iiinova — where your digital self keeps evolving

SEES Lab

@seeslab.bsky.social

715 followers 252 following 36 posts

Marta Sales-Pardo & Roger Guimerà. Complex systems & networks; Statiscal learning; Comput. social science; Systems biology at @universitatURV @icreacommunity

Posts Replies Media

SEES Lab @seeslab.bsky.social · 04/05/2026

To verify this, we implemented and analyzed the results of a Turing-like test, where experts were asked to distinguish between real and generated molecules

100

SEES Lab @seeslab.bsky.social · 04/05/2026

Because chemical validity is satisfied by construction, #CoCoGraph needs much fewer parameters than the state of the art and it can focus on learning subtle chemical patterns, leading to generation of molecules that are more realistic than existing models

110

SEES Lab @seeslab.bsky.social · 04/05/2026

#CoCoGraph is a collaborative constrained graph diffusion model for the generation of realistic synthetic molecules. Unlike previous generative models for molecules, we use ideas from graph theory to guarantee that all generated molecules are chemically valid

100

SEES Lab @seeslab.bsky.social · 14/07/2025

As a proof of concept, we successfully annotate three previously unidentified compounds frequently found in human samples

100

SEES Lab @seeslab.bsky.social · 14/07/2025

Our results demonstrate that SingleFrag surpasses state-of-the-art in silico fragmentation tools, providing a powerful method for annotating unknown MS/MS spectra of known compounds

100

SEES Lab @seeslab.bsky.social · 25/06/2025

Leveraging the model’s efficiency, we created a database of 8.2M synthetically generated molecules and conducted a Turing-like test with organic chemistry experts to further assess the plausibility of the generated molecules, and potential biases and limitations of #CoCoGraph

100

SEES Lab @seeslab.bsky.social · 25/06/2025

#CoCoGraph outperforms state-of-the-art approaches on standard benchmarks while requiring up to an order of magnitude fewer parameters

110

SEES Lab @seeslab.bsky.social · 02/06/2025

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

042

SEES Lab @seeslab.bsky.social · 02/06/2025

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...

010

SEES Lab @seeslab.bsky.social · 02/06/2025

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...

000

SEES Lab @seeslab.bsky.social · 30/04/2025

As a consequence of these, our approach leads to better alignment than the state of the art on synthetic and real networks

110

SEES Lab @seeslab.bsky.social · 30/04/2025

With respect to existing methods for "graph matching": 1️⃣ Our approach naturally allows for the alignment of many networks 2️⃣ All assumptions are explicit and can be adapted to specific scenarios 3️⃣ It results in a posterior over alignments, rather than a single alignment

100

SEES Lab @seeslab.bsky.social · 05/02/2025

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...

2135