Artificial Intelligence in the Life Sciences

Background: Alzheimers disease (AD) is a multifactorial neurodegenerative disorder in which copper dyshomeostasis, mitochondrial stress, oxidative injury and immune dysregulation may contribute to pathogenesis. Cuproptosis, a copper-triggered regulated cell death pathway, has emerged as a potential mechanistic link to AD, but its therapeutic and biomarker implications remain incompletely defined. Methods: We integrated transcriptomic, machine learning, immune infiltration, QSFR, molecular docking, docking validation and ADME analyses using GEO blood- and brain-based AD cohorts. Differentially expressed genes were intersected with curated cuproptosis-related genes, followed by pathway enrichment, construction and validation of a hybrid ensemble classifier, CIBERSORT-based immune correlation analysis, QSFR-driven target prioritization, ligand docking, consensus docking validation and SwissADME profiling. Results: The transcriptomic analyses revealed reproducible AD associated signatures enriched in neurodegenerative, oxidative stress, mitochondrial and inflammatory pathways. Across multiple machine learning models, FDX1, PDHB, PDHA1, DLAT and DLD consistently emerged as the most important cuproptosis-related genes, with the hybrid ensemble achieving the best diagnostic performance. Immune profiling suggested that these genes are linked to distinct immune infiltration patterns. QSFR and docking prioritized FDX1 as a key target and Clioquinol, PBT2 and Ebselen showed the strongest and most consistent binding behavior. Docking validation confirmed reliable pose reproduction and enrichment over decoys, while ADME analysis supported Clioquinol, PBT2 and Ebselen as the most balanced candidates for further consideration. Conclusion: This integrated workflow identifies a cuproptosis-centered mitochondrial gene module as a robust AD signature and highlights Clioquinol, PBT2 and Ebselen as promising repurposing candidates. The findings provide a prioritized computational framework for future experimental validation of copper-linked therapeutic strategies in AD.

Recent deep learning models for L1000 chemical perturbation prediction incorporate dedicated drug molecular encoders. We retrained seven such models from scratch with zeroed or shuffled drug inputs, and compared them with a multilayer perceptron that uses only cell-line basal expression. Under drug-blind evaluation, ablation caused negligible performance changes and the drug-free baseline matched all models. Current architectures do not yet utilise drug molecular features for generalisation to unseen compounds.

The rapid growth of molecular foundation models and large language models has encouraged a scale centred view of AI in drug discovery, in which larger pretrained models are expected to supersede compact cheminformatics models and graph neural networks (GNNs) trained for individual tasks. We test this assumption across 26 endpoints for molecular properties, toxicity, safety liabilities and biological activity, grouped into ADME, toxicity and bioactivity classes. The benchmark contains 78 endpoint and split entries spanning random, Murcko scaffold and structure separated 5-fold CV. Ordered from easiest to hardest, these splits approximate retrospective evaluation on a closed library, scaffold expansion in hit to lead, and library expansion on novel chemotypes. Each entry includes ML, GNN, pretrained molecular sequence and LLM based SAR families. Across 156 fold mean comparisons, classical ML such as RF(ECFP4) and ExtraTrees(RDKit) win 116, GNNs such as GIN and Ligandformer win 25, pretrained sequence models such as MoLFormer and ChemBERTa2 win 12, and LLM based SAR baselines win three. ML dominates random split interpolation but loses part of this advantage under harder splits; GNN and sequence models also decline but gain relative ground, whereas LLM based SAR is weaker in absolute terms yet less sensitive to the split axis. Paired bootstrap analyses support family level trends more strongly than individual model rankings. SAR knowledge derived from training folds improves many GPT5.5-SAR and Opus4.7-SAR metrics but does not make rule based reasoning a universal substitute for supervised predictors. Compact specialized models remain highly effective for molecular property and activity prediction. Larger models add value for SAR interpretation and reasoning in low data settings, but predictive performance depends on the fit among model, task and validation scenario, not on scale alone.

Drug-induced inhibition of the hERG potassium channel is the leading cause of cardiac safety-related drug attrition, but the Comprehensive in Vitro Proarrhythmia Assay (CiPA) framework requires activity data on multiple cardiac ion channels to assess proarrhythmic risk. We present CardioSafe, a three-branch multi-task neural network with cross-attention fusion that integrates chemical fingerprints, ChemBERTa embeddings, and predicted L1000 transcriptomic features to predict blocker status and potency for hERG, Nav1.5, and Cav1.2, with an exploratory IKs head. CardioSafe was trained on the largest publicly reported multi-channel cardiac ion channel dataset, combining ChEMBL 36 with the hERGCentral database (331127 hERG, 3160 Nav1.5, 1138 Cav1.2, and 115 IKs compounds), curated under a pharmacology-aware policy that retains censored measurements and inhibition-percentage votes. Under Tanimoto-similarity-controlled splits, CardioSafe outperforms the leading published comparators (CToxPred2 and CardioGenAI) on the data-rich hERG head; on the smaller Nav1.5 and Cav1.2 heads the standard evaluation is statistically inconclusive. A reverse-leak audit revealed that 22% of Nav1.5 and 21% of Cav1.2 test compounds were present in published comparators training data (92% as exact compound matches); after removing these contaminated compounds, CardioSafes lead on Nav1.5 and Cav1.2 also reaches statistical significance, demonstrating that prior cross-publication benchmarks for these channels were inflated by training-data overlap. Scientific contributionWe present the first multi-task neural network jointly predicting blocker activity for the three primary CiPA cardiac ion channels (hERG, Nav1.5, Cav1.2) within a single architecture. We introduce a reverse-leak audit methodology that reveals systematic test-set contamination in cross-publication cardiac safety benchmarks, establishing a stricter evaluation protocol. We provide the empirical test of predicted L1000 transcriptomic features as auxiliary input for cardiac ion channel prediction and document a well-characterized negative result. Graphical abstractCardioSafe encodes each query SMILES with three branches (chemical fingerprints + descriptors, pretrained ChemBERTa, and predicted L1000 transcriptomic signatures), fuses them via a cross-attention block with four learnable per-channel query tokens, and emits binary blocker calls plus pChEMBL regression for hERG, Nav1.5, Cav1.2, and (exploratory) IKs. O_FIG O_LINKSMALLFIG WIDTH=200 HEIGHT=59 SRC="FIGDIR/small/723181v1_ufig1.gif" ALT="Figure 1"> View larger version (13K): org.highwire.dtl.DTLVardef@1c0ba2aorg.highwire.dtl.DTLVardef@1fe3a0borg.highwire.dtl.DTLVardef@194de8aorg.highwire.dtl.DTLVardef@9e4f74_HPS_FORMAT_FIGEXP M_FIG C_FIG

Drug-induced arrhythmias, particularly Torsades de Pointes (TdP), pose a significant risk to patient safety and can sometimes have life-threatening outcomes. They remain a major concern in drug development and regulation. Machine learning (ML) has become a powerful tool for analyzing complex biological and chemical datasets, enabling researchers to identify subtle patterns that differentiate safe compounds from those likely to cause dangerous cardiac effects. However, most existing in silico approaches do not sufficiently incorporate biological elements, relying heavily on chemical and structural properties or on computationally expensive simulations. Here, we introduce BioMADE, a novel ML framework that harnesses small-molecule-protein activity profiles from publicly available datasets to predict TdP risk without requiring exhaustive mechanistic annotation. Activity data from ChEMBL were used to train individual models for each gene, which predict activity values for any given compound. A curated set of arrhythmia-relevant genes was then used to construct a latent biological embedding (BioMADE embedding) for each molecule. We validated the performance of these features in distinguishing biological elements such as ATC3 class, showing superior classification performance compared with representations such as Molformer (lacks biological information) and MACCS (limited chemical properties) (0.85 AUROC vs 0.81 and 0.73, respectively). BioMADE representations served as input to a support vector machine classifier to discriminate TdP-inducing drugs from safe compounds. BioMADE achieved an AUROC of 0.89 in internal validation, indicating strong predictive performance. Against state-of-the-art models such as ADMEThyst, BioMADE achieved an AUROC of 0.74 on ADMEThysts validation set (vs. 0.72 for ADMEThyst). When we combined both approaches, the AUROC reached 0.77. These results demonstrate that BioMADE provides a scalable, biology-informed, and generalizable approach for predicting drug-induced toxicities. By integrating protein activity profiles into toxicology modeling, our framework highlights the critical role of human biology in adverse drug reaction prediction, an aspect often overshadowed by purely chemical or structural descriptors.

Most clinical trials fail due to either lack of efficacy or safety concerns. Human genetics can address both failure reasons: disease-associated genes are not only promising therapeutic targets but also predict drug side effects. However, because the same genetic signal underlies both outcomes, we need methods that disentangle which disease genes mediate therapeutic benefit versus adverse side effects. We use DraphNet, our previously developed model that maps drug molecular effects onto disease genes to generate two gene sets per drug: one linked to its therapeutic effects (IND genes) and one linked to its side effects (SE genes). We show that IND and SE genes overlap for 76% of the tested drugs (compared to a null model). We also show that drugs sharing greater IND similarity also have greater SE similarity ({rho}=0.57, p<1e-300). To show how our approach enables insights into drug biology, we construct groupings of drugs based on their IND and SE genes. We find that drugs in the same IND grouping are enriched for co-occurrence in the same SE grouping (OR=212.37). We present two examples to illustrate the kind of insights this network enables: identification of drugs with shared IND but distinct SE genes as repurposing candidates, and identification of drugs with shared SE but distinct IND genes to assist treatment selection in patients with comorbidities. Finally, we develop a neural network that directly links drug molecular effects onto disease genes and learns a gene-level score that quantifies each genes relative contribution to drug therapeutic versus side effects on disease.

We screened a 5 receptor x 7 aptamer = 35-cell cross-target matrix with HADDOCK3 [1] under blind ambiguous-interaction-restraint (AIR) protocols on AlphaFold-modelled receptors. The screen surfaced 12 operationally distinct failure modes (collapsing to [~]8 conceptual classes; [&#167;]3.1). The K_D-calibration subset is n = 4 cells with literature K_D records under matched assay conditions; the broader cohort includes [&ge;] 6 biological cognate or intended-cognate cells. The principal case study is P01031 (complement C5, 1676 aa, [&ge;] 12 structural domains): all 7 panel members produced positive HADDOCK3 top-1 scores under a scale-adaptive AIR. Score-term decomposition locates the anomaly in the AIR term (+217 to +268 to top-1 score). With AIR zeroed, scores fall to -131 to -74 -- the small-receptor regime. Boltz-2 cofolding chain-pair ipTM (cpi_AB) is an independent channel: P01031 shows the lowest median cpi_AB (0.211; 0/7 above the 0.5 confident-interface threshold). To our knowledge, this is the first reported case study of a 1676 aa multi-domain receptor exhibiting this signature under blind scale-adaptive AIR -- an n = 1 mechanistic case, not a statistical generalisation. We adapt the QSAR applicability domain concept [14-16] to in silico aptamer screening. [&#167;]3.7 reports an empirical Mode 1 mitigation (pLDDT-aware AIR prefilter; cohort Jaccard recovery [~]10x).

Understanding which disease genes are altered by a drug can provide insight into the biology of effect, help us understand adverse drug effects, and suggest new drug uses. Here, we build on our model Draphnet in a new formulation with a similar goal. Draphnet was designed to explain drug therapeutic and side effects by learning a network connecting drugs to the disease genes they alter. Our new model, DraPhormer, has a similar goal but instead of relying on a linear model, learning of drug to gene connections uses a transformer model. DraPhormer integrates drug molecular data, disease genetics, and known drug effects on diseases, along with language models representing all of these entities. We show in simulations that DraPhormer can explain the genetic mechanisms of drug effects. Then, we present our design for incorporating drug and disease biology into the model. Finally, we benchmark the models ability to learn drug indications and side effects in real data.

Counterfactual Explanation (CE) algorithms have been successfully applied to uncover the main factors driving computational diagnostic and prognostic predictions on tabular medical data. Recently, a new Network Medicine paradigm has been introduced for patient diagnosis and prognosis using Patient Similarity Networks (PSNs), i.e. graphs where patients are represented as nodes and their clinical and biomolecular similarities as edges. In this context, graph-based algorithms, including Graph Neural Networks (GNNs), can provide predictions using not only individual patient features but also their relations within a network of clinically and biomolecularly similar individuals. In this work, we propose the first CE algorithm tailored to explain diagnostic and prognostic predictions within PSNs. Alongside a contrastive GNN backbone, we introduce a versatile, model-agnostic counterfactual search method compatible with any underlying classifier. Preliminary results on synthetic data and on a cohort of patients affected by the Alzheimers disease show that our algorithm is competitive both with seminal tabular based CE algorithms and GNNExplainer, a well-established method for explaining graph-based classification tasks.

Drug-target affinity (DTA) prediction is a key task in drug discovery, enabling the estimation of the interaction strength between candidate compounds and biological targets. However, current models rely on connectivity-based molecular representations and do not explicitly account for the spatial organization, also known as stereochemistry. This limitation becomes evident when considering chirality, where a drug can exist as enantiomers, i.e., molecules that share the same atoms and bonds but differ in their three-dimensional arrangement. Despite their chemical similarity, they can interact differently with the same target, leading to variations in binding affinity and biological activity. In this paper, we propose a stereochemistry-aware DTA prediction framework that incorporates this information into molecular representations. Drug representations are learned from chemical structure using a directed-bond message passing graph neural network that captures enantiomers configurations, while protein targets are represented through sequence-based embeddings. Experiments on the Davis dataset demonstrate that our model can improve affinity prediction. Importantly, a case study on a manually curated dataset of enantiomers with different biological action shows that the model is able to distinguish the affinities in the two forms consistent with their experimentally observed biological activity. These findings support the relevance of stereochemistry-aware molecular representation for more accurate and chemically faithful DTA prediction.

We introduce the Serna Bio GenAI platform, a generative chemistry and multiparametric optimization platform for the design of RNA-targeting small molecules. Targeting RNA with small molecules has proven historically challenging but offers notable potential upsides, including access to unique mechanisms of action and the ability to target otherwise untargetable genes. We consider a major challenge here to be designing chemistry specific to RNA-targeting. Molecular design is a valuable application of AI in drug discovery, but many publicly available models use training data focused on protein-targeting - the modality best historically explored in drug discovery. We showcase the difference and value in building a specifically RNA-targeting platform, comparing its performance to state-of-the-art public chemical generators and experimentally validating its chemical designs in comparison to chemistry designed by a human expert.

In any field, unquestioningly accepting artificial intelligence (AI) results should be considered bad practise. Here, we devised a comparative modelling-based strategy for validating protein structures that exploits the well-known observation that protein folds are far more conserved than protein sequences. We identify proteins with a similar fold to the AlphaFold-generated query protein and determine their structural alignment to the query. The hypothesis is that if the sequence alignment coincides with the structural alignment, then the structure is validated. The strategy is implemented on a helix-by-helix and strand-by-strand basis using a multi-template pairwise local profile alignment method that works well into the twilight zone. The method is illustrated by application to the transmembrane transporter PEPT1, for which the structure is known, and the S-deacylases ABHD13 and ABHD16A, for which only AI-generated models exist. ABHD16A is particularly challenging because a sequence alignment search with BLASTp does not reveal any structural homologues and therefore requires work with extremely remote homologues; however, both models are validated through this strategy and are stable during classical molecular dynamics simulations. The ability of the strategy to identify errors is assessed with reference to misaligned ABHD13 models and misfolded decoy proteins.

Molecular similarity searching is a workhorse of cheminformatics, but the dominant Tanimoto/topological-fingerprint paradigm has well-known blind spots. It is highly sensitive to molecular size, suffers from steep activity cliffs, and frequently fails to retrieve scaffold-hopping bioisosteres. A complementary descriptor that has received comparatively little attention is global elemental composition. Despite the conceptual simplicity of comparing molecules by their elemental ratios, no widely deployed method exists for the statistically rigorous identification of "chemical twins" defined by stoichiometric proximity. We address this gap with TwinSAR (Stoichiometric Analysis and Retrieval), an adaptive kernel-based algorithm that combines three methodological innovations: (i) binary fingerprint blocking that partitions molecule by element-presence patterns and bounds the cost of all-pairs comparison from O(NM) to O({sum}nimi) enabling million/billion-scale searches; (ii) a per-block adaptive radial basis function (RBF) kernel whose precision parameter is calibrated independently for each fingerprint block via the median heuristic, providing fair similarity comparison across chemical sub-spaces of vastly different density; and (iii) a logit-transformed Z-score filter that maps bounded RBF scores onto an unbounded scale, allowing high-similarity pairs to be prioritized relative to the empirical score distribution of their own fingerprint block. TwinSAR is offered in two operating modes: (i) a deterministic BULK mode for exact reproducibility; and (ii) a stochastic FAST mode that achieved a 3.29x wall-clock speed-up in the present benchmark while preserving the similar unique-query and unique-target coverage. Statistical validation showed that detected twin pairs are 12.7x more similar in absolute ratio space than block-matched random pairs (p < 0.001), while a column-permutation negative control returned a median of zero spurious twins across three independent permutations. A controlled benchmark further established that an 8-element representation (single-element heavy-atom ratios) is sensitivity-equivalent to a comprehensive 254-element representation while running 3.55x faster. As a case study, TwinSAR was deployed in an end-to-end virtual screening pipeline against the BCL-2 target protein, where it reduced a 327,071-compound commercial library to a 390 focused candidate panel. The chemical interpretability of the retrieved twins is illustrated by their structural diversity around conserved heavy-atom skeletons. TwinSAR therefore provides a fast, conformation-free, and statistically principled prefilter that is fully orthogonal to topological fingerprints.

Selective inhibition of phosphodiesterase 4B (PDE4B) remains a promising strategy for preserving the anti-inflammatory benefit of PDE4 inhibition in chronic obstructive pulmonary disease while reducing PDE4D-associated tolerability liabilities. This study integrated SHAP-interpretable machine learning, natural product virtual screening, hierarchical docking, post-docking MM-GBSA, isoform cross-docking, binding-pocket comparison, ADMET prediction, and 100 ns molecular dynamics simulations to identify PDE4B-selective inhibitors from the LOTUS natural product database. A Random Forest classifier trained on curated ChEMBL PDE4B bioactivity data achieved an external performance with AUC-ROC = 0.955, accuracy = 0.893, F1-score = 0.896, MCC = 0.785, and prioritized 119,698 predicted actives from 276,518 LOTUS compounds. SHAP analysis identified BertzCT and TPSA as major contributors to predicted activity. Sequential Lipinski, PAINS, and QED filtering retained 14,210 candidates for structure-based evaluation. Extra precision docking identified four leads with PDE4B docking scores of -9.123 to -12.080 kcal/mol, all outperforming roflumilast (-7.658 kcal/mol). Cross-docking and post-docking MM-GBSA supported preferential PDE4B binding for three candidates. The top lead, LTS0048837, maintained a stable PDE4B-bound pose during simulation, with comparatively stronger interaction persistence than its PDE4D complex and the roflumilast reference. These findings nominate LTS0048837 as a computationally prioritized PDE4B-selective natural product lead requiring experimental enzyme, cellular, and pharmacokinetic validation.

Ab initio prediction of side effect frequencies is important for assessing the risk-benefit profile of drugs and for identifying potential adverse effects early in development. A key challenge is chirality: many drugs exist as enantiomers, pairs of molecules with the same atoms and bond connectivity but different three-dimensional arrangements. Although chemically similar, enantiomers can interact differently with biological targets and therefore exhibit distinct efficacy and adverse-effect profiles. Here we introduce F2S (Features to Signatures), a method to predict the frequencies of drug side effects while explicitly accounting for chirality. Drug representations are learned directly from chemical structure using a directed-bond message-passing graph neural network that captures stereochemical configurations. Side effect representations are derived from curated textual descriptions encoded with a frozen PubMedBERT model. Side effect frequencies are predicted from the dot product between drug and side effect signatures together with biases for drugs and side effects. We evaluated F2S extensively across multiple settings, including cold-start and warm-start prediction, prospective evaluation, and scenarios controlling for chemical similarity between training and test drugs. Across these evaluations, F2S achieves performance comparable to state-of-the-art methods for general side-effect frequency prediction while producing fewer false positives and substantially improves the prediction of frequency differences between enantiomer pairs. Finally, F2S learns compact 10-dimensional signatures that support interpretability: drug signatures reflect therapeutic class and shared targets, side-effect signatures capture phenotype similarity, and the learned bias terms correlate with the popularity of drugs and side effects.

Inflammation and oxidative stress (OS) are key to Parkinsons disease (PD). We performed a cross-dataset integrative transcriptomic analysis to identify OS- and inflammation-related hub genes persistently dysregulated in PD and to evaluate their response to nutrigenomic interventions using publicly available datasets. Four GEO datasets (GSE7621, GSE20141, GSE20146, GSE49036) were analysed to identify differentially expressed genes (DEGs), which were intersected with GeneCards OS-inflammation gene sets. Functional enrichment analyses, including gene ontology (GO), pathway over-representation analysis (ORA), and protein-protein interaction (PPI) analysis, were used to identify key pathways and hub genes. Gene-food bioactive compound (FBC) association was explored by integrating PD signatures with nutrigenomic profiles from NutriGenomeDB. We identified 183 DEGs in PD, enriched in synaptic, dopaminergic, OS, and inflammatory pathways. Intersection analysis yielded 26 OS-inflammation-related genes and 10 central regulators, including TH, DDC, SNCA, LRRK2, HSPB1, and HSPA1B. revealed opposing transcriptional patterns, with several FBCs suppressing stress-related genes and upregulating dopaminergic markers such as TH, GCH1, and DDC. Overall, this integrative analysis highlights OS-inflammation gene networks in PD and identifies candidate diet-gene interactions that warrant further experimental validation

Adverse drug events (ADEs) are a significant source of preventable patient harm, yet many ADE signals remain buried in free-text clinical notes. Clinical notes often describe adverse events (AEs) in relation to drugs in two ways: whether a drug causes the AE (the AE is an ADE) or a drug is given to treat an AE (it is considered the Reason for drug treatment). In the N2C2 2018 benchmark, ADEs and Reasons are annotated as separate entity types, despite often being similar in both wording and clinical meaning. This shared similarity makes them difficult to distinguish during entity extraction, leading to errors in relation classification. Therefore, we propose a two-stage framework that first detects AEs as a unified event category and then classifies drug-event pairs into Drug-ADE, Drug-Reason, or No-Relation. In the end-to-end evaluation on the N2C2 2018 benchmark, our system achieves F1 scores of 0.93 for Drug-ADE and 0.94 for Drug-Reason, improving over previously reported end-to-end benchmarks of 0.48 for Drug-ADE and 0.59 for Drug-Reason. Overall, these results support a more precise task formulation in which AEs are detected broadly first, and the ADE vs Reason distinction is resolved at the relation layer. Furthermore, they motivate the development of AE-focused datasets annotated independently of drug linkage to enable more reliable end-to-end pharmacovigilance systems.

ObjectiveHow structured clinical features and cluster-semantic embeddings interact under self-distillation in EHR prediction models is unknown. Existing approaches treat these sources separately (gradient-boosted trees exploit tabular features while sequence models process text), and their interaction under self-distillation regularisation remains uncharacterised. We introduce the Narrative Velocity (NV) framework and evaluate this interaction in a 7-model benchmark. Materials and MethodsCadence is a [~]5.86M-parameter residual multilayer perceptron (MLP) combining structured EHR features with frozen PubMedBERT embeddings of cluster-label strings under born-again self-distillation from a prior Cadence checkpoint (seed-42 teacher; [1]). Cadence is benchmarked against six comparators on MIMIC-IV v3.1 with dual-sex TRIPOD+AI reporting (5 student seeds for Cadence; 2-3 seeds for baselines). ResultsAt full-cohort scale, Cadence achieves 38.04 {+/-} 0.04% male and 35.66 {+/-} 0.04% female top-1 accuracy, exceeding the strongest non-neural baseline (XGBoost-2420, trained on the identical 2,420-dimensional input) by +1.35 pp male and +0.82 pp female (paired t-test on shared seeds 42-44: t(2) = 69.06, p = 2.10 x 10-4 male; t(2) = 25.32, p = 1.56 x 10-3 female). On time-to-next-event regression Cadence lowers MAE by 7.68 d male and 7.30 d female versus XGBoost-2420; FT-Transformer attains the lowest absolute MAE at full scale (27.58 d male, 36.63 d female), revealing a classification-regression trade-off across model families. A controlled 2 x 2 random-vector ablation isolates the self-distillation-embedding interaction at +0.49 pp top-1 (95% CI [0.35, 0.64] pp; bootstrap, n = 10,000 resamples; 3-teacher-seed mean +0.513 {+/-} 0.010 pp) under a matched-dimensionality null. A 3-teacher-seed validation (multi_teacher_02) confirms the interaction is robust to teacher-seed identity (per-seed values +0.525, +0.509, +0.507 pp; mean +0.513 {+/-} 0.010 pp). Cadence achieves the best Brier score among evaluated models (0.774 male / 0.798 female) but its raw probabilities are systematically miscalibrated (ECE 0.077 vs. XGBoost-884s 0.010); after a single scalar temperature scaling step (T * {approx} 0.81), ECE drops to {approx}0.028 while Brier remains best. On a small (n = 1,120 patients, 39,120 events) external OCR-extracted BWH cohort, Cadence ranked 3rd of 7 models with three confounded sources of error (institutional shift, OCR noise, centroid mapping); we therefore report this as a generalisation probe rather than a definitive external validation. At the longer h30 evaluation horizon Cadences MAE advantage reverses (47.35 d versus XGBoost 45.06 d), reflecting the absence of a matched-horizon self-distillation teacher. DiscussionThe 2 x 2 random-vector ablation confirms that the self-distillation gain on PubMedBERT embeddings (+0.78 pp) exceeds that on matched-dimensionality random vectors (+0.29 pp) by +0.49 pp, isolating the interaction to semantic content rather than feature dimensionality. The factorial decomposition (+0.49-0.51 pp interaction) and the sequential pipeline-level decomposition (Supplementary Table S3) are complementary triangulations under different reference frames and are not directly additive. ConclusionThis 7-model benchmark establishes a dual-sex, dual-metric, cross-institutional reference for next clinical event prediction under the TRIPOD+AI reporting framework. These results characterise discrimination and calibration on a single retrospective cohort; prospective evaluation, decision-curve analysis, and harm-benefit assessment are required before clinical deployment.

Foundation models (FMs) are powerful tools to allow the broad clinical application of artificial intelligence (AI) in healthcare systems, offering adaptability to different disease, modalities and clinical settings. However, FMs require large-scale datasets to train and fine-tune, while most real-world data are localized in siloed healthcare settings with strict data privacy protection, a restriction that poses a fundamental challenge in the cross-healthcare institution development of FMs. Here, we develop a fully homomorphic collaborative learning framework, named as FOCAL, that enables secure FM-driven diagnosis without exposing raw patient information. Different from traditional federated learning (FL) frameworks that aggregate locally trained models, FOCAL integrates fully homomorphic encryption (FHE) with split training to effectively execute collaborative learning completely over encrypted data. Specifically, we apply FOCAL on different types of retinal and pathology FMs to demonstrate its clinical performance. When facing gradient inversion attacks, FOCAL reduced the data leakage rate from 90.6% to 0% with comparable accuracy performance of the state-of-the-art FL paradigms, owing to the provable security provided by FHE. Moreover, under the same level of security, FOCAL can boost the macro-average AUROC by nearly 50% (from 0.5202 to 0.9831) when evaluated against fully encrypted FL models. In the multi-institution comparative experiments, FOCAL consistently outperforms all single-institution FMs, improving AUROCs by 9.62% and 14.46% on the ocular disease diagnosis and severity classification, respectively. Lastly, external validations on both retinal and pathology FMs further verified the accuracy and security advantages of FOCAL and highlighted its reliable interpretability and generalizability for cross-institution clinical development and implementation of FMs. FOCAL is a novel method to build a secure data-sharing AI community, facilitating healthcare institutions to benefit from and contribute to next-generation FMs development without compromising patient privacy and data security.

Matrixyl (palmitoyl pentapeptide-4, KTTKS core) is a collagen-stimulating peptide used in topical anti-ageing products, but its in-use efficacy is limited by poor permeation through the stratum corneum. We describe a deterministic computational workflow that combines a tournament genetic algorithm and NSGA-II with exact RDKit molecular descriptors to search the fixed-length, edit-distance-2 neighbourhood of KTTKS (3,706 candidate sequences) for analogs with descriptors more favourable for passive transdermal diffusion. The search returns a 9-member Pareto frontier that quantifies the trade-off between predicted permeability and motif preservation. Five of the nine frontier members carry the same substitution, lysine to proline at position 4 (K4P). This single change lowers the topological polar surface area by 25.6%, removes the +1 charge contributed by lysine, and reduces the functional-preservation score from 1.00 (KTTKS) to 0.67. The frontier ranking is unchanged by {+/-}30% perturbations to the TPSA and Mw penalty weights and by a 30% increase in the LogP penalty; only a 30% reduction in the LogP penalty produces rank movement. The frontier matches the ground-truth Pareto set obtained by exhaustive enumeration of all 3,706 candidates (precision and recall both 100%). On the basis of these results we recommend three sequences for experimental validation: PTTPS (largest predicted gain), KTTPS (single-mutation, conservative), and KTTPP (backup). All code, results, and figures are released under MIT and CC BY 4.0.