protein
PulseAugur coverage of protein — every cluster mentioning protein across labs, papers, and developer communities, ranked by signal.
9 day(s) with sentiment data
-
AI designs proteins from functional descriptions
An AI system has been developed that can design proteins based on simple instructions describing their desired function. This breakthrough allows researchers to specify a protein's task, such as binding to a specific vi…
-
MIT develops AI for robot reasoning and substance simulation; NVIDIA supports Korean open models
Researchers at MIT have developed an AI-assisted learning platform that enables robots to understand and act on commands beyond their literal interpretation. Separately, MIT has also created a single AI model capable of…
-
New benchmark evaluates protein motif scaffolding models for dynamic stability
Researchers have introduced BILBY-PRO, a new benchmark for evaluating protein motif scaffolding models, which systematically derives functional motifs from PROSITE-linked experimental structures. This benchmark comprise…
-
New BILBY framework reveals static success doesn't guarantee dynamic protein design fidelity
Researchers have introduced BILBY, a new framework for evaluating protein motif scaffolding models. BILBY-PRO offers a benchmark of 220 functional motifs derived from PROSITE, while BILBY-MD provides a molecular dynamic…
-
AI designs novel proteases for protein breakdown
Researchers have utilized artificial intelligence to design novel proteases, which are enzymes capable of breaking down other proteins. This advancement in protein design could lead to new therapeutic applications and a…
-
AI designs proteins that degrade stable molecular bonds
Researchers have utilized AI to engineer novel proteins capable of degrading other proteins. These AI-designed proteins can break down molecular bonds that have remained stable for centuries. This advancement holds pote…
-
Class-incremental learning methods fail to transfer across protein encoders
Researchers have evaluated nine class-incremental learning (CIL) methods on frozen protein encoders, finding that these methods do not reliably transfer across different protein representations. The study highlights tha…
-
AI designs novel proteins for targeted degradation
Scientists have developed an artificial intelligence system capable of designing novel proteins that can effectively degrade other specific proteins. This breakthrough in protein engineering could lead to new therapeuti…
-
AI designs novel proteins to cut target proteins, aiding disease research · 5 sources tracked
Researchers have utilized AI to engineer novel proteins capable of cleaving other proteins, a process that normally takes hundreds of years without enzymatic assistance. By employing AI-based design tools, scientists we…
-
Biologist questions AI-discovered enzyme findings
A biologist has expressed skepticism regarding an enzyme discovered by artificial intelligence, stating that the AI's findings do not align with their own research. The discovery involves ribonucleic acid (RNA) and prot…
-
Product Monte Carlo algorithm simplifies Bayesian computation
Researchers have introduced Product Monte Carlo (PMC), a novel algorithm designed to compute expectations under a product of densities. This method addresses challenges in large-scale Bayesian computation, federated lea…
-
Amazon launches new Alexa Tablets to challenge iPad with Android integration
Amazon has introduced a new line of Alexa Tablets, aiming to compete with Apple's iPad. These new tablets will run on Android with a stock-like interface and include access to the Google Play Store, a significant depart…
-
Generative AI designs enhanced proteins for improved DNA editing
Researchers have leveraged generative AI to design novel proteins that significantly enhance DNA editing capabilities. One such AI-designed protein, when integrated into an experimental gene-editing system, demonstrated…
-
New LSCO method optimizes protein expression using AI language models
Researchers have developed a novel method called Latent-Space Codon Optimization (LSCO) to improve the efficiency of protein expression. This technique recasts the discrete problem of codon selection into a continuous o…
-
Graph Neural Network Reliability Explored in Protein Function Prediction
A new research paper published on arXiv explores the reliability of Graph Neural Networks (GNNs) in predicting protein function. The study investigates whether tissue-specific interaction structures within protein netwo…
-
New methods enhance LLM decoding for long contexts and graph data
Two new research papers introduce novel methods for improving the efficiency and structure-awareness of autoregressive decoding in large language models, particularly for handling long contexts and graph-based data. Com…
-
New research accelerates diffusion model sampling with draft trees and replica exchange · 2 sources tracked
Two new research papers propose novel methods for accelerating diffusion model sampling. The first, "Accelerating Diffusion Sampling via Speculative Draft Trees," introduces draft trees to improve candidate consideratio…
-
3D Printing Waste Converted Into Edible Protein
Researchers are investigating a new method to address waste generated by 3D printing by transforming it into edible protein. Early findings suggest this approach holds promise for sustainability in 3D printing processes.
-
AI pioneers novel proteins, opening new scientific frontiers
Artificial intelligence is enabling the creation of novel proteins that have never existed in nature. This breakthrough opens up new possibilities in scientific research and development.
-
In-context learning emerges across diverse AI modalities, study finds
A new research paper proposes the Convergent Emergence Hypothesis, suggesting that few-shot in-context learning (ICL) capabilities, observed in large language models, may emerge broadly across different data modalities.…