UniPro
PulseAugur coverage of UniPro — every cluster mentioning UniPro across labs, papers, and developer communities, ranked by signal.
6 day(s) with sentiment data
-
New Curate-DTI dataset offers construct-aware drug-protein bioactivity data
A new dataset called Curate-DTI has been released, focusing on drug-protein bioactivity. This dataset distinguishes itself by including construct-aware protein targets, addressing limitations of using only UniProt acces…
-
New UniPRO framework reveals optimal fusion order for multimodal retrieval
Researchers have developed UniPRO, a framework for analyzing the optimal order of fusing multimodal data in retrieval tasks. Their findings indicate that the sequence in which visual, acoustic, and speech information is…
-
New GenFish method advances drug discovery with generative retrieval
Researchers have developed GenFish, a novel generative retrieval approach for reverse target fishing, a crucial process in drug discovery. This method utilizes residual vector quantization to convert protein language mo…
-
Google DeepMind uses AI workbench to accelerate antimicrobial peptide discovery
Google DeepMind has developed Google Antigravity, an agentic science workbench designed to accelerate the discovery of new antimicrobial peptides (AMPs). This platform integrates multiple databases and utilizes a deep l…
-
AI advances protein design with language guidance and security focus · 6 sources tracked
Researchers are exploring new methods for protein design using advanced AI models, focusing on natural language guidance and data integrity. One study details two data-only poisoning attacks that can manipulate protein …
-
UniPro model unifies 2D and 3D medical image segmentation
Researchers have introduced UniPro, a novel model designed to unify various medical image segmentation tasks across different data dimensions. UniPro addresses the fragmentation in current methods by integrating semanti…
-
New method uses knowledge graphs to ground LLM-generated biomedical hypotheses
Researchers have developed HypoKG, a novel method for generating biomedical hypotheses using large language models (LLMs) by integrating three major biological databases into a unified knowledge graph. This approach aim…
-
New Homo-RAG framework uses LLMs for cross-species gene function prediction
Researchers have developed Homo-RAG, a novel framework that uses large language models to predict gene function across different species. This system integrates homology-guided retrieval with evidence-aware ranking, lev…
-
LLM-powered agents simplify protein engineering for biologists
Two new agent frameworks, AutoProteinEngine (AutoPE) and TourSynbio-Search, have been developed to simplify protein engineering for biologists. AutoPE utilizes large language models (LLMs) to enable natural language int…
-
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…
-
Generative AI Transforms Bioinformatics: A Systematic Review
A systematic review published on arXiv examines the impact of generative artificial intelligence (GenAI) on bioinformatics, covering models, applications, and methodological advancements. The review found that GenAI sig…
-
AI Co-Scientist Workflow Targets EGFR Inhibitor Resistance
Researchers have developed an AI co-scientist workflow to discover new EGFR inhibitors, specifically targeting the C797S mutation that causes resistance to existing treatments. The process involves using ChEMBL and UniP…
-
PairSAE method enhances interpretability in protein co-folding models
Researchers have developed PairSAE, a novel method for achieving mechanistic interpretability in protein co-folding foundation models. Unlike standard sparse autoencoders that struggle with the quadratic feature explosi…
-
New AI method audits protein models for hazardous designs
Researchers have developed VFUSE, a novel approach using Sparse Autoencoders (SAEs) to interpret generative protein models like RoseTTAFold3 and RFDiffusion3. This method aims to identify and understand features associa…
-
Google DeepMind launches AI toolkit to speed up life science research
Google DeepMind has developed a new AI toolkit called Science Skills for Google, designed to accelerate research workflows. This toolkit integrates insights from over 30 major life science sources, including UniProt and…
-
BioTool dataset enhances LLM biomedical tool-calling capabilities
Researchers have developed BioTool, a new dataset aimed at improving the ability of large language models to utilize specialized biomedical tools. The dataset includes 34 tools from major databases and over 7,000 human-…
-
AI model CRC-Screen certifies DNA synthesis orders against hazards
Researchers have developed a new method called CRC-Screen to improve the accuracy of screening DNA synthesis orders for potential hazards. The system addresses a critical flaw in current methods where screening fails wh…
-
AI interprets protein models to detect biological risks
Researchers have developed a new method called SAEBER, utilizing Sparse Autoencoders (SAEs) to analyze protein design models like RFDiffusion3 and RoseTTAFold3. This technique identifies features within the models that …