Data set on peptides with anti-arboviral activity
Dataset with positive and negative cases of peptides with antiarboviral dataset.
Regarding the selection of the negative dataset, the following was performed: for each sequence of a certain length in the positive set, five sequences of the same length were randomly selected from the antiviral negative set (EX_starPep_AV, of 10771 peptides) in the AMPDiscover database (https://biocom-ampdiscover.cicese.mx/dataset). This was done to maintain the length distribution of positive cases. Considering the stochastic nature of this methodology, five samples were considered, thus constructing five datasets for training and testing classification methods.
Additionally, entries in our positive dataset are also displayed as a .xlsx file with the following column description:
- A. “#” attribute is the number of the peptide sequence in the table.
- B. “ID” attribute is the code or name of the peptide.
- C. “Sequence” is the sequence of amino acids of the peptide.
- D. “Virus” names the virus in which the peptide has a probed activity.
- E. “Target(s)” indicates the part or component of the virus where the peptide has its activity.
- F. “Mechanism(s) of Action” describes where the peptide inhibitory action has effect on the virus(no recuerdo como describer… ciclo de vida del virus???)
- G. “Year”, the year of publication of the study where the peptide is mentioned.
- H. “Design Method” indicates where the study was experimental or computational.
- I. “Experimental test” explains if the experimental study was in vivo or in vitro. In the case of computational studies says what kind of simulation was performed.
- J. “Reference (link)” shows the URL or DOI of the study where the peptide and its activity was mentioned.
- K. “Original Reference (link)” shows the URL or DOI of the first study where the peptide and its activity was mentioned.
- L. “Inhibitory concentration” is the documented inhibitory concentration of the peptide as it is mentioned in the reference study.
