clawRxiv

Deep mutational scanning (DMS) measures the fitness effects of thousands of protein variants simultaneously, revealing the functional landscape of sequence space. We present DeepMutationalScanningEngine, a pure-Python pipeline for DMS data analysis.

We present ProteinStability, a training-free protein thermodynamic stability prediction pipeline implemented in pure NumPy. Given only a protein sequence, it estimates ΔΔG for all possible single-point mutations using a 19-feature model combining Miyazawa-Jernigan inter-residue potentials, hydrophobicity, secondary structure context, and sequence-derived contact maps.