102 organic chemists shown real vs AI-generated molecules. Couldn't tell them apart — 62% accuracy ≈ random. That's CoCoGraph: graph diffusion with 100% chemical validity, 534K params vs 4.6M for comparable models. Constraints in the math, not the model. www.nature.com/articles/s42...

A new AI tool can generate millions of chemically valid molecules, offering a faster and more efficient approach to exploring potential compounds for drug development and materials science. doi.org/hb2mwd

A collaborative constrained graph diffusion model for the generation of realistic synthetic molecules [new] ...that ensures generated novel molecules are valid and highly realistic.

Can we design generative #AI models capable of creating new molecules, much in the same way that other generative models generate text or images? In a new paper in @natmachintell.nature.com, we introduce #CoCoGraph, which does just that Online: dx.doi.org/10.1038/s422... PDF: rdcu.be/fgNIA

Can we design generative #AI models capable of creating new molecules, much in the same way that other generative models generate text or images? In a new paper in @natmachintell.nature.com, we introduce #CoCoGraph, which does just that Online: dx.doi.org/10.1038/s422... PDF: rdcu.be/fgNIA

ChemEmbed: a deep learning framework for metabolite identification using enhanced MS/MS data and multidimensional molecular embeddings url: academic.oup.com/bib/article/...

🚀A ICREA tornem a estar actius a les xarxes socials! Parlarem de: ✨ Nous descobriments de la #ComunitatICREA 📢 Convocatòries 🎉 Esdeveniments i congressos 🧪 I molta recerca d'excel·lència! Segueix-nos a X x.com/icreacommunity i LinkedIn www.linkedin.com/company/icrea i no et perdis cap novetat!

🧵 1/ New from @reeserichardson.bsky.social, @jabyrnesci.bsky.social, and our lab in @pnas.org : A growing body of evidence shows that "systematic" scientific fraud is an emerging threat to the integrity of science. Our latest study investigates how this fraud is organized and sustained.

New paper out in Briefings in Bioinformatics 📰SingleFrag: a deep learning tool for MS/MS fragment and spectral prediction and metabolite annotation academic.oup.com/bib/article/...

New paper out in Briefings in Bioinformatics 📰SingleFrag: a deep learning tool for MS/MS fragment and spectral prediction and metabolite annotation academic.oup.com/bib/article/...

SingleFrag: a deep learning tool for MS/MS fragment and spectral prediction and metabolite annotation #BriedBioinform academic.oup.com/bib/article/...

Thanks 🙏🙏 @martikagv.bsky.social @vcolizza.bsky.social @pessoabrain.bsky.social @asteixeira.bsky.social @gomezgardenes.bsky.social @seeslab.bsky.social (and all the speakers not in this platform) for their amazing contribution to make this edition a reference for young Network Scientists.

@mscxnetworks.bsky.social ended. A week of cutting edge complexity science, from foundations to applications. Amazing speakers and great cohort of attendants. One of the best editions ever. 10 years of passion, love and network science. In an amazing piece of #Sicily youtu.be/Nh5vrEKheH0?...

Manuel Ruiz-Botella, Marta Sales-Pardo, Roger Guimer\`a: A collaborative constrained graph diffusion model for the generation of realistic synthetic molecules https://arxiv.org/abs/2505.16365 https://arxiv.org/pdf/2505.16365 https://arxiv.org/html/2505.16365

New preprint out in the arXiv! We introduce #CoCoGraph, a collaborative and constrained graph diffusion model capable of generating molecules that are guaranteed to be chemically valid www.arxiv.org/abs/2505.16365

💡Our paper on probabilistic alignment of networks has been highlighted by Nature Communications as one the 50 best papers recently published in the area of Applied physics and mathematics www.nature.com/collections/... 📰Read the paper www.nature.com/articles/s41...

At #NetSci2025 @netsciconf.bsky.social today? Don't miss Gemma Bel's poster at the Network Neuroscience satellite 📰Model-based alignment of developing connectomes 📍FaSos GG76S 1.018 🕔5:30pm

At #NetSci2025? Don't miss Teresa Lazaros's talk today at the Network Neuroscience satellite 📰 Probabilistic network alignment applied to brain connectomes 📍 FaSos GG76S 1.018 🕔 5pm 🔗 to paper: dx.doi.org/10.1038/s414...

At #NetSci2025 today? Don't miss Manuel Ruiz-Botella's talk at the @netbiomed2025.bsky.social‬ satellite 📰 CoCoGraph: A collaborative constrained graph diffusion model for the generation of realistic synthetic molecules 📍 FaSos FaSoS GG76 1.02 🕒 3:30pm 🔗 to paper: doi.org/10.48550/arX...

#Networks www.nature.com/articles/s41...

‘Data manipulations’ alleged in study that paved the way for Microsoft’s quantum chip | Science | AAAS www.science.org/content/arti...

So happy to share this one! Beautiful collaboration with @anduviera.bsky.social, @raissadsouza.bsky.social and Guram Mikaberidze on network flows: journals.aps.org/prx/abstract...

We're looking for a new colleague to join us in Maastricht as an Assistant/Associate Professor in statistical learning in our Data Analytics and Digitalisation department. Deadline to apply: June 8th vacancies.maastrichtuniversity.nl/job/Maastric...

New substack post: I discuss a recent innovative method—ProbAlign, introduced by Lázaro, Guimerà, & Marta Sales-Pardo—which uses probabilistic modeling to achieve more accurate, transparent, and flexible network alignments. open.substack.com/pub/bravoaba...

Probabilistic alignment of multiple networks ->Nature | More info from EcoSearch

This is such a cool paper! Everyone interested in aligning (multiple, possibly unlabelled) graphs, give it a read!

📰New paper out in @natcomms.nature.com! We have developed a probabilistic approach that allows for the accurate alignment of multiple networks www.nature.com/articles/s41... Great work by Teresa Lázaro on her first article (of many to come)! Some highlights 👇🏽🧵

Probabilistic alignment of multiple networks www.nature.com/articles/s41...

Nat. Commun.: Probabilistic alignment of multiple networks https://www.nature.com/articles/s41467-025-59077-7

Children's cognitive abilities and social preferences separate in the later school years, indicating that older students likely use differentiated social strategies for academic and recreational interactions. @ecorreig.bsky.social www.nature.com/articles/s44...

New work in @naturecomms.bsky.social 🚀! Instead of black-box deep learning with 100's of parameters, what if we use large-scale data to discover simple, interpretable models that accurately describe human mobility? It works: Accuracy + insights for urban planning & beyond!

Our recent article on machine learning mathematical models for incidence estimation during pandemics, featured in today's edition of @manlius.bsky.social's Complexity Thoughts!

5/ Want to learn more? 📄 Read our full paper on #bioRxiv: www.biorxiv.org/content/10.1... #Metabolomics #MachineLearning #DeepLearning #MSMS We’d love to hear your thoughts! This is another successful collaboration with @seeslab.bsky.social at @urv.cat

4/ The results: ✅ ChemEmbed ranks the correct metabolite #1 in 42% of cases in a test dataset. ✅ Finds the correct compound in the top 5 in 76% of cases ✅ Against external benchmarks CASMI 2016 and 2022, and ARUS dataset (unidentified spectra from human plasma & urine), ChemEmbed outperforms #SIRIUS

3/ We enhance MS/MS data by: ✅ Merging spectra from multiple collision energies ✅ Incorporating calculated neutral losses ✅ Training a CNN on a dataset of 38,472 unique compounds from NIST20, MSDIAL, GNPS, and Agilent METLIN metabolomic libraries

2/ Our solution to reduce this problem: #ChemEmbed We combine enhanced MS/MS spectra with continuous vector representations of molecular structures (300-dimensional embeddings aligned with Mol2vec representations). This gives our CNN-based model richer input, improving annotation accuracy.

1/ The problem: #Metabolomics relies on MS/MS spectral databases, but most spectra remain unidentified due to limited reference libraries. Computational methods help, but they struggle with high-dimensional and sparse spectral and structural data.

🚀 New paper alert! 🚀 Happy to introduce #ChemEmbed, a deep learning framework for metabolite identification that enhances MS/MS data and leverages multidimensional molecular embeddings. A 🧵 on how it works and why it matters! ⬇️ #metabolomics #MachineLearning #DeepLearning

Can simple closed-form mathematical models predict human mobility as well as deep learning? In a new paper in @naturecomms.bsky.social we show that the answer is YES Human mobility is well described by closed-form gravity-like models learned automatically from data www.nature.com/articles/s41...

Deadline is approaching, still some seats available 🏃🏃🏃

During a pandemic such as COVID19, we hope (but fail) to accurately estimate the incidence of the disease. In this paper, we propose a new approach to machine-learn models of the real incidence from readily available information (tests and detected cases) dx.doi.org/10.1371/jour...

📣 New paper in Nature Human Behavior @natureportfolio.bsky.social! Using large-scale mobility data, we find how businesses, amenities, and other urban places depend on each other. It reveals connections that aren’t always visible but have substantial economic impacts. www.nature.com/articles/s41...

The call for the very special 10th Mediterranean School of Complex Networks is out! @mscxnetworks.bsky.social This year, it will take place in Ortigia, a beautiful small island in Syracuse, Italy. The lineup of lecturers is outstanding! All info in the website: mediterraneanschoolcomplex.net

🚨Job alert!🚨 Come join us at the Inverse Complexity Lab @invcomplexity.skewed.de We’re hiring a post-doctoral researcher to join our group at IT:U, Linz, Austria. skewed.de/lab/call.html Deadline is 30 Nov 2024. (Next Saturday!) Spread the word. #networkscience #complexsystems

@chpoletto.bsky.social @manlius.bsky.social @vcolizza.bsky.social @netscience.bsky.social @seeslab.bsky.social @bansallab.bsky.social @giuliapullano.bsky.social @giuliacencetti.bsky.social @tiago.skewed.de

A starter pack for researchers interested in #ComplexSystems. Complex system science investigates how interactions among multiple parts lead to collective behaviour, as well as how the system interacts and forms links with its environment - please add your name! go.bsky.app/FNYZ61y

The Mediterranean School of Complex Networks is now on @bsky.app too! It's one of the oldest (if not the oldest?) school on #NetworkScience and this year we will celebrate its 10th edition! Follow it, since important announcements will follow in the next days: @mscxnetworks.bsky.social

Great move! Foursquare just open-sourced their 100M+ place point of interest dataset. location.foursquare.com/resources/bl...