2020
DOI: 10.1101/2020.04.10.036566
|View full text |Cite
Preprint
|
Sign up to set email alerts
|

Interpretable Deep Learning for De Novo Design of Cell-Penetrating Abiotic Polymers

Abstract: There are more amino acid permutations within a 40-residue sequence than atoms on Earth. This vast chemical search space hinders the use of human learning to design functional polymers. Here we couple supervised and unsupervised deep learning with highthroughput experimentation to drive the design of high-activity, novel sequences reaching 10 kDa that deliver antisense oligonucleotides to the nucleus of cells. The models, in which natural and unnatural residues are represented as topological fingerprints, deci… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
8
0

Year Published

2020
2020
2022
2022

Publication Types

Select...
4
2
1

Relationship

4
3

Authors

Journals

citations
Cited by 7 publications
(8 citation statements)
references
References 45 publications
0
8
0
Order By: Relevance
“…We also synthesized an Omomyc–Omomyc derivative containing Mach3, a nuclear-targeting miniprotein that we recently designed. 45 To obtain this 231 residue covalent protein complex, we removed Alloc from the C-terminal lysine and synthesized, by AFPS, the 41-residue Mach3 sequence from the resulting free amine and finally added a TAMRA label, obtaining compound 12 .…”
Section: Resultsmentioning
confidence: 99%
“…We also synthesized an Omomyc–Omomyc derivative containing Mach3, a nuclear-targeting miniprotein that we recently designed. 45 To obtain this 231 residue covalent protein complex, we removed Alloc from the C-terminal lysine and synthesized, by AFPS, the 41-residue Mach3 sequence from the resulting free amine and finally added a TAMRA label, obtaining compound 12 .…”
Section: Resultsmentioning
confidence: 99%
“…Most of these biopolymers, however, are currently produced by recombinant methods. AFPS can significantly expedite and improve the synthesis quality of these structures, as already demonstrated in the context of tumor neoantigen peptides for personalized immunotherapy and cell-penetrating peptides. In the event of an aggregating sequence, we demonstrated that single-point mutations can avoid aggregation during synthesis. Introducing point mutations into peptide and protein sequences is common practice in biology, often to interrogate function of a specific amino acid.…”
Section: Discussionmentioning
confidence: 99%
“…AFPS can significantly expedite and improve the synthesis quality of these structures, as already demonstrated in the context of tumor neoantigen peptides for personalized immunotherapy and cell-penetrating peptides. (44)(45)(46) In the event of an aggregating sequence, we demonstrated that single-point mutations can avoid aggregation during synthesis. Introducing point mutations into peptide and protein sequences is common practice in biology, often to interrogate function of a specific amino acid.…”
Section: Discussionmentioning
confidence: 89%