Antifungipept

A tool for predicting, screening, and designing antifungal peptide (AFP) using machine learning.

AFP20200317_409380

Basic Information

Uniprot id: tr|A0A0K8PBK1|A0A0K8PBK1_STRAJ

Sequence: GGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGG

Sequence Length: 46

Antifungal Index (AFI): 54.7

Probability of Antifungal Activity Prediction: 0.93

Predicted Antifungal Activity - MIC (Probability)

C. albicans: 21.29 μM (0.792)

C. krusei: 47.4 μM (0.576)

C. neoformans: 52.44 μM (0.022)

C. parapsilosis: 169.24 μM (0.493)

Description:

Notes

The radar chart delineates the antifungal efficacy of peptides. Within this graphical representation, each axis corresponds to a distinct metric; proximity to the periphery signifies reduced AFI (Antifungal Index) or MIC (Minimum Inhibitory Concentration) values, thus denoting heightened antifungal potency. The aggregate area spanned by the data points encapsulates the peptide's efficacy profile across varied metrics, offering a consolidated visual depiction of its antifungal potential.

The AFI, denoted in micromolar (μM), encapsulates the spectrum of antifungal activity. A diminished AFI value is indicative of a peptide's elevated potential as a broad-spectrum antifungal agent. The computation of AFI is based on the geometric mean of the predicted MICs against a range of fungal species, providing a composite measure of antifungal performance.

The pMIC values, derived via a negative base-2 logarithmic transformation of MIC figures, serve as the focal point for QSAR modeling. These transformed values, depicted in the radar chart, furnish a more intuitive comparison of antifungal strength—whereby an augmented pMIC value correlates to superior antifungal efficacy.

Reference

J. Chem. Inf. Model. 2024, 64 (10), 4277–4285.. Link

ACS Med. Chem. Lett. 2022, 13, 1, 99-104. Link