Journal: Bioinformatics

Article Title: Knowledge-enhanced protein subcellular localization prediction from 3D fluorescence microscope images

doi: 10.1093/bioinformatics/btaf331

Figure Lengend Snippet: The effects of asymmetric loss (ASL) and class confidence weights (CCW) on the class imbalance and weak annotation issues. (A) Results on the 11 categories with small sample sizes before and after using ASL. (B) Results of the prediction with and without using ASL or CCW. The red protein labels in the examples are not reflected in the shown single cells. Incorporating ASL and CCW enables the model to identify the categories of the single cells more accurately, even under weak annotation influence.

Article Snippet: The results indicated that the most critical components in classification performance were the ASL and the 2D branch, and CCW has the most significant impact on the OpenCell dataset, which aligns closely with its weak annotation issue. shows that incorporating ASL has enhanced the accuracy for categories with small sample sizes, demonstrating that ASL could perform well in the class imbalance situation.

Techniques:

Journal: International Journal of Molecular Sciences

Article Title: Targeting HIV/HCV Coinfection Using a Machine Learning-Based Multiple Quantitative Structure-Activity Relationships (Multiple QSAR) Method

doi: 10.3390/ijms20143572

Figure Lengend Snippet: Performance of 60 multiple QSAR models built based on Naïve Bayes ( A ) and the support vector machine ( B ) using different fingerprints determined by test set validation.

Article Snippet: The Naïve Bayes classification models were built using KNIME (version 3.4.2).

Techniques: Plasmid Preparation, Biomarker Discovery

Journal: Journal of Medical Internet Research

Article Title: Phenotype Instance Verification and Evaluation Tool (PIVET): A Scaled Phenotype Evidence Generation Framework Using Web-Based Medical Literature

doi: 10.2196/jmir.9610

Figure Lengend Snippet: Classification scores for different sizes of synonyms using the Phenotype Instance Verification and Evaluation Tool (PIVET) framework.

Article Snippet: Using the PIVET classification ridge model, we predicted the clinical relevance scores of these ambiguous phenotypes. shows the two extremes based on the averaged prediction score: phenotypes with the highest probability of being “clinically significant” (top two rows) and phenotypes with the lowest probability of being “clinically significant” (bottom two rows), as well as the annotator’s comment on the phenotype and the average lift calculated by PIVET.

Techniques: