Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
October 11, 2025Open Access

Macon: Enhance Protein Mutation Representation using Contrastive Learning with Effect Prediction on Protein–protein Interactions

View Full Paper
Ask AI
Bookmark
Share

Authors

WLWeihao LiZLZhe LiuGLGuan Ning Lin

Discussion

Loading...

Member takes

Overview

Macon demonstrates improved prediction of mutation effects in protein-protein interactions, suggesting robust representation methods are crucial for understanding functional variants.

Key Points

  • Macon achieves an accuracy of 0.73 on predicting the effects of mutations in protein-protein interactions.
  • The two-stage framework utilizes contrastive learning to differentiate between wild-type and mutant protein sequences.
  • Integration of contrastive embeddings with protein language model features enhances classification of diverse mutation effects.
  • Results indicate the potential of Macon in facilitating functional interpretation of protein variants in disease mechanisms.

Cite This Study

Li et al. (2025) studied this question.

synapsesocial.com/papers/68e9b1d9ba7d64b6fc132d3ehttps://doi.org/10.21203/rs.3.rs-7469880/v1
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Identifying driver mutations in sequenced cancer genomes: computational approaches to enable precision medicine2014 · 237 citations
  2. 2Predicting Protein–Protein Interactions from the Molecular to the Proteome Level2016 · 392 citations
  3. 3ProAffiMuSeq: sequence-based method to predict the binding free energy change of protein–protein complexes upon mutation using functional classification2019 · 46 citations
  4. 4Mutations at protein-protein interfaces: Small changes over big surfaces have large impacts on human health2016 · 173 citations
  5. 5Evaluating Protein Transfer Learning with TAPE2019 · 703 citations