PhD Studentship in Artificial Intelligence for Structure-Based Virtual Screening Imperial College London Closing date: 13 April 2026 Predictive models built with artificial intelligence (AI) methods are powerful tools to discover molecules with the potential to become drugs to tre...

Interested in gaining a PhD at the interface between AI and structure-based drug design? A fully funded PhD studentship is available at my group at Imperial College London www.linkedin.com/pulse/phd-st...

Enjoyed speaking at the SAE Media Group's AI in Drug Discovery conference. A big thank you to them for organising and also for my interview www.smgconferences.com/documentport...

chemrxiv.org/doi/full/10....

Our new preprint. First prospective use of a transformer model for drug repurposing against Streptococcus pneumoniae, a major AMR threat. Great collaboration with Nick Croucher’s lab. Of 11 tested, 9 showed strong activity, some against multidrug‑resistant strains.
#AI #AMR

Enjoyed reading "Hit identification in ultra large virtual screening: an integrative review and future challenges"
www.sciencedirect.com/science/arti...

Frontiers | Structure-based virtual screening for TRPM8 modulators Transient receptor potential melastatin 8 (TRPM8) is an emerging therapeutic target, yet the performance of available structural models for docking and optim...

Interested in drugging ion channels? Check out our study www.frontiersin.org/journals/dru...

So much done, so much more left to do: "Seven in 10 people now survive their cancer five years or more, up from only half in the mid-70s" pressroom.cancer.org/cancer-stati...

Fellowship FutureHouse is a philanthropically-funded moonshot focused on building an AI Scientist. Our 10-year mission is to build semi-autonomous AIs for scientific research, to accelerate the pace of discovery...

FutureHouse has announced the 2026 AI-for-Science Independent Postdoctoral Fellowship (deadline 13 Feb 2026). Applicants need a co-advisor. I am happy to consider candidates: email p.ballester@imperial.ac.uk with CV + 2-page proposal. All info at www.futurehouse.org/fellowship

AI in drug Discovery SAE is proud to present the 7th Annual AI in Drug Discovery Conference on 9th-10th March 2026

Looking forward to speaking at this AI for Drug Discovery conference www.smgconferences.com/pharmaceutic...

Brandolini’s Bullshit Asymmetry Principle: “The amount of energy needed to refute bullshit is an order of magnitude bigger than to produce it.” And this is often what it means to be a referee nowadays...

Predicting temozolomide response in low-grade glioma patients with large-scale machine learning - BMC Methods Background Temozolomide is the primary chemotherapeutic agent and first-line treatment for low-grade glioma. Although low-grade gliomas are generally less aggressive than high-grade gliomas, they can eventually progress into high-grade gliomas, making it crucial to maximise the efficacy of initial treatment. Methods We analysed data from 109 patients with low-grade gliomas in The Cancer Genome Atlas to evaluate the predictive performance of 12 machine learning classification algorithms for temozolomide response, using six types of omics data. Cross-validation and bootstrapping bias correction were applied to compare these models with a conventional biomarker-based model using promoter methylation status of O6-methylguanine-DNA methyltransferase. The Matthews Correlation Coefficient (MCC) was used as the primary evaluation metric. Results The microRNA-based model using the Extreme Gradient Boosting algorithm achieved the best performance (MCC = 0.447), outperforming both the automated machine learning method JADBio (MCC = 0.250) and the biomarker-based model (MCC = 0.331). Incorporating clinical variables, such as patient age and Karnofsky score, further improved predictive power, with the logistic regression model with optimal model complexity achieving the highest MCC (0.483). Feature importance analysis on the best model revealed six predictive microRNAs, including three tumour-related factors (miR-335, let-7f, and miR-7-2) and three potential biomarkers (miR-204, miR-6513, and miR-376). Discussion This study systematically demonstrates the potential of large-scale analyses combining machine learning and omics data to predict temozolomide response, offering superior predictive accuracy compared with standard biomarkers. However, validation in independent clinical datasets remains necessary before clinical translation.

Happy to share our latest research on predicting temozolomide response in low-grade glioma patients using large-scale machine learning.

We explored 12 machine learning classification algorithms across six types of omics data.

link.springer.com/article/10.1...

🚀 Just published in Pattern Recognition:

We present LDMO-CCP, a conformal prediction model using molecular clustering for better uncertainty quantification across chemical spaces.

🔹 Identifies Proscilladin as broad-spectrum cell-active inhibitor

👉 doi.org/10.1016/j.pa...

Really enjoyed my visit and talk last week at UC Berkeley (bidmap.berkeley.edu/seminars/ped...).

Many thanks to BidMap for the warm hospitality!