Sulfotransferase SULT2B1 facilitates colon cancer metastasis by promoting SCD1‐mediated lipid metabolism

Che, Gang; Wang, Wankun; Wang, Jiawei; He, Cheng; Yin, Jie; Chen, Zhendong; He, Chao; Wang, Xujing; Yang, Yan; Liu, Jian

doi:10.1002/ctm2.1587

Cited by 5 publications

(1 citation statement)

References 56 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Using the feature-selection procedure given in METHODS, we identified 11 enzyme genes for the binary classification problem and 14 enzyme genes for the ternary problem. It is noteworthy that all the 11 genes have literature support, showing that they each are associated with metastasis [17,18,19,20]. For the 14 genes, our functional analyses have revealed that they are mainly involved in sex hormone and xenobiotic metabolism, which makes sense as we have discovered that metastasized cancers have considerably elevated cholesterol metabolisms, leading to the production of sex hormones as well as mineral-and glucocorticoid (manuscript in preparation).…”

Section: Feature Selectionmentioning

confidence: 79%

Optimizing Model Performance and Interpretability: an application to biological data classification

Huang,

Cao,

Chen

et al. 2024

Preprint

View full text Add to dashboard Cite

In biological data classification, both performance accuracy and result interpretability are desired and yet difficult to achieve simultaneously. We present a framework for transcriptomic data-based classification that can accomplish both. The key idea is as follows: 1) to identify metabolic pathways whose expressions have strong discerning power in separating samples having distinct labels, hence providing a basis for providing interpretability of the classification results; 2) to select pathways from the afore-identified whose expression variance for each can be largely captured by its first principal component of the gene-expression matrix for the pathway, hence allowing to select a minimal number of discerning pathways; 3) to select a minimal set of genes whose collective discerning power covers 95% of the discerning power for each selected pathway, giving rise to a set of features (genes) for classification; and 4) to select a model among the available ones and model parameters that give the optimal classification results. We have demonstrated the effectiveness of this framework on two cancer biology problems. We anticipate that this framework will be used for the selection of features, model, and model parameters for a wide range of biological data classification problems.

show abstract

Section: Feature Selectionmentioning

confidence: 79%