Results 91 to 100 of about 218,805 (280)

Prediction of Total Petroleum Hydrocarbons and Heavy Metals in Acid Tars Using Machine Learning

Applied Sciences
Hazardous petroleum wastes are an inevitable source of environmental pollution. Leachates from these wastes could contaminate soil and potable water sources and affect human health.
Mihaela Tita, Ion Onutu, Bogdan Doicin
doaj   +1 more source

AutomataGPT: Transformer‐Based Forecasting and Ruleset Inference for Two‐Dimensional Cellular Automata

Advanced Science, EarlyView.
We introduce AutomataGPT, a generative pretrained transformer (GPT) trained on synthetic spatiotemporal data from 2D cellular automata to learn symbolic rules. Demonstrating strong performance on both forward and inverse tasks, AutomataGPT establishes a scalable, domain‐agnostic framework for interpretable modeling, paving the way for future ...
Jaime A. Berkovich, Noah S. David, Markus J. Buehler   +2 more
wiley   +1 more source

Evaluating the Utilities of Foundation Models in Single‐Cell Data Analysis

Advanced Science, EarlyView.
This study delivers the first systematic, task‐level evaluation of single‐cell foundation models across eight core analytical tasks. By benchmarking 10 leading models with the scEval framework, it reveals where foundation models truly add value, where task‐specific methods still dominate, and provides concrete, reproducible guidelines to steer the next
Tianyu Liu, Kexing Li, Yuge Wang, Hongyu Li, Hongyu Zhao   +4 more
wiley   +1 more source

De Novo Multi‐Mechanism Antimicrobial Peptide Design via Multimodal Deep Learning

Advanced Science, EarlyView.
Current AI‐driven peptide discovery often overlooks complex structural data. This study presents M3‐CAD, a generative pipeline that leverages 3D voxel coloring and a massive database of over 12 000 peptides to capture nuanced physicochemical contexts.
Xiaojuan Li, Haifan Gong, Yue Wang, Yinuo Zhao, Lixiang Li, Peijing Bao, Qingzhou Kong, Jialu Fu, Boyao Wan, Yumeng Zhang, Jinghui Zhang, Jiekun Ni, Zhongxue Han, Xueping Nan, Kunping Ju, Longfei Sun, Yuerui Ma, Huijun Chang, Mengqi Zheng, Yanbo Yu, Xiaoyun Yang, Xiuli Zuo, Haina Wang, Yanqing Li   +23 more
wiley   +1 more source

A trust-region method for stochastic variational inference with applications to streaming data

, 2015
Stochastic variational inference allows for fast posterior inference in complex Bayesian models. However, the algorithm is prone to local optima which can make the quality of the posterior approximation sensitive to the choice of hyperparameters and ...
Hoffman, Matthew D., Theis, Lucas
core  

Hyperparameter Learning via Distributional Transfer

, 2018
Bayesian optimisation is a popular technique for hyperparameter learning but typically requires initial exploration even in cases where similar prior tasks have been solved. We propose to transfer information across tasks using learnt representations of training datasets used in those tasks.
Law, HCL, Zhao, P, Chan, L, Huang, J, Sejdinovic, D   +4 more
openaire   +3 more sources

High‐Fidelity Synthetic Data Replicates Clinical Prediction Performance in a Million‐Patient Diabetes Cohort

Advanced Science, EarlyView.
This study generates high‐fidelity synthetic longitudinal records for a million‐patient diabetes cohort, successfully replicating clinical predictive performance. However, deeper analysis reveals algorithmic biases and trajectory inconsistencies that escape standard quality metrics. These findings challenge current validation norms, demonstrating why a
Francisco Ortuño, Víctor M. de la Oliva Roque, Javier‐Ignacio Ramirez‐Lopez, David P. Kreil, Joaquín Dopazo, Carlos Loucera   +5 more
wiley   +1 more source

Causal Prediction of TP53 Variant Pathogenicity Using a Perturbation‐Informed Protein Language Model

Advanced Science, EarlyView.
A TP53‐specific predictor, CaVepP53, is developed by fine‐tuning ESMC on experimentally validated variants, quantifying pathogenicity via Euclidean distances. It outperforms general‐purpose models and extends to five cancer genes, enabling interpretable variant classification for precision medicine.
Huiying Chen, Yang Zhao, Boqiang Hu, Wuke Wang, Minfang Song, Annabeth Xinyu Zhao, Xiangyang Li, Gefei Wang, Yanfen Wang, Weiyan Zheng, Xinpeng Zhang, Xia Lin, Yanbin Yin, Xingxu Huang, Jinfang Zheng, Tingbo Liang   +15 more
wiley   +1 more source

Structural Eigenmodes of the Brain to Improve the Source Localization of EEG: Application to Epileptiform Activity

Advanced Science, EarlyView.
Geometry and connectivity are complementary structures, which have demonstrated their ability to represent the brain's functional activity. This study evaluates geometric and connectome eigenmodes as biologically informed constraints for EEG source localization.
Pok Him Siu, Philippa J. Karoly, Sina Mansour L., Artemio Soto‐Breceda, Levin Kuhlmann, Mark J. Cook, David B. Grayden   +6 more
wiley   +1 more source

Machine Learning for Green Solvents: Assessment, Selection and Substitution

Advanced Science, EarlyView.
Environmental regulations have intensified demand for green solvents, but discovery is limited by Solvent Selection Guides (SSGs) that quantify solvent sustainability. Training a machine learning model on GlaxoSmithKline SSG, a database of sustainability metrics for 10,189 solvents, GreenSolventDB is developed. Integrated with Hansen solubility metrics,
Rohan Datta, Janhavi Nistane, Abhishek Sose, Harikrishna Sahu, Rampi Ramprasad   +4 more
wiley   +1 more source