Machine Learning Informs RNA‐Binding Chemical Space**

Yazdani, Kamyar; Jordan, Deondre; Yang, Mo; Fullenkamp, Christopher R.; Schneekloth, John S.; Calabrese, David; Boer, Robert E.; Hilimire, Thomas A.; Allen, Timothy E. H.; Khan, Rabia T

doi:10.1002/anie.202211358

Cited by 34 publications

(31 citation statements)

References 68 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The recent advances in RNA binder screening hint that discovery rate of selective RNA binders is not that different to that of protein binders, which suggests that many more selective RNA binders will be within reach in the near future. , Combining high-throughput screening with a PINAD or a different approach to targeted RNA degradation holds potential for a rapid drug discovery platform, the need for which was affirmed during the COVID-19 pandemic. Viruses are capable of rapid mutation as a part of their immune evasion strategy, which greatly complicates antiviral drug discovery campaigns .…”

Section: Discussionmentioning

confidence: 99%

Proximity-Induced Nucleic Acid Degrader (PINAD) Approach to Targeted RNA Degradation Using Small Molecules

et al. 2023

Self Cite

View full text Add to dashboard Cite

Nature has evolved intricate machinery to target and degrade RNA, and some of these molecular mechanisms can be adapted for therapeutic use. Small interfering RNAs and RNase H-inducing oligonucleotides have yielded therapeutic agents against diseases that cannot be tackled using protein-centered approaches. Because these therapeutic agents are nucleic acid-based, they have several inherent drawbacks which include poor cellular uptake and stability. Here we report a new approach to target and degrade RNA using small molecules, proximity-induced nucleic acid degrader (PINAD). We have utilized this strategy to design two families of RNA degraders which target two different RNA structures within the genome of SARS-CoV-2: G-quadruplexes and the betacoronaviral pseudoknot. We demonstrate that these novel molecules degrade their targets using in vitro, in cellulo, and in vivo SARS-CoV-2 infection models. Our strategy allows any RNA binding small molecule to be converted into a degrader, empowering RNA binders that are not potent enough to exert a phenotypic effect on their own. PINAD raises the possibility of targeting and destroying any disease-related RNA species, which can greatly expand the space of druggable targets and diseases.

show abstract

Section: Discussionmentioning

confidence: 99%

Proximity-Induced Nucleic Acid Degrader (PINAD) Approach to Targeted RNA Degradation Using Small Molecules

et al. 2023

Self Cite

View full text Add to dashboard Cite

show abstract

“…However, delivering ASOs to cells can be difficult due to their poor permeability, and short ASOs may also bind to other RNAs with similar sequences, leading to unintended effects. To overcome these limitations, some researchers have focused on developing small molecules that bind and inhibit miRNAs [8, 9]. Unlike ASOs, small molecules are typically easier to formulate, and have better bioavailability, making them more suitable for drug development.…”

Section: Introductionmentioning

confidence: 99%

Functional microRNA-Targeting Drug Discovery by Graph-Based Deep Learning

Arshadi¹,

Salem

Karner

et al. 2023

Preprint

View full text Add to dashboard Cite

MicroRNAs are recognized as key drivers in many cancers, but targeting them with small molecules remains a challenge. We present RiboStrike, a deep learning framework that identifies small molecules against specific microRNAs. To demonstrate its capabilities, we applied it to microRNA-21 (miR-21), a known driver of breast cancer. To ensure the selected molecules only targeted miR-21 and not other microRNAs, we also performed a counter-screen against DICER, an enzyme involved in microRNA biogenesis. Additionally, we used auxiliary models to evaluate toxicity and select the best candidates. Using datasets from various sources, we screened a pool of nine million molecules and identified eight, three of which showed anti-miR-21 activity in both reporter assays and RNA sequencing experiments. One of these was also tested in mouse models of breast cancer, resulting in a significant reduction of lung metastases. These results demonstrate RiboStrike's ability to effectively screen for microRNA-targeting compounds in cancer.

show abstract

“…In addition, hits were identified by comparing the Z-scores from the DHX15 rG4 screen with the Z-scores from a compiled data set of 23 other nucleic acid screens performed by our lab. 25 By analyzing spot morphology and structural diversity, we recognized 17 compounds as competitive hits, yielding a final hit rate of 0.1%. Single-concentration screening by SPR and a fluorescence quenching assay were performed on commercial stocks of the hits to evaluate their binding ability toward the DHX15 rG4 (Supplementary Figure 4).…”

mentioning

confidence: 99%

Competitive Microarray Screening Reveals Functional Ligands for the DHX15 RNA G-Quadruplex

Prestwood,

Yang,

Lewis

et al. 2024

ACS Med. Chem. Lett.

Self Cite

View full text Add to dashboard Cite

RNAs are increasingly considered valuable therapeutic targets, and the development of methods to identify and validate both RNA targets and ligands is more important than ever. Here, we utilized a bioinformatic approach to identify a hairpincontaining RNA G-quadruplex (rG4) in the 5′ untranslated region (5′ UTR) of DHX15 mRNA. By using a novel competitive small molecule microarray (SMM) approach, we identified a compound that specifically binds to the DHX15 rG4 (K D = 12.6 ± 1.0 μM). This rG4 directly impacts translation of a DHX15 reporter mRNA in vitro, and binding of our compound (F1) to the structure inhibits translation up to 57% (IC 50 = 22.9 ± 3.8 μM). This methodology allowed us to identify and target the mRNA of a cancer-relevant helicase with no known inhibitors. Our target identification method and the novelty of our screening approach make our work informative for future development of novel small molecule cancer therapeutics for RNA targets.

show abstract

Machine Learning Informs RNA‐Binding Chemical Space**

Cited by 34 publications

References 68 publications

Proximity-Induced Nucleic Acid Degrader (PINAD) Approach to Targeted RNA Degradation Using Small Molecules

Proximity-Induced Nucleic Acid Degrader (PINAD) Approach to Targeted RNA Degradation Using Small Molecules

Functional microRNA-Targeting Drug Discovery by Graph-Based Deep Learning

Competitive Microarray Screening Reveals Functional Ligands for the DHX15 RNA G-Quadruplex

Contact Info

Product

Resources

About