AI News Archive: August 11, 2026 — Part 17
Sourced from 500+ daily AI sources, scored by relevance.
- Desmin p.R406W mutation is associated with arrhythmias through structural and electrophysiological remodeling
Background and Aims. Mutations in the desmin (DES) gene cause a variety of cardiomyopathies associated with arrhythmias, yet the electrophysiological consequences of these variants remain largely uncharacterized. The aim of this study was to investigate the pathogenic mechanisms of the de novo DES p.R406W variant, which was identified in a 9-year-old patient who suffered from severe ventricular arrhythmias and sudden cardiac death without overt structural heart disease. Methods. Human induced pluripotent stem cell-derived cardiomyocytes (hiPSC-CMs) carrying the DES p.R406W variant (including the patient's line) were compared to isogenic controls. Action potentials (AP) of hiPSC-CMs were recorded using patch-clamp. Furthermore, 3D engineered heart tissues (EHTs) were generated from hiPSC-CMs and their APs were recorded with sharp microelectrodes. Analytical techniques also included transmission electron microscopy (TEM) and integrated transcriptomic and proteomic profiling. Finally, a heterozygous knock-in (KI) mouse model carrying the Des p.R405W ortholog was evaluated through surface ECG, echocardiography and ex vivo cardiac optical mapping. Results. The DES p.R406W mutation prolonged AP duration in IM-R406W hiPSC-CMs and EHTs vs Control ones. Multi-omics analysis of EHTs revealed a dysregulation of genes and proteins involved in contractile function, cell adhesion, and electrical activity. TEM imaging revealed changes in Z-disc architecture in mutant tissues. Twenty-week-old Des p.R405W KI mice exhibited ventricular conduction slowing (prolonged QRS) and a high susceptibility to ventricular tachyarrhythmias, likely due to reentrant mechanisms. Mild hypertrophy was also observed, but only in females. Conclusion. The DES p.R406W variant is highly pathogenic, causing electrical and structural remodeling of the myocardium. This study highlights the effectiveness of hiPSC-CMs and EHTs in recapitulating the clinical phenotype of desminopathy, providing a platform for investigating the mechanisms of early-onset cardiac arrhythmias and SCD.
- AbPACER: parent-aware, affinity-label-blind prioritization of affinity-matured scFv clones from phage-display NGS
Background: Affinity-maturation phage-display next-generation sequencing (NGS) yields more paired single-chain variable fragment clones than can be characterized experimentally, creating a fixed-budget prioritization problem. Read counts provide empirical support rather than direct affinity labels. We developed AbPACER (Antibody Parent-Aware Contextual Evidence Ranker), an affinity-label-blind neural ranker combining parent-relative mutation descriptors, frozen antibody-language-model context, and NGS evidence from related clones. AbPACER is campaign-adaptive rather than zero-shot: for each campaign, it is fitted to paired sequences and round-resolved R1-R3 counts before returning a 384-candidate assay list. We evaluated it in two retrospective phage-display campaigns and separately assessed its supervised mean-squared-error adaptation on AlphaSeq, denoted AbPACER-MSE. Results: From frozen top-5% candidate sets containing 16,323 Fas-associated factor 1 (FAF1) and 7,487 vascular endothelial growth factor receptor (VEGFR) clones, each method ranked the complete target-specific set and selected 384 candidates. In FAF1, AbPACER recovered 2.00 +/- 0.00 of seven retrospective panel clones, recovering two in every seed, compared with 1/7 by total count, 1.00 +/- 0.00 by Ens-Grad CNN, 1.67 +/- 1.15 by A2Binder-HL, and 1.33 +/- 0.58 by AbAffinity. In VEGFR, AbPACER recovered 2.33 +/- 0.58 of three panel clones, the highest observed learned-method mean, whereas total count recovered 3/3. No learned method was uniformly best at broader hypothetical budgets. On the public AlphaSeq common split of 11,670 fixed-test variants, AbPACER-MSE recovered 187.0 +/- 2.6 of the true top-384, closely matching AbAffinity (188.0 +/- 2.6) and exceeding A2Binder (175.7 +/- 6.4) and Ens-Grad CNN (154.0 +/- 6.1). AbPACER-MSE updated 1.378 million task-specific parameters, compared with 651.04 million for AbAffinity, and achieved Pearson 0.687 +/- 0.003 and Spearman 0.652 +/- 0.002. Conclusions: AbPACER provides a campaign-specific, parent-aware framework for fixed-budget prioritization from affinity-label-blind phage-display NGS data. At the 384-candidate endpoint, it showed the highest mean recovery among learned methods in both retrospective campaigns. AbPACER-MSE closely matched AbAffinity in true top-384 recovery while updating substantially fewer task-specific parameters. These results motivate prospective evaluation of sequence-conditioned reranking as a complement to count-based prioritization.
- Convergent biology, divergent drivers: a cross-species comparison of human and canine invasive urothelial carcinoma
Traditional animal models are often inbred and genetically uniform. This makes them powerful for controlled experiments, but it limits how well they represent the patient-to-patient variation seen in real-world disease. Comparative oncology seeks to address this gap by studying naturally occurring cancers in outbred companion animals, especially dogs. Canine medicine offers two important advantages: first, prospective trials can often be completed faster than in humans and second, dogs are already part of the translational pipeline through pharmacokinetic and toxicology studies. Here, we assessed the transcriptional fidelity of human and canine invasive urothelial carcinoma in primary tumors and patient-derived organoids. We then used single-cell and spatial data to resolve the underlying cellular organization. Despite strong species and platform differences, human and canine tumors preserved the same major luminal-basal structure and a similar tumor microenvironment. The two species reached this shared biology through different recurrent mutations. These included FGFR3 alterations in humans and BRAF alterations in dogs, which converged on overlapping pathways and a luminal phenotype. Human and canine organoids also underwent a similar shift in culture. Both became more proliferative and metabolic while losing inflammatory programs. Thus, organoids preserved important tumor biology while introducing predictable platform effects. Single-cell and spatial analyses showed that the luminal-basal axis reflects a gradient of cell states organized around the tumor-stroma boundary, rather than two discrete tumor types. This helps explain why bulk RNA-sequencing subtypes are reproducible but coarse. Together, these findings define where canine and human bladder cancer agree, where they differ, and how dogs can support parallel therapeutic and diagnostic development.
- ASPIRE: the Amplicon Sequencing Profiler for Investigating Respiratory Ecosystems
Microbial communities inhabiting the respiratory tract contribute to health status through interactions with host physiology, immune function, and local environmental conditions. Advances in small subunit ribosomal RNA (SSU or 16S rRNA) gene amplicon sequencing enable culture-independent profiling of microbial communities as amplicon sequence variants (ASVs), revealing links between microbial dysbiosis and respiratory diseases, and the use of mass spectrometry to measure volatile organic compounds (VOCs) in exhaled breath shows emerging promise for biomarker discovery. Here we present ASPIRE, the Amplicon Sequencing Profiler for Investigating Respiratory Ecosystems, an accessible Nextflow workflow for processing, analyzing, and interpreting linked ASV-VOC data from respiratory microbiome studies. ASPIRE is designed to support scalable comparative analysis across respiratory sample types while preserving intermediate file outputs for inspection and reuse within a standardized file structure.
- Systematic assessment of the biological impact of cellular deconvolution on downstream analyses of disease transcriptomes
Background Cellular deconvolution methods estimate cell type proportions from bulk RNA seq data, typically using single cell RNA seq derived signatures, enabling separation of disease associated transcriptional changes into composition driven and cell intrinsic effects. However, these approaches depend on model assumptions and the stability of cell type signatures, and it remains unclear how deconvolution related uncertainties influence downstream analyses and biological conclusions. Results We systematically evaluated the effect of cell type correction on disease relevant transcriptomic insights, using Alzheimer's disease (AD) as a model and the Mount Sinai Brain Bank cohort as a primary dataset. Applying dtangle, selected after comparison with another deconvolution approach, we estimated cell type proportions across four brain regions and assessed how correction reshaped differential gene expression and pathway enrichment. Cell type correction (CTC) markedly altered differentially expressed gene (DEG) profiles in a region dependent manner: the superior temporal gyrus lost all significant signals, while the frontal pole gained DEGs with improved cross region concordance. At the pathway level, correction shifted enrichment from synaptic loss and immune activation toward suppression of stress response and immune regulatory programs, suggesting that composition changes partly obscure cell intrinsic regulatory signals. Overlap with AD genome wide association study loci and replication in an independent cohort indicated that cell intrinsic changes are more consistently validated than composition driven changes. Notably, KCNN2 and RIMS1, not currently recognized as canonical AD biomarkers, emerged as robust transcriptional signatures, potentially reflecting both compositiondriven and cell intrinsic dysregulation and warranting further investigation. Conclusions Parallel evaluation of uncorrected and CTC analyses distinguishes composition driven from cell intrinsic transcriptional effects and highlights robust disease signatures in heterogeneous tissues such as the brain.
- Highly contiguous genomes of Rhodnius prolixus and Triatoma rubida reveal the molecular basis of haematophagy evolution in Triatominae
Insects of the subfamily Triatominae, commonly known as kissing bugs, are obligate blood-feeding vectors of Trypanosoma cruzi, the causative agent of Chagas disease. Rhodnius prolixus is among the most epidemiologically important vectors in Latin America, whereas Triatoma rubida frequently invades homes and is a potential vector in the southern United States and northern Mexico. Triatomines likely evolved from predatory reduviid assassin bugs through a transition from feeding on arthropods associated with vertebrate hosts to feeding directly on vertebrate blood. To investigate the genomic basis of this ecological and dietary shift, we generated highly contiguous, near chromosome-level genome assemblies and structural gene annotations for R. prolixus and T. rubida. The new R. prolixus assembly improves scaffold N50 more than 40-fold over the current reference genome, from 1.1 to 43.9 Mb, while reducing assembly gaps by several orders of magnitude. Both assemblies exceed 97% BUSCO completeness. Comparative analyses with representative hemipteran genomes revealed expansions of gene families associated with chemosensation and metabolism, including detoxification, protein degradation, and digestion, together with signatures of positive selection in genes involved in digestive and sensory functions. These assemblies represent the most contiguous and complete genomic resources available for Triatominae and provide a robust foundation for investigating vector biology, host adaptation, and the evolutionary origins of blood feeding within Reduviidae.
- Epigenetic dysregulation of Th2 cytokine genes in MuSK myasthenia gravis and its modulation by immunosuppressive therapy
Background and objectives: Myasthenia gravis associated with antibodies against muscle-specific kinase (MuSK-MG) is a well-characterized IgG4-autoimmune disease, however, the mechanisms driving IgG4 predominance remain poorly understood. This study investigated whether promoter DNA methylation of cytokine genes involved in IgG4 class switching is associated with this immune response. Methods: Peripheral blood mononuclear cells were isolated from MuSK-MG patients (n=36), acetylcholine receptor myasthenia gravis (AChR-MG) patients as disease controls (n=7), and sex-matched healthy controls (n=12). Promoter DNA methylation of IL4, IL10, and IL13 was assessed by methylation-sensitive high-resolution melting and relative cytokine mRNA expression by qPCR. Associations with clinical variables, and antibody levels were subsequently evaluated. Results: MuSK-MG patients showed lower median IL13 promoter methylation compared with healthy controls (p = 0.004). Median IL4 promoter methylation was also reduced in MuSK-MG compared with healthy controls (p < 0.001) and AChR-MG disease controls (p < 0.001), whereas no differences were observed for IL10 promoter methylation. Relative mRNA expression of IL4 (p = 0.0005), IL10 (p = 0.0462), and IL13 (p = 0.0002) was increased in MuSK-MG compared with AChR-MG. Compared with healthy controls, only IL4 expression remained significantly increased (p < 0.0001). Promoter methylation was inversely correlated with relative mRNA expression for IL4 (p < 0.0001), while IL13 showed a similar but non-significant trend (p = 0.054), no association was observed for IL10. Multivariable analysis demonstrated that treatment at sampling was independently associated with lower IL10 and IL13 promoter methylation, whereas no associations were observed with age, sex, disease phase, or disease duration. Promoter methylation did not correlate with total serum IgG4 or anti-MuSK IgG4 levels. Discussion: MuSK-MG is associated with selective hypomethylation of IL4 and IL13 promoters accompanied by increased cytokine gene expression, while IL10 promoter methylation remains unchanged. The association between treatment and IL10 and IL13 promoter methylation suggests that immunosuppressive therapy may influence epigenetic regulation in MuSK-MG. Together, these findings support a role for epigenetic dysregulation of Th2-associated cytokines in the immunological environment associated with IgG4 subclass switch. To our knowledge, this is the first study investigating IL4, IL10, and IL13 promoter DNA methylation in MuSK-MG.
- fNIRS reveals that live social interactions and visual realism influence neural responses
The human face is central to social interactions, supporting the ability to interpret others' mental states using theory of mind (ToM). We examined whether functional near-infrared spectroscopy (fNIRS) would reveal brain-activation differences between live and pre-recorded social conversations in brain regions implicated in ToM. Furthermore, we examined whether activation depended on the visual realism of a social partner - viewed as a human or an animated avatar. By one view, social interactions may be dependent on how natural the social partner appears; by another view, social interactions may depend only upon the attribution of responses to a real human regardless of visual appearance. Neural activation for pre-recorded compared to live interactions was prolonged, consistent with extended cognitive effort. Activation patterns in the right temporoparietal junction differed between interacting with humans versus avatars, along with a stronger preference for looking at the eyes when interacting with a human (vs. avatar), underscoring the social relevance of real faces. Findings highlight the importance of both live interactions and facial realism in shaping social-cognitive processing, a finding with relevance for optimizing online social interactions.
- Physics-Informed Estimation of Electrostatic Attraction During Fingertip Sliding Under Varying Speed and Normal Force
Electrostatic actuation is an emerging technology for generating tactile sensations on capacitive touchscreens through voltage-induced attractive forces between a fingertip and the surface. However, accurate control of electrostatic attraction during natural touchscreen interactions remains challenging because the applied normal force and sliding speed continuously vary, and their effects on the fingertip--screen contact and resulting actuation strength are not fully characterized. Here, we show how normal force and sliding speed systematically alter fingertip--screen contact area and electrical impedance, and use these measured changes to estimate electrostatic attraction during sliding. Contact area, interaction forces, and electrical impedance were measured simultaneously as participants slid their fingertips across an electrostatic surface under systematically varied normal forces and sliding speeds. These measurements revealed condition-dependent changes in fingertip contact, electrical interaction impedance, effective capacitance, derived effective gap thickness, and electrostatic attraction. We then incorporated these measured contact quantities into a physics-informed, data-driven model based on parallel-plate capacitor theory, in which effective capacitance, apparent contact area, and effective voltage determine the estimated electrostatic attraction. The resulting model links force- and speed-dependent changes in these quantities to electrostatic attraction while accounting for inter-participant variability through a participant-specific scaling factor. These findings provide experimentally grounded guidance for designing electrostatic surface-haptic feedback and future adaptive control strategies under realistic touch conditions.
- Moirai: single-cell trajectory inference grounded in gene-level expression dynamics
Underlying the development of multicellular organisms is the process of cell differentiation, which is governed by the concerted and sequential change in gene expression. Various methods have been developed that employ scRNA-seq data to infer the position of a cell along a pseudo-temporal axis and identify relevant genes involved in the process. These trajectory inference methods typically rely on global transcriptomic changes and mathematical methods. However, overemphasis on large-scale transcriptomic changes may impair sensitivity to identify branching points and convergent trajectories, which are rather governed by small-scale transcriptional events. Motivated by this, we developed Moirai, a graph-based trajectory inference method that identifies gene expression patterns that change dynamically over a developmental continuum and leverages these to define a common pseudotime axis between all cells. In doing so, Moirai shifts the focus to individual gene dynamics, which enhances its ability to detect putative branching points that are masked by global transcriptomic similarities. We apply Moirai to four developmental datasets, where we demonstrate its ability to recover gene expression patterns of genes with a known involvement in the respective developmental process, motivating their use for defining a cell's pseudotime. We furthermore show that Moirai can robustly infer gene expression patterns across different embedding approaches, highlighting the value of moving the focus of the inference process to the small-scale transcriptional dynamics.
- Near-infrared phenomic and genomic prediction for seed protein in winter legume white lupin (Lupinus albus L.): A utility comparison
White lupin (Lupinus albus L.) is a cool-season grain legume with seed crude protein of 33-47%, competitive with soybean (Glycine max L.) meal. It also fixes nitrogen and mobilizes soil phosphorus. Because soybean is a summer crop, white lupin can occupy Southeastern winter fields as a complementary protein source. Breeding for seed protein is limited by the cost and throughput of reference phenotyping. To determine how each is best deployed, we compared the utility of near-infrared spectroscopy (NIRS)-based phenomic selection with genomic selection based on 246,847 SNPs from low-pass, whole genome sequencing in a panel of Auburn University breeding lines and USDA National Plant Germplasm System germplasm. A handheld NIR calibration against Dumas reference protein reached screening-grade accuracy. Under common cross-validation, phenomic predictive ability was 0.93 and genomic was 0.12. The low genomic value was consistent with moderate heritability and strong genotype-by-year interaction. Beyond predictive ability, NIRS recovered superior accessions the strictest selection intensity, and 40 to 60 reference assays sufficed to calibrate the model. Handheld NIRS is a low-cost tool for protein calibration and early-generation screening, while genomic prediction remains suited to parental selection, together supporting a complementary strategy for legume breeding
- PPAR-γ/PCK1 metabolic pathway modulate synovitis and fibrosis in KOA rats
Background: Knee osteoarthritis (KOA) is a prevalent degenerative joint disease in which synovial inflammation and fibrosis are closely linked to pain, stiffness, and functional limitation. Growing evidence suggests that metabolic dysregulation, particularly in lipid metabolism, is involved in KOA pathogenesis, but the underlying mechanisms remain incompletely defined. Methods: Sprague Dawley rats underwent bilateral anterior cruciate ligament transection to establish a KOA model; sham-operated rats served as controls. RNA sequencing of synovial tissues was performed to identify differentially expressed genes (DEGs) and enriched pathways, followed by GO/KEGG and GSEA analyses. In vivo, adeno-associated virus vectors were used to overexpress or knock down PPAR-{gamma} and phosphoenolpyruvate carboxykinase 1 (PCK1) via intra-articular injection. Ex vivo, primary rat fibroblast-like synoviocytes (FLSs) were stimulated with IL-1{beta} and transfected with PPAR-{gamma} or PCK1 siRNA/overexpression plasmids. synovitis and fibrosis were evaluated by HE, Masson, and Sirius Red staining, immunofluorescence, ELISA, RT-qPCR, and Western blotting. Results: RNA-seq revealed 621 up-regulated and 228 down-regulated genes in KOA synovium versus sham, with DEGs significantly enriched in PPAR signaling, adipocytokine, and AMPK pathways. Metabolism-related genes including Fabp5, Plin1, Adipoq, Lep, and Pck1 were up-regulated. GSEA indicated downregulation of PPAR-{gamma} signaling in KOA synovium. In vivo and ex vivo, PPAR-{gamma} expression was reduced in KOA, whereas PCK1, FABP5, and ADIPOQ were increased. PPAR-{gamma} overexpression alleviated synovial inflammation, collagen I deposition, and fibrosis, and suppressed FABP5, ADIPOQ, and PCK1 expression; PPAR-{gamma} knockdown produced the opposite effects. Functional studies showed that PCK1 overexpression aggravated synovial inflammatory cell infiltration and fibrosis, elevated IL-1-{beta}, IL-18, and TGF-{beta}, and decreased TIMP1 levels in serum, synovial tissue, and FLSs supernatants, whereas PCK1 silencing reversed these changes. Conclusions: The PPAR-{gamma}/PCK1 metabolic axis modulates synovitis and fibrosis in KOA. Downregulation of PPAR-{gamma} and consequent upregulation of PCK1 promote synovitis and fibrotic remodeling. These findings identify the PPAR-{gamma}/PCK1 pathway as a potential therapeutic target for KOA.
- Fast calcium-dependent fluorescent labeling for recording of neuronal activation
Calcium transients encode cellular and neuronal activity across timescales ranging from milliseconds to hours, yet linking these transient signals to downstream molecular states remains a major challenge. We recently introduced Caprola, a calcium-dependent protein labeling tool that converts calcium transients into permanent fluorescent marks for later analysis. In this way, Caprola enables tracking of neuronal activities in animal models as well as retrospective identification of labeled cells for isolation and transcriptomic analysis. However, the relatively slow labeling kinetics of Caprola required high concentrations of fluorophore probe and relatively long labeling times, which limits its sensitivity and applicability, in particular in vivo. To address this limitation, we generated Caprola variants with up to 29-fold faster labeling rates than their predecessor. We demonstrate that our new Caprola variants record calcium transients in cells and in zebrafish larval brains under conditions where previous Caprola variants did not show labeling. We further expand the applicability of Caprola to activity-dependent marking of postsynaptic compartments, opening new avenues for coupling functional activity histories with downstream molecular and transcriptomic analyses.
- Direct anti-inflammatory actions of N,N-dimethyltryptamine on microglia are revealed by proteomic profiling and receptor pharmacology
N,N-dimethyltryptamine (DMT) is an endogenous psychedelic tryptamine that has recently emerged as a promising therapeutic candidate for acute ischemic stroke. Although DMT consistently reduces infarct size, attenuates neuroinflammation, and improves functional outcome in experimental stroke, the cellular and receptor mechanisms underlying these effects remain poorly understood. Primary rat microglial cultures were used to examine the direct anti-inflammatory effects of DMT following lipopolysaccharide (LPS)-induced activation. Microglial morphology, phagocytosis, and proteomic alterations were analyzed. Radioligand binding assays determined the affinity of DMT for microglial sigma-1 receptors (Sig-1Rs). Pharmacological inhibition of Sig-1Rs and serotonin (5-HT) receptors was performed to define receptor-specific mechanisms. Translational relevance was evaluated in acute mouse brain slices subjected to mild oxygem-glucose deprivation (mOGD) and anoxic episodes, where microglial activation, spreading depolarizations (SDs), and neuronal injury were assessed. DMT directly suppressed LPS-induced microglial activation, promoted a homeostatic morphology, and reduced phagocytic activity. Proteomic profiling demonstrated that DMT selectively reprogrammed inflammatory pathways by suppressing proteins involved in cytokine and chemokine signaling and oxidative stress while largely preserving arachidonic acid-prostaglandin synthesis. DMT bound microglial Sig-1Rs with micromolar affinity comparable to that reported in whole-brain preparations. Pharmacological inhibition revealed that DMT-induced morphological reprogramming required both Sig-1R and serotonergic signaling, whereas suppression of phagocytosis was largely independent of either receptor pathway. In acute brain slices, DMT attenuated microglial activation, reduced SD propagation and ischemic neuronal injury, and tissue-level neuroprotection depended on serotonergic signaling. DMT directly targets microglia and selectively remodels inflammatory states rather than broadly suppressing microglial activation. The receptor mechanisms underlying its actions are context dependent, with Sig-1R and serotonergic signaling contributing differentially according to the cellular response and experimental model. These findings provide mechanistic insight into the neuroprotective actions of DMT and support its ongoing clinical translation as a potential therapy for ischemic stroke.
- Functional, transcriptomic, and proteomic profiles of human primary and stem cell-derived beta cells in a state of high insulin production and increased fragility
Insulin production is a cardinal feature of pancreatic {beta} cells. Studies in rodents show that {beta} cells can switch between low and high insulin gene activity states and that elevated insulin production makes {beta} cells more vulnerable to stresses associated with diabetes. In people, genetically elevated insulin production increases the risk of type 1 diabetes. Via effects on obesity, hyperinsulinemia contributes to the pathogenesis of type 2 diabetes. Here, we characterize {beta} cells in low and high INS gene activity states sorted from primary human islets transduced with INS-GFP adenovirus and differentiated INS-EGFP knock-in embryonic stem cells (SC{beta} cells). We profile {beta} cell function, protein synthesis, resilience to diabetes associated stress, single {beta} cell transcriptomes and their co-activity networks, and purified {beta} cell proteomes. We show that human {beta} cells transition between distinct states. High INS cells have elevated maturity marker mRNAs and proteins, increased protein translation, are larger, but also more susceptible to cell death when exposed to diabetes-relevant stresses. We also catalogue thousands of differences in proteins in high INS stem cell-derived {beta} cells compared directly with high INS primary {beta} cells. Our study improves our understanding of the delicate balance between insulin production and {beta} cell resilience and guides the engineering of better {beta} cells.
- A Multi-stage Precision Stratification (MPS) Framework for Navigating Adjuvant Immunotherapy in Hepatocellular Carcinoma After Resection
Background: Recurrence rates following curative resection for hepatocellular carcinoma (HCC) remain persistently high, benefit from adjuvant immunotherapy varies substantially across patients, and the field currently lacks a standardized framework to characterize the postoperative host immune contexture. Purpose: To propose and validate a Multi-stage Precision Stratification (MPS) framework and evaluate its value in prognostic stratification and prediction of immunotherapy response. Methods: The Immune Health Index (IHI = S + R - E) integrating immune surveillance (S), immune exhaustion (E), and immune reserve (R) was constructed to define four immune phenotypes. Prognostic value was assessed in four public HCC cohorts (n=931) with single-cell transcriptomic validation (GSE140228, 61,690 cells); a blood-count-based clinical version cIHI_v8 was constructed in the Qinghai QPHCC cohort (n=490 survival analysis). Results: IHI was an independent protective prognostic factor in TCGA-LIHC (multivariate HR=0.795, P=0.034); four-cohort random-effects meta-analysis yielded HR=0.818 (95% CI: 0.696-0.961), I-squared=31.4%. QPHCC cIHI_v8 multivariate HR=0.452, HR=0.715 after ALBI adjustment; Bayesian evidence synthesis yielded BF_10=1280 for cIHI_v8 (>100 constitutes Decisive evidence), whereas the 4-cohort meta BF_10=2.19 (Anecdotal). Following NLP-based reverse stage derivation (n=490, achieving full AJCC/BCLC stage coverage from 0%), IHI remained significant after AJCC adjustment (HR=0.8642, P=0.000079), IHI provided positive incremental C-index across all stage-adjusted models; stratified analysis showed the strongest effect in early-stage (AJCC I-II: HR=0.8109, P<0.0001) and MVI-negative patients (HR=0.8538, P=0.0020). Bootstrap 1000x resampling: median HR=0.8646 (95% CI: 0.7985-0.9443), all iterations yielded HR<1. Conclusions: The MPS framework provides a mechanism-driven biological stratification tool for adjuvant immunotherapy in post-resection HCC, moving from "fixed-protocol extrapolation" to "immune contexture navigation."
- Cine Cardiac MRI Captures Cardiovascular Disease Risk Beyond Established Clinical Risk Factors: Evidence from the UK Biobank
Early and accurate risk stratification of cardiovascular disease (CVD) is crucial to initiate timely preventive interventions. As large-scale multimodal clinical cohorts become increasingly available, there is growing interest in whether incorporating additional sources of information can improve CVD risk stratification. Cine cardiac MR (CMR) represents a compelling example of such a source, as it captures objective, high-dimensional structural and functional information about the heart, independent of patient-reported data. In this study, we deploy a flexible vision-tabular method to incorporate cine CMR into CVD risk assessment together with structured clinical data. Using a large prospective imaging cohort from the UK Biobank, we show that cine CMR encodes CVD risk beyond established risk scores, increasing AUROC by 0.036 over SCORE2, the best-performing traditional risk score (0.742 vs. 0.706, textit{p} = 0.04). Furthermore, we find that cine CMR achieves risk discrimination capabilities on par with automated, image-derived phenotypes, removing the dependency on segmentation pipelines. Lastly, we demonstrate that integrating cine CMR with clinical variables through a vision-tabular learning framework stabilizes risk prediction under real-world conditions of incomplete tabular data, a common challenge in clinical practice. Together, these findings position cine CMR as a promising modality for CVD risk assessment.
- Deep learning with multiscale spatial context improves global dengue suitability mapping
Infectious-disease risk models often rely on occurrence records that are incomplete and spatially biased by surveillance effort, diagnostic access, and outbreak history. Ecological niche modelling (ENM) can identify areas where disease occurrence is environmentally plausible, yet most approaches represent locations using only pointwise covariate values and therefore overlook the surrounding spatial context and rely on presence-only data. Here, we present a deep-learning framework for presence-only data that estimates relative disease suitability by comparing the environmental conditions surrounding reported occurrences with those sampled across the wider study area. The model processes gridded environmental patches at local, neighbourhood, and broader landscape scales, learns the contribution of each scale, and accommodates missing raster values. Using dengue virus as a global case study, we evaluate whether multiscale spatial representation improves upon point-based ENM baselines including random forest and maximum entropy (MaxEnt) under a spatially disjoint train-test design. The model achieved a Boyce index of 0.971 and an AUC of 0.976 on the held-out test set. Learned scale weights and ablation experiments indicated that neighbourhood context contributed most strongly, while local and broader-scale information provided complementary predictive signals. Compared with point-based baselines, the model identified 6-18% more environmentally suitable area across South Asia, Southeast Asia, and South America, encompassing tens of millions of residents. These findings demonstrate that multiscale spatial context can improve estimates of relative dengue suitability. More broadly, mask-aware convolutional density-ratio estimation provides a flexible framework for mapping environmentally structured pathogens from incomplete, presence-only occurrence data.
- Machine learning models for predicting prostate cancer and clinically significant prostate cancer at biopsy: An updated analysis of an expanded Japanese cohort
Background: A 2019 report from our institution described a multilayer artificial neural network (ANN) for predicting prostate cancer at biopsy in 334 patients, trained with TensorFlow 1.x and evaluated at three fixed step counts without separating hyperparameter selection from test evaluation. We re-analyzed an expanded cohort from the same institution using contemporary machine-learning practice. Methods: We pooled all available biopsy episodes from the same institutional database (n = 526; 524 after excluding one non-binary outcome code and one record with missing digital rectal examination [DRE] data), retaining the same seven predictors used in the original report (age, prior biopsy history, PSA, prostate volume, DRE, and MRI diffusion-weighted imaging findings in the peripheral and transition zones). Because 27 patients contributed more than one biopsy episode, we used patient-ID-grouped, stratified k-fold cross-validation (StratifiedGroupKFold; scikit-learn 1.8.0) with 3 and 5 folds, repeated over 10 random partitions, to avoid leakage between folds. Four classifiers were compared: L2-regularized logistic regression, gradient boosting, random forest, and a shallow (single hidden layer) multilayer perceptron. Two outcomes were modeled: detection of any prostate cancer, and detection of clinically significant prostate cancer (Gleason score [≥] 7). Results: Any-cancer prevalence was 55.7% (292/524) and Gleason score [≥] 7 prevalence was 39.7% (208/524). With repeated 5-fold cross-validation, gradient boosting gave the highest discrimination for any prostate cancer (mean AUC 0.826, 95% CI 0.823-0.830) and for Gleason score [≥] 7 (mean AUC 0.855, 95% CI 0.852-0.859), closely followed by random forest and logistic regression (AUC 0.81-0.85). The shallow multilayer perceptron performed worse and less consistently than the other three models (any-cancer AUC 0.671; Gleason score [≥] 7 AUC 0.742) and than the deeper five-hidden-layer ANN reported in 2019. Results with 3-fold cross-validation were essentially unchanged. Conclusions: In an expanded cohort, regularized logistic regression, gradient boosting, and random forest all discriminated prostate cancer at biopsy at least as well as the previously reported multilayer ANN, using far simpler models and a methodology that separates hyperparameter tuning from performance estimation. A shallow neural network offered no advantage over these simpler alternatives in this sample size. This is a preprint; the study has not undergone external peer review.
- Pushing a Frozen CXR Foundation Model: A LoRA Partial-Fine-Tuning Study on NIH ChestX-ray14 with a Model-Conditional Label-Flip Sensitivity Analysis
Foundation models for chest X-ray interpretation make it possible to adapt specialised visual representations with relatively small trainable modules. We report a retrospective study of Low-Rank Adaptation (LoRA) of Rad-DINO Vision Transformer Base with 14x14 patches (ViT-B/14) for 14-class multi-label classification on the National Institutes of Health (NIH) ChestX-ray14 dataset. The official test labels were accessed during earlier model development and configuration comparisons; consequently, every official-test result in this manuscript is explicitly descriptive and non-confirmatory. We used a patient-disjoint 90/10 split of the official trainval pool (77,988 training and 8,536 validation images) and retained the released 25,596-image test partition. The historically selected all-linear LoRA configuration with safe augmentation and g=37 produced a descriptive test macro AUROC of 0.8462 versus the frozen baseline of 0.8295. Comparisons of target modules, patch-token grids, and a Rad-DINO-specific local query head are reported as retrospective comparisons rather than unbiased model-selection evidence. A confident-learning diagnostic flagged 17,653 of 86,524 trainval images (20.4%); this is a model-based flag rate, not a ground-truth label-error rate. A separate counterfactual relabeling sensitivity analysis, which uses the same model to identify and rescore disagreements, changed the descriptive AUROC to approximately 0.9445 after 6,509 policy-defined flips. This value is not achieved model performance and is not a radiologist-audited label-quality ceiling. We provide a validation-only threshold and artifact protocol for future locked evaluation, but a genuinely untouched holdout and new locked selection are required for a confirmatory headline. The existing Zenodo record contains the 25 publication figures only.
- Protocol for the Development and Prospective Evaluation of ASHA Assist India: An AI-Assisted Mobile Platform for Community-Based Stroke Prevention in Rural India
Background Stroke remains one of the leading causes of mortality and long-term disability worldwide, with low- and middle-income countries bearing a disproportionate share of the global disease burden. In India, delays in risk identification, fragmented referral pathways, and limited continuity of preventive care present significant challenges, particularly in rural communities. As a frontline health worker Accredited Social Health Activists (ASHAs) are strategically positioned to support community-based stroke prevention; however, existing workflows are frequently constrained by multi-tasking, predominantly paper-based documentation and fragmented digital systems. Advances in mobile health, artificial intelligence along with digital health ecosystem provided by Ayushman Bharat Digital Mission (ABDM) provide an opportunity to strengthen community healthcare through integrated digital platforms. Objective This protocol describes the design, system architecture, and prospective evaluation framework of ASHA Assist India, an integrated AI-assisted mobile health platform intended to support community-based stroke prevention by connecting citizens, ASHA workers, Primary Health Centres (PHCs), and higher levels of healthcare facilities within a unified digital ecosystem. Methods ASHA Assist India has been designed as a modular, cloud-based digital health platform supporting standardized data collection, longitudinal health monitoring, referral management, and AI-assisted clinical decision support. The proposed system comprises four user-facing applications corresponding to citizens, ASHA workers, PHCs, and referral hospitals, integrated through a centralized backend providing authentication, secure data management, interoperability, analytics, and notification services. The AI framework includes three planned analytical modules: (i) population-level stroke risk stratification, (ii) longitudinal stroke risk prediction, and (iii) acute stroke symptom recognition. A prospective implementation study is planned to evaluate platform usability, feasibility, workflow integration, implementation outcomes, and operational performance within routine community healthcare settings. Future validation of the AI modules will be conducted using prospectively collected longitudinal datasets. Expected Impact The proposed platform aims to strengthen community-based stroke prevention by improving digital workflow integration, facilitating coordinated referral pathways, and supporting longitudinal monitoring through the existing healthcare providers at health and wellness centres like ASHA, Community Health Officers (CHOs), ANM, etc. Beyond stroke prevention, the modular architecture is intended to provide a scalable framework for future digital health programmes addressing multiple non-communicable diseases within primary healthcare systems. Publication of this protocol establishes a transparent implementation and evaluation framework that may guide future research, digital health innovation, and implementation science in resource-constrained settings.
- Are you found by AI?
Free scan: Make AI recommend your website
- Zugrow
Away you grow!
- Running Out of Data in AI
Is AI running out of high-quality training data?
- More than 1 billion people are using the Gemini app every month.
The Gemini app has officially surpassed 1 billion monthly users, making it the fastest-growing product in Google’s history. Here’s some data about how people are using G…
- Google’s Gemini app surges to 1 billion users
Google also shared numbers of how people are actually using the chatbot, with 63% of Gemini users talking directly to the assistant using the voice feature. Plus, Gemini now generates more than 150 million images every day, according to Google.
- Gemini Becomes Google’s Fastest-Growing Product Ever After Hitting 1 Billion Monthly Users
Google said in a Tuesday blog post 63% of users directly talk to Gemini, including more “voice only” users.
- Google’s Gemini App Hits 1 Billion Monthly Users
Google’s Gemini App Hits 1 Billion Monthly Users theinformation.com
- Google’s Gemini AI app passes 1 billion monthly active users
Google LLC’s Gemini artificial intelligence app has passed 1 billion monthly active users, making it the 14th product in the company’s history to reach that mark. The company announced the milestone today in a blog post from Josh Woodward, vice president of Google Labs, Gemini and AI Studio. Chief Executive Sundar Pichai said in a […] The post Google’s Gemini AI app passes 1 billion monthly active users appeared first on SiliconANGLE .
- Spotify will label ‘AI Persona’ profiles and exclude their music from recommendations
Spotify is introducing “AI Persona” labels for artist profiles that represent AI-generated identities and will exclude their music from editorial, algorithmic, and personalized recommendations by default.
- Spotify to slap 'AI Persona' badges on AI-generated artist profiles
Spotify to slap 'AI Persona' badges on AI-generated artist profiles Reuters
- Spotify Will Label A.I. Artists and Avoid Promoting Them
The new label, which will begin to be applied next month, is an effort by the streaming service to be more transparent about A.I.-generated music on its app.
- Spotify asks artists to disclose whether they’re humans or AI
Spotify asks artists to disclose whether they’re humans or AI Fortune
- Spotify responds to concerns over AI songs
Music streaming service Spotify has announced it is introducing a feature that will enable listeners to see if an artist is AI-generated.
- Spotify to ask artists to disclose whether they're humans or AI from Aug 11
Starting Aug. 11, Spotify will allow artists to identify themselves as AI-generated. The labels will begin appearing on artist profiles starting in mid-September.
- Spotify is introducing AI Persona tags to differentiate real artists from fake ones, vowing to become ‘the most transparent and trustworthy place to listen to music’ — but the tool isn’t targeting the music itself
Spotify's new AI Persona tags distinguish AI-generated artists from real humans, and the platform is excluding these artists from your recommendations.
- Spotify asks creators to label songs when they’re AI-generated
Spotify asks creators to label songs when they’re AI-generated The Straits Times
- Spotify to launch new badge identifying AI music in September
Spotify to launch badge identifying AI music
- Spotify will now tell you when an artist isn’t real
Spotify will label AI-generated artist identities and stop recommending their music by default beginning in mid-September.
- Spotify Will Start Labeling AI Artists on Its Platform Next Month
The human creators behind AI-generated profiles are encouraged to voluntarily identify themselves. If they don’t, the streaming platform says it has a plan to catch them.
- Spotify AI Persona labels will alert listeners if an artist isn't real
The streaming service has faced an onslaught of AI-generated music.
- Spotify Will Now Flag 'AI Personas' and Stop Recommending Their Music
Spotify Will Now Flag 'AI Personas' and Stop Recommending Their Music PCMag UK
- Spotify To Launch Badge Identifying AI Music
Spotify To Launch Badge Identifying AI Music Barron's
- Spotify’s AI Persona Label to Pluck AI Artists From Your Algorithm
Stamped on artist profiles, it’ll help listeners figure out who’s an AI musician, and who isn’t.
- Spotify says it won’t recommend music from ‘AI Personas’
Spotify will apply an ‘AI Persona’ badge to profiles that do ‘not represent a real person.’
- AI could help unlock more oil — and emissions
Move over, data centers. AI's climate impact may extend well beyond the electricity it consumes. Why it matters: A new peer-reviewed study finds AI could help produce more oil and natural gas — and produce a climate impact the authors argue could far outweigh the technology's benefits for renewable energy. Driving the news: The research, just published in a Nature journal, concludes AI's role in boosting oil and gas production would outweigh its climate benefits from accelerating renewable energy, leading to a net increase in emissions under a range of scenarios. The study is among the first to estimate how AI-driven gains in fossil fuel production could affect global emissions. "Most assessments of AI's climate impact are framed as a tradeoff between data center energy use and the emissions AI might help avoid through renewables and efficiency gains," said Holly Alpine, co-author of the paper. "What's missing from that calculation entirely is the other side of the same ledger: the emissions enabled from using AI to make fossil fuel production cheaper and more profitable," Alpine said. Holly Alpine and Will Alpine , former Microsoft employees who founded the nonprofit initiative Enabled Emissions Campaign in 2024, co-led the study with researchers from Purdue University and an independent researcher. How it works : AI can help oil companies find new resources and recover more from existing fields. It can also help renewable energy by improving forecasting and operations. The new study argues the fossil-fuel gains are likely to dominate. By the numbers : The researchers estimate AI could add emissions equal to roughly 1% to 5% of the global energy sector's 2024 emissions under the scenarios they modeled. The study estimates those emissions would be roughly three to 13 times the International Energy Agency's estimate of current data-center emissions. The other side : A spokesperson for the American Petroleum Institute, the oil industry's main trade group, disputed the idea that more energy and lower emissions are in conflict. "The U.S. oil and natural gas industry is continuing to produce more energy while reducing emissions by investing in better technology, implementing stronger operational practices and supporting science-based policy," API spokesperson Andrea Woods said in a statement. State of play: The oil industry's embrace of AI has accelerated over the past two years. Producers like Chevron, ExxonMobil, ADNOC and Aramco say AI is helping identify promising drilling prospects and improve recovery from existing fields. Oilfield-service giants SLB, Halliburton and Baker Hughes are deploying AI to guide drilling and optimize well placement. Analysts and consultancies, from Goldman Sachs to Wood Mackenzie, argue AI could lower production costs and increase economically recoverable reserves. The big picture : AI is a general-purpose technology that can boost productivity in both fossil fuels and clean energy. Some experts argue the more important question is which applications society chooses to prioritize. What they're saying : "I think cleantech is going to win anyway, so let's just focus on how we unlock clean energy resources with AI," said Brian Janous, who previously worked with Holly Alpine at Microsoft and now runs data center developer Cloverleaf Infrastructure. "I'm glad Will and Holly are doing what they're doing. I'm not sure what it's going to change, but at least it puts pressure on," he said. Zoom in : The researchers used a computer model of the global economy that estimates how AI-driven productivity gains ripple through energy markets. Across the study's 64 modeled scenarios, emissions declined only when fossil-fuel productivity gains from AI were zero, Holly Alpine said. The finding suggests that supporting renewable energy alone "will not get us" to lower emissions. Yes, but: The model doesn't attempt to estimate AI's potential to accelerate cleantech breakthroughs such as fusion or long-duration storage. "There is a lot of AI dreaming out there," said Michael Lazarus, senior scientist emeritus at the climate research group Stockholm Environment Institute who advised the authors on the study. "I don't know how one would anticipate that and model it." What we're watching: The study's authors are making a call that echoes that of many others working at the intersection of AI and environmental issues: more transparency. "If we can start with transparency about the effects, then we can start to think about how to govern it," said Will Alpine.
- SpaceXAI Announces AI Agents Product ‘Grok Bot’
SpaceXAI Announces AI Agents Product ‘Grok Bot’ theinformation.com
- Grok Bot wants to take work off your plate, not just answer your queries
Grok Bot, SpaceXAI and Cursor's new AI agent app, signs into your existing tools to complete real tasks on its own, only checking in when approval is needed.
- Grok Bot is an all-new iPhone and Mac app from SpaceXAI and Cursor
SpaceXAI and Cursor are in the process of becoming a single company , but first, the two firms are releasing an all-new iPhone and Mac app called Grok Bot.
- CoreWeave Shares Surge After Booming AI Demand Bolsters Outlook
CoreWeave Inc., a provider of computing that powers artificial intelligence systems, soared in late trading after the AI spending frenzy spurred faster sales growth than anticipated.