Using a Classifier Fusion Strategy to Identify Anti-angiogenic Peptides

Abstract

Anti-angiogenic peptides perform distinct physiological functions and potential therapies for angiogenesis-related diseases. Accurate identification of anti-angiogenic peptides may provide significant clues to understand the essential angiogenic homeostasis within tissues and develop antineoplastic therapies. In this study, an ensemble predictor is proposed for anti-angiogenic peptide prediction by fusing an individual classifier with the best sensitivity and another individual one with the best specificity. We investigate predictive capabilities of various feature spaces with respect to the corresponding optimal individual classifiers and ensemble classifiers. The accuracy and Matthew’s Correlation Coefficient (MCC) of the ensemble classifier trained by Bi-profile Bayes (BpB) features are 0.822 and 0.649, respectively, which represents the highest prediction results among the investigated prediction models. Discriminative features are obtained from BpB using the Relief algorithm followed by the Incremental Feature Selection (IFS) method. The sensitivity, specificity, accuracy, and MCC of the ensemble classifier trained by the discriminative features reach up to 0.776, 0.888, 0.832, and 0.668, respectively. Experimental results indicate that the proposed method is far superior to the previous study for anti-angiogenic peptide prediction.

Prediction of Therapeutic Peptides Using Machine Learning: Computational Models, Datasets, and Feature Encodings

“…In CTD, the C (Composition) computes the frequency of every amino acid group with some particular property in a peptide sequence, can be defined as [52]:…”

“…where a i , i ∈ {1, 2, • • • , n} is the number of groups, n is the total number of groups, and L is the length of the sequence. The T (transition) describes the occurrence of amino acids of a particular property accompanied with the amino acids of another property, which can be expressed as [52]:…”

“…where i, j ∈ {1, 2, • • • , n} represents the corresponding property group, n is the total number of groups, L is the length of sequence, and a i,j represents the number of dipeptide having amino acid residues belongs to two different groups. Lastly, the D (distribution) is the distribution measure of all amino acids belongs to a particular property group along the sequence length, measured by the location of first, 25%, 50%, 75% and 100% of the amino acid sequence [99], [102], which can be formulated as [52]:…”

“…, a i,n are the measures of i th group residues in the sequence length at the positon of 25%, 50%, 75% and 100% respectively. Referred to [52], and [101] for additional details.…”

“…The amino acid sequences of proteins or peptides are first transformed into numerical representations usually using physicochemical properties like hydrophobicity, hydrophilicity, etc. Then this numerical information is transformed to its corresponding frequency domain using discrete Fourier transformation (DFT) to obtain discrete components, which may reveal the hidden significant features from the sequences without loss of information [52], [123], [124]. The frequency domain shows the discrete component's periodicity and power distribution contained in the peptide sequence over frequencies [52].…”