| Author Summary | Machine learning techniques may replace expensive in-vitro laboratory experiments by learning an accurate model of it. |
| Author Summary | Finally, in-vitro and in-silico results are provided to support and validate this theoretical discovery. |
| Introduction | I n-silico predictions are faster and cheaper than in-vitro assays, however, predicting the bioactivity of all possible peptide to select the most bioactive ones would require a prohibitive amount of computational time. |
| Simulation of a drug discovery | Comparing hmndom and the oracle accuracies on the CAMPs and BPPs databases To provide additional support for its accuracy, predictor hmndom was used to predict the bioactivity values of unseen but in-vitro validated peptides of the CAMPs and BPPs databases. |