Article

Positional SHAP (PoSHAP) for Interpretation of Machine Learning Models Trained from Biological Sequences

2021-03-05

Abstract excerpt

Machine learning with multi-layered artificial neural networks, also known as “deep learning,” is effective for making biological predictions. However, model interpretation is challenging, especially for sequential input data used with recurrent neural network architectures. Here, we introduce a framework called “Positional SHAP” (PoSHAP) to interpret models trained from biological sequences by utilizing SHapely A...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: 4f644bcd-90bc-5886-b14f-5700aeb0a6ca
DOI: 10.1101/2021.03.04.433939

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Positional SHAP (PoSHAP) for Interpretation of Machine Learning Models Trained from Biological SequencesDOI 10.1101/2021.03.04.433939Read

Comprehensive evaluation and interpretative insights of peptide-HLA binding prediction tools using explainable artificial intelligenceSemantic proximity Read

Attention mechanism-based deep learning pan-specific model for interpretable MHC-I peptide binding predictionSemantic proximity Read

Deep learning pan-specific model for interpretable MHC-I peptide binding prediction with improved attention mechanism.Semantic proximity Read

Building Trust in Deep Learning-based Immune Response Predictors with Interpretable ExplanationsSemantic proximity Read

Building Trust in Deep Learning-based Immune Response Predictors with Interpretable ExplanationsSemantic proximity Read

Learning probabilistic protein-DNA recognition codes from DNA-binding specificities using structural mappings.Semantic proximity Read

Learning probabilistic protein-DNA recognition codes from DNA-binding specificities using structural mappingsSemantic proximity Read

Pan-specific Multi Allelic pHLA Presenting Prediction through Resnet-based and LSTM-based Neural NetworksSemantic proximity Read

Disentangled multimodal evolutionary representations for cross-virus predictive modeling of antigenic changeSemantic proximity Read

DeepSeqPanII: an interpretable recurrent neural network model with attention mechanism for peptide-HLA class II binding predictionSemantic proximity Read

An Explainable AI Framework Integrating Machine and Deep Learning Models for Multi-Species DNA Functional Group ClassificationSemantic proximity Read

Paying Attention to Attention: High Attention Sites as Indicators of Protein Family and Function in Language ModelsSemantic proximity Read