Recent applications of artificial intelligence in RNA-targeted small molecule drug discovery.

INTRODUCTION: Targeting RNAs with small molecules offers an alternative to the conventional protein-targeted drug discovery and can potentially address unmet and emerging medical needs. The recent rise of interest in the strategy has already resulted in large amounts of data on disease associated RNAs, as well as on small molecules that bind to such RNAs. Artificial intelligence (AI) approaches, including machine learning and deep learning, present an opportunity to speed up the discovery of RNA-targeted small molecules by improving decision-making efficiency and quality. AREAS COVERED: The topics described in this review include the recent applications of AI in the identification of RNA targets, RNA structure determination, screening of chemical compound libraries, and hit-to-lead optimization. The impact and limitations of the recent AI applications are discussed, along with an outlook on the possible applications of next-generation AI tools for the discovery of novel RNA-targeted small molecule drugs. EXPERT OPINION: Key areas for improvement include developing AI tools for understanding RNA dynamics and RNA - small molecule interactions. High-quality and comprehensive data still need to be generated especially on the biological activity of small molecules that target RNAs.

Probing RNA-Small Molecule Interactions Using Biophysical and Computational Approaches.

Interest in small molecules that target RNA is flourishing, and the expectation set on them to treat diseases with unmet medical needs is high. However, several challenges remain, including difficulties in selecting suitable tools and establishing workflows for their discovery. In this context, we optimized experimental and computational approaches that were previously employed for the protein targets. Here, we demonstrate that a fluorescence-based assay can be effectively used to screen small molecule libraries for their ability to bind and stabilize an RNA stem-loop. Our screen identified several fluoroquinolones that bind to the target stem-loop. We further probed their interactions with the target using biolayer interferometry, isothermal titration calorimetry (ITC), and nuclear magnetic resonance spectroscopy. The results of these biophysical assays suggest that the fluoroquinolones bind the target in a similar manner. Armed with this knowledge, we built models for the complexes of the fluoroquinolones and the RNA target. Then, we performed fragment molecular orbital (FMO) calculations to dissect the interactions between the fluoroquinolones and the RNA. We found that the binding free energies obtained from the ITC experiments correlated strongly with the interaction energies calculated by FMO. Finally, we designed fluoroquinolone analogues and performed FMO calculations to predict their binding free energies. Taken together, the results of this study support the importance of conducting orthogonal assays in binding confirmation and compound selection and demonstrate the usefulness of FMO calculations in the rational design of RNA-targeted small molecules.

Discovery of RNA-targeted small molecules through the merging of experimental and computational technologies.

INTRODUCTION: The field of RNA-targeted small molecules is rapidly evolving, owing to the advances in experimental and computational technologies. With the identification of several bioactive small molecules that target RNA, including the FDA-approved risdiplam, the biopharmaceutical industry is gaining confidence in the field. This review, based on the literature obtained from PubMed, aims to disseminate information about the various technologies developed for targeting RNA with small molecules and propose areas for improvement to develop drugs more efficiently, particularly those linked to diseases with unmet medical needs. AREAS COVERED: The technologies for the identification of RNA targets, screening of chemical libraries against RNA, assessing the bioactivity and target engagement of the hit compounds, structure determination, and hit-to-lead optimization are reviewed. Along with the description of the technologies, their strengths, limitations, and examples of how they can impact drug discovery are provided. EXPERT OPINION: Many existing technologies employed for protein targets have been repurposed for use in the discovery of RNA-targeted small molecules. In addition, technologies tailored for RNA targets have been developed. Nevertheless, more improvements are necessary, such as artificial intelligence to dissect important RNA structures and RNA-small-molecule interactions and more powerful chemical probing and structure prediction techniques.

Developing an Updated Strategy for Estimating the Free-Energy Parameters in RNA Duplexes.

For the last 20 years, it has been common lore that the free energy of RNA duplexes formed from canonical Watson-Crick base pairs (bps) can be largely approximated with dinucleotide bp parameters and a few simple corrective constants that are duplex independent. Additionally, the standard benchmark set of duplexes used to generate the parameters were GC-rich in the shorter duplexes and AU-rich in the longer duplexes, and the length of the majority of the duplexes ranged between 6 and 8 bps. We were curious if other models would generate similar results and whether adding longer duplexes of 17 bps would affect the conclusions. We developed a gradient-descent fitting program for obtaining free-energy parameters-the changes in Gibbs free energy (ΔG), enthalpy (ΔH), and entropy (ΔS), and the melting temperature (Tm)-directly from the experimental melting curves. Using gradient descent and a genetic algorithm, the duplex melting results were combined with the standard benchmark data to obtain bp parameters. Both the standard (Turner) model and a new model that includes length-dependent terms were tested. Both models could fit the standard benchmark data; however, the new model could handle longer sequences better. We developed an updated strategy for fitting the duplex melting data.

Crystallization of oligonucleotides containing A-rich repeats suggests a structural contribution to the autoregulation mechanism of PABP translation.

Eukaryotic poly(A)-binding protein (PABP) commonly binds to the 3'-UTR poly(A) tail of every mRNA, but it also binds to the 5'-UTR of PABP mRNA for autoregulation of its expression. In the sequence of the latter binding site, the contiguous A residues are segmented discretely by the insertion of short pyrimidine oligonucleotides as linkers, so that (A)(6-8) segments are repeated six times. This differs from the poly(A)-tail sequence, which has a higher binding affinity for PABP. In order to examine whether the A-rich repeats have a functional structure, several RNA/DNA analogues were subjected to crystallization. It was found that some of them could be crystallized. Single crystals thus obtained diffracted to 4.1 Å resolution. The fact that the repeated sequences can be crystallized suggests the possibility that the autoregulatory sequence in PABP mRNA has a specific structure which impedes the binding of PABP. When PABP is excessively produced, it could bind to this sequence by releasing the structure in order to interfere with initiation-complex formation for suppression of PABP translation. Otherwise, PABP at low concentration preferentially binds to the poly(A) tail of PABP mRNA.

Crystal structures of the armadillo repeat domain of adenomatous polyposis coli and its complex with the tyrosine-rich domain of Sam68.

Adenomatous polyposis coli (APC) is a tumor suppressor protein commonly mutated in colorectal tumors. APC plays important roles in Wnt signaling and other cellular processes. Here, we present the crystal structure of the armadillo repeat (Arm) domain of APC, which facilitates the binding of APC to various proteins. APC-Arm forms a superhelix with a positively charged groove. We also determined the structure of the complex of APC-Arm with the tyrosine-rich (YY) domain of the Src-associated in mitosis, 68 kDa protein (Sam68), which regulates TCF-1 alternative splicing. Sam68-YY forms numerous interactions with the residues on the groove and is thereby fixed in a bent conformation. We assessed the effects of mutations and phosphorylation on complex formation between APC-Arm and Sam68-YY. Structural comparisons revealed different modes of ligand recognition between the Arm domains of APC and other Arm-containing proteins.

The unique structure of carbonic anhydrase αCA1 from Chlamydomonas reinhardtii.

Chlamydomonas reinhardtii α-type carbonic anhydrase (Cr-αCA1) is a dimeric enzyme that catalyses the interconversion of carbon dioxide and carbonic acid. The precursor form of Cr-αCA1 undergoes post-translational cleavage and N-glycosylation. Comparison of the genomic sequences of precursor Cr-αCA1 and other αCAs shows that Cr-αCA1 contains a different N-terminal sequence and two insertion sequences. A 35-residue peptide in one of the insertion sequences is deleted from the precursor during maturation. The crystal structure of the mature form of Cr-αCA1 has been determined at 1.88 Šresolution. Each subunit is cleaved into the long and short peptides, but they are linked together by a disulfide bond. The two subunits are linked by a disulfide bond. N-Glycosylations occur at three asparagine residues and the attached N-glycans protrude into solvent regions. The subunits consist of a core ß-sheet structure composed of nine ß-strands. At the centre of the ß-sheet is the catalytic site, which contains a Zn atom bound to three histidine residues. The amino-acid residues around the Zn atom are highly conserved in other monomeric and dimeric αCAs. The short peptide runs near the active site and forms a hydrogen bond to the zinc-coordinated residue in the long chain, suggesting an important role for the short peptide in Cr-αCA1 activity.