Supplementary Figure S6 from SpatialDeX Is a Reference-Free Method for Cell-Type Deconvolution of Spatial Transcriptomics Data in Solid Tumors حسب Xinyi Liu (20493753)

Supplementary Figure S5 from SpatialDeX Is a Reference-Free Method for Cell-Type Deconvolution of Spatial Transcriptomics Data in Solid Tumors حسب Xinyi Liu (20493753)

Supplementary Figure S8 from SpatialDeX Is a Reference-Free Method for Cell-Type Deconvolution of Spatial Transcriptomics Data in Solid Tumors حسب Xinyi Liu (20493753)

Supplementary Figure S1 from SpatialDeX Is a Reference-Free Method for Cell-Type Deconvolution of Spatial Transcriptomics Data in Solid Tumors حسب Xinyi Liu (20493753)

Supplementary Figure S4 from SpatialDeX Is a Reference-Free Method for Cell-Type Deconvolution of Spatial Transcriptomics Data in Solid Tumors حسب Xinyi Liu (20493753)

Supplementary Figure S9 from SpatialDeX Is a Reference-Free Method for Cell-Type Deconvolution of Spatial Transcriptomics Data in Solid Tumors حسب Xinyi Liu (20493753)

Supplementary Figure S3 from SpatialDeX Is a Reference-Free Method for Cell-Type Deconvolution of Spatial Transcriptomics Data in Solid Tumors حسب Xinyi Liu (20493753)

Optimization outcome for the Rosenbrock function. حسب Shikun Chen (14625352)

"…The approach leverages gradient information from neural networks to guide SLSQP optimization while maintaining XGBoost’s prediction precision. …"

Optimization outcome for the Rastrigin function. حسب Shikun Chen (14625352)

"…The approach leverages gradient information from neural networks to guide SLSQP optimization while maintaining XGBoost’s prediction precision. …"

2D Rastrigin function. حسب Shikun Chen (14625352)

"…The approach leverages gradient information from neural networks to guide SLSQP optimization while maintaining XGBoost’s prediction precision. …"

2D Levy function. حسب Shikun Chen (14625352)

"…The approach leverages gradient information from neural networks to guide SLSQP optimization while maintaining XGBoost’s prediction precision. …"

2D Rosenbrock function. حسب Shikun Chen (14625352)

"…The approach leverages gradient information from neural networks to guide SLSQP optimization while maintaining XGBoost’s prediction precision. …"

Optimization outcome for the Levy function. حسب Shikun Chen (14625352)

"…The approach leverages gradient information from neural networks to guide SLSQP optimization while maintaining XGBoost’s prediction precision. …"

Details of the metaheuristic algorithms. حسب Junhao Wei (6816803)

"…<div><p>Whale Optimization Algorithm (WOA) is a biologically inspired metaheuristic algorithm with a simple structure and ease of implementation. …"

Parameter settings for algorithms. حسب Junhao Wei (6816803)

"…<div><p>Whale Optimization Algorithm (WOA) is a biologically inspired metaheuristic algorithm with a simple structure and ease of implementation. …"

Exponentially attenuated sinusoidal function. حسب Hang Zhao (143592)

"…The Pareto optimal front was generated using MOCOA with the indicators of spectral kurtosis and KL divergence, by which the optimal intrinsic mode functions were obtained. A deep VMD-attention network based on MOCOA was developed for ECG signal classification. …"

A Dataset of Curie and Neel Temperatures auto-generated with ChemDataExtractor and the Snowball Algorithm حسب Charles Kelly (21712413)

LBQANA python code + Merged Gene Expression Dataset from GSE10810, GSE17907, GSE20711, GSE42568, GSE45827, and GSE61304 for Breast Cancer Biomarker Discovery حسب M RN (9866504)

"…To address batch effects introduced during the merging process, the Empirical Bayes algorithm from the sva package (via the ComBat function) was applied. …"

PATH has state-of-the-art performance versus previous binding affinity prediction algorithms. حسب Yuxi Long (11024307)

"…<p>^<b>a</b>PATH⁺ shows comparable or better performance with less overfitting, as evidenced by a smaller slope, with much less increase in RMSEs beyond the training dataset, compared to established binding affinity prediction algorithms spanning a variety of methods. The benchmarked algorithms include physics-based and deep learning algorithms from the famous AutoDock framework (scoring function of AutoDock4 implemented in the AutoDockFR package [<a href="http://www.ploscompbiol.org/article/info:doi/10.1371/journal.pcbi.1013216#pcbi.1013216.ref068" target="_blank">68</a>,<a href="http://www.ploscompbiol.org/article/info:doi/10.1371/journal.pcbi.1013216#pcbi.1013216.ref077" target="_blank">77</a>], Vinardo [<a href="http://www.ploscompbiol.org/article/info:doi/10.1371/journal.pcbi.1013216#pcbi.1013216.ref069" target="_blank">69</a>], GNINA [<a href="http://www.ploscompbiol.org/article/info:doi/10.1371/journal.pcbi.1013216#pcbi.1013216.ref070" target="_blank">70</a>]), empirical (AA-Score [<a href="http://www.ploscompbiol.org/article/info:doi/10.1371/journal.pcbi.1013216#pcbi.1013216.ref071" target="_blank">71</a>]), knowledge-based (SMoG2016 [<a href="http://www.ploscompbiol.org/article/info:doi/10.1371/journal.pcbi.1013216#pcbi.1013216.ref072" target="_blank">72</a>]), and deep learning-based scoring functions (OnionNet [<a href="http://www.ploscompbiol.org/article/info:doi/10.1371/journal.pcbi.1013216#pcbi.1013216.ref073" target="_blank">73</a>], PLANET [<a href="http://www.ploscompbiol.org/article/info:doi/10.1371/journal.pcbi.1013216#pcbi.1013216.ref074" target="_blank">74</a>]). …"

Assessment of the level of difficulty of the task from subjects (A) and therapists (B) when using the tablet compared to the paper-based support during the item 18, 19 and 22 compl... حسب Dominique Vincent-Genod (20552594)