Fabrizio Pucci (@fabpucci) 's Twitter Profile
Fabrizio Pucci

@fabpucci

Assistant Professor, Computational Biophysics, Université Libre de Bruxelles, 3biocompbio.github.io/3BIO-BioInfo

ID: 1373850761730387969

calendar_today22-03-2021 04:16:40

61 Tweet

151 Takipçi

419 Takip Edilen

Fabrizio Pucci (@fabpucci) 's Twitter Profile Photo

#pycofitness, our new tool for the fitness prediction of #protein and #RNA #variants using DCA, is out in @OUPBioinfo academic.oup.com/bioinformatics… Easy to use and install via #pip, have a look to github.com/KIT-MBS/pycofi… Marianne Rooman (IB)^2 @PolytechBXL Université libre de Bruxelles

Fabrizio Pucci (@fabpucci) 's Twitter Profile Photo

Our FiTMuSiC method for #variant #fitness prediction is out on Genetics at BMC. We were among the top performing groups in the #CAGI6 HMBS challenge. Webserver at babylone.ulb.ac.be/FiTMuSiC humgenomics.biomedcentral.com/articles/10.11…

Horacio V. Guzman (@whoratz) 's Twitter Profile Photo

Off to q@fz_juelich, for the NIC days on biomolecular evolution, assembly and function, just learned about integrating (co)evolution and structural data of proteins with Music & my colab Fabrizio Pucci

Off to q@fz_juelich, for the NIC days on biomolecular evolution, assembly and function, just learned about integrating (co)evolution and structural data of proteins with Music &amp; my colab <a href="/FabPucci/">Fabrizio Pucci</a>
Fabrizio Pucci (@fabpucci) 's Twitter Profile Photo

In Athens for the #ISQBP2024 meeting… Leveraging #structural and #coevolutionary information in #protein #stability prediction

In Athens for the #ISQBP2024 meeting… Leveraging #structural and #coevolutionary information in #protein #stability prediction
Fabrizio Pucci (@fabpucci) 's Twitter Profile Photo

Here our new preprint in which we used simple #evolutionary #models to study the impact of mutations on #protein #stability biorxiv.org/content/10.110… Marianne Rooman Matsvei Tsishyn (IB)^2 @PolytechBXL

Fabrizio Pucci (@fabpucci) 's Twitter Profile Photo

PhD position available here in Bruxelles to work with us Maxime Tarabichi Marianne Rooman on #AI4Cancer, Leveraging AI to study #Cancer #Evolution. More details here euraxess.ec.europa.eu/jobs/254491

Biology+AI Daily (@biologyaidaily) 's Twitter Profile Photo

Exploring Evolution to Uncover Insights into Protein Mutational Stability • This paper explores how evolutionary data can enhance predictions of protein stability changes upon mutations. By analyzing a large mutational stability dataset, the authors tested various evolutionary

Exploring Evolution to Uncover Insights into Protein Mutational Stability

• This paper explores how evolutionary data can enhance predictions of protein stability changes upon mutations. By analyzing a large mutational stability dataset, the authors tested various evolutionary
Roland Dunbrack 🏳️‍🌈 @rolanddunbrack.bsky.social (@rolanddunbrack) 's Twitter Profile Photo

Everything old is new again. This preprint explores it well. This was the model 10-20 years ago - sequence conservation and solvent accessibility predicts mutational stability decently well. We did this 12 years ago for biological assemblies. researchgate.net/profile/Roland…

Fabrizio Pucci (@fabpucci) 's Twitter Profile Photo

How to predict the impact of mutations on protein solubility and design more soluble proteins? Check out our computational tool SOuLMuSiC. Preprint available at biorxiv.org/content/10.110… Freely available at babylone.3bio.ulb.ac.be/SOuLMuSiC/ Simone Attanasio Marianne Rooman (IB)^2

Fabrizio Pucci (@fabpucci) 's Twitter Profile Photo

Are residue conservation and solvent accessibility all you need for predicting the impact of mutations on proteins? Have a look to our manuscript biorxiv.org/content/10.110… Marianne Rooman Matsvei Tsishyn (IB)^2 Université libre de Bruxelles EPBruxelles

Pascal Notin (@notinpascal) 's Twitter Profile Photo

Have we hit a "scaling wall" for protein language models? 🤔 Our latest ProteinGym v1.3 release suggests that for zero-shot fitness prediction, simply making pLMs bigger isn't better beyond 1-4B parameters. The winning strategy? Combining MSAs & structure in multimodal models!

Pascal Notin (@notinpascal) 's Twitter Profile Photo

Even simple methods leveraging these 2 modalities significantly outperform billion-parameter sequence-only models. So, what's next? Better retrieval, advanced multimodal approaches, & alignment. Read more: pascalnotin.substack.com/p/have-we-hit-… #BioTech #AI #pLMs

Michael Desai (@michaelmdesai) 's Twitter Profile Photo

Just got news that all of my NIH and NSF grants were officially terminated today. Have been expecting this for some time, so it's not surprising, but still jarring to see the news. Have heard similar news from dozens of colleagues. Will be hard, but we'll find a way forward.

Rouskin Lab (@rouskinlab) 's Twitter Profile Photo

At 15, I left all my family and friends and came to the US , ALONE, seeking a country where MERIT and HARD WORK mattered-not politics. For 30 years, I worked tirelessly, even doing reseach at MIT the day my mother died, knowing she’d want me to keep pushing forward. Today, my

At 15, I left all my family and friends and came to the US , ALONE, seeking a country where MERIT and HARD WORK mattered-not politics. For 30 years, I worked tirelessly, even doing reseach at MIT the day my mother died, knowing she’d want me to keep pushing forward. Today, my