All Publications


  • FAST-MaP: Chemical Mapping of RNA Structures Using Primer-less Sequencing. bioRxiv : the preprint server for biology Verma, J., Blair, H. M., Kladwang, W., Das, R. 2026

    Abstract

    RNA structure governs the function of non-coding RNAs and influences mRNA stability and translation, making testing of models of experimental RNA structure relevant to fields spanning structural biology, virology, and molecular therapeutics. Here we present FAST-MaP (Fast and Accessible Sequencing Technology for Mutational Profiling), a protocol that enables per-nucleotide RNA structure characterization using standard molecular biology equipment and requiring no sequencing infrastructure or bioinformatics expertise. RNA is chemically modified with orthogonal probes (2A3 and DMS), reverse-transcribed, and PCR-amplified to produce dsDNA amplicons that are submitted directly to a commercial primer-less sequencing service. Returned FASTQ files are processed through a freely accessible web server to generate normalized reactivity profiles within minutes. The complete protocol, from DNA template to structural data, can be completed in approximately one week. We illustrate the workflow on a 659-nucleotide RNA, demonstrating how to test structure preservation across buffers, and how to test specific secondary and tertiary structure predictions of the RNA from computational modeling or cryo-electron microscopy. The protocol requires only standard molecular-biology skills and does not require sequencing or bioinformatics expertise.

    View details for DOI 10.64898/2026.09.22.753544

    View details for PubMedID 42818313

    View details for PubMedCentralID PMC13622246

  • De novo design of RNA pseudoknots with deep learning. Science (New York, N.Y.) Townley, J., Kladwang, W., Baker, D., Blair, H. M., Choe, C. A., El Nesr, G., Favor, A., Fisker, E., Haack, D. B., He, S., Hingey, J., Huang, P. S., Huang, R., Joshi, C. K., Karagianes, T., Kubaney, A., Liò, P., Mancino, A., Romano, J., Rudolfs, B., Spellmon, N., Toor, N., Verma, J., Wu, V., Yu, Z., Participants, E., Das, R. 2026; 393 (6814): 931-937

    Abstract

    RNA design has been hindered by the limited accuracy of three-dimensional (3D) structure prediction. In this study, we show that intricate RNA structures can be generated with current deep learning tools through accurate de novo design of pseudoknot secondary structures. In an Eterna competition involving 57 pseudoknots, generative artificial intelligence (AI) methods matched experienced human designers in solving most blind challenges, evaluated by single nucleotide-resolution chemical mapping, compensatory mutagenesis, and cryo-electron microscopy. AI-generated molecules with accurate secondary structures formed well-ordered 3D folds stabilized by noncanonical tertiary interactions not modeled during design. Success was guided by an RNet foundation model trained on prior chemical mapping data, suggesting that some difficult RNA design tasks may be tractable without first solving RNA 3D structure prediction.

    View details for DOI 10.1126/science.aeg6829

    View details for PubMedID 42658941

  • Ribonanza: deep learning of RNA structure through dual crowdsourcing. bioRxiv : the preprint server for biology He, S., Huang, R., Townley, J., Kretsch, R. C., Karagianes, T. G., Cox, D. B., Blair, H., Penzar, D., Vyaltsev, V., Aristova, E., Zinkevich, A., Bakulin, A., Sohn, H., Krstevski, D., Fukui, T., Tatematsu, F., Uchida, Y., Jang, D., Lee, J. S., Shieh, R., Ma, T., Martynov, E., Shugaev, M. V., Bukhari, H. S., Fujikawa, K., Onodera, K., Henkel, C., Ron, S., Romano, J., Nicol, J. J., Nye, G. P., Wu, Y., Choe, C., Reade, W., Participants, E., Das, R. 2024

    Abstract

    Prediction of RNA structure from sequence remains an unsolved problem, and progress has been slowed by a paucity of experimental data. Here, we present Ribonanza, a dataset of chemical mapping measurements on two million diverse RNA sequences collected through Eterna and other crowdsourced initiatives. Ribonanza measurements enabled solicitation, training, and prospective evaluation of diverse deep neural networks through a Kaggle challenge, followed by distillation into a single, self-contained model called RibonanzaNet. When fine tuned on auxiliary datasets, RibonanzaNet achieves state-of-the-art performance in modeling experimental sequence dropout, RNA hydrolytic degradation, and RNA secondary structure, with implications for modeling RNA tertiary structure.

    View details for DOI 10.1101/2024.02.24.581671

    View details for PubMedID 38464325