Comparison of the predicted and observed secondary structure of T4 phage lysozyme.

By B. Matthews. 1975

Subfields: Computational Biology & Bioinformatics

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Biology & Bioinformatics

Citations in the corpus

GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding (2018, methodology): “We follow the original work and report the Matthews correlation coefficient (Matthews, 1975), which evaluates classifiers on unbalanced binary classification tasks with a range from -1 to 1, with 0 being the performance”
Multi-Task Deep Neural Networks for Natural Language Understanding (2019, methodology): “It uses Matthews correlation coefﬁcient (Matthews, 1975) as the evaluation metric.”
To Tune or Not to Tune? Adapting Pretrained Representations to Diverse Tasks (2019, methodology): “It uses the Matthews correlation coefficient (Matthews, 1975) for evaluation and is available at: nyu-mll.”
Towards Coherent and Engaging Spoken Dialog Response Generation Using Automatic Conversation Evaluators (2019, neutral): “Furthermore, since the class distribution of the dataset is highly imbalanced, we also calculate Matthews correlation co-efﬁcient (MCC), which takes into account true and false positives and negatives.”
Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time (2022, methodology): “We use the standard metric for each dataset: average of accuracy and F1 score for MRPC, accuracy for RTE, Matthews correlation for CoLA (Matthews, 1975) and accuracy for SST-2.”
Fine-Tuning Pretrained Language Models: Weight Initializations, Data Orders, and Early Stopping (2020, methodology): “Models are evaluated on Matthews correlation (MCC; Matthews, 1975), which ranges between –1 and 1, with random guessing being 0.”
Revisiting Few-sample BERT Fine-tuning (2020, methodology): “Matthews correlation coefficient [30] is used to evaluate the performance.”
Interpretable Predictions of Tree-based Ensembles via Actionable Feature Tweaking (2017, methodology): “We measure two standard quality metrics, F1 and Mahews Correlation Coecient (MCC) [17].”
Assessment of three-dimensional RNA structure prediction in CASP15 (2023, neutral): “…Network Fidelity (INF) is then computed as the Matthews Correlation Coefficient, the geometric mean of the positive predictive value and sensitivity as in Gorodkin 24,25 : superim-posing each nucleotide of the predicted model over the corresponding nucleotide of the reference model one at a time.”
Modeling aspects of the language of life through transfer-learning protein sequences (2019, methodology): “Predictions of intrinsic disorder were evaluated through the Matthew ’ s correlation coefficient (MCC [100]) and the False-Positive Rate (FPR) as those are more informative for tasks with high class imbalance.”
Investigating BERT’s Knowledge of Language: Five Analysis Methods with NPIs (2019, methodology): “The performance of the models is measured as Matthews Correlation Coefﬁcient (MCC; Matthews, 1975) between the predicted label and the gold label.”
Cyberbullying Detection With Fairness Constraints (2020, methodology): “c curve, and F 1 score may lead to misleading conclusions on imbalanced datasets (such as here), we evaluate our models with Matthews correlation coefﬁcient (MCC) which does not exhibit such drawback [60], [61], [62], [63]. MCC generates a high score only if the binary predictor was able to correctl”
Prediction, conservation analysis, and structural characterization of mammalian mucin-type O-glycosylation sites. (2005, methodology): “As performance measure we used the joint Matthews correlation coefficient (Matthews, 1975) of the three resulting networks on their respective test sets and this is what we aimed to maximize.”
Prediction of protein subcellular localization (2006, methodology): “The Matthew's correlation coefficient MCC is given by[39]”
ResUNet-a: a deep learning framework for semantic segmentation of remotely sensed data (2019, methodology): “The di ﬀ erence in performance is signiﬁcant: the Tanimoto loss with complement achieves for the same number of epochs an MCC = 85 .”