Results 151 to 160 of about 110,596 (265)

Loss function influence on hyperparameter optimization for observational healthcare prediction models. [PDF]

J Am Med Inform Assoc
Vereijken F, Reps JM, Rijnbeek P, Williams RD.   +3 more
europepmc   +1 more source

A Generative Neuro‐Symbolic AI for Protein Sequence Design

Advanced Science, EarlyView.
We introduce EffieDes, a neuro‐symbolic framework coupling deep learning‐based fitness landscape parameterization with exact automated reasoning. Unlike greedy sampling, EffieDes identifies sequences that globally optimize fitness while satisfying intricate design constraints.
Marianne Defresne, Delphine Dessaux, Samuel Buchet, Lucie Barthe, Liza Ammar‐Khodja, Bessam Azizi, Valentin Durante, Gianluca Cioci, Simon de Givry, Alain Roussel, Luis F. Garcia‐Alles, Thomas Schiex, Sophie Barbe   +12 more
wiley   +1 more source

Bilevel Optimized Implicit Neural Representation for Scan-Specific Accelerated MRI Reconstruction. [PDF]

IEEE Trans Med Imaging
Yu H, Fessler JA, Jiang Y.
europepmc   +1 more source

Physics‐Guided Descriptors Enable Data‐Efficient Prediction of Battery Coulombic Efficiency

Advanced Science, EarlyView.
This work integrates multiscale simulations with data‐driven approaches to predict Coulombic efficiency (CE). Multiscale simulations of battery systems are performed to extract Physics‐Guided descriptors and construct a dataset. Machine learning models trained on this dataset are then subjected to interpretable analysis to identify the most influential
Qintao Sun, Xuewei Gu, Yulin Jie, Hao Yang, Shuhong Jiao, Chao Tang, Yangping Sheng, Yuhao Lu, Ruiguo Cao, Tao Cheng   +9 more
wiley   +1 more source

Calibration of Priors for Bayesian Model-Based Dose-Finding Trial Designs With Joint Outcomes. [PDF]

Stat Med
Alger E, Lee SM, Cheung YKK, Yap C.
europepmc   +1 more source

UCtracker: A Deep Learning–Based DNA Methylation Model for Noninvasive Diagnosis and Recurrence Surveillance of Urothelial Carcinoma in a Prospective Study

Advanced Science, EarlyView.
We developed UCtracker, a urine DNA methylation–based deep learning model, for noninvasive diagnosis and postoperative surveillance of urothelial carcinoma. UCtracker demonstrates high diagnostic accuracy, robustness at ultralow sequencing depth, early recurrence detection, and dynamic risk‐stratified monitoring of molecular residual disease ...
Shengwei Xiong, Gaojie Li, Yucai Wu, Yuan Liang, Heng Guo, Yu Zhang, Gengyan Xiong, Long Tian, Xin Zhang, Ye Tian, Zhengguo Ji, Bin Guo, Yue Shi, Jian Fan, Zhihua Li, Yanqing Gong, Shiming He, Xuesong Li, Weimin Ci, Liqun Zhou   +19 more
wiley   +1 more source

HSTXGB: a hyperparameter self-tuning XGBoost method integrating pre- and post-processing for gene regulatory network inference. [PDF]

Front Genet
Huang M, Guo S, Jiang F, Xiong Y, Chen X.   +4 more
europepmc   +1 more source

Unveiling Mechanisms of SEI Formation and Sodium Loss in Sodium Batteries via Interface Reactor Sampling

Advanced Science, EarlyView.
An “Interface Reactor” strategy boosts simulation stability by 2–3 orders of magnitude, enabling stable 100 ns molecular dynamics of electrode‐electrolyte interfaces. Distinct SEI formation mechanisms are revealed: mixed co‐formation in carbonates versus surface‐energy‐controlled NaF crystallization in ethers. Metadynamics simulations further elucidate
Zhoulin Liu, Ziliang Wang, Zherui Chen, Jianchun Sha, Fengzijun Pan, Pingyang Zhang, Yinghe Zhang   +6 more
wiley   +1 more source

From QSAR to deep learning: an interpretable comprehensive pipeline with a read-across approach for mutagenicity prediction <i>via</i> the Enalos Cloud Platform. [PDF]

RSC Adv
Varsou DD, Tsoumanis A, Longhin EM, Dusinska M, Mintis DG, Kolokathis PD, Papavasileiou KD, Lynch I, Melagraki G, Afantitis A.   +9 more
europepmc   +1 more source

CLRe: A Synergistic Dual‐Engine Framework for One‐Step Retrosynthesis Prediction

Advanced Science, EarlyView.
CLRe uses a contrastive difficulty score to order pretrained seq2seq fine‐tuning for retrosynthesis. Reaction embeddings define the ranking score, and a cumulative easy‐to‐hard schedule expands from the easiest subset to the full training set while earlier examples remain active.
Tianhao Su, Xitao Wang, Musen Li, Guanhua Qin, Shunbo Hu, Tong‐Yi Zhang   +5 more
wiley   +1 more source