Article

Pool PaRTI: A PageRank-Based Pooling Method for Identifying Critical Residues and Enhancing Protein Sequence Representations

2024-10-05

Abstract excerpt

<h4>Motivation</h4> Protein language models produce token-level embeddings for each residue, resulting in an output matrix with dimensions that vary based on sequence length. However, downstream machine learning models typically require fixed-length input vectors, necessitating a pooling method to compress the output matrix into a single vector representation of the entire protein. Traditional pooling methods oft...

Topics

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

Identifiers and source

Literature Corpus work: d2e5a3ce-b8f9-5265-b7f0-cb4cc9f7e11d
DOI: 10.1101/2024.10.04.616701

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Pool PaRTI: A PageRank-Based Pooling Method for Identifying Critical Residues and Enhancing Protein Sequence RepresentationsDOI 10.1101/2024.10.04.616701Read

Mixture of Experts Enable Efficient and Effective Protein Understanding and DesignSemantic proximity Read

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

ProtSyntax: a protein large language model for decoding post-translational modification syntax and functionSemantic proximity Read

Interpreting Protein Language Models: high attention sites predict functional regionsSemantic proximity Read

Contrasting Sequence with Structure: Pre-training Graph Representations with PLMsSemantic proximity Read

ProtAttn-QuadNet: An attention-based deep learning framework for protein–protein interaction prediction using ProtBERT embeddingsSemantic proximity Read

SETH predicts nuances of residue disorder from protein embeddingsSemantic proximity Read

Fast and accurate protein function prediction from sequence through pretrained language model and homology-based label diffusionSemantic proximity Read

Applying Protein Language Models Using Limited Dataset. Sequence-Based Hot Spot Prediction in Protein Interactions Using AutoGluonSemantic proximity Read

PIPENN-EMB: ensemble net and protein embeddings generalise protein interface prediction beyond homologySemantic proximity Read

Fine-Tuning Protein Language Models Unlocks the Potential of Underrepresented Viral ProteomesSemantic proximity Read