NNAlign

NNAlign identifies sequence motifs linked to quantitative peptide readouts by aligning peptide sequences and training artificial neural network models to characterize receptor–ligand interactions.

Key Features:

• Artificial Neural Network Models: Leverages artificial neural networks to model receptor-ligand interactions from input ligand sequences and associated quantitative target values.
• Sequence Alignment and Motif Identification: Aligns peptide sequences and identifies binding motifs associated with quantitative readouts.
• Predictive Modeling: Generates predictive models that scan other protein or peptide sequences to detect occurrences of identified motifs.

Scientific Applications:

• Peptide Microarray Analysis: Analyzes quantitative peptide datasets such as peptide microarrays containing over 100,000 data points to discover interaction motifs.
• Receptor–Ligand Interaction Characterization: Characterizes motifs relevant to receptor–ligand interaction mechanisms from diverse biological datasets with quantitative peptide measurements.

Methodology:

Aligns peptide sequences while simultaneously identifying motifs linked with quantitative readouts; trains artificial neural networks on ligand sequences with associated target values; outputs models capable of scanning sequences for identified motifs.