bibliography.bib

@INPROCEEDINGS{Davis2006-di,
  title     = "The relationship between {Precision-Recall} and {ROC} curves",
  booktitle = "Proceedings of the 23rd international conference on Machine
               learning",
  author    = "Davis, Jesse and Goadrich, Mark",
  abstract  = "Receiver Operator Characteristic (ROC) curves are commonly used
               to present results for binary decision problems in machine
               learning. However, when dealing with highly skewed datasets,
               Precision-Recall (PR) curves give a more informative picture of
               an algorithm's performance. We show that a deep connection
               exists between ROC space and PR space, such that a curve
               dominates in ROC space if and only if it dominates in PR space.
               A corollary is the notion of an achievable PR curve, which has
               properties much like the convex hull in ROC space; we show an
               efficient algorithm for computing this curve. Finally, we also
               note differences in the two types of curves are significant for
               algorithm design. For example, in PR space it is incorrect to
               linearly interpolate between points. Furthermore, algorithms
               that optimize the area under the ROC curve are not guaranteed to
               optimize the area under the PR curve.",
  publisher = "Association for Computing Machinery",
  pages     = "233--240",
  series    = "ICML '06",
  month     =  jun,
  year      =  2006,
  address   = "New York, NY, USA",
  location  = "Pittsburgh, Pennsylvania, USA"
}


@ARTICLE{Xu2021-ku,
  title     = "Comprehensive assessment of machine learning-based methods for
               predicting antimicrobial peptides",
  author    = "Xu, Jing and Li, Fuyi and Leier, Andr{\'e} and Xiang, Dongxu and
               Shen, Hsin-Hui and Marquez Lago, Tatiana T and Li, Jian and Yu,
               Dong-Jun and Song, Jiangning",
  abstract  = "Abstract. Antimicrobial peptides (AMPs) are a unique and diverse
               group of molecules that play a crucial role in a myriad of
               biological processes and cellular fu",
  journal   = "Brief. Bioinform.",
  publisher = "Oxford University Press",
  month     =  mar,
  year      =  2021,
  language  = "en"
}

@ARTICLE{Gabere2017-ne,
  title    = "Empirical comparison of web-based antimicrobial peptide
              prediction tools",
  author   = "Gabere, Musa Nur and Noble, William Stafford",
  abstract = "Motivation: Antimicrobial peptides (AMPs) are innate immune
              molecules that exhibit activities against a range of microbes,
              including bacteria, fungi, viruses and protozoa. Recent increases
              in microbial resistance against current drugs has led to a
              concomitant increase in the need for novel antimicrobial agents.
              Over the last decade, a number of AMP prediction tools have been
              designed and made freely available online. These AMP prediction
              tools show potential to discriminate AMPs from non-AMPs, but the
              relative quality of the predictions produced by the various tools
              is difficult to quantify. Results: We compiled two sets of AMP
              and non-AMP peptides, separated into three
              categories-antimicrobial, antibacterial and bacteriocins. Using
              these benchmark data sets, we carried out a systematic evaluation
              of ten publicly available AMP prediction methods. Among the six
              general AMP prediction tools-ADAM, CAMPR3(RF), CAMPR3(SVM),
              MLAMP, DBAASP and MLAMP-we find that CAMPR3(RF) provides a
              statistically significant improvement in performance, as measured
              by the area under the receiver operating characteristic (ROC)
              curve, relative to the other five methods. Surprisingly, for
              antibacterial prediction, the original AntiBP method
              significantly outperforms its successor, AntiBP2 based on one
              benchmark dataset. The two bacteriocin prediction tools, BAGEL3
              and BACTIBASE, both provide very good performance and BAGEL3
              outperforms its predecessor, BACTIBASE, on the larger of the two
              benchmarks. Contact: gaberemu@ngha.med.sa or
              william-noble@uw.edu. Supplementary information: Supplementary
              data are available at Bioinformatics online.",
  journal  = "Bioinformatics",
  volume   =  33,
  number   =  13,
  pages    = "1921--1929",
  month    =  jul,
  year     =  2017,
  language = "en"
}

@ARTICLE{Chicco2020-re,
  title     = "The advantages of the Matthews correlation coefficient ({MCC})
               over {F1} score and accuracy in binary classification evaluation",
  author    = "Chicco, Davide and Jurman, Giuseppe",
  abstract  = "BACKGROUND: To evaluate binary classifications and their
               confusion matrices, scientific researchers can employ several
               statistical rates, accordingly to the goal of the experiment
               they are investigating. Despite being a crucial issue in machine
               learning, no widespread consensus has been reached on a unified
               elective chosen measure yet. Accuracy and F1 score computed on
               confusion matrices have been (and still are) among the most
               popular adopted metrics in binary classification tasks. However,
               these statistical measures can dangerously show overoptimistic
               inflated results, especially on imbalanced datasets. RESULTS:
               The Matthews correlation coefficient (MCC), instead, is a more
               reliable statistical rate which produces a high score only if
               the prediction obtained good results in all of the four
               confusion matrix categories (true positives, false negatives,
               true negatives, and false positives), proportionally both to the
               size of positive elements and the size of negative elements in
               the dataset. CONCLUSIONS: In this article, we show how MCC
               produces a more informative and truthful score in evaluating
               binary classifications than accuracy and F1 score, by first
               explaining the mathematical properties, and then the asset of
               MCC in six synthetic use cases and in a real genomics scenario.
               We believe that the Matthews correlation coefficient should be
               preferred to accuracy and F1 score in evaluating binary
               classification tasks by all scientific communities.",
  journal   = "BMC Genomics",
  publisher = "Springer",
  volume    =  21,
  number    =  1,
  pages     = "6",
  month     =  jan,
  year      =  2020,
  keywords  = "Accuracy; Binary classification; Biostatistics; Confusion
               matrices; Dataset imbalance; F1 score; Genomics; Machine
               learning; Matthews correlation coefficient",
  language  = "en"
}