Feedback is delighted to learn that researchers have discovered what Taylor Swift is accidentally doing to rescue the science of plants from mid-ness. We never miss a beat, so Feedback, prompted by assistant news editor and Swiftie Alexandra Thompson, has been taking a close look at a major paper in the Annals of Botany, published in August. It is called "Dance with plants: Taylor Swift's music videos as advance organizers for meaningful learning in botany" . The thesis is that high school students exhibit "a general low interest in plants", leading to "plant blindness". Teachers struggling to convey the magic of botany are repeating material and are getting sick of it.

Modern scientific discovery faces growing challenges in integrating vast and heterogeneous knowledge critical to breakthroughs in biomedicine and drug development. Traditional hypothesis-driven research, though effective, is constrained by human cognitive limits, the complexity of biological systems, and the high cost of trial-and-error experimentation. Deep learning models, especially graph neural networks (GNNs), have accelerated prediction generation, but the sheer volume of outputs makes manual selection for validation unscalable. Large language models (LLMs) offer promise in filtering and hypothesis generation, yet suffer from hallucinations and lack grounding in structured knowledge, limiting their reliability. To address these issues, we propose HypoChainer, a collaborative visualization framework that integrates human expertise, LLM-driven reasoning, and knowledge graphs (KGs) to enhance hypothesis generation and validation. HypoChainer operates in three stages: First, exploration and contextualization -- experts use retrieval-augmented LLMs (RAGs) and dimensionality reduction to navigate large-scale GNN predictions, assisted by interactive explanations. Second, hypothesis chain formation -- experts iteratively examine KG relationships around predictions and semantically linked entities, refining hypotheses with LLM and KG suggestions. Third, validation prioritization -- refined hypotheses are filtered based on KG-supported evidence to identify high-priority candidates for experimentation, with visual analytics further strengthening weak links in reasoning. We demonstrate HypoChainer's effectiveness through case studies in two domains and expert interviews, highlighting its potential to support interpretable, scalable, and knowledge-grounded scientific discovery.

"Alexa," I asked the Echo display in my kitchen, "what was that song from The Hills? You know, that MTV show? Can you play it on the Echo Show in the office?" The old Alexa wouldn't have had a prayer of answering such a poorly worded query. But the new Alexa, now packing AI-enhanced smarts, handled it easily.

Neurodegenerative diseases (NDDs) are complex and lack effective treatment due to their poorly understood mechanism. The increasingly used data analysis from Single nucleus RNA Sequencing (snRNA-seq) allows to explore transcriptomic events at a single cell level, yet face challenges in interpreting the mechanisms underlying a disease. On the other hand, Neural Network (NN) models can handle complex data to offer insights but can be seen as black boxes with poor interpretability. In this context, explainable AI (XAI) emerges as a solution that could help to understand disease-associated mechanisms when combined with efficient NN models. However, limited research explores XAI in single-cell data. In this work, we implement a method for identifying disease-related genes and the mechanistic explanation of disease progression based on NN model combined with SHAP. We analyze available Huntington's disease (HD) data to identify both HD-altered genes and mechanisms by adding Gene Set Enrichment Analysis (GSEA) comparing two methods, differential gene expression analysis (DGE) and NN combined with SHAP approach. Our results show that DGE and SHAP approaches offer both common and differential sets of altered genes and pathways, reinforcing the usefulness of XAI methods for a broader perspective of disease.

Wearable sensors offer a non-invasive way to collect physical activity (PA) data, with walking as a key component. Existing models often struggle to detect gait bouts in individuals with neurodegenerative diseases (NDDs) involving involuntary movements. We developed J-Net, a deep learning model inspired by U-Net, which uses a pre-trained self-supervised foundation model fine-tuned with Huntington`s disease (HD) in-lab data and paired with a segmentation head for gait detection. J-Net processes wrist-worn accelerometer data to detect gait during daily living. We evaluated J-Net on in-lab and daily-living data from HD, Parkinson`s disease (PD), and controls. J-Net achieved a 10-percentage point improvement in ROC-AUC for HD over existing methods, reaching 0.97 for in-lab data. In daily-living environments, J-Net estimates showed no significant differences in median daily walking time between HD and controls (p = 0.23), in contrast to other models, which indicated counterintuitive results (p < 0.005). Walking time measured by J-Net correlated with the UHDRS-TMS clinical severity score (r=-0.52; p=0.02), confirming its clinical relevance. Fine-tuning J-Net on PD data also improved gait detection over current methods. J-Net`s architecture effectively addresses the challenges of gait detection in severe chorea and offers robust performance in daily living. The dataset and J-Net model are publicly available, providing a resource for further research into NDD-related gait impairments.

Background: Huntington's disease (HD) is a rare, genetically determined brain disorder that limits the life of the patient, although early prognosis of HD can substantially improve the patient's quality of life. Current HD prognosis methods include using a variety of complex biomarkers such as clinical and imaging factors, however these methods have many shortfalls, such as their resource demand and failure to distinguish symptomatic and asymptomatic patients. Quantitative biomedical signaling has been used for diagnosis of other neurological disorders such as schizophrenia and has potential for exposing abnormalities in HD patients. Methodology: In this project, we used a premade, certified dataset collected at a clinic with 27 HD positive patients, 36 controls, and 6 unknowns with electroencephalography, electrocardiography, and functional near-infrared spectroscopy data. We first preprocessed the data and extracted a variety of features from both the transformed and raw signals, after which we applied a plethora of shallow machine learning techniques. Results: We found the highest accuracy was achieved by a scaled-out Extremely Randomized Trees algorithm, with area under the curve of the receiver operator characteristic of 0.963 and accuracy of 91.353%. The subsequent feature analysis showed that 60.865% of the features had p<0.05, with the features from the raw signal being most significant. Conclusion: The results indicate the promise of neural and cardiac signals for marking abnormalities in HD, as well as evaluating the progression of the disease in patients.

Experts have discovered an'impulsivity switch' in the brain that lets mammals suppress the urge to'jump the gun' and only act when the time is right. In lab experiments on mice, researchers found a brain area that's responsible for driving action and another that's responsible for suppressing that drive. Manipulating neurons, also known as nerve cells, in these areas can override our ability to control the urge to jump the gun and therefore trigger impulsive behaviour. Keeping the'impulsivity switch' on is how athletes stop themselves from running before the starting gun has fired, how dogs obey a command to resist a treat, or how lions in the wild can wait for the perfect moment to pounce on its prey. Keeping our'impulsivity switch' on is how athletes stop themselves from running before the starting gun has fired (file photo) 'We discovered a brain area responsible for driving action and another for suppressing that drive,' said study author Joe Paton, director of the Champalimaud Neuroscience Programme in Lisbon, Portugal.

IBM is using its AI-based health prediction skills to help tackle the challenge of Huntington's disease. The tech firm has teamed up with CHDI Foundation on an artificial intelligence model that can predict when patients will experience Huntington's symptoms and, crucially, determine how rapidly those symptoms will progress. The team used MRI brain scans to train the AI, using signals from white matter (relatively untapped in brain studies) to help the system gauge how cognitive and motor performance will change over time. The existing understanding of the disease only indicates that symptoms tend to materialize between the ages of 30 and 50, not which symptoms and how they'll evolve. The researchers are "optimistic" that a single MRI scan could produce more accurate estimates of functional decline across multiple categories.

Researchers at McGill University showed that analysis of blood samples using artificial intelligence (AI) could predict and provide a more comprehensive explanation for the progression of neurodegenerative diseases. The findings were published in the journal Brain. The results were gathered from analyzing the blood-brain samples of over 1,900 patients with the presence of late-onset Alzheimer's and Huntington's disease. Researchers used a novel gene expression contrastive trajectory inference (GE-cTI) method able to unveil enriched temporal patterns, while also predicting neuropathological severity among affected participants. Spanning decades, the machine learning algorithm identified how the patients' genes expressed themselves uniquely, a first study of which revealed how molecular changes underlies neurodegeneration.

Tencent (a Chinese technology company) and Medicaid (a medical firm established in the U.K.) formed a partnership to create AI when monitoring patients with Parkinson's disease. They collaborated in developing an app that produces a video test for find hand movements. The app uses the device's camera to record the patient opening and closing their hands. The recording is then turned into a graph which is then sent to a medical professional for examination. Currently, the app takes 30 minutes to send results however Tencent and Medopad are working to decrease the hold-up time to 3 minutes.