AIMC Topic: Proteins

Clear Filters Showing 21 to 30 of 1967 articles

Exploring Protein-Protein Docking Tools: Comprehensive Insights into Traditional and Deep-Learning Approaches.

Journal of chemical information and modeling
Protein-protein interactions are crucial for numerous biological activities such as signaling, enzyme catalysis, gene expression regulation, cell adhesion, immune response, and drug action. Structural characterization of these interactions can elucid...

EquiCPI: SE(3)-Equivariant Geometric Deep Learning for Structure-Aware Prediction of Compound-Protein Interactions.

Journal of chemical information and modeling
Accurate prediction of compound-protein interactions (CPI) remains a cornerstone challenge in computational drug discovery. While existing sequence-based approaches leverage molecular fingerprints or graph representations, they critically overlook th...

Medium-sized protein language models perform well at transfer learning on realistic datasets.

Scientific reports
Protein language models (pLMs) can offer deep insights into evolutionary and structural properties of proteins. While larger models, such as the 15 billion parameter model ESM-2, promise to capture more complex patterns in sequence space, they also p...

SE(3)-equivariant ternary complex prediction towards target protein degradation.

Nature communications
Targeted protein degradation (TPD) has rapidly emerged as a powerful modality for drugging previously "undruggable" proteins. TPD employs small molecules like PROTACs and molecular glue degraders (MGD) to induce target protein degradation via the for...

A fast (CNN + MCWS-transformer) based architecture for protein function prediction.

Statistical applications in genetics and molecular biology
The transformer model for sequence mining has brought a paradigmatic shift to many domains, including biological sequence mining. However, transformers suffer from quadratic complexity, i.e., O( ), where is the sequence length, which affects the tra...

HADDOCK3: A Modular and Versatile Platform for Integrative Modeling of Biomolecular Complexes.

Journal of chemical information and modeling
HADDOCK is a widely used resource for integrative modeling of a variety of biomolecular complexes that is able to incorporate experimental knowledge into physics-based calculations during complex prediction, refinement, scoring and analysis. Here we ...

Improved Prediction of Drug-Protein Interactions through Physics-Based Few-Shot Learning.

Journal of chemical information and modeling
Accurate prediction of drug-protein interactions is crucial for drug discovery. Due to the bottleneck of traditional scoring functions, many machine learning scoring functions (MLSFs) have been proposed for structure-based drug screening. However, ex...

The continuous evolution of biomolecular force fields.

Structure (London, England : 1993)
Biomolecular force fields have continuously evolved to improve their accuracy and broaden their applications in biological and therapeutic discoveries. The rapid adaptation of advanced computational technology, in particular the recent deep learning ...

'Intelligent' proteins.

Cellular and molecular life sciences : CMLS
We present an idea of protein molecules that challenges the traditional view of proteins as simple molecular machines and suggests instead that they exhibit a basic form of "intelligence". The idea stems from suggestions coming from Integrated Inform...

MMSol: Predicting Protein Solubility with an Antinoise Multimodal Deep Model.

Journal of chemical information and modeling
Protein solubility plays a critical role in determining its biological function, such as enabling proper protein delivery and ensuring that proteins remain soluble during cellular processes or therapeutic applications. Accurate prediction of protein ...