Metrics for multi-class classification: an overview

M Grandini, E Bagli, G Visani - arxiv preprint arxiv:2008.05756, 2020 - arxiv.org
Classification tasks in machine learning involving more than two classes are known by the
name of" multi-class classification". Performance indicators are very useful when the aim is …

A survey on legal judgment prediction: Datasets, metrics, models and challenges

J Cui, X Shen, S Wen - IEEE Access, 2023 - ieeexplore.ieee.org
Legal judgment prediction (LJP) applies Natural Language Processing (NLP) techniques to
predict judgment results based on fact descriptions automatically. The present work …

SignalP 6.0 predicts all five types of signal peptides using protein language models

F Teufel, JJ Almagro Armenteros, AR Johansen… - Nature …, 2022 - nature.com
Signal peptides (SPs) are short amino acid sequences that control protein secretion and
translocation in all living organisms. SPs can be predicted from sequence data, but existing …

The Matthews correlation coefficient (MCC) is more informative than Cohen's Kappa and Brier score in binary classification assessment

D Chicco, MJ Warrens, G Jurman - Ieee Access, 2021 - ieeexplore.ieee.org
Even if measuring the outcome of binary classifications is a pivotal task in machine learning
and statistics, no consensus has been reached yet about which statistical rate to employ to …

The advantages of the Matthews correlation coefficient (MCC) over F1 score and accuracy in binary classification evaluation

D Chicco, G Jurman - BMC genomics, 2020 - Springer
Background To evaluate binary classifications and their confusion matrices, scientific
researchers can employ several statistical rates, accordingly to the goal of the experiment …

[HTML][HTML] The impact of class imbalance in classification performance metrics based on the binary confusion matrix

A Luque, A Carrasco, A Martín, A de Las Heras - Pattern Recognition, 2019 - Elsevier
A major issue in the classification of class imbalanced datasets involves the determination of
the most suitable performance metrics to be used. In previous work using several examples …

Modeling aspects of the language of life through transfer-learning protein sequences

M Heinzinger, A Elnaggar, Y Wang, C Dallago… - BMC …, 2019 - Springer
Background Predicting protein function and structure from sequence is one important
challenge for computational biology. For 26 years, most state-of-the-art approaches …

DeepLoc: prediction of protein subcellular localization using deep learning

JJ Almagro Armenteros, CK Sønderby… - …, 2017 - academic.oup.com
Motivation The prediction of eukaryotic protein subcellular localization is a well-studied topic
in bioinformatics due to its relevance in proteomics research. Many machine learning …

Why Cohen's Kappa should be avoided as performance measure in classification

R Delgado, XA Tibau - PloS one, 2019 - journals.plos.org
We show that Cohen's Kappa and Matthews Correlation Coefficient (MCC), both extended
and contrasted measures of performance in multi-class classification, are correlated in most …

CovidXrayNet: Optimizing data augmentation and CNN hyperparameters for improved COVID-19 detection from CXR

MMA Monshi, J Poon, V Chung, FM Monshi - Computers in biology and …, 2021 - Elsevier
To mitigate the spread of the current coronavirus disease 2019 (COVID-19) pandemic, it is
crucial to have an effective screening of infected patients to be isolated and treated. Chest X …