Naim Abdul-Khalek

This paper describes a two-stage membrane-based biorefinery process that selectively removes green pigments and unwanted proteins from clover-grass, resulting in a high-quality protein product with reduced allergens and increased antioxidants.

Pfly predicts peptide detectability in mass spectrometry using a deep learning model trained on synthetic and biological data, offering customizable classification for different experimental conditions.

This study characterizes the proteome of brewers spent grain (BSG) and identifies key proteins, differential abundance, and safety concerns to guide downstream processing for functional food ingredients.

The paper uses deep learning to analyze how neighboring amino acid pairs affect MS1 intensity, identifying key motifs and their impact on peptide response.

The paper develops a deep learning model to predict peptide MS1 intensities using sequence data and identifies key physicochemical properties influencing the response.