Molecular de-extinction of antibiotics enabled by deep learning

Abstract

Molecular de-extinction is an emerging field that aims to resurrect molecules to solve present-day problems such as antibiotic resistance. Here, we introduce a deep learning approach called Antibiotic Peptide de-Extinction (APEX) to mine the proteomes of all available extinct organisms (the “extinctome”) searching for encrypted peptide (EP) antibiotics. APEX mined a total of 10,311,899 EPs and identified 37,176 sequences predicted to have broad-spectrum antimicrobial activity, 11,035 of which were not found in extant organisms. Chemical synthesis and experimental validation yielded archaic EPs (AEPs) with activity against dangerous bacterial pathogens. Most peptides killed bacteria by depolarizing their cytoplasmic membrane, contrary to known antimicrobial peptides, which target the outer membrane. Notably, lead peptides, including those derived from the woolly mammoth, ancient sea cow, giant sloth, and extinct giant elk, exhibited anti-infective activity in preclinical mouse models. We propose molecular de-extinction, accelerated by deep learning, as a framework for discovering therapeutic molecules.

Peptides from non-immune proteins target infections through antimicrobial and immunomodulatory properties

“…1A) 20 . EPs from the human proteome were previously classified 8 as: (1) peptides derived from secreted proteins with diverse biological functions, including plasma proteins, coagulation factors, protein inhibitors, enzymes, and signaling cascade factors; or (2) peptide hormones with well-defined putative functions, but previously undisclosed antibiotic properties, such as neuropeptides, regulators of G-protein-coupled receptors (GPCRs), and diuretic hormones.…”

“…Highly hydrophobic peptides and those containing multiple cysteine residues were filtered out from the selection process. In total, 39 EPs were selected for synthesis and biological characterization and named according to their parent protein groups: Immune proteeins (i.e, immunosins) and non-immune proteins [i.e., (1) collagenins, (2) neuronins, (3) eyesins, (4) toothins, and (5) zipperins].…”

“…The innate immune system traditionally has been thought to be orchestrated by immune proteins. Computational and AI tools have recently been used to identify novel antimicrobial molecules encoded within genomes and proteomes [1][2][3][4][5][6][7][8][9] ; the presence of these molecules suggests that there is much dark matter still to be explored for antibiotic discovery. Encrypted peptides (EPs) were discovered as a result of such efforts.…”