Graph AI generates neurological hypotheses validated in molecular, organoid, and clinical systems

• URL: http://arxiv.org/abs/2512.13724v1
• Date: Sat, 13 Dec 2025 06:55:20 GMT
• Title: Graph AI generates neurological hypotheses validated in molecular, organoid, and clinical systems
• Authors: Ayush Noori, Joaquín Polonuer, Katharina Meyer, Bogdan Budnik, Shad Morton, Xinyuan Wang, Sumaiya Nazeen, Yingnan He, Iñaki Arango, Lucas Vittor, Matthew Woodworth, Richard C. Krolewski, Michelle M. Li, Ninning Liu, Tushar Kamath, Evan Macosko, Dylan Ritter, Jalwa Afroz, Alexander B. H. Henderson, Lorenz Studer, Samuel G. Rodriques, Andrew White, Noa Dagan, David A. Clifton, George M. Church, Sudeshna Das, Jenny M. Tam, Vikram Khurana, Marinka Zitnik,
• Abstract summary: We present PROTON, a graph transformer that generates hypotheses across molecular, organoid, and clinical systems.<n>In Parkinson's disease, PROTON linked genetic risk loci to genes essential for dopaminergic neuron survival and predicted pesticides toxic to patient-derived neurons.<n>In bipolar disorder, PROTON predicted calcitriol as a candidate drug that reversed proteomic alterations observed in cortical organoids derived from BD patients.
• Score: 40.641407952995856
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Neurological diseases are the leading global cause of disability, yet most lack disease-modifying treatments. We present PROTON, a heterogeneous graph transformer that generates testable hypotheses across molecular, organoid, and clinical systems. To evaluate PROTON, we apply it to Parkinson's disease (PD), bipolar disorder (BD), and Alzheimer's disease (AD). In PD, PROTON linked genetic risk loci to genes essential for dopaminergic neuron survival and predicted pesticides toxic to patient-derived neurons, including the insecticide endosulfan, which ranked within the top 1.29% of predictions. In silico screens performed by PROTON reproduced six genome-wide $α$-synuclein experiments, including a split-ubiquitin yeast two-hybrid system (normalized enrichment score [NES] = 2.30, FDR-adjusted $p < 1 \times 10^{-4}$), an ascorbate peroxidase proximity labeling assay (NES = 2.16, FDR $< 1 \times 10^{-4}$), and a high-depth targeted exome sequencing study in 496 synucleinopathy patients (NES = 2.13, FDR $< 1 \times 10^{-4}$). In BD, PROTON predicted calcitriol as a candidate drug that reversed proteomic alterations observed in cortical organoids derived from BD patients. In AD, we evaluated PROTON predictions in health records from $n = 610,524$ patients at Mass General Brigham, confirming that five PROTON-predicted drugs were associated with reduced seven-year dementia risk (minimum hazard ratio = 0.63, 95% CI: 0.53-0.75, $p < 1 \times 10^{-7}$). PROTON generated neurological hypotheses that were evaluated across molecular, organoid, and clinical systems, defining a path for AI-driven discovery in neurological disease.

Related papers

• Transforming Multi-Omics Integration with GANs: Applications in Alzheimer's and Cancer [0.0]
  We introduce Omics-GAN, a Generative Adversarial Network (GAN)-based framework designed to generate high-quality synthetic multi-omics profiles.<n>We demonstrated Omics-GAN on three omics types (mRNA, methylation and DNA methylation) using the ROSMAP cohort for Alzheimer's disease.<n>A support vector machine (SVM) with repeated 5-fold cross-validation improved prediction accuracy compared to original omics profiles.<n>Boxplot analyses confirmed that synthetic data preserved statistical distributions while reducing noise and outliers.
  arXiv  Detail & Related papers  (2025-10-22T05:55:49Z)
• Design and Validation of a Responsible Artificial Intelligence-based System for the Referral of Diabetic Retinopathy Patients [65.57160385098935]
  Early detection of Diabetic Retinopathy can reduce the risk of vision loss by up to 95%.<n>We developed RAIS-DR, a Responsible AI System for DR screening that incorporates ethical principles across the AI lifecycle.<n>We evaluated RAIS-DR against the FDA-approved EyeArt system on a local dataset of 1,046 patients, unseen by both systems.
  arXiv  Detail & Related papers  (2025-08-17T21:54:11Z)
• Alz-QNet: A Quantum Regression Network for Studying Alzheimer's Gene Interactions [28.571441947616513]
  Alzheimer's, being a multifactorial disease, requires understanding the gene-gene interactions underlying it for theranostics and progress.<n>Our proposed Quantum Regression Network (Alz-QNet) introduces a pioneering approach with insights from the state-of-the-art Quantum Gene Regulatory Networks (QGRN)<n>Using the proposed Alz-QNet framework, we explore the interactions between key genes ($APP$, $FGF14$, $YY1$, $EGR1$, $GAS7$, $AKT3$, $SREBF2$, and $PLD
  arXiv  Detail & Related papers  (2025-08-06T04:31:49Z)
• Predicting Neoadjuvant Chemotherapy Response in Triple-Negative Breast Cancer Using Pre-Treatment Histopathologic Images [2.23127246021293]
  Triple-negative breast cancer (TNBC) remains a major clinical challenge due to its aggressive behavior and lack of targeted therapies.<n>We present an attention-based multiple instance learning framework designed to predict pathologic complete response (pCR) directly from pre-treatment hematoxylin and eosin (H&E)-stained biopsy slides.
  arXiv  Detail & Related papers  (2025-05-20T02:06:34Z)
• Towards an AI co-scientist [48.11351101913404]
  We introduce an AI co-scientist, a multi-agent system built on Gemini 2.0.<n>The AI co-scientist is intended to help uncover new, original knowledge and to formulate demonstrably novel research hypotheses.<n>The system's design incorporates a generate, debate, and evolve approach to hypothesis generation, inspired by the scientific method.
  arXiv  Detail & Related papers  (2025-02-26T06:17:13Z)
• scMamba: A Pre-Trained Model for Single-Nucleus RNA Sequencing Analysis in Neurodegenerative Disorders [43.24785083027205]
  scMamba is a pre-trained model designed to improve the quality and utility of snRNA-seq analysis.<n>Inspired by the recent Mamba model, scMamba introduces a novel architecture that incorporates a linear adapter layer, gene embeddings, and bidirectional Mamba blocks.<n>We demonstrate that scMamba outperforms benchmark methods in various downstream tasks, including cell type annotation, doublet detection, imputation, and the identification of differentially expressed genes.
  arXiv  Detail & Related papers  (2025-02-12T11:48:22Z)
• Using Pre-training and Interaction Modeling for ancestry-specific disease prediction in UK Biobank [69.90493129893112]
  Recent genome-wide association studies (GWAS) have uncovered the genetic basis of complex traits, but show an under-representation of non-European descent individuals. Here, we assess whether we can improve disease prediction across diverse ancestries using multiomic data.
  arXiv  Detail & Related papers  (2024-04-26T16:39:50Z)
• Deep Phenotyping of Non-Alcoholic Fatty Liver Disease Patients with Genetic Factors for Insights into the Complex Disease [1.7527259446915058]
  Non-alcoholic fatty liver disease (NAFLD) is a prevalent chronic liver disorder characterized by the excessive accumulation of fat in the liver. We aim to identify subgroups of NAFLD patients based on demographic, clinical, and genetic characteristics.
  arXiv  Detail & Related papers  (2023-11-13T19:31:12Z)
• minoHealth.ai: A Clinical Evaluation Of Deep Learning Systems For the Diagnosis of Pleural Effusion and Cardiomegaly In Ghana, Vietnam and the United States of America [0.0]
  We evaluate how well minoHealth.ai systems, developed my minoHealth AI Labs, will perform at diagnosing cardiomegaly and pleural effusion. chest x-rays from Ghana, Vietnam and the USA, and how well AI systems will perform when compared with radiologists working in Ghana. For cardiomegaly, minoHealth.ai systems scored Area under the Receiver operating characteristic Curve (AUC-ROC) of 0.9 and 0.97 while the AUC-ROC of individual radiologists ranged from 0.77 to 0.86.
  arXiv  Detail & Related papers  (2022-10-31T20:12:41Z)
• Controlling False Positive/Negative Rates for Deep-Learning-Based Prostate Cancer Detection on Multiparametric MR images [58.85481248101611]
  We propose a novel PCa detection network that incorporates a lesion-level cost-sensitive loss and an additional slice-level loss based on a lesion-to-slice mapping function. Our experiments based on 290 clinical patients concludes that 1) The lesion-level FNR was effectively reduced from 0.19 to 0.10 and the lesion-level FPR was reduced from 1.03 to 0.66 by changing the lesion-level cost.
  arXiv  Detail & Related papers  (2021-06-04T09:51:27Z)
• Disentangling brain heterogeneity via semi-supervised deep-learning and MRI: dimensional representations of Alzheimer's Disease [2.7724592931061016]
  We describe Smile-GAN, a novel semi-supervised deep-clustering method, which dissects neuroanatomical heterogeneity. Smile-GAN identified 4 neurodegenerative patterns/axes, including P1, normal anatomy and highest cognitive performance; P2, mild/diffuse atrophy and more prominent executive dysfunction; P3, focal medial temporal atrophy and relatively greater memory impairment; P4, advanced neurodegeneration.
  arXiv  Detail & Related papers  (2021-02-24T22:09:16Z)
• Predicting Prostate Cancer-Specific Mortality with A.I.-based Gleason Grading [2.752534470219667]
  We developed a system to predict prostate-cancer specific mortality via A.I.-based Gleason grading. We evaluated its ability to risk-stratify patients on an independent retrospective cohort of 2,807 prostatectomy cases.
  arXiv  Detail & Related papers  (2020-11-25T02:05:24Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.