Skip to main content
Fig. 4 | BMC Bioinformatics

Fig. 4

From: MATHLA: a robust framework for HLA-peptide binding prediction integrating bidirectional LSTM and multiple head attention mechanism

Fig. 4

Heatmap of weight scores of two heads (head 0 and 1) in the attention model for both HLA pseudo-sequences and peptide sequences. Weight scores of the test data associated with HLA-A, B and C supergroups are displayed separately. Each row is corresponding to the position of amino acid residue on HLA pseudo-sequence and peptide sequence. Each column corresponds to peptide of different lengths (8aa to 15aa)

Back to article page

BMC Bioinformatics

ISSN: 1471-2105

Contact us