Daniel Garzon Otero
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Daniel Garzon Otero has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
Aneesh Mandapati
University of Virginia, Chemical Engineering Department, 385 McCormick Road, Charlottesville, Virginia 22903, United States
2 shared publications- Camille Louise Bilodeau
University of Virginia
2 shared publications Omid Akbari
University of Virginia, Chemical Engineering Department, 385 McCormick Road, Charlottesville, Virginia 22903, United States
2 shared publicationsCamille Bilodeau
University of Virginia
1 shared publication- Omid Akbari
University of Virginia
1 shared publication
Latest Publications
- Open Access
- 13 January 2026
- Published by American Chemical Society (ACS) in Journal of Chemical Information and Modeling
- Vol. 66 (2) , 1264-1273
PepFoundry: A Pipeline for Building Machine-Learning Ready Representations of Nonstandard Peptides Containing Cycles, Non-natural Residues, Polymer Units, and More
Peptides featuring synthetic modifications, such as noncanonical amino acids, backbone modifications, cyclic structures, and polymer units have become central to modern drug design due to their enhanced stability and functional diversity. However, current machine learning (ML) approaches are restricted by challenges associated with transforming peptide sequences into atom-level representations, leading ML efforts to focus largely on datasets containing linear peptides comprised of standard residues. Here, we present PepFoundry, a Python package that handles peptide sequences beyond canonical amino acids and linear topologies by using SMILES strings in the CHUCKLES format. PepFoundry generates atom-mapped RDKit molecule objects, enabling the extraction of atom-level features, such as Morgan fingerprints and graph representations. We demonstrate its utility by processing a dataset of peptide sequences containing noncanonical amino acids and generating atomic level features for downstream property prediction. We show that atomic-level representations of peptides containing noncanonical amino acids consistently outperform sequence-level representations, regardless of model type. We additionally explore the representation of noncanonical peptides through latent space visualization and show that models with atomic-level information can effectively learn relationships between analogous sequences of l-peptides, d-peptides, and peptoids. This framework allows for the flexible incorporation of new amino acid chemistries, enabling existing ML methods to be straightforwardly applied to datasets of peptides containing nonstandard features. It also facilitates the rapid construction of customized peptide libraries and provides a scalable platform to accelerate ML-driven peptide discovery and optimization.
- 13 January 2026
- Published by American Chemical Society (ACS) in Journal of Chemical Information and Modeling
- Vol. 66 (2) , 1264-1273
Open AccessPepFoundry: A Pipeline for Building Machine-Learning Ready Representations of Nonstandard Peptides Containing Cycles, Non-natural Residues, Polymer Units, and More
Peptides featuring synthetic modifications, such as noncanonical amino acids, backbone modifications, cyclic structures, and polymer units have become central to modern drug design due to their enhanced stability and functional diversity. However, current machine learning (ML) approaches are restricted by challenges associated with transforming peptide sequences into atom-level representations, leading ML efforts to focus largely on datasets containing linear peptides comprised of standard residues. Here, we present PepFoundry, a Python package that handles peptide sequences beyond canonical amino acids and linear topologies by using SMILES strings in the CHUCKLES format. PepFoundry generates atom-mapped RDKit molecule objects, enabling the extraction of atom-level features, such as Morgan fingerprints and graph representations. We demonstrate its utility by processing a dataset of peptide sequences containing noncanonical amino acids and generating atomic level features for downstream property prediction. We show that atomic-level representations of peptides containing noncanonical amino acids consistently outperform sequence-level representations, regardless of model type. We additionally explore the representation of noncanonical peptides through latent space visualization and show that models with atomic-level information can effectively learn relationships between analogous sequences of l-peptides, d-peptides, and peptoids. This framework allows for the flexible incorporation of new amino acid chemistries, enabling existing ML methods to be straightforwardly applied to datasets of peptides containing nonstandard features. It also facilitates the rapid construction of customized peptide libraries and provides a scalable platform to accelerate ML-driven peptide discovery and optimization.
- Open Access
- 5 November 2025
- Published by American Chemical Society (ACS) in ChemRxiv
PepFoundry: A Pipeline for Building Machine-Learning Ready Representations of Non-Standard Peptides Containing Cycles, Non-natural Residues, Polymer Units, and More
Peptides featuring synthetic modifications, such as non-canonical amino acids, backbone modifications, cyclic structures, and polymer units have become central to modern drug design due to their enhanced stability and functional diversity. However, current machine learning (ML) approaches are restricted by challenges associated with transforming peptide sequences into atom-level representations, leading ML efforts to focus largely on datasets containing linear peptides comprised of standard residues. Here, we present PepFoundry, a Python package that handles peptide sequences beyond canonical amino acids and linear topologies using SMILES strings in the CHUCKLES format. PepFoundry generates atom-mapped RDKit molecule objects, enabling the extraction of atom- level features such as Morgan fingerprints and graph representations. We demonstrate its utility by processing a dataset of peptide sequences containing non-canonical amino acids and generating atomic level features for downstream property prediction. We show that atomic-level representations of peptides containing non-canonical amino acids consistently outperform sequence-level representations, regardless of model type. We additionally explore the representation of non-canonical peptides through latent space visualization and show that models with atomic-level information can effectively learn relationships between analogous sequences of L-peptides, D-peptides, and peptoids. This framework allows for the flexible incorporation of new amino acid chemistries, enabling existing ML methods to be straightforwardly applied to datasets of peptides containing non-standard features. It also facilitates the rapid construction of customized peptide libraries and provides a scalable platform to accelerate ML- driven peptide discovery and optimization.
- 5 November 2025
- Published by American Chemical Society (ACS) in ChemRxiv
Open AccessPepFoundry: A Pipeline for Building Machine-Learning Ready Representations of Non-Standard Peptides Containing Cycles, Non-natural Residues, Polymer Units, and More
Peptides featuring synthetic modifications, such as non-canonical amino acids, backbone modifications, cyclic structures, and polymer units have become central to modern drug design due to their enhanced stability and functional diversity. However, current machine learning (ML) approaches are restricted by challenges associated with transforming peptide sequences into atom-level representations, leading ML efforts to focus largely on datasets containing linear peptides comprised of standard residues. Here, we present PepFoundry, a Python package that handles peptide sequences beyond canonical amino acids and linear topologies using SMILES strings in the CHUCKLES format. PepFoundry generates atom-mapped RDKit molecule objects, enabling the extraction of atom- level features such as Morgan fingerprints and graph representations. We demonstrate its utility by processing a dataset of peptide sequences containing non-canonical amino acids and generating atomic level features for downstream property prediction. We show that atomic-level representations of peptides containing non-canonical amino acids consistently outperform sequence-level representations, regardless of model type. We additionally explore the representation of non-canonical peptides through latent space visualization and show that models with atomic-level information can effectively learn relationships between analogous sequences of L-peptides, D-peptides, and peptoids. This framework allows for the flexible incorporation of new amino acid chemistries, enabling existing ML methods to be straightforwardly applied to datasets of peptides containing non-standard features. It also facilitates the rapid construction of customized peptide libraries and provides a scalable platform to accelerate ML- driven peptide discovery and optimization.
- Open Access
- 11 December 2024
- Published by Royal Society of Chemistry (RSC) in Molecular Systems Design & Engineering
- Vol. 10 (3) , 205-218
PepMNet: a hybrid deep learning model for predicting peptide properties using hierarchical graph representations
Peptides are a powerful class of molecules that can be applied to a range of problems including biomaterials development and drug design.
- 11 December 2024
- Published by Royal Society of Chemistry (RSC) in Molecular Systems Design & Engineering
- Vol. 10 (3) , 205-218
Open AccessPepMNet: a hybrid deep learning model for predicting peptide properties using hierarchical graph representations
Peptides are a powerful class of molecules that can be applied to a range of problems including biomaterials development and drug design.