AlphaFold3
PulseAugur coverage of AlphaFold3 — every cluster mentioning AlphaFold3 across labs, papers, and developer communities, ranked by signal.
- 2026-06-29 research_milestone AlphaFold3 was enhanced to more realistically predict biomolecular structures and interactions by integrating experimental data. source
4 day(s) with sentiment data
-
AI framework ContactSeek uses AlphaFold3 to improve genome editor specificity
A new AI-driven framework named ContactSeek has been developed to enhance the specificity of genome editors. This framework leverages predicted contact probabilities from AlphaFold3 to improve the precision of these gen…
-
Peking University releases open-source Claude Science alternative, OpenAI4S
Researchers from Peking University and Yuan Kong AI Agent Lab have released OpenAI4S, an open-source scientific research agent that mimics the capabilities of Anthropic's closed-source Claude Science. This new agent, av…
-
Chinese researchers use AlphaFold3 for precise gene editing tool design
Researchers from Peking University and East China Normal University have developed ContactSeek, an AI framework that leverages AlphaFold3's contact probability predictions. This new approach aims to enhance the precisio…
-
Shanghai AI Lab unveils Mobius architecture for scientific intelligence
Shanghai AI Laboratory has unveiled Intern-S2-Preview-397B, a new foundation model for scientific intelligence. This 397 billion parameter model utilizes a novel "Mobius" architecture that separates knowledge storage fr…
-
Molecule Mind launches AI operating system for biological R&D
Professor Xu Jinbo's team at Molecule Mind has officially launched MoleculeOS, an AI-native operating system designed for biological research and development. This system aims to transition AI from a single-point tool t…
-
New TCR-SRIM model offers interpretable epitope prediction
Researchers have developed TCR-SRIM, a novel model designed for predicting T cell receptor (TCR)-epitope binding. This model integrates protein language model embeddings with interpretable contact prototypes to analyze …
-
New framework optimizes protein ensemble generation, improving AlphaFold3 accuracy
Researchers have developed a new framework for optimizing protein ensemble generation, improving the accuracy and thermodynamic plausibility of models like AlphaFold3. This method optimizes latent representations to max…
-
AlphaFold3 enhanced with experimental data for realistic biomolecular predictions
AlphaFold3, a new AI model, has been enhanced to more accurately predict the structures and interactions of biomolecules. This advancement incorporates experimental data, leading to more reliable predictions in the fiel…
-
MegaFold system boosts training efficiency for 3D attention protein models
Researchers have developed MegaFold, a new system designed to make training large-scale 3D attention protein models more efficient. This approach addresses the significant computational and memory challenges posed by mo…
-
New SAE methods enhance interpretability and stability
Researchers have introduced several advancements in Sparse Autoencoders (SAEs) to improve their interpretability and stability. Concept-SAE offers a controllable interface for probing user-defined concepts within SAEs, …
-
New computational methods boost antibody-antigen complex modeling
Researchers have developed new computational methods to improve the modeling of antibody-antigen complexes, addressing a performance gap compared to general protein-protein interactions. The study explored protein langu…
-
New computational methods boost antibody-antigen interaction modeling
Researchers have developed new computational methods to improve the modeling of antibody-antigen interactions, a crucial step in discovering therapeutic antibodies. Existing protein language models (PLMs) show promise f…
-
AlphaFold's probabilistic roots in probability kinematics revealed
A new paper reinterprets the success of AlphaFold, a groundbreaking protein structure prediction model, by connecting its underlying mechanisms to probability kinematics (PK). The authors demonstrate that AlphaFold's le…
-
AI models outperform physics-based methods in protein-ligand docking
A new benchmark called PoseX has been developed to evaluate protein-ligand docking methods, comparing AI approaches against traditional physics-based techniques. Experiments using PoseX demonstrated that AI methods gene…