The effectiveness of most cancer targeted therapies is short-lived. Tumors often develop resistance that might be overcome with drug combinations. However, the number of possible combinations is vast, necessitating data-driven approaches to find optimal patient-specific treatments. Here we report AstraZeneca’s large drug combination dataset, consisting of 11,576 experiments from 910 combinations across 85 molecularly characterized cancer cell lines, and results of a DREAM Challenge to evaluate computational strategies for predicting synergistic drug pairs and biomarkers. 160 teams participated to provide a comprehensive methodological development and benchmarking. Winning methods incorporate prior knowledge of drug-target interactions. Synergy is predicted with an accuracy matching biological replicates for >60% of combinations. However, 20% of drug combinations are poorly predicted by all methods. Genomic rationale for synergy predictions are identified, including ADAM17 inhibitor antagonism when combined with PIK3CB/D inhibition contrasting to synergy when combined with other PI3K-pathway inhibitors in PIK3CA mutant cells.

Introduction: Precision medicine is the concept of treating diseases based on environmental factors, lifestyles, and molecular profiles of patients. This approach has been found to increase success rates of clinical trials and accelerate drug approvals. However, current precision medicine applications in early drug discovery use only a handful of molecular biomarkers to make decisions, whilst clinics gear up to capture the full molecular landscape of patients in the near future. This deep multi-omics characterization demands new analysis strategies to identify appropriate treatment regimens, which we envision will be pioneered by artificial intelligence. Areas covered: In this review, the authors discuss the current state of drug discovery in precision medicine and present our vision of how artificial intelligence will impact biomarker discovery and drug design. Expert opinion: Precision medicine is expected to revolutionize modern medicine; however, its traditional form is focusing on a few biomarkers, thus not equipped to leverage the full power of molecular landscapes. For learning how the development of drugs can be tailored to the heterogeneity of patients across their molecular profiles, artificial intelligence algorithms are the next frontier in precision medicine and will enable a fully personalized approach in drug design, and thus ultimately impacting clinical practice.

Abundant heterogeneous immune cells infiltrate lesions in chronic inflammatory diseases and characterization of these cells is needed to distinguish disease-promoting from bystander immune cells. Here, we investigate the landscape of non-communicable inflammatory skin diseases (ncISD) by spatial transcriptomics resulting in a large repository of 62,000 spatially defined human cutaneous transcriptomes from 31 patients. Despite the expected immune cell infiltration, we observe rather low numbers of pathogenic disease promoting cytokine transcripts (IFNG, IL13 and IL17A), i.e. >125 times less compared to the mean expression of all other genes over lesional skin sections. Nevertheless, cytokine expression is limited to lesional skin and presented in a disease-specific pattern. Leveraging a density-based spatial clustering method, we identify specific responder gene signatures in direct proximity of cytokines, and confirm that detected cytokine transcripts initiate amplification cascades of up to thousands of specific responder transcripts forming localized epidermal clusters. Thus, within the abundant and heterogeneous infiltrates of ncISD, only a low number of cytokine transcripts and their translated proteins promote disease by initiating an inflammatory amplification cascade in their local microenvironment.

Pharmacometrics (PM) and machine learning (ML) are both valuable for drug development to characterize pharmacokinetics (PK) and pharmacodynamics (PD). Pharmacokinetic/pharmacodynamic (PKPD) analysis using PM provides mechanistic insight into biological processes but is time- and labor-intensive. In contrast, ML models are much quicker trained, but offer less mechanistic insights. The opportunity of using ML predictions of drug PK as input for a PKPD model could strongly accelerate analysis efforts. Here exemplified by rifampicin, a widely used antibiotic, we explore the ability of different ML algorithms to predict drug PK. Based on simulated data, we trained linear regressions (LASSO), Gradient Boosting Machines, XGBoost and Random Forest to predict the plasma concentration-time series and rifampicin area under the concentration-versus-time curve from 0–24 h (AUC_0–24h) after repeated dosing. XGBoost performed best for prediction of the entire PK series (R²: 0.84, root mean square error (RMSE): 6.9 mg/L, mean absolute error (MAE): 4.0 mg/L) for the scenario with the largest data size. For AUC_0–24h prediction, LASSO showed the highest performance (R²: 0.97, RMSE: 29.1 h·mg/L, MAE: 18.8 h·mg/L). Increasing the number of plasma concentrations per patient (0, 2 or 6 concentrations per occasion) improved model performance. For example, for AUC_0–24h prediction using LASSO, the R² was 0.41, 0.69 and 0.97 when using predictors only (no plasma concentrations), 2 or 6 plasma concentrations per occasion as input, respectively. Run times for the ML models ranged from 1.0 s to 8 min, while the run time for the PM model was more than 3 h. Furthermore, building a PM model is more time- and labor-intensive compared with ML. ML predictions of drug PK could thus be used as input into a PKPD model, enabling time-efficient analysis.

Generative artificial intelligence is revolutionizing digital twin development, enabling virtual patient representations that predict health trajectories, with large language models (LLMs) showcasing untapped clinical forecasting potential. We developed the Digital Twin—Generative Pretrained Transformer (DT-GPT), extending LLM-based forecasting solutions to clinical trajectory prediction. DT-GPT leverages electronic health records without requiring data imputation or normalization and overcomes real-world data challenges such as missingness, noise, and limited sample sizes. Benchmarking on non-small cell lung cancer, intensive care unit, and Alzheimer’s disease datasets, DT-GPT outperformed state-of-the-art machine learning models, reducing the scaled mean absolute error by 3.4%, 1.3% and 1.8%, respectively. It maintained distributions and cross-correlations of clinical variables, and demonstrated explainability through a human-interpretable interface. Additionally, DT-GPT’s ability to perform zero-shot forecasting highlights potential advantages of LLMs as clinical forecasting platforms, proposing a path towards digital twin applications in clinical trials, treatment selection, and adverse event mitigation.

The development of functional neurons is a complex orchestration of multiple signaling pathways controlling cell proliferation and differentiation. Because the balance of antioxidants is important for neuronal survival and development, we hypothesized that ferroptosis must be suppressed to gain neurons. We find that removal of antioxidants diminishes neuronal development and laminar organization of cortical organoids, which is fully restored when ferroptosis is inhibited by ferrostatin-1 or when neuronal differentiation occurs in the presence of vitamin A. Furthermore, iron-overload-induced developmental growth defects in C. elegans are ameliorated by vitamin E and A. We determine that all-trans retinoic acid activates the Retinoic Acid Receptor, which orchestrates the expression of anti-ferroptotic genes. In contrast, retinal and retinol show radical-trapping antioxidant activity. Together, our study reveals an unexpected function of vitamin A in coordinating the expression of essential cellular gatekeepers of ferroptosis, and demonstrates that suppression of ferroptosis by radical-trapping antioxidants or by vitamin A is required to obtain mature neurons and proper laminar organization in cortical organoids.