@KevinKaichuang: When training protein language models, people usually discard metagenomic proteins that don't cluster with at least 1 o…

X AI KOLs Timeline Papers

Summary

Research indicates that discarding singleton proteins in metagenomic datasets during the training of protein language models is likely incorrect, based on findings from a collaborative study.

When training protein language models, people usually discard metagenomic proteins that don't cluster with at least 1 other protein (singletons). With @riavinod_ @Samir_char @avapamini @lorin_crawford , we show that this is probably not the right strategy. https://t.co/x0pdjvevfa
Original Article
View Cached Full Text

Cached at: 08/18/26, 02:23 AM

When training protein language models, people usually discard metagenomic proteins that don’t cluster with at least 1 other protein (singletons).

With @riavinod_ @Samir_char @avapamini @lorin_crawford , we show that this is probably not the right strategy. https://t.co/x0pdjvevfa

Similar Articles

ProtSent: Protein Sentence Transformers

arXiv cs.LG

This article introduces ProtSent, a contrastive fine-tuning framework for protein language models that improves embedding quality for downstream tasks like remote homology detection and structural retrieval.

Better Protein Function Prediction by Modeling Survivorship Bias

arXiv cs.LG

This paper introduces Evo-PU, a positive-unlabeled learning framework that models survivorship bias in protein sequence data by leveraging evolutionary mutation processes. The authors demonstrate that Evo-PU outperforms standard PU methods and protein language models in predicting protein functionality for influenza, RSV, and SARS-CoV-2.