Top Tweets for #STRINGdb

almost 2 years ago

Glad to share our preprint: SPACE: STRING Proteins As Complementary Embeddings: https://t.co/Q41BXVvTfT Great thanks to all the contributors: Damian Szklarczyk, Christian von Mering, and @larsjuhljensen #bioinformatics #proteinEmbeddings #STRINGdb #computationalBiology

Biology+AI Daily @BiologyAIDaily

almost 2 years ago

SPACE: STRING Proteins as Complementary Embeddings • Presenting SPACE: a collection of embeddings that aligns protein network and sequence data across 1,322 eukaryotic species in the STRING database. • Key innovation: SPACE uses the FedCoder framework to align species-specific protein network embeddings, creating a unified, cross-species embedding space while preserving species-specific network integrity. • Complementary to sequence-based embeddings, SPACE integrates protein-protein interaction networks and orthology relations, providing a holistic view of protein functions and interactions. • Demonstrated performance: SPACE excels in subcellular localization and protein function prediction tasks, consistently outperforming individual sequence or network embeddings in precision and recall metrics. • Applications include cross-species predictions for subcellular localization, functional annotations, and translational research, offering a scalable, efficient tool for bioinformatics and computational biology. • Precomputed embeddings and tools are made publicly available in STRING v12.0, providing an accessible resource for the scientific community. @larsjuhljensen @DeweiHuX 💻Code: https://t.co/31il2ue7it 📜Paper: https://t.co/aGExOG5yos #ProteinEmbeddings #Bioinformatics #MachineLearning #STRINGDatabase #ComputationalBiology

BiologyAIDaily's tweet photo. SPACE: STRING Proteins as Complementary Embeddings

• Presenting SPACE: a collection of embeddings that aligns protein network and sequence data across 1,322 eukaryotic species in the STRING database.

• Key innovation: SPACE uses the FedCoder framework to align species-specific protein network embeddings, creating a unified, cross-species embedding space while preserving species-specific network integrity.

• Complementary to sequence-based embeddings, SPACE integrates protein-protein interaction networks and orthology relations, providing a holistic view of protein functions and interactions.

• Demonstrated performance: SPACE excels in subcellular localization and protein function prediction tasks, consistently outperforming individual sequence or network embeddings in precision and recall metrics.

• Applications include cross-species predictions for subcellular localization, functional annotations, and translational research, offering a scalable, efficient tool for bioinformatics and computational biology.

• Precomputed embeddings and tools are made publicly available in STRING v12.0, providing an accessible resource for the scientific community.

@larsjuhljensen @DeweiHuX
💻Code: https://t.co/31il2ue7it
📜Paper: https://t.co/aGExOG5yos

#ProteinEmbeddings #Bioinformatics #MachineLearning #STRINGDatabase #ComputationalBiology

168

Top Tweets for #STRINGdb

Last Seen Hashtags on Sotwe

Trends for you

Most Popular Users