GSK needs to extract actionable disease insights from rapidly growing genetic, genomic, clinical, and health datasets so it can predict patient risk and treatment response, prioritize experiments, and improve the speed and success rate of drug and vaccine R&D.
Reported impact
GSK reports that AI and machine learning are already helping predict patient responses and disease risk, narrow research toward higher-need disease areas, and reduce research and development costs by cutting the time and resources needed to make progress on new medicines and vaccines.
GSK is using an in-house AI and machine learning stack to analyze large-scale genetic, genomic, clinical, and health datasets for drug discovery and patient stratification. The implementation combines GSK’s historical clinical archives with external datasets such as UK Biobank, including genome sequencing data and electronic health records, through a single platform that gives researchers pooled access to data resources. In-house algorithms and machine learning models are used to identify patterns in biological data, predict future patient responses to potential medicines, estimate who is at risk of developing diseases such as hepatitis B, and identify lupus patients least likely to respond to traditional treatments. GSK also runs a lab-in-the-loop reverse translation process in which engineers, geneticists, and biologists use active learning pipelines to rank hypotheses and targets, test them experimentally, and feed results back into the models for additional prioritization.
GSK combines internal clinical archives with external sources such as UK Biobank genome data and linked electronic health records in a single platform. Machine learning models and in-house algorithms analyze these pooled datasets to predict disease risk and treatment response, while active-learning lab-in-the-loop pipelines prioritize experiments; experimental results are then fed back to guide further research and clinical trial decisions.
"A key part of reimaging the traditionally linear drug development process at GSK involves integrating teams of biological scientists and technology experts to approach questions from new angles, as well as creating a single platform, from which researchers can access pooled data resources."
"Advanced technology allows GSK researchers to predict future responses to a potential therapy for chronic hepatitis B too."
"Another is using AI and machine learning to create a reverse translation process that creates a feedback loop, also known as lab-in-the-loop."
"In this process, tech engineers collaborate with geneticists and biologists to develop pipelines using a method called active learning."
"In-house algorithms are being used to analyse genetic and genomic data that can identify which patients with lupus ... are least likely to respond to traditional treatments."
"Machine learning models are also used to help predict who is at risk of developing hepatitis B and assess who is likely to be a carrier without their knowledge."
"UK Biobank, a database which contains massive amounts of genetic and health data from half a million British volunteers, is one of the datasets that GSK is using."
"integrating AI and machine learning techniques into scientific development is helping to reduce research and development costs by cutting down the amount of time and resources previously needed to make similar progress."
Review how this reference was scored and trace each normalized claim back to its documented source.
Scoring methodology
Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.
Traceability
Field coverage shows which facts each source supports. Dates are shown only when documented by the source.
Related
In-house Sample Jul 28, 2026 Novartis Novartis R&D needs to turn large volumes of scientific, clinical, operational, and real-world data into faster, higher-quality decisions across drug discovery and development, reducing cycle times, surfacing safety… less than 10 percent of drug candidates historically reach the market AI models · AI-enhanced analytics · Generative AI In-house Sample Apr 13, 2026 Elevance Health Elevance Health needed to find fraud, waste, and abuse in very large volumes of claims, payment, contract, and medical-record data so it could detect billing errors, suspicious coding patterns, and improper payments… across an annualized volume of nearly 23,000 reviews In-house Sample Feb 24, 2026 Sanofi Sanofi needed a faster, more objective way to decide which R&D programs to advance, accelerate, or stop while weighing costs, clinical trial enrollment timelines, unmet need, competition, and each program's probability… more than one billion data points across Sanofi Aily Labs · Plai 