papers in training set
Top 0.1%
2.4%
13
Computers in Biology and Medicine
○ 128 papers in training set
Top 2%
2.3%
14
Protein Science
○ 246 papers in training set
Top 2%
2.3%
15
Communications Biology
○ 993 papers in training set
Top 11%
2.1%
16
Bioinformatics Advances
◐ 203 papers in training set
Top 3%
1.4%
17
PLOS ONE
● 5266 papers in training set
Top 55%
1.0%
18
Frontiers in Bioinformatics
○ 49 papers in training set
Top 2%
0.8%
19
Nature Machine Intelligence
○ 70 papers in training set
Top 2%
0.8%
20
International Journal of Molecular Sciences
○ 494 papers in training set
Top 16%
0.8%
21
Proteins: Structure, Function, and Bioinformatics
○ 88 papers in training set
Top 2%
0.6%
22
Biomolecules
○ 100 papers in training set
Top 4%
0.6%

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.