Unsupervised machine learning leads to an abiotic picomolar peptide ligand

24 May 2023, Version 1
This content is a preprint and has not undergone peer review at the time of posting.


Here, we combined unsupervised machine learning (ML), non-natural amino acids, and affinity-selection mass-spectrometry (AS-MS) for the discovery of ultra-high affinity peptidomimetics that bind to a protein target. Peptides and peptidomimetics were discovered using AS-MS, encoded using diverse representations, and decomposed into two-dimensional “maps” of the chemical space by dimensionality reduction. These maps showed well-defined clusters of target-specific binders distinct from the remaining chemical space that included nonspecific and nonbinding peptides. Experimental testing of abiotic peptidomimetics confirmed the discovery of low nanomolar to picomolar binders and the accurate mapping of high-affinity binders across the co-learned sequence space. With ML and AS-MS, we anticipate this cartographic approach will accelerate the definition of chemical design spaces for the prediction and generation of functional peptidomimetics.


Peptide binders
Affinity selection-mass spectrometry
Unsupervised learning
Sequence mapping
Machine learning

Supplementary materials

Supplementary Material
Preparation of synthetic split-pool peptide and peptidomimetic libraries; AS-MS and nLC-MS/MS experiment protocols; details on the encoding and dimensionality reduction methods; report of all consensus, centroid, and logo plots for all clusters; comparison of our clustering method to perform motif detection versus the MEME suite; as well as peptidomimetic synthesis, purification, and verification


Comments are not moderated before they are posted, but they can be removed by the site moderators if they are found to be in contravention of our Commenting Policy [opens in a new tab] - please read this policy before you post. Comments should be used for scholarly discussion of the content in question. You can find more information about how to use the commenting feature here [opens in a new tab] .
This site is protected by reCAPTCHA and the Google Privacy Policy [opens in a new tab] and Terms of Service [opens in a new tab] apply.