Beyond templates: advancing protein–protein interaction structure prediction with AI
Dr Alan Nafiiev evaluates template-based, docking and template-free approaches to PPI prediction, highlighting how AI can enhance structural accuracy.
List view / Grid view
Dr Alan Nafiiev evaluates template-based, docking and template-free approaches to PPI prediction, highlighting how AI can enhance structural accuracy.
Zasocitinib is a highly selective, investigational TYK2 inhibitor developed to target immune-mediated diseases with fewer off-target effects than traditional JAK inhibitors. This article explores its mechanism, selectivity data and clinical progress.
For decades, molecular glues have been stumbled upon rather than designed. A new scientific approach is now changing that – expanding what is considered druggable.
Scientists have mapped the diversity of fibroblasts and discovered how ‘rogue’ fibroblasts drive multiple diseases, revealing drug targets that could transform treatments across the body.
Virginia Tech computer scientists have created a new AI tool, ProRNA3D-single, that can generate 3D models of how viral RNA binds to human proteins – a development that could speed up drug discovery.
Helmholtz Munich and Parse Biosciences have collaborated to create the world’s largest lung disease perturbation atlas – which could aid the discovery of new therapeutic targets and accelerate the development of future lung disease treatments.
AI is increasingly used in drug discovery, but hidden bias and ‘black box’ models threaten trust and transparency. This article explores how explainable AI can turn opaque predictions into clear, accountable insights.
By combining human tissue models with explainable AI, researchers can analyse complex patient data to identify which treatments work best for which patients. First applied to inflammatory bowel disease, this approach could improve clinical trial success rates across many diseases.
From precision proteomics to AI-powered immune profiling, next-generation laboratory technologies are changing how new therapies are discovered and developed. Here are four innovations set to shape the lab of the future - and the future of drug discovery.
Penn engineers have built an AI model that creates new antibiotics – and early tests show some work as well as existing approved drugs.
Quantitative Systems Pharmacology (QSP) is fast becoming a standard tool in drug development, offering a human-relevant way to predict drug effects before the clinic. Dr Josh Apgar of Certara explains how it is helping to cut reliance on animal testing and speed discovery.
With over 1,000 skin diseases lacking approved treatments, a search-and-develop model is changing how new therapies are sourced and developed. Chief Scientific Officer, Jacob Pontoppidan Thyssen, outlines the strategy behind it.
Scientists at Tufts University have developed an AI tool that demonstrates how tuberculosis drugs kill bacteria – an advancement that could speed-up the discovery of shorter, more effective treatments.
AI is starting to transform drug discovery, but progress is still slow and big challenges remain. Thibault Géoui explores the gaps, hurdles and breakthroughs needed before it can truly change pharma R&D.
Thibault Géoui explains why AI could finally help pharma overcome its productivity crisis and why the payoff won’t come as quickly as the optimists claim.