MarcinMagnus 🦋 @mmagnus42.bsky.social

SONATA BIS from the @NCN_PL ($1.2M) to launch a new RNA design lab to build AI models grounded in experimental data at the Centrum Nowych Technologii @UniWarszawski. Hiring: Experimental Postdoc (SELEX) & Bioinformatics / AI (postdoc and PhD) mmagnus@fas.harvard.edu #rna

I'm thrilled to join over 1900+ global experts in oligos, peptides, and mRNA at #TIDESUSA! Learn more here: lnkd.in/e6KdVeN7 #rna #rnastructure

Excited to have @edric_choi present his latest work on RNA chemical mapping at the CASP Nucleic Acids Reading Group! Thursday April 16 2026 on Zoom; Pacific Daylight Saving Time 8 am / Eastern Daylight Saving Time 11 am -- free to attend and full of interactive discussions.

Hi Nucleic Acid enthusiasts, #rna #rnastructure #rnadesign Tomorrow I will be speaking at the Institute of Genetics and Biotechnology seminar at the University of Warsaw about our work on OpenRNAFold and new research directions in the Magnus lab. The seminar will be held online (see link below). Eastern Daylight Saving Time 8:30 am / Central European Time: 1:30 pm OpenRNAFold: an end-to-end approach for RNA 3D structure prediction Abstract: RNA plays central roles in gene expression as messenger RNA and in many biological processes as structured non-coding RNAs. Understanding these functions requires knowledge of RNA tertiary structure, but experimental structure determination is slow and expensive, leading to a large gap between sequence and structure data. Inspired by advances in protein structure prediction, such as AlphaFold, RNA structure prediction has attracted growing interest. However, current deep learning models for RNA often report inflated accuracy due to structural overlap between training and test sets. Early benchmarks also indicate that AlphaFold3 remains inaccurate for RNA structures. Because RNA structures are scarce, we focus on two essentials: carefully curated training data to prevent data leakage (RNA3DB, Szikszai, et al., 2024), and high-quality sequence alignments (rnahub.org, Magnus, et al., 2025). Using these datasets and alignments, we are currently testing our own AlphaFold-based RNA model that explicitly emphasizes base pairing and RNA geometry. This work aims to improve RNA 3D structure prediction and is being evaluated in upcoming blind challenges such as CASP and RNA-Puzzles. It will also serve as a platform for further deep learning developments in RNA design and therapeutics in my Laboratory of RNA Design and Therapeutics at CeNT, University of Warsaw, scheduled to open in mid-2026. Thursday March 27 2026 on Google Meet lnkd.in/e6c2JrUv

We had a great session at our RNA CASP SIG featuring prof. Tiwary talking about his method that brings together deep learning, molecular dynamics, and statistical physics to understand structural ensembles of RNA, not just single structures. RNA function depends on dynamic 3D conformations, yet most approaches still focus on static predictions. RNAnneal addresses this by generating diverse structural ensembles from sequence, learning thermodynamic representations in a reduced latent space (PCA + SPIB), and scoring conformations via a probabilistic framework grounded in physics. This is a clear step toward physisc-aware RNA modeling, where capturing interactions, heterogeneity, and thermodynamics becomes central, especially for applications like RNA-targeted drug discovery and functional RNA design. #rna #casprnasig #rnastructure youtube.com/watch?v=OZQeE4…

PostDoc and 2 PhD positions in two NCN grants available soon!

Come learn about super interesting and cool DNA structure at our nucleic acid structure webinar by Cameron Mackereth "Unusual DNA architecture in a dopamine-bound aptamer complex" on March 5 Meeting ID: 934 4593 5624 Passcode: 802843 Mailing list: groups.google.com/g/casp-rna-sig

PyMOL4RNA: colorbyrmsd to spot differences between structures. It is especially useful for visually highlighting local and global deviations between reference RNAs and predicted models. #rnatools hashtag#rna hashtag#rnastructure github.com/mmagnus/rna-to…

In ~20h Please join us for an exciting seminar by Dr Yun-Xing Wang, this Wednesday 26th November 8am Pacific. This seminar will not be recorded and is on Wednesday (not Thursday which is US thanksgiving) on zoom.

@SerdaMaciej Nie tylko w Polsce, Polacy na Harvardzie też tak maja 😅

Wszyscy naukowcy w Polsce, w piąteczek: Powietrze pachnie jak malinowa mamba, nikt nie przeklina, nikt nie mówi carramba

@sokrypton @buildmodels works for me (now) files.rcsb.org/view/6X5M.cif

Massive turnout for the BoltzGen seminar at MIT!

Please join us for our next seminar, featuring Danny IncaRNAto, PhD: “Discovery of RNA regulatory structural switches via ensemble mapping” @incaRNAtolab #rna #casprnasig #rnastructure

Dear nucleic acid enthusiasts! Our next webinar this Thursday, October 2nd, by Prof. Debswapna Bhattacharya. This seminar will not be recorded. Title: RNAbpFlow: Base pair-augmented SE(3)-flow matching for conditional RNA 3D structure generation Join us!

Join is in 24h for a talk on RNA3D structure: EvryRNA tools with a special focus on RNAdvisor: an RNA structural quality assessment tool Thursday, September 18; Eastern Daylight Time 11 am #rna #casprnasig #rnastructure

Hehe join the team 😅 writing a grant for my lab at the University of Warsaw 🧬

It’s Sunday so I’m writing a grant due tomorrow. Meanwhile in an alternative universe:

What do you prefer? 👉 every .cif/.pdb file with its own 3D thumbnail preview 📷 or the default macOS/Linux icon for all? With the latest RNA-tools fix, you can now visualize CIF files directly - each structure gets its own preview. #rnatools

What do you prefer? 👉 every .cif/.pdb file with its own 3D thumbnail preview 👉 or the default macOS/Linux icon for all? With the latest RNA-tools fix, you can now visualize CIF files directly - each structure gets its own preview. #rnatools

A great opportunity to work with one of the best. If you love #RNA and plants, this is for you!