TraitProtNet: Deciphering the Genome for Trait Prediction with Interpretable Deep Learning
Wang, S.
Show abstract
Genome data is far from fully explored. We present TraitProtNet, an innovative deep learning framework for predictive trait profiling in fungi, leveraging genome data and pretrained language models. The use of Integrated Gradients and bioinformatic analysis provides insights into the models interpretability, complementing traditional omics by highlighting the difference between protein importance and expression levels. This framework offers significant potential for future applications in both agriculture and medicine.
Matching journals
The top 5 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Accurate plant pathogen effector protein classification ab initio with deepredeff, an ensemble of convolutional neural networks 95%
- HiTaC: a hierarchical taxonomic classifier for fungal ITS sequences compatible with QIIME2 93%
- DeepSEA: an alignment-free deep learning tool for functional annotation of antimicrobial resistance proteins 93%
Similar papers in this journal
"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.