All Artificial Intelligence (AI) articles – Page 2
-
ArticleWhy AI models need patient data to deliver in drug discovery
Despite rapid advances in AI, many drug discovery models still struggle to translate computational predictions into clinical outcomes. Thomas Clozel explains how Owkin is training AI on large-scale patient-derived data while integrating experimental and clinical validation directly into model development.
-
ArticleTurning GWAS signals into drug targets with scalable CRISPR
Genome-wide association studies have linked thousands of genetic variants to disease, yet most remain disconnected from drug-relevant biology. Neville Sanjana, Professor at New York University and Core Faculty Member at the New York Genome Center, explains how scalable CRISPR screens systematically link noncoding variants to causal genes and therapeutic targets.
-
NewsISSCR consortium submits recommendations on NAMs to FDA
The ISSCR Consortium on Advanced Stem Cell-Based Models is calling for greater flexibilty from the FDA to accomodate rapidly changing technologies like stem cell-derived systems, organoids and computational approaches.
-
NewsC-Path launches coalition to advance human-relevant drug discovery
The New Approach Methodologies Developer Coalition brings together technology developers, pharmaceutical companies and regulators in a precompetitive initiative to establish qualification standards for complex in vitro models, microphysiological systems and related human-relevant technologies.
-
ArticleAACR 2026 part one: AI design, precision biology and the next wave of oncology innovation
At AACR 2026, industry leaders discussed how oncology R&D is moving beyond isolated technological advances towards integrated discovery systems.
-
NewsOutSee wins Longitude Prize award for ALS target discovery
OutSee has secured a Discovery Award from the Longitude Prize on ALS, providing £100,000 in funding and access to genomic data from 9,000 patients. The company will deploy its AI-driven Nomaly platform to identify novel therapeutic targets for amyotrophic lateral sclerosis over a nine-month research programme.
-
NewsAI-designed viral vectors achieve 50-fold brain enrichment over AAV9
WhiteLab Genomics has presented preclinical data showing that viral vectors designed using artificial intelligence achieved approximately 50-fold higher DNA enrichment in the brain compared to AAV9, with no detectable liver signal following intravenous administration in mice.
-
NewsAI system transforms weak antibiotics into powerful treatments
University of Pennsylvania researchers have developed ApexGO, an AI system that refines imperfect antibiotic candidates through calculated modifications rather than database screening.
-
NewsAI system reduces animal testing in drug discovery by 50 percent
German researchers have developed genESOM, a generative AI system that could reduce animal numbers in preclinical drug testing by 30 to 50 percent.
-
NewsOpenBind launches AI model to accelerate drug discovery
Diamond Light Source has launched OpenBind v1, an open-access AI model and dataset designed to address critical data shortages in drug discovery by providing standardised protein-drug binding measurements at atomic resolution.
-
NewsNew framework evaluates AI reliability in immune system prediction
Researchers at the University of South Florida have developed a comprehensive framework to test how accurately AI systems can predict immune responses, addressing critical questions about the reliability of computational tools in drug discovery.
-
NewsMachine learning identifies five distinct Parkinson’s disease subtypes
A new study from VIB and KU Leuven has revealed that Parkinson’s disease comprises five distinct molecular subtypes, each requiring tailored therapeutic approaches.
-
ArticleThe scale divide: competing strategies in AI drug discovery
Two approaches to AI in preclinical drug discovery are diverging, from multi-thousand GPU systems to models with only a handful of parameters, with early results raising questions about which will deliver.
-
NewsAI tool reveals DNA exists in partially open states
Researchers have discovered that DNA wrapped around nucleosomes exists in multiple partially open states rather than simply locked or accessible configurations.
-
ArticleWhen scale meets insight: reinventing SPR for the future of drug discovery
Carterra’s new 48-channel SPR platform reimagines throughput, automation and data quality for modern discovery workflows.
-
NewsAI system detects pain in laboratory mice through facial analysis
Researchers at ETH Zurich have developed an automated system that uses infrared imaging and artificial intelligence to assess pain in laboratory mice by analysing subtle facial expressions, offering a more consistent and humane alternative to traditional manual observation methods.
-
ArticleFrom leaderboards to lab notebooks: AI designs reach preclinical testing
For years, AI drug discovery has been judged on benchmark performance. Now, a set of studies shows what happens when those designs are made and tested in preclinical settings.
-
ArticleThe future of academic core labs: scaling operational excellence without increasing staff
The grounds have shifted the foundations of academic core facilities and the current climate demands their strategic agility in order to thrive. Boyd Butler at Molecular Devices reveals how these labs can capitalise on this opportunity to increase value and efficiency.
-
ArticleBeyond serendipity: rational design and AI’s expansion of the undruggable target landscape
For decades, drugging the ‘undruggable’ was thought to require luck rather than logic. Today, AI is transforming serendipity into strategy by enabling rational, data-driven approaches to previously inaccessible targets.
-
NewsAI platform models protein flexibility to accelerate drug design
A new artificial intelligence platform developed at the University of Virginia addresses a critical limitation in computational drug design by modelling protein flexibility during molecular interactions. The suite of tools uses diffusion models to generate drug candidates whilst accounting for induced fit dynamics, potentially improving success rates in early-stage development.