32 articles tagged with #biotech. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.
Researchers introduce AIMS-Fold, a guided-diffusion framework that integrates structural proteomics data (XL-MS and HDX-MS measurements) with protein structure prediction models to improve accuracy in predicting protein complex conformations. The approach outperforms unguided computational models on challenging induced proximity drug targets, advancing structure-based drug design capabilities.
Bittensor Subnet 68 has screened over 11 million molecules across nine disease targets using decentralized computing, demonstrating a practical application of blockchain technology in pharmaceutical research. The subnet operates three live competitions rewarding computational contributions through its Yuma Consensus mechanism, enabling companies like Metanova Labs to conduct drug discovery at reduced operational costs.
OpenAI has launched GPT-Rosalind, an AI model designed to accelerate pharmaceutical drug discovery, partnering with major life sciences companies including Amgen, Moderna, and Thermo Fisher. The model represents a significant application of advanced AI technology beyond traditional software domains, with potential to compress drug development timelines and reduce research costs.
According to PitchBook data, AI is driving a resurgence of early-stage venture capital investment into previously neglected tech sectors. Healthcare technology, cybersecurity, biotech, and Software-as-a-Service (SaaS) are experiencing significant funding increases as AI applications revitalize these markets.
KALA BIO (KALA) stock surged 70% in pre-market trading after announcing plans to launch its first commercial AI agent within 14 days through the Researgency.ai platform. The company is positioning itself as a 'Palantir for Biotech' with its AI-driven strategy.
Researchers have introduced Mozi, a dual-layer architecture designed to make AI agents more reliable for drug discovery by implementing governance controls and structured workflows. The system addresses critical issues of unconstrained tool use and poor long-term reliability that have limited LLM deployment in pharmaceutical research.
OpenAI is investing in Merge Labs, a company developing brain-computer interfaces that aim to bridge biological and artificial intelligence. The investment focuses on enhancing human capabilities, agency, and experience through advanced neural interface technology.
Biohub has launched an AI toolkit that democratizes drug discovery by enabling smaller biotech firms to access advanced protein design and AI-powered research capabilities previously available only to large pharmaceutical companies. This development has the potential to reshape the biotech industry by lowering barriers to entry and accelerating innovation across the sector.
The inaugural Enhanced Games, launching in Las Vegas with 42 athletes, explicitly permits performance-enhancing drugs to test human physical limits. While positioned as a 2026 longevity trend, the event raises questions about sports ethics, regulatory frameworks, and potential market implications for biotech and wellness sectors.
Biologists have leveraged AI Co-Scientist tools to identify novel genetic factors capable of rejuvenating human cells and reversing cellular aging. This breakthrough demonstrates the practical application of AI in accelerating biological research and understanding aging mechanisms at the genetic level.
Calico Life Sciences has implemented Co-Scientist, an AI tool designed to aggregate dispersed research findings and identify new research directions in aging studies. This application demonstrates how AI systems can accelerate scientific discovery by synthesizing complex datasets across multiple studies.
Filippo Menolascina leverages Co-Scientist AI to accelerate the discovery of liver disease mechanisms and identify new treatment options. The research aims to explain why certain existing drugs are effective only for specific patient populations, potentially enabling more personalized therapeutic approaches.
Boston Children's Hospital and MIT researchers are collaborating to develop RNA-based treatments for ALS (amyotrophic lateral sclerosis), combining their biological expertise to advance therapeutic approaches. This interdisciplinary partnership leverages complementary research capabilities to address a neurodegenerative disease with limited current treatment options.
Researchers introduce EDMolGPT, a generative AI model that uses electron density data from protein binding pockets to design novel drug molecules. The approach improves upon existing methods by incorporating physically grounded density information rather than empty pocket structures, enabling more accurate molecular generation with realistic 3D conformations.
Inhibrx Biosciences (INBX) stock surged 17% following positive Phase 2 clinical trial results showing that INBRX-106 combination therapy doubled response rates in head and neck cancer patients, demonstrating meaningful therapeutic efficacy.
Johnson & Johnson's CEO highlights America's competitive edge in healthcare innovation, citing AI-driven drug discovery and a $55 billion domestic manufacturing investment as evidence of the U.S. health innovation engine's momentum and future potential.
Beacon Biosignals, founded by MIT researchers Jake Donoghue and Jarrett Revels, is developing an AI-powered platform that analyzes brain activity during sleep to diagnose and treat neurological diseases. The company represents a convergence of neuroscience and machine learning, positioning artificial intelligence as a diagnostic tool in healthcare.
OpenAI has released GPT-Rosalind, a specialized AI model designed specifically for drug discovery and life sciences applications that can significantly accelerate research timelines. However, the model's access is restricted and not available to the general public, limiting its immediate impact to institutional researchers and pharmaceutical companies.
Researchers introduce MAT-Cell, a neuro-symbolic AI framework that combines large language models with biological constraints to improve single-cell annotation accuracy. The system uses multi-agent reasoning and verification processes to overcome limitations in both supervised learning and LLM-based approaches, demonstrating superior performance on cross-species benchmarks.
Max Hodak discusses revolutionary potential of brain-computer interfaces in healthcare, including vision restoration for the blind and broader human-technology interaction improvements. He also touches on longevity research suggesting some people alive today may reach 1000 years of age.
A comprehensive evaluation of Boltz-2, an AI-based drug discovery tool, reveals significant limitations in predicting protein-ligand binding structures and affinities. The study found only weak correlations with physics-based methods and concluded that while useful for initial screening, Boltz-2 lacks the precision required for reliable drug lead identification.
A new open-source AI model has been developed specifically for genomics, trained on trillions of DNA bases. The system can identify various genetic elements including genes, regulatory sequences, and splice sites, representing a significant advancement in AI-powered biological analysis.
Researchers developed BioProAgent, a neuro-symbolic AI framework that combines large language models with deterministic constraints to enable reliable scientific planning in wet-lab environments. The system achieves 95.6% physical compliance compared to 21.0% for existing methods by using finite state machines to prevent costly experimental failures.
Researchers introduce MERA (Multimodal Mixture-of-Experts with Retrieval Augmentation), a new AI framework for protein active site identification that addresses challenges in drug discovery. The system achieves 90% AUPRC performance on active site prediction through hierarchical multi-expert retrieval and reliability-aware fusion strategies.
Researchers have developed Brain-OF, the first omnifunctional brain foundation model that can process fMRI, EEG, and MEG data simultaneously within a unified framework. The model introduces novel techniques like Any-Resolution Neural Signal Sampler and Masked Temporal-Frequency Modeling, trained on 40 datasets to achieve superior performance across diverse neuroscience tasks.
