Results 131 to 140 of about 85,695 (269)

AS‐pHopt: An Optimal pH Prediction Model Enhanced by Active Site of Enzymes

Advanced Intelligent Discovery, EarlyView.
To address the low accuracy of enzyme optimal pH (pHopt) prediction, this study develops active site‐based pHopt (AS‐pHopt), a prediction model enhanced by active site information and pseudo‐label prediction. Integrating key structural and physicochemical features affecting enzyme pHopt, AS‐pHopt uses Evolutionary Scale Modeling (ESM)‐2 with active ...
Wenxiang Song, Xinmin Li, Hongbo Yu, Le Xiong, Guixia Liu, Weihua Li, Yun Tang   +6 more
wiley   +1 more source

A Hybrid Transfer Learning Framework for Brain Tumor Diagnosis

Advanced Intelligent Systems, Volume 7, Issue 3, March 2025.
A novel hybrid transfer learning approach for brain tumor classification achieves 99.47% accuracy using magnetic resonance imaging (MRI) images. By combining image preprocessing, ensemble deep learning, and explainable artificial intelligence (XAI) techniques like gradient‐weighted class activation mapping and SHapley Additive exPlanations (SHAP), the ...
Sadia Islam Tonni, Md. Alif Sheakh, Mst. Sazia Tahosin, Md. Zahid Hasan, Taslima Ferdaus Shuva, Touhid Bhuiyan, Muhammad Ali Abdullah Almoyad, Nabil Anan Orka, Md. Tanvir Rahman, Risala Tasin Khan, M. Shamim Kaiser, Mohammad Ali Moni   +11 more
wiley   +1 more source

Predicting Materials Thermodynamics Enabled by Large Language Model‐Driven Dataset Building and Machine Learning

Advanced Intelligent Systems, EarlyView.
Illustration of text data mining of rare earth mineral thermodynamic parameters with the large language model‐powered LMExt. A dataset is built with mined thermodynamic properties. Subsequently, a machine learning model is trained to predict formation enthalpy from the dataset.
Juejing Liu, Haydn Anderson, Noah I. Waxman, Vsevolod Kovalev, Byron Fisher, Elizabeth Li, Xiaofeng Guo   +6 more
wiley   +1 more source

Explaining ML predictions with SHAP

Proceedings of the Python in Science Conference
This article explores how SHAP (SHapley Additive exPlanations) can be used to interpret machine learning model predictions by providing consistent and theoretically grounded feature attributions.
openaire   +2 more sources

DeepDiff-SHAP: Interpretable deep learning for subgroup-specific causal inference using conditional SHAP

Precision medicine aims to tailor healthcare strategies to individual differences in genetic, clinical, and environmental factors. However, identifying subgroup-specific causal relationships in complex biomedical data remains a major challenge, especially when standard causal inference methods average over population heterogeneity.
Aditya Sriram, Soyeon Kim, Joseph A Carcillo, Hyun Jung Park   +3 more
openaire   +1 more source

Machine Learning‐Driven Digital Twin of a Field‐Effect Transistor‐Based Hormone Biosensor for Real‐Time Estradiol Monitoring

Advanced Intelligent Systems, EarlyView.
A machine learning‐driven digital twin simulates an aptamer‐functionalized BioFET measuring 17β‐estradiol. Real‐time Isd signals are processed, features are extracted, and trained models estimate hormone concentration. In parallel, a one‐step‐ahead forward model learns biosensor dynamics and generates realistic synthetic signals, enabling in silico ...
Anastasiia Gorelova, Alexandra Parichenko, Shirong Huang, Santiago Melia, Gianaurelio Cuniberti   +4 more
wiley   +1 more source

Single‐Injection Multi‐Omics Analysis by Direct Infusion Mass Spectrometry

Angewandte Chemie, EarlyView.
A high‐throughput direct infusion mass spectrometry platform, enabled by gas‐phase ion mobility separation, supports single‐injection analysis of peptides, polar metabolites, and lipids. Coupled with custom software, it identified ∽1,300 proteins and ∽600 metabolites in ∽4.3 minutes per sample, and demonstrated broad utility in macrophage polarization ...
Yuming Jiang, Ivan Salladay‐Perez, Amanda Momenzadeh, Jesús Muñoz‐Estrada, Uktarsh Tripathi, Anthony J. Covarrubias, Jesse G. Meyer   +6 more
wiley   +2 more sources

Metalearning‐Driven Inverse Optimization for Precision Microstructure Fabrication in Digital Light Processing Three‐Dimensional Printing

Advanced Intelligent Systems, EarlyView.
Metalearning‐based inverse optimization enables precise microscale three‐dimensional printing using a DLP system. Distorted structures from conventional printing are analyzed via neural network regression, which predicts optimal exposure time and mask design.
Jae Won Choi, Suhyeong Lim, Jeongsu Lee, Cheol Woo Ha   +3 more
wiley   +1 more source

Accelerating Catalyst Materials Discovery With Large Artificial Intelligence Models

Angewandte Chemie, EarlyView.
AI‐empowered catalysis research via integrated database platform, universal machine learning interatomic potentials (MLIPs), and large language models (LLMs). ABSTRACT The integration of artificial intelligence (AI) into catalysis is fundamentally reshaping the research paradigm of catalyst discovery.
Di Zhang, Yuanzheng Chen, Chuanyu Liu, Yan Liu, Hongliang Xin, Jiayu Peng, Pengfei Ou, Hao Li   +7 more
wiley   +2 more sources

Integrating Artificial Intelligence With Droplet‐Based Microfluidics: Advances, Challenges, and Emerging Opportunities

Advanced Intelligent Systems, EarlyView.
Droplet‐based microfluidics enables precise, high‐throughput microscale reactions but continues to face challenges in scalability, reproducibility, and data complexity. This review examines how artificial intelligence enhances droplet generation, detection, sorting, and adaptive control and discusses emerging opportunities for clinical and industrial ...
Junyan Lai, Sukrit Gaira, Rongfeng Wang, Qingtian Zhang, Ming Li, Liao Wu, Diangeng Li, Yi Li, Chengchen Zhang, Jinhong Guo, Shi‐Yang Tang   +10 more
wiley   +1 more source