Life Sciences

193 items

Nature Sep 14, 2026
A Nature news report describes a proof-of-concept study published in Nature Neuroscience in which a single surgically implanted 253-electrode array covering a fairly large area of the sensorimotor cortex, combined with artificial intelligence, simultaneously decoded attempted phrases and attempted or imagined gestures in two participants with impaired speech and movement after a brainstem stroke or with amyotrophic lateral sclerosis, producing on-screen text and driving a personalized animated avatar within seconds of the user’s intent, thereby translating both verbal and non-verbal communication through one implant.
A Nature news report describes a proof-of-concept study published in Nature Neuroscience in which a single surgically implanted 253-electrode array covering a fairly large area of the sensorimotor cortex, combined with artificial intelligence, simultaneously decoded attempted phrases and attempted or imagined gestures in two participants with impaired speech and movement after a brainstem stroke or with amyotrophic lateral sclerosis, producing on-screen text and driving a personalized animated avatar within seconds of the user’s intent, thereby translating both verbal and non-verbal communication through one implant.
‘Multifunctional’ brain implant translates speech and gestures in real time
A Nature news report describes a proof-of-concept study published in Nature Neuroscience in which a single surgically implanted 253-electrode array covering a fairly large area of the sensorimotor cortex, combined with artificial intelligence, simultaneously decoded attempted phrases and attempted or imagined gestures in two participants with impaired speech and movement after a brainstem stroke or with amyotrophic lateral sclerosis, producing on-screen text and driving a personalized animated avatar within seconds of the user’s intent, thereby translating both verbal and non-verbal communication through one implant.
A Nature news report describes a proof-of-concept study published in Nature Neuroscience in which a single surgically implanted 253-electrode array covering a fairly large area of the sensorimotor cortex, combined with artificial intelligence, simultaneously decoded attempted phrases and attempted or imagined gestures in two participants with impaired speech and movement after a brainstem stroke or with amyotrophic lateral sclerosis, producing on-screen text and driving a personalized animated avatar within seconds of the user’s intent, thereby translating both verbal and non-verbal communication through one implant.
Journal of Infection and Chemotherapy Sep 14, 2026
This pilot study collected ticks between May 2023 and December 2024 from patients presenting tick bites at 10 medical institutions in Okayama, Hiroshima, and Kagawa prefectures, supplemented with wild tick images, and developed a two-stage AI pipeline of object detection and genus-level classification in which a YOLO-based model trained on 3258 annotated public images achieved mAP@0.5 of 0.954 and ResNet50 achieved mean validation accuracy of 95% on 533 tick images covering four genera, integrating the system into a prototype smartphone application with geospatial visualization to support clinical risk assessment and public health surveillance.
This pilot study collected ticks between May 2023 and December 2024 from patients presenting tick bites at 10 medical institutions in Okayama, Hiroshima, and Kagawa prefectures, supplemented with wild tick images, and developed a two-stage AI pipeline of object detection and genus-level classification in which a YOLO-based model trained on 3258 annotated public images achieved mAP@0.5 of 0.954 and ResNet50 achieved mean validation accuracy of 95% on 533 tick images covering four genera, integrating the system into a prototype smartphone application with geospatial visualization to support clinical risk assessment and public health surveillance.
Development of an AI-Based Smartphone Application for Rapid Tick Identification and Geospatial Mapping: A Pilot Study
This pilot study collected ticks between May 2023 and December 2024 from patients presenting tick bites at 10 medical institutions in Okayama, Hiroshima, and Kagawa prefectures, supplemented with wild tick images, and developed a two-stage AI pipeline of object detection and genus-level classification in which a YOLO-based model trained on 3258 annotated public images achieved mAP@0.5 of 0.954 and ResNet50 achieved mean validation accuracy of 95% on 533 tick images covering four genera, integrating the system into a prototype smartphone application with geospatial visualization to support clinical risk assessment and public health surveillance.
This pilot study collected ticks between May 2023 and December 2024 from patients presenting tick bites at 10 medical institutions in Okayama, Hiroshima, and Kagawa prefectures, supplemented with wild tick images, and developed a two-stage AI pipeline of object detection and genus-level classification in which a YOLO-based model trained on 3258 annotated public images achieved mAP@0.5 of 0.954 and ResNet50 achieved mean validation accuracy of 95% on 533 tick images covering four genera, integrating the system into a prototype smartphone application with geospatial visualization to support clinical risk assessment and public health surveillance.
Magnetic resonance in medicine Sep 14, 2026
This work proposes ESPIRiT-Diffusion, a physics-guided score-based diffusion reconstruction framework that incorporates multi-set ESPIRiT coil sensitivity map-based data-consistency constraints into the Langevin equation for 8.8- and 10.7-fold accelerated joint intracranial and carotid vessel wall imaging (VWI) at 0.6 mm³ isotropic resolution; in retrospective experiments with Cartesian, CAIPI, and variable-density undersampling it showed improved reconstruction performance compared with ESPIRiT, DL-ESPIRiT, SENSE-Diffusion, and SPIRiT-Diffusion with better preservation of fine vessel wall structures, and in prospective patient experiments it provided favorable visualization of vessel wall lesions with no statistically significant differences in reader scores from the 3-fold CS reference a
This work proposes ESPIRiT-Diffusion, a physics-guided score-based diffusion reconstruction framework that incorporates multi-set ESPIRiT coil sensitivity map-based data-consistency constraints into the Langevin equation for 8.8- and 10.7-fold accelerated joint intracranial and carotid vessel wall imaging (VWI) at 0.6 mm³ isotropic resolution; in retrospective experiments with Cartesian, CAIPI, and variable-density undersampling it showed improved reconstruction performance compared with ESPIRiT, DL-ESPIRiT, SENSE-Diffusion, and SPIRiT-Diffusion with better preservation of fine vessel wall structures, and in prospective patient experiments it provided favorable visualization of vessel wall lesions with no statistically significant differences in reader scores from the 3-fold CS reference a
ESPIRiT-Diffusion: Physics-Guided Diffusion Model Reconstruction for Highly Accelerated Joint Intracranial and Carotid Vessel Wall Imaging
This work proposes ESPIRiT-Diffusion, a physics-guided score-based diffusion reconstruction framework that incorporates multi-set ESPIRiT coil sensitivity map-based data-consistency constraints into the Langevin equation for 8.8- and 10.7-fold accelerated joint intracranial and carotid vessel wall imaging (VWI) at 0.6 mm³ isotropic resolution; in retrospective experiments with Cartesian, CAIPI, and variable-density undersampling it showed improved reconstruction performance compared with ESPIRiT, DL-ESPIRiT, SENSE-Diffusion, and SPIRiT-Diffusion with better preservation of fine vessel wall structures, and in prospective patient experiments it provided favorable visualization of vessel wall lesions with no statistically significant differences in reader scores from the 3-fold CS reference a
This work proposes ESPIRiT-Diffusion, a physics-guided score-based diffusion reconstruction framework that incorporates multi-set ESPIRiT coil sensitivity map-based data-consistency constraints into the Langevin equation for 8.8- and 10.7-fold accelerated joint intracranial and carotid vessel wall imaging (VWI) at 0.6 mm³ isotropic resolution; in retrospective experiments with Cartesian, CAIPI, and variable-density undersampling it showed improved reconstruction performance compared with ESPIRiT, DL-ESPIRiT, SENSE-Diffusion, and SPIRiT-Diffusion with better preservation of fine vessel wall structures, and in prospective patient experiments it provided favorable visualization of vessel wall lesions with no statistically significant differences in reader scores from the 3-fold CS reference a
medRxiv Sep 14, 2026
Using 5,613 autopsy cases from the Mayo Clinic Brain Bank collected between 1998 and 2023, this study fine-tuned a large language model to convert narrative gross descriptions into semi-quantitative scores for 39 features (extraction accuracy 0.95 on 200 manually annotated feature-level test examples), then classified seven neuropathologic diagnostic categories with a CatBoost classifier and a second fine-tuned LLM, both including age at death, sex, and brain weight; on a held-out test set of 562 cases CatBoost reached accuracy 0.73, kappa 0.65, and macro-average AUC 0.92, while the text-based LLM reached accuracy 0.75 and kappa 0.68, with macro-average sensitivity 0.66 for both, PSP sensitivity 0.92 and 0.93, MSA sensitivity 0.87 and 0.92, but AD-LBD sensitivity only 0.21 and 0.
Using 5,613 autopsy cases from the Mayo Clinic Brain Bank collected between 1998 and 2023, this study fine-tuned a large language model to convert narrative gross descriptions into semi-quantitative scores for 39 features (extraction accuracy 0.95 on 200 manually annotated feature-level test examples), then classified seven neuropathologic diagnostic categories with a CatBoost classifier and a second fine-tuned LLM, both including age at death, sex, and brain weight; on a held-out test set of 562 cases CatBoost reached accuracy 0.73, kappa 0.65, and macro-average AUC 0.92, while the text-based LLM reached accuracy 0.75 and kappa 0.68, with macro-average sensitivity 0.66 for both, PSP sensitivity 0.92 and 0.93, MSA sensitivity 0.87 and 0.92, but AD-LBD sensitivity only 0.21 and 0.
Diagnostic Value of Large Language Model-Extracted Gross Brain Findings in Neurodegenerative Diseases
Using 5,613 autopsy cases from the Mayo Clinic Brain Bank collected between 1998 and 2023, this study fine-tuned a large language model to convert narrative gross descriptions into semi-quantitative scores for 39 features (extraction accuracy 0.95 on 200 manually annotated feature-level test examples), then classified seven neuropathologic diagnostic categories with a CatBoost classifier and a second fine-tuned LLM, both including age at death, sex, and brain weight; on a held-out test set of 562 cases CatBoost reached accuracy 0.73, kappa 0.65, and macro-average AUC 0.92, while the text-based LLM reached accuracy 0.75 and kappa 0.68, with macro-average sensitivity 0.66 for both, PSP sensitivity 0.92 and 0.93, MSA sensitivity 0.87 and 0.92, but AD-LBD sensitivity only 0.21 and 0.
Using 5,613 autopsy cases from the Mayo Clinic Brain Bank collected between 1998 and 2023, this study fine-tuned a large language model to convert narrative gross descriptions into semi-quantitative scores for 39 features (extraction accuracy 0.95 on 200 manually annotated feature-level test examples), then classified seven neuropathologic diagnostic categories with a CatBoost classifier and a second fine-tuned LLM, both including age at death, sex, and brain weight; on a held-out test set of 562 cases CatBoost reached accuracy 0.73, kappa 0.65, and macro-average AUC 0.92, while the text-based LLM reached accuracy 0.75 and kappa 0.68, with macro-average sensitivity 0.66 for both, PSP sensitivity 0.92 and 0.93, MSA sensitivity 0.87 and 0.92, but AD-LBD sensitivity only 0.21 and 0.
Journal of Chemical Information and Modeling Sep 14, 2026
This work introduces PockLigGPT, a GPT-based framework for ligand generation conditioned on the amino acid sequence of a protein pocket, trained in four stages (large-scale ZINC20 chemical pretraining, ChEMBL bioactivity-oriented adaptation, pocket-sequence-conditioned fine-tuning, and pocket-specific docking-guided reinforcement learning with AutoDock Vina-based rewards), achieving competitive docking-oriented performance under a standardized evaluation protocol while maintaining chemical plausibility and Lipinski-based drug-likeness, with docking studies on Alzheimer's disease-associated targets and token-level analyses supporting its utility for de novo drug design.
This work introduces PockLigGPT, a GPT-based framework for ligand generation conditioned on the amino acid sequence of a protein pocket, trained in four stages (large-scale ZINC20 chemical pretraining, ChEMBL bioactivity-oriented adaptation, pocket-sequence-conditioned fine-tuning, and pocket-specific docking-guided reinforcement learning with AutoDock Vina-based rewards), achieving competitive docking-oriented performance under a standardized evaluation protocol while maintaining chemical plausibility and Lipinski-based drug-likeness, with docking studies on Alzheimer's disease-associated targets and token-level analyses supporting its utility for de novo drug design.
PockLigGPT: Pocket-Sequence-Conditioned Molecular Generation with GPTs and RL
This work introduces PockLigGPT, a GPT-based framework for ligand generation conditioned on the amino acid sequence of a protein pocket, trained in four stages (large-scale ZINC20 chemical pretraining, ChEMBL bioactivity-oriented adaptation, pocket-sequence-conditioned fine-tuning, and pocket-specific docking-guided reinforcement learning with AutoDock Vina-based rewards), achieving competitive docking-oriented performance under a standardized evaluation protocol while maintaining chemical plausibility and Lipinski-based drug-likeness, with docking studies on Alzheimer's disease-associated targets and token-level analyses supporting its utility for de novo drug design.
This work introduces PockLigGPT, a GPT-based framework for ligand generation conditioned on the amino acid sequence of a protein pocket, trained in four stages (large-scale ZINC20 chemical pretraining, ChEMBL bioactivity-oriented adaptation, pocket-sequence-conditioned fine-tuning, and pocket-specific docking-guided reinforcement learning with AutoDock Vina-based rewards), achieving competitive docking-oriented performance under a standardized evaluation protocol while maintaining chemical plausibility and Lipinski-based drug-likeness, with docking studies on Alzheimer's disease-associated targets and token-level analyses supporting its utility for de novo drug design.
World Journal of Otorhinolaryngology - Head and Neck Surgery Sep 14, 2026
Following PRISMA-ScR guidance, this scoping review searched EMBASE, PubMed (MEDLINE), CINAHL, SCOPUS, and Cochrane plus citation searching, and from 252 records included 12 studies, of which only 3 provided original data (one urology primary study, one urology expert commentary, and one narrative review with hand surgery survey data), with the remainder mostly narrative reviews whose cited evidence largely came from nonsurgical specialties, indicating that empirical research on ambient dictation AI in surgical specialties remains sparse.
Following PRISMA-ScR guidance, this scoping review searched EMBASE, PubMed (MEDLINE), CINAHL, SCOPUS, and Cochrane plus citation searching, and from 252 records included 12 studies, of which only 3 provided original data (one urology primary study, one urology expert commentary, and one narrative review with hand surgery survey data), with the remainder mostly narrative reviews whose cited evidence largely came from nonsurgical specialties, indicating that empirical research on ambient dictation AI in surgical specialties remains sparse.
The Use of Ambient Dictation Artificial Intelligence in Clinical Spaces in Surgery: A Scoping Review
Following PRISMA-ScR guidance, this scoping review searched EMBASE, PubMed (MEDLINE), CINAHL, SCOPUS, and Cochrane plus citation searching, and from 252 records included 12 studies, of which only 3 provided original data (one urology primary study, one urology expert commentary, and one narrative review with hand surgery survey data), with the remainder mostly narrative reviews whose cited evidence largely came from nonsurgical specialties, indicating that empirical research on ambient dictation AI in surgical specialties remains sparse.
Following PRISMA-ScR guidance, this scoping review searched EMBASE, PubMed (MEDLINE), CINAHL, SCOPUS, and Cochrane plus citation searching, and from 252 records included 12 studies, of which only 3 provided original data (one urology primary study, one urology expert commentary, and one narrative review with hand surgery survey data), with the remainder mostly narrative reviews whose cited evidence largely came from nonsurgical specialties, indicating that empirical research on ambient dictation AI in surgical specialties remains sparse.
Journal of Chemical Information and Modeling Sep 14, 2026
This study comprehensively benchmarked tabular foundation models (TFMs) based on in-context learning for small organic molecule property prediction, comparing several TFMs with multiple machine learning methods across 11 data sets (regression, random and structure-aware splits, up to 10,000 molecules each), and found that TFMs consistently outperform XGBoost, CatBoost, multilayer perceptrons, and other descriptor-based methods even with careful hyperparameter selection for the baselines, achieve accuracy on par with or better than graph-based methods including those pretrained on chemical data, with Uni-Mol2 slightly outperforming TFMs in some experiments, while retrieval (selecting the 500 closest neighbors by Tanimoto similarity for each test molecule) yields further improvement on relat
This study comprehensively benchmarked tabular foundation models (TFMs) based on in-context learning for small organic molecule property prediction, comparing several TFMs with multiple machine learning methods across 11 data sets (regression, random and structure-aware splits, up to 10,000 molecules each), and found that TFMs consistently outperform XGBoost, CatBoost, multilayer perceptrons, and other descriptor-based methods even with careful hyperparameter selection for the baselines, achieve accuracy on par with or better than graph-based methods including those pretrained on chemical data, with Uni-Mol2 slightly outperforming TFMs in some experiments, while retrieval (selecting the 500 closest neighbors by Tanimoto similarity for each test molecule) yields further improvement on relat
In-Context Learning Meets Small Molecule Property Prediction: Benchmarking Novel Machine Learning Approaches
This study comprehensively benchmarked tabular foundation models (TFMs) based on in-context learning for small organic molecule property prediction, comparing several TFMs with multiple machine learning methods across 11 data sets (regression, random and structure-aware splits, up to 10,000 molecules each), and found that TFMs consistently outperform XGBoost, CatBoost, multilayer perceptrons, and other descriptor-based methods even with careful hyperparameter selection for the baselines, achieve accuracy on par with or better than graph-based methods including those pretrained on chemical data, with Uni-Mol2 slightly outperforming TFMs in some experiments, while retrieval (selecting the 500 closest neighbors by Tanimoto similarity for each test molecule) yields further improvement on relat
This study comprehensively benchmarked tabular foundation models (TFMs) based on in-context learning for small organic molecule property prediction, comparing several TFMs with multiple machine learning methods across 11 data sets (regression, random and structure-aware splits, up to 10,000 molecules each), and found that TFMs consistently outperform XGBoost, CatBoost, multilayer perceptrons, and other descriptor-based methods even with careful hyperparameter selection for the baselines, achieve accuracy on par with or better than graph-based methods including those pretrained on chemical data, with Uni-Mol2 slightly outperforming TFMs in some experiments, while retrieval (selecting the 500 closest neighbors by Tanimoto similarity for each test molecule) yields further improvement on relat
Nature Medicine Sep 14, 2026
Whole-genome sequencing of 7,851 parent–offspring families identified de novo mutations with parent-of-origin and post-zygotic features that were associated with distinct assisted reproductive technology (ART) procedures independently of parental age at conception, and increased paternal mutational burden statistically mediated the effects of advanced parental age and ART on gestational duration and other birth outcomes.
Whole-genome sequencing of 7,851 parent–offspring families identified de novo mutations with parent-of-origin and post-zygotic features that were associated with distinct assisted reproductive technology (ART) procedures independently of parental age at conception, and increased paternal mutational burden statistically mediated the effects of advanced parental age and ART on gestational duration and other birth outcomes.
De novo mutations bridge parental reproductive factors and offspring health
Whole-genome sequencing of 7,851 parent–offspring families identified de novo mutations with parent-of-origin and post-zygotic features that were associated with distinct assisted reproductive technology (ART) procedures independently of parental age at conception, and increased paternal mutational burden statistically mediated the effects of advanced parental age and ART on gestational duration and other birth outcomes.
Whole-genome sequencing of 7,851 parent–offspring families identified de novo mutations with parent-of-origin and post-zygotic features that were associated with distinct assisted reproductive technology (ART) procedures independently of parental age at conception, and increased paternal mutational burden statistically mediated the effects of advanced parental age and ART on gestational duration and other birth outcomes.
Nature News Sep 14, 2026
A consortium of pharmaceutical companies called the AI Structural Biology (AISB) Network fine-tuned OpenFold3, previously trained only on PDB data, on 20,167 protein–ligand structures from five companies, and on a held-out test set of 1,056 protein–ligand structures the model reached high accuracy on more than half of them, versus about one-third for the public OpenFold3 and around 40% for the open-source model Boltz-2, while also outperforming models trained only on each company's own data, indicating that pooling data is more valuable than keeping it siloed.
A consortium of pharmaceutical companies called the AI Structural Biology (AISB) Network fine-tuned OpenFold3, previously trained only on PDB data, on 20,167 protein–ligand structures from five companies, and on a held-out test set of 1,056 protein–ligand structures the model reached high accuracy on more than half of them, versus about one-third for the public OpenFold3 and around 40% for the open-source model Boltz-2, while also outperforming models trained only on each company's own data, indicating that pooling data is more valuable than keeping it siloed.
Drug companies' private protein structures markedly improve AI folding models
A consortium of pharmaceutical companies called the AI Structural Biology (AISB) Network fine-tuned OpenFold3, previously trained only on PDB data, on 20,167 protein–ligand structures from five companies, and on a held-out test set of 1,056 protein–ligand structures the model reached high accuracy on more than half of them, versus about one-third for the public OpenFold3 and around 40% for the open-source model Boltz-2, while also outperforming models trained only on each company's own data, indicating that pooling data is more valuable than keeping it siloed.
A consortium of pharmaceutical companies called the AI Structural Biology (AISB) Network fine-tuned OpenFold3, previously trained only on PDB data, on 20,167 protein–ligand structures from five companies, and on a held-out test set of 1,056 protein–ligand structures the model reached high accuracy on more than half of them, versus about one-third for the public OpenFold3 and around 40% for the open-source model Boltz-2, while also outperforming models trained only on each company's own data, indicating that pooling data is more valuable than keeping it siloed.
bioRxiv Sep 13, 2026
This work introduces iterative Gene Enrichment Analysis (iGEA), a software framework that repeatedly selects the most significant enriched term and removes its overlapping genes to yield compact non-overlapping enriched terms within each gene-set collection, then integrates collection-specific results into a cross-collection gene-term network; applied to a published set of HIV dependency factors, iGEA identified five compact modules spanning secretory trafficking, nuclear transport, transcription elongation, proteostasis, and innate immune signaling, providing a structured representation for human interpretation and LLM-assisted exploration.
This work introduces iterative Gene Enrichment Analysis (iGEA), a software framework that repeatedly selects the most significant enriched term and removes its overlapping genes to yield compact non-overlapping enriched terms within each gene-set collection, then integrates collection-specific results into a cross-collection gene-term network; applied to a published set of HIV dependency factors, iGEA identified five compact modules spanning secretory trafficking, nuclear transport, transcription elongation, proteostasis, and innate immune signaling, providing a structured representation for human interpretation and LLM-assisted exploration.
Iterative Gene Enrichment Analysis: interpretable networks for human and AI-assisted biological insights
This work introduces iterative Gene Enrichment Analysis (iGEA), a software framework that repeatedly selects the most significant enriched term and removes its overlapping genes to yield compact non-overlapping enriched terms within each gene-set collection, then integrates collection-specific results into a cross-collection gene-term network; applied to a published set of HIV dependency factors, iGEA identified five compact modules spanning secretory trafficking, nuclear transport, transcription elongation, proteostasis, and innate immune signaling, providing a structured representation for human interpretation and LLM-assisted exploration.
This work introduces iterative Gene Enrichment Analysis (iGEA), a software framework that repeatedly selects the most significant enriched term and removes its overlapping genes to yield compact non-overlapping enriched terms within each gene-set collection, then integrates collection-specific results into a cross-collection gene-term network; applied to a published set of HIV dependency factors, iGEA identified five compact modules spanning secretory trafficking, nuclear transport, transcription elongation, proteostasis, and innate immune signaling, providing a structured representation for human interpretation and LLM-assisted exploration.

Page 19 · showing 10