AI-Assisted Label-Free Monitoring Bone Mineral Metabolism on Demineralized Bone Paper by Patrick Ryan (532054)

“…Here, we present a label-free, longitudinal, and quantitative monitoring of mineralized collagen formation by osteoblasts and subsequent osteoclast-driven mineral resorption on DBP using brightfield microscopy. A Segment.ai machine learning algorithm is applied for time-lapse bright-field image analysis, enabling identification of osteoclast resorption areas and automated quantification of large image datasets over a three-week culture period. …”

AI-Assisted Label-Free Monitoring Bone Mineral Metabolism on Demineralized Bone Paper by Patrick Ryan (532054)

“…Here, we present a label-free, longitudinal, and quantitative monitoring of mineralized collagen formation by osteoblasts and subsequent osteoclast-driven mineral resorption on DBP using brightfield microscopy. A Segment.ai machine learning algorithm is applied for time-lapse bright-field image analysis, enabling identification of osteoclast resorption areas and automated quantification of large image datasets over a three-week culture period. …”

Comparison of the improved LRM and RM results. by YueSheng Jiang (19267984)

Result charts for different window sizes. by YueSheng Jiang (19267984)

Reliability of the optimized frequency parameters and sFC matrix edges in the high-dimensional cases as well as of the GoF. by Kevin J. Wischnewski (21354521)

PyNoetic’s classification module supports a range of popular and widely used ML classification models with just a single line of function call. by Gursimran Singh (575288)

Subjects:

BOFdat: Generating biomass objective functions for genome-scale metabolic models from experimental data by Jean-Christophe Lachance (6619307)

“…Despite its importance, no standardized computational platform is currently available to generate species-specific biomass objective functions in a data-driven, unbiased fashion. To fill this gap in the metabolic modeling software ecosystem, we implemented BOFdat, a Python package for the definition of a <b>B</b>iomass <b>O</b>bjective <b>F</b>unction from experimental <b>dat</b>a. …”

Plot depicting the feature importance of the top 15 features of each model. by Aastha Vatsyayan (9981916)

Subjects:

Scatterplot of class probability vs the predicted class for the XGBoost model across all VUS variants 251 exonic VUS variants that were a part of the validation dataset. by Aastha Vatsyayan (9981916)

Subjects:

Copper exposure in <i>ATP7B</i> Knock-out HepG2 cells overexpressed with the plasmid containing wildtype and mutant <i>ATP7B</i> gene. by Aastha Vatsyayan (9981916)

Subjects:

A complete list of the 73 features used in training the model, along with the ACMG attribute they provide information about, along with their description, as well as their datatype... by Aastha Vatsyayan (9981916)

Subjects:

Scatterplot of class probability vs the actual ACMG class for the TabNet model across the validation set of 156 variants. by Aastha Vatsyayan (9981916)

Subjects:

Model hyperparameters used for the XGBoost model. by Aastha Vatsyayan (9981916)

Subjects:

The Precision-Recall curve of both the models. by Aastha Vatsyayan (9981916)

Subjects:

S4 Table - by Aastha Vatsyayan (9981916)

Subjects:

Train and validation accuracies of the TabNet model across 187 epochs. by Aastha Vatsyayan (9981916)

Subjects:

Primers used in site-directed mutagenesis. by Aastha Vatsyayan (9981916)

Subjects:

The overview of the workflow followed for model development and variant classification with TabNet and XGBoost models. by Aastha Vatsyayan (9981916)

Subjects:

S2 Table - by Aastha Vatsyayan (9981916)

Subjects:

Barplot comparing the accuracy, MCC, NPV and PPV of 13 models with TabNet and XGBoost. by Aastha Vatsyayan (9981916)

Subjects: