Skip to content
DraconiticResearch
Search Sources API
179,152 studies31 sourcesUpdated 13 min ago
PreprintCC BY-NC-ND 4.0arXiv

Automatic Generation of Novel Highly-Functional Molecular Sequences

  • Vincent R. Ragusa
  • Chrisoph Adami
Open at sourcePDFDOICite

Abstract

While multiple methods now exist to generate functional sequence variants from existing annotated examples, it is unclear how well such methods can be used to generate sequences that exceed the functionality of those contained in the example set. Using two complete fitness landscapes, we quantify how effectively generative tools can search sequence space and find rare, novel, highly functional sequences, focusing on variational auto-encoders and information-theoretic methods. We find that an information-theoretic method that does not require training and runs significantly faster than standard Machine-Learning/Artificial Intelligence (ML/AI) methods also is significantly more effective in finding rare highly-functional sequences. We discuss the application of this novel method to discover rare polypeptides with anti-bacterial properties that are specific to bacterial, but not eukaryotic, cell membranes.

Related

  1. Molecular and functional characterization of a highly mosquitocidal Bacillus thuringiensis strain VCRC-B669
    Akash Ashok Dhotre, Mathivanan Ashokkumar, Sahadiya Mandodan +2
    Scientific ReportsPeer-reviewedCC BY-NC-ND 4.0Full textMolecular biology & gene regulationCrossref
  2. A highly contiguous genome assembly of Cyclamen persicum to accelerate functional genomics and breeding
    DNA research : an international journal for rapid publication of reports on genes and genomesPeer-reviewedCC BYFull textMolecular biology & gene regulationEurope PMC
  3. Automatic Text-fishing, Unification, and Normalization Application in Python (aTUNApy): a tool to build molecular databases
    Aylin Del Moral Morales, José L. Medina-Franco
    ChemRxivPreprintCC BYFull textMolecular biology & gene regulationChemRxiv
  4. Conditional Generation And Inpainting Of Non-coding RNA Sequences With Masked Discrete Diffusion
    U. Upadhyay, C. Dai, J. Herold +2
    bioRxivPreprintCC BYFull textBiophysicsbioRxiv
  5. Mind the gap between functional groups and surface of magnetic nanoparticles for highly specific magnetic-based protein assays in biological medium
    R. Amin, Y. Wang, F. Wolgast +6
    bioRxivPreprintAll rights reservedFull textGeneral biochemistrybioRxiv

Cite

BibTeXRIS
BibTeX
@misc{ragusa2026automatic,
  title = {{Automatic Generation of Novel Highly-Functional Molecular Sequences}},
  author = {Vincent R. Ragusa and Chrisoph Adami},
  howpublished = {arXiv},
  year = {2026},
  month = nov,
  doi = {10.48550/arxiv.2611.03603},
  eprint = {2611.03603},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2611.03603},
  note = {CC BY-NC-ND 4.0},
}
RIS
TY  - UNPB
TI  - Automatic Generation of Novel Highly-Functional Molecular Sequences
AU  - Vincent R. Ragusa
AU  - Chrisoph Adami
PY  - 2026
DA  - 2026/11/02
PB  - arXiv
DO  - 10.48550/arxiv.2611.03603
UR  - https://arxiv.org/abs/2611.03603
AB  - While multiple methods now exist to generate functional sequence variants from existing annotated examples, it is unclear how well such methods can be used to generate sequences that exceed the functionality of those contained in the example set. Using two complete fitness landscapes, we quantify how effectively generative tools can search sequence space and find rare, novel, highly functional sequences, focusing on variational auto-encoders and information-theoretic methods. We find that an information-theoretic method that does not require training and runs significantly faster than standard Machine-Learning/Artificial Intelligence (ML/AI) methods also is significantly more effective in finding rare highly-functional sequences. We discuss the application of this novel method to discover rare polypeptides with anti-bacterial properties that are specific to bacterial, but not eukaryotic, cell membranes.
ER  -