Tessera
Folgen

Lorenzo Pantolini

@lorenzopantolini.bsky.social

Postdoc at Biozentrum, University of Basel. Applying AI to structural biology, specializing in pLMs and remote homology detection.

10 Posts64 Follower39 Folgt
Pedro Beltrao@pedrobeltrao.bsky.social · 3w ago

Team science preprint, exploring the capabilities and limitations of Alphafold3 across different application areas, including protein-RNA, protein-lipid, ubiquitination,TCR and antibody recognition with @ninjani.bsky.social @labvanni.bsky.social @dgfeller.bsky.social www.biorxiv.org/content/10.6...

Capabilities, specificity gaps and training-data dependence of AlphaFold3 across diverse application areas

Structure prediction models have moved from single proteins to assemblies that include diverse biomolecules and their modifications. AlphaFold3 (AF3) and related models extended structural modelling v...

biorxiv.org

Janani Durairaj (Jay)@ninjani.bsky.social · 2mo ago

Search with TEA 🍵 Against Many! → On the web: pickybinders.org/tea/steam → Locally: github.com/PickyBinders... Feedback welcome!

STEAM - Search with TEA against Many

Generated by create next app

pickybinders.org

Lorenzo Pantolini@lorenzopantolini.bsky.social · 8mo ago

Fresh from bioRxiv our latest work introducing The Embedded Alphabet (TEA), a powerful new representation for protein sequences obtained by discretising ESM2 embeddings into 20 characters. Pre-print: www.biorxiv.org/content/10.1... 🧵👇(1/n)

Peter Škrinjar@peterskrinjar.bsky.social · 3mo ago

Now published in NSMB! Paper: doi.org/10.1038/s415... Full PDF: rdcu.be/fhBtI Overview of additions since the preprint👇 (1/5)

Evaluating generalization in protein–ligand cofolding methods - Nature Structural & Molecular Biology

This work introduces the Runs N’ Poses dataset for benchmarking deep learning methods on the protein–ligand complex prediction task. It shows that current methods rely on memorization, challenging the...

doi.org

Peter Škrinjar@peterskrinjar.bsky.social · last yr.

Excited to share our latest preprint evaluating AlphaFold3, Boltz-1, Chai-1 and Protenix for predicting protein-ligand interactions, featuring our newly introduced benchmark dataset 🌹Runs N’ Poses🌹! www.biorxiv.org/content/10.1... 🧵👇 (1/n)

Janani Durairaj (Jay)@ninjani.bsky.social · 4mo ago

@lorenzopantolini.bsky.social and I are headed to @iclr-conf.bsky.social at Rio soon, with talks about this work at @gembioworkshop.bsky.social and LMRL workshops. Reach out to chat about representation learning for de novo protein design! 🫖

Janani Durairaj (Jay)@ninjani.bsky.social · 6mo ago

A fun little idea that worked surprisingly well, using a structure-informed yet structure-independent alphabet for de novo protein design: www.biorxiv.org/content/10.6... 🧵(1/n)

Torsten Schwede@torstenschwede.bsky.social · 5mo ago

Is #AI hitting a plateau in structure prediction? Help us find out at CASP17! 🧪🧬 Calling for Targets: Immune Complexes, protein - ligand complexes, RNA/DNA, conformational ensembles, membrane proteins, viral origins, and large complexes. The Rule of Thumb: If AF3 can’t model it, we want it.

The Critical Assessment of Structure Prediction (CASP) experiment is calling for prediction targets: Immune Complexes, Organic Ligand-Protein Complexes, Nucleic Acids and Complexes, Conformational Ensembles, Difficult Protein Structures and Complexes. Rule of Thumb: If AlphaFold3 can generate a high-quality model, it is likely not a CASP-grade challenge. If it struggles, we want it.
Lorenzo Pantolini@lorenzopantolini.bsky.social · 6mo ago

Remote homology and protein design: two sides of the same coin. Instead of finding remote homologs, we used TEA to design completely de novo proteins, folding into desired TEA sequences. I always love working with Jay, and “speed-running” this proof of concept was no exception.

Janani Durairaj (Jay)@ninjani.bsky.social · 6mo ago

A fun little idea that worked surprisingly well, using a structure-informed yet structure-independent alphabet for de novo protein design: www.biorxiv.org/content/10.6... 🧵(1/n)

Lorenzo Pantolini@lorenzopantolini.bsky.social · 8mo ago

Fresh from bioRxiv our latest work introducing The Embedded Alphabet (TEA), a powerful new representation for protein sequences obtained by discretising ESM2 embeddings into 20 characters. Pre-print: www.biorxiv.org/content/10.1... 🧵👇(1/n)

Rewriting protein alphabets with language models

Detecting remote homology with speed and sensitivity is crucial for tasks like function annotation and structure prediction. We introduce a novel approach using contrastive learning to convert protein...

biorxiv.org