Sign in

Michele Invernizzi

@invemichele.bsky.social
423 followers 203 following 11 posts

Computational physicist at peptone.io PhD @GroupParrinello, PostDoc @franknoe.bsky.social Disordered Proteins, AI for Science, Molecular Dynamics, Enhanced Sampling 🔗 scholar.google.com/citations?user=f…

PostsRepliesMedia
Michele Invernizzi @invemichele.bsky.social · 21/01/2026
Sampling IDPs is tough, but can be worth the effort! OPES multithermal made it a little easier for us, hopefully you'll find it useful as well
093
Reposted by Michele Invernizzi
Kresten Lindorff-Larsen @lindorfflarsen.bsky.social · 21/01/2026
Third preprint of the year is from @julianstreit.bsky.social who, with our collaborators at Peptone, show that multithermal On-the-fly Probability Enhanced Sampling (OPES) enables efficient generation of atomistic ensembles for disordered peptides and proteins 🍝 www.biorxiv.org/content/10.6...
Figure 1 from the paper: Sampling disordered peptides and proteins with OPES multithermal simulations. a. Representative multithermal molecular dynamics simulation showing fluctuations in potential energy (left) as the system explores a broad temperature range (colour scale). The right panel shows the relative effective sample size, N_eff, sampled across temperatures, demonstrating relatively uniform ensemble coverage. The black horizontal line represents the expected sample size in an equivalent temperature replica exchange setup (1 / M, where M is the number of temperatures). B. Structures of the most helical conformations sampled during multithermal simulations for four systems of increasing complexity: the helical control peptide (AAQAA)3, the ACTR20-60 fragment, full-length ACTR, and HTTex1 with 16 glutamine repeats (16Q). c. Free-energy landscapes plotted as a function of helicity (see Methods) and radius of gyration for the ACTR20-60 fragment, full-length ACTR and HTTex1 16Q at 300 K.
1265
Reposted by Michele Invernizzi
Kresten Lindorff-Larsen @lindorfflarsen.bsky.social · 20/10/2025
We (@sobuelow.bsky.social) developed AF-CALVADOS to integrate AlphaFold and CALVADOS to simulate flexible multidomain proteins at scale See preprint for: — Ensembles of >12000 full-length human proteins — Analysis of IDRs in >1500 TFs 📜 doi.org/10.1101/2025... 💾 github.com/KULL-Centre/...
Figure showing the AF-CALVADOS restraining and simulation protocol based on AF2 structure, PAE and pLDDT
19439
Michele Invernizzi @invemichele.bsky.social · 09/05/2025
We have a job opening at Peptone.io for an ML researcher. Come help us find new ways to understand and drug intrinsically disordered proteins (IDPs), it's a very interesting and important problem! Link in the reply ↓
Overlayed configurations of a small molecule binding (?) to an unstructured protein
1177
Michele Invernizzi @invemichele.bsky.social · 06/05/2025
Very interesting and powerful method! www.nature.com/articles/s43...
nature.com
Everything everywhere all at once: a probability-based enhanced sampling approach to rare events - Nature Computational Science
A single semi-automatic enhanced sampling method for rare events, based on machine-learned committor functions, allows simultaneous sampling of reactive events, calculation of free energy and understa...
030
Reposted by Michele Invernizzi
Andrew White 🐦‍⬛ @andrew.diffuse.one · 01/05/2025
The plan at FutureHouse has been to build scientific agents for discoveries. We’ve spent the last year researching the best way to make agents. We’ve made a ton of progress and now we’ve engineered them to be used at scale, by anyone. Free and on API.
1133
Reposted by Michele Invernizzi
Paul Robustelli @paulrobustelli.bsky.social · 30/04/2025
Presenting one of my favorite manuscripts I've ever worked on: "Characterizing structural and kinetic ensembles of intrinsically disordered proteins using writhe" www.biorxiv.org/content/10.1... by Tommy Sisk, with a generative modeling component done in collaboration with @smnlssn.bsky.social
24010
Reposted by Michele Invernizzi
Diego del Alamo @delalamo.xyz · 27/04/2025
"De novo prediction of protein structural dynamics" I'll be presenting an overview of the field tomorrow at a workshop. Link to a PDF copy of the presentation: delalamo.xyz/assets/post_...
delalamo.xyz
56917
Reposted by Michele Invernizzi
Magnus Petersen @omorfiamorphism.bsky.social · 27/04/2025
Presenting our work on minimum energy path generation between two states for physical systems at the FPI Workshop at @ICLR tomorrow! Scaling up to solvated BPTI and observing the same conformational changes as long reference MD with six orders fewer force field evals! Drop by!
1102
Reposted by Michele Invernizzi
Riccardo Capelli @riccardocapelli.bsky.social · 23/04/2025
New preprint on arXiv! We propose a new technique to compute kinetic rates using multiple independent non-equilibrium (ratchet&pawl MD) simulations! We focused here on ligand unbinding kinetics, but this method can be applied to any situation where a reaction coordinate can be defined!
arxiv.org
Kinetic rates calculation via non-equilibrium dynamics
This study introduces a novel computational approach based on ratchet-and-pawl molecular dynamics (rMD) for accurately estimating ligand dissociation kinetics in protein-ligand complexes. By integrati...
241
Reposted by Michele Invernizzi
Kresten Lindorff-Larsen @lindorfflarsen.bsky.social · 17/04/2025
AlphaFold is amazing but gives you static structures 🧊 In a fantastic teamwork, @mcagiada.bsky.social and @emilthomasen.bsky.social developed AF2χ to generate conformational ensembles representing side-chain dynamics using AF2 💃 Code: github.com/KULL-Centre/... Colab: github.com/matteo-cagia...
320663
Reposted by Michele Invernizzi
Alexis Verger 🧬🧫🧪 @alexis-verger.cpesr.fr · 07/04/2025
BoltzDesign1: Inverting All-Atom Structure Prediction Model for Generalized Biomolecular Binder Design by @yehlincho.bsky.social @martinpacesa.bsky.social @sokrypton.org 🧶🧬 www.biorxiv.org/content/10.1...
15216
Reposted by Michele Invernizzi
Gräter lab @graeterlab.bsky.social · 31/03/2025
Wondering how to predict protein flexibility in a sec? No time to run MD simulations but want to go beyond pLDDT? Check out BBFlow arxiv.org/html/2503.05... Useful in particular for de novo designs. Led by Nico Wolf & Leif Seute, w Seva, Simon, and Jan. @mpip-mainz.mpg.de @hitsters.bsky.social
0399
Reposted by Michele Invernizzi
Gabriel Rocklin @grocklin.bsky.social · 26/03/2025
Small proteins can be more complex than they look! We know proteins fluctuate between different conformations- but by how much? How does it vary from protein to protein? Can highly stable domains have low stability segments? @ajrferrari.bsky.social experimentally tested >5,000 domains to find out!
48736
Reposted by Michele Invernizzi
Gina El Nesr @ginaelnesr.bsky.social · 20/03/2025
Protein function often depends on protein dynamics. To design proteins that function like natural ones, how do we predict their dynamics? @hkws.bsky.social and I are thrilled to share the first big, experimental datasets on protein dynamics and our new model: Dyna-1! 🧵
610538
Reposted by Michele Invernizzi
Kresten Lindorff-Larsen @lindorfflarsen.bsky.social · 19/03/2025
Straight to the reading list: Training a machine learning model based on residues with missing NMR assignments as a proxy for protein motion
1244
Reposted by Michele Invernizzi
GiovanniMaria Piccini @giovannimpiccini.bsky.social · 13/03/2025
Very excited for my first BSKY post. We present a new method, Loxodynamics, for exploring chemical and catalytic reaction space!
094
Reposted by Michele Invernizzi
Kresten Lindorff-Larsen @lindorfflarsen.bsky.social · 12/03/2025
Our review on machine learning methods to study sequence–ensemble–function relationships in disordered proteins is now out in COSB authors.elsevier.com/sd/article/S... Led by @sobuelow.bsky.social and Giulio Tesei
Figure from the paper illustrating sequence–ensemble–function relationships for disordered proteins. ML prediction (black) and design (orange) approaches are highlighted on the connecting arrows. Prediction of properties/functions from sequence (or vice versa, design) can include biophysics approaches via structural ensembles, or bioinformatics approaches via other hetero- geneous sources. The lower panels show examples of properties and functions of IDRs for predictions or design targets. ML, machine learning; IDRs, intrinsically disordered proteins and regions.
09027
Reposted by Michele Invernizzi
PLUMED @plumed.org · 04/03/2025
The paper describing our community effort to collect and organize #plumed tutorials has been published in the Journal of Chemical Physics, as part of the Michele Parrinello Festschrift! doi.org/10.1063/5.02...
doi.org
PLUMED Tutorials: A collaborative, community-driven learning ecosystem
In computational physics, chemistry, and biology, the implementation of new techniques in shared and open-source software lowers barriers to entry and promotes
03010
Reposted by Michele Invernizzi
John Chodera @jchodera.bsky.social · 19/02/2025
As a peek toward where we're headed: Right now, CADD scientists are forced to use the same model week after week, even if new experimental data says the model is inaccurate. If we can fine- models, we can exploit that data to systematically improve our predictions week by week!
Illustration showing how in 2025, CADD scientists are forced to use the same published force field model week after week in a manner than cannot learn from new experimental data that contradicts it.

In the future (2027?), CADD scientists will be able to make good general predictions with a foundation simulation model, but will be able to fine-tune that model after every new batch of data to deliver systematically more accurate predictions week after week.
031
Reposted by Michele Invernizzi
Frank Noe @franknoe.bsky.social · 19/02/2025
The BioEmu-1 model and inference code are now public under MIT license!!! Please go ahead, play with it and let us know if there are issues. github.com/microsoft/bi...
github.com
GitHub - microsoft/bioemu: Inference code for scalable emulation of protein equilibrium ensembles with generative deep learning
Inference code for scalable emulation of protein equilibrium ensembles with generative deep learning - microsoft/bioemu
210339
Reposted by Michele Invernizzi
Grant Rotskoff @grant.rotskoff.cc · 23/12/2024
I am hiring a postdoctoral scholar with a start date summer or fall 2025. Projects will be focused on thermodynamically consistent generative models, broadly defined. If you’re interested, please send a CV and one paragraph about why you think you’d be a good fit to rotskoff@stanford.edu
04721
Reposted by Michele Invernizzi
Kresten Lindorff-Larsen @lindorfflarsen.bsky.social · 21/12/2024
It’s been 20 years today since my first paper on intrinsically disordered proteins Mapping Long-Range Interactions in α-Synuclein using Spin-Label NMR and Ensemble Molecular Dynamics Simulations doi.org/10.1021/ja04... and I thought I would tell the somewhat random path that led to this paper. 1/n
doi.org
Mapping Long-Range Interactions in α-Synuclein using Spin-Label NMR and Ensemble Molecular Dynamics Simulations
The intrinsically disordered protein α-synuclein plays a key role in the pathogenesis of Parkinson's disease (PD). We show here that the native state of α-synuclein consists of a broad distribution of...
3768
Reposted by Michele Invernizzi
Vaughn Cooper @vscooper.micropopbio.org · 12/12/2024
With today's report outlining risks on mirror life www.science.org/doi/full/10.... many have asked: Could mirror life survive in the wild? Yes. While mirror life in the wild could have some significant disadvantages (like finding food it can digest), they do not appear to be insurmountable: 🧵
science.org
Confronting risks of mirror life
Broad discussion is needed to chart a path forward.
710762
Reposted by Michele Invernizzi
Pietro Novelli @pienovelli.bsky.social · 12/12/2024
In his book “The Nature of Statistical Learning” V. Vapnik wrote: “When solving a given problem, try to avoid a more general problem as an intermediate step”
183
Michele Invernizzi @invemichele.bsky.social · 11/12/2024
See you at #NeurIPS2024, where we are presenting the latest Peptone.io paper @workshopmlsb.bsky.social www.mlsb.io/papers_2024/...
title and abstract of the paper "Improving Inverse Folding models at Protein Stability Prediction without additional Training or Data"
030
Reposted by Michele Invernizzi
Bussi Lab @bussilab.org · 06/12/2024
📢 New #preprint describing our community effort to share #plumed tutorials arxiv.org/abs/2412.03595 ! Explore the tutorials at www.plumed-tutorials.org
arxiv.org
PLUMED Tutorials: a collaborative, community-driven learning ecosystem
In computational physics, chemistry, and biology, the implementation of new techniques in a shared and open source software lowers barriers to entry and promotes rapid scientific progress. However, ef...
26024
Reposted by Michele Invernizzi
Frank Noe @franknoe.bsky.social · 06/12/2024
Now something that is extremely hard to sample with all-atom MD: a big intrinsically disordered protein (IDP) like Complexin II. Different answers depending on MD forcefield. BioEmu - not traind on IDPs - looks reasonable, agrees with experimental evidence and is super fast.
251
Reposted by Michele Invernizzi
Frank Noe @franknoe.bsky.social · 06/12/2024
Super excited to preprint our work on developing a Biomolecular Emulator (BioEmu): Scalable emulation of protein equilibrium ensembles with generative deep learning from @msftresearch.bsky.social ch AI for Science. www.biorxiv.org/content/10.1...
21441147
Reposted by Michele Invernizzi
Max Bonomi @bonomimax.bsky.social · 06/12/2024
Do you want to work at the interface of molecular simulations, structural biology experiments and #AI? Come to Paris for a PhD at @pasteur.fr 1 PhD position is available in our lab funded by ERC_Research. Please repost!! #compchem #compbio Info 👇 research.pasteur.fr/b/15Hr
research.pasteur.fr
One PhD thesis in integrative structural biology | Research - Institut Pasteur
15340
Reposted by Michele Invernizzi
Frank Noe @franknoe.bsky.social · 05/12/2024
071
Michele Invernizzi @invemichele.bsky.social · 06/12/2024
I am going to read this in detail, congratulation to @franknoe.bsky.social and the team! www.biorxiv.org/content/10.1...
biorxiv.org
150
Reposted by Michele Invernizzi
Kresten Lindorff-Larsen @lindorfflarsen.bsky.social · 20/11/2024
Your talk in Copenhagen reminded me of some work we did where we showed that if you combine a FF and long-range (coevol) contacts you can determine an accurate structure of CsgA (Tian, JACS, 2015), but that if you switch off the FF then you only get the topology right, ...
1122
Reposted by Michele Invernizzi
Erik Thiede @erikhthiede.bsky.social · 26/11/2024
Something that's come up in a few conversations and I think is underappreciated: the X-ray / cryo-EM structures you download from the PDB are average structures, but not *typical* structures: very few proteins in your sample actually look like that.
3244
Reposted by Michele Invernizzi
Bussi Lab @bussilab.org · 25/11/2024
New #openreview from our group at disq.us/p/3145xzw! @bussigio.bsky.social and Ivan Gilardoni reviewed a #preprint by @paulrobustelli.bsky.social on the determination of conformational ensembles for intrinsically disordered proteins, combining molecular dynamics simulations and experimental data
disq.us
0133