All Machine Learning (ML) articles
-
NewsMALVINA machine learning platform reveals how bacteria behave inside human cells
A new machine learning-based platform called MALVINA measures bacterial invasion, intracellular accumulation and DNA damage at single-cell resolution, exposing infection dynamics that conventional assays cannot detect.
-
NewsELRIG Drug Discovery 2026 celebrates 20th anniversary at ExCeL London
ELRIG Drug Discovery 2026 returns to ExCeL London for its 20th year, with AI, automation and advanced cell models among the technologies set to feature across the two-day programme.
-
InterviewA sceptical guide to AI agents in drug discovery
AI agents promise to transform drug discovery, but where do they really add value? Dr Eric Ma examines search, model choice, vendor lock-in and why scientific expertise matters more than ever.
-
NewsAI consortium targets antibody developability prediction with 10,000-sequence dataset
A new industry consortium led by Ginkgo Datapoints and Apheris is assembling a 10,000-antibody dataset to train AI models that can flag developability problems earlier in the drug discovery pipeline.
-
ArticleAI agents vs scientists: what should we automate in drug discovery?
AI agents can search, analyse and plan across drug discovery workflows, but where should scientists hand over control? We examine what to automate, what to check and where human judgement matters most.
-
ArticleWhy AI struggles with new drug targets – and how physics could help
Virtual screening can assess billions of compounds, but performance can fall on unfamiliar targets. Combining AI with molecular physics could help make predictions more reliable.
-
NewsInsilico Medicine launches open-source AI longevity research toolkit
Insilico Medicine has published a Cell cover study introducing LongevityBench, a suite of specialised AI models and an autonomous agentic discovery platform.
-
NewsUK’s first AI-robotic organoid lab opens in Liverpool
A £20 million high-security facility in Liverpool is set to accelerate drug and vaccine discovery by integrating artificial intelligence, robotics and human organoid technology within a Category 3 containment environment.
-
NewsInsilico launches specialist AI models for drug discovery chemistry
Insilico Medicine has unveiled a suite of compact, domain-trained AI models targeting ADMET prediction, retrosynthesis and target activity across GPCR and kinase panels, claiming state-of-the-art results on more than 70 benchmarks.
-
ArticleHow AI-driven systems biology will reset the starting line for drug development
AI is making drug discovery faster, but can it make it more successful? Discover why combining AI with systems biology could help researchers tackle the biological complexity behind drug failure.
-
NewsAutomated MRI pipeline standardises preclinical stroke damage measurement
An automated imaging pipeline developed at USC’s Stevens Neuroimaging and Informatics Institute can measure stroke-related brain tissue damage from MRI scans with accuracy matching human experts, offering a scalable, standardised tool for preclinical drug evaluation across multi-site research networks.
-
ArticleWhy single-cell foundation models have underdelivered and what drug discovery needs instead
Foundation models have delivered breakthroughs in protein biology, but single-cell models have struggled to match them. What is holding them back?
-
NewsWhat Google’s AI talent exodus could mean for future drug discovery
The departure of leading AI researchers from Google to found Discovery Loop raises important questions about the future direction of artificial intelligence in scientific research and drug development.
-
ArticleGene therapy’s biggest challenge is the cell’s own defence mechanisms
What if one of gene therapy’s biggest obstacles isn’t delivery, but the body’s own cells? Discover why DNA silencing is emerging as a major challenge for long-lasting genetic medicines.
-
NewsInsilico Medicine launches AI drug discovery benchmarking platform
Insilico Medicine has unveiled a benchmarking platform designed to assess whether AI models can perform genuine drug discovery tasks, using decontaminated real-world datasets and proprietary validated programmes to move beyond inflated benchmark scores.
-
NewsResearchers develop AI system to accelerate tuberculosis drug discovery
Researchers at Texas A&M have developed AI-driven platforms to help scientists navigate the bottlenecks of tuberculosis drug discovery, from eliminating nuisance compounds to unlocking years of archived research data.
-
ArticleAI’s promise and practical limits in drug discovery
From ChatGPT to AI agents and world models, where is AI really heading in drug discovery? Dr Raminderpal Singh explains what researchers should focus on now.
-
ArticleAI’s real value in drug discovery may be choosing the right experiment
AI is becoming more capable, but its value still depends on the data, questions and decisions behind it. Where is it genuinely improving drug discovery and where do the limitations remain?
-
NewsAI and lab techniques accelerate tuberculosis drug discovery
Researchers at UMass Amherst have combined high-throughput laboratory screening with an AI neural network to identify compounds capable of breaching the protective outer membrane of Mycobacterium tuberculosis, potentially accelerating the search for new TB therapeutics.
-
NewsLargest chemical reactions database launched to boost AI drug discovery
Researchers at the University of Michigan have assembled a database of more than 50,000 chemical experiments, offering AI systems an unprecedented resource to accelerate drug discovery and reduce reliance on scarce precious metal catalysts.