Machine Learning Guides Peptide Nucleic Acid Flow Synthesis and Sequence Design

Peptide nucleic acids (PNAs) are potential antisense therapies for genetic, acquired, and viral diseases. Efficiently selecting candidate PNA sequences for synthesis and evaluation from a genome containing hundreds to thousands of options can be challenging. To facilitate this process, we leverage here machine learning (ML) algorithms and automated synthesis technology to predict PNA synthesis efficiency and guide rational PNA sequence design. The training data was collected from individual fluorenylmethyloxycarbonyl (Fmoc) deprotection reactions performed on a fully automated PNA synthesizer. Our optimized ML model allows for 93% prediction accuracy and 0.97 Pearson’s r. The predicted synthesis scores were validated to be correlated with the experimental HPLC crude purities (correlation coefficient R2 = 0.95). Furthermore, we demonstrated a general applicability of ML through designing synthetically accessible antisense PNA sequences from 102,315 predicted candidates targeting exon 44 of the human dystrophin gene, SARS-CoV-2, HIV, as well as selected genes associated with cardiovascular diseases, type II diabetes, and various cancers. Collectively, ML provides an accurate prediction of PNA synthesis quality and serves as a useful computational tool for rational PNA sequence design.

Synthesis of α-(R)-/γ-(S)-Dimethyl Substituted Peptide Nucleic Acid Submonomer Using Mitsunobu Reaction

One of the major challenges facing modern biochemical and biomedical technologies are finding molecular tools for diagnosis and detection of genetic diseases. In this connection, several classes of oligonucleotides have been developed that can recognize and bind to DNA and RNA with high affinity and sequence selectivity and withstand enzymatic degradation by proteases and nucleases; however, few can traverse the cell membrane on their own. One such promising class of nucleic acid mimics developed in the last two decades which showed good results in vitro, are the peptide nucleic acids (PNAs). New chiral α- and γ-peptide Nucleic Acid (PNA) submonomer with methyl substituents in pseudopeptide backbone were synthesized via Mitsunobu reaction. The α-(R)-/γ-(S)-configuration of the chiral centres will ensure the preorganization of the PNA oligomer into a right-handed helix. The results obtained showed that Boc/Fmoc-submonomer compatible with Boc-protocol PNAs solid-phase synthesis on an MBHA resin. We synthesized simple and efficient α-R-, γ-S-disubstituted PNA submonomer based on L-Ala and D-Ala with the construction of the intermediate pseudopeptide moiety by Mitsunobu reaction for subsequent use in the Boc-Protocol of solid phase PNA synthesis.