@fengel97 Profile picture

Felipe Engelberger

@fengel97

PhD Student at @MeilerLab @UniLeipzig | Member of the PB³ Lab @pb3_lab | Biochem @Uchile | Founder @DataRoot_CL

Similar User
Theoretical & Computational Biophysics Department photo

@CompBioPhys

Giulia Palermo photo

@palermo_lab

Alex MacKerell photo

@alex_mackerell

PB³ Lab photo

@pb3lab

Stephane Redon photo

@StephaneRedon

matthieu Chavent photo

@Matth_Chavent

Alexandre Bonvin - also on Bluesky photo

@amjjbonvin

Ramirez Lab photo

@theramirezlab

Gabriel Rocklin photo

@grocklin

Son Tung Ngo photo

@sontungngo84

Cesar Ramirez-Sarmiento @cesarramirez.bsky.social photo

@cxarramirez

Lukas Stelzl photo

@l_stelzl

Simon Duerr photo

@simonduerr

Rafael A. Pulido Del Pino photo

@RafaelAPDP

Dheeraj Prakaash photo

@DJ_Biophys

Pinned

I am thrilled to share my first article as a first author. Last semester while working as a T.A we implemented a set of 12 tutorials related to different bioinformatics topics within Jupyter Notebooks running on Google Colab. pubs.acs.org/doi/10.1021/ac… (1/4)


Felipe Engelberger Reposted

Thrilled to have shared my personal and scientific journey on the Baker Lab podcast! I hope it serves as an inspiration for aspiring scientists in Latin America.

NEW EPISODE 🎧 Susana Vazquez Torres crossed continents to become a scientist. In our lab, she's used AI to create new antitoxins for snakebites. Apple: podcasts.apple.com/us/podcast/the… Spotify: open.spotify.com/episode/580T5E…



Felipe Engelberger Reposted

Started teaching again! This time decided to try use #claude (@AnthropicAI) and @codesandbox for hosting to implement an interactive GREMLIN (Potts) model (w = coevolution, b = conservation) to show students how you go from MSA to contacts! 9kssnq.csb.app


Felipe Engelberger Reposted

The Google Colab version of RFdiffusion with the conditional fold generation option worked well! We successfully placed two helices in the beta barrel structure. The RMSD between prediction and X-ray is only 0.3 Å! colab.research.google.com/github/sokrypt… colab.research.google.com/github/sokrypt…

Tweet Image 1


Felipe Engelberger Reposted

7/ In particular, we showcase gLM2's ability to directly learn coevolutionary signal in protein-protein interfaces with no supervision! The learned contact maps can be extracted using @ZhidianZ et al's categorial Jacobian method.

Tweet Image 1

Felipe Engelberger Reposted

4/ Metagenomes feature significant bias and redundancies, but deduplicating large genomic databases can be computationally expensive. We implement *genomic SemDeDup*, an embedding-based deduplication for genomic sequences, resulting in tunable balancing and pruning of the corpus

Tweet Image 1

Felipe Engelberger Reposted

NEWS | Epic announcement coming tomorrow, thanks to @RosettaCommons @MeilerLab 🎉 Stay tuned!


Felipe Engelberger Reposted

Amazing time at the @ImperialX_AI open day - super cool facilities and great content😆. Excited to receive a poster prize at the end! Electronic aspects inspired from @bradyajohnston who gave great advice to make sure the iPad stayed stuck! Animation code taken from @sokrypton 😎

Tweet Image 1

Felipe Engelberger Reposted

We recently created some new tools in Rosetta around ML protein design methods (including ProteinMPNN, ESM2, MIF-ST). You can run all of this using `docker run -it rosettacommons/rosetta:ml` (no python involved). We then benchmarked the different methods: biorxiv.org/content/10.110…


Felipe Engelberger Reposted

Had a great time at the ML for Drug Discovery Summer School & MoML conference in Montréal (my first time in🇨🇦!) Kudos to the organizers for arranging such a great lineup of talks & labs! thanks to the hackathon, got some hands on experience with some concepts taught👨🏼‍💻

Tweet Image 1
Tweet Image 2
Tweet Image 3
Tweet Image 4

Yesterday, I had the chance to present my first spotlight poster at #MoML2024 at @Mila_Quebec AI Institute! I presented joint work done with @luisa_kaermer and our amazing advisors, @JWestermayr and @MeilerLab Huge thanks to @Esporascicomm for the amazing graphic design work!

Tweet Image 1

A 2D version of “AlphaFold pseudo Multi Dimensional Scaling” skills

New paper: How can you tell if a transformer has the right world model? We trained a transformer to predict directions for NYC taxi rides. The model was good. It could find shortest paths between new points But had it built a map of NYC? We reconstructed its map and found this:

Tweet Image 1


Amazing first week of #MoML2024 🇨🇦

Tweet Image 1
Tweet Image 2
Tweet Image 3
Tweet Image 4

Felipe Engelberger Reposted

My last paper from grad school is officially out and in the cover of Biochemistry 🥲 We used HDX-MS and accelerated MD to figure out why a short intrinsically disordered linker affected the protease activity of murine uPA. Big shout out to my co-authors @fengel97 @cxarramirez !!

New issue! 📢 Discover nucleosome substrates, ligand sensing, nitrone formation, allosteric networks, and much more! ➡ go.acs.org/9Et Cover art: Torres-Paris et al. investigate how the linker region of muPA affects protease activity 🐁 ➡ go.acs.org/9Es

Tweet Image 1


Felipe Engelberger Reposted

Honest question. Do we mean dynamics as in time-dependence, or as in conformational flexibility and variability ? Both are important, but in a sense, different things.


Felipe Engelberger Reposted

sad but obvious realization, in the context of the recent gzip ~ llm scaling laws paper. LZ compression algorithms are optimal in the same way memorization is learning—only true with infinite data.


Felipe Engelberger Reposted

Information geometry and optimal transport are cool in theory, but flow matching in the Fisher-Rao metric is even cooler in practice ! It was great to be part of this awesome team, thanks for having me!

Wonder how to generate discrete data with Riemannian Flow Matching? Well, here is our most recent work addressing this issue: Fisher Flow Matching 😎 ➡️ Available here: arxiv.org/abs/2405.14664 🔥 Let me break it down 🧵 (1/10) @bose_joey @mmbronstein @ismaililkanc @MirceaSci

Tweet Image 2


Felipe Engelberger Reposted

Our @NatRevPhys perspective article on neural operators and their ability to accelerate simulations and design is now out. rdcu.be/dD8BI @Nature 1. Neural operators learn mappings between functions, e.g. spatiotemporal processes and partial differential equations.…

Tweet Image 1

Felipe Engelberger Reposted

If you are (or you know) a young researcher interested in doing a post-doc in Chile, mixing probability+graphs+deep learning, please contact me! Please spread this for visibility! (adding some images taken in the last 3 months for motivation)

Tweet Image 1
Tweet Image 2
Tweet Image 3
Tweet Image 4

Felipe Engelberger Reposted

A new version of the Hitchhiker’s Guide is up, including general improvements: - a blurb on frame-based invariant GNNs (like AF2’s IPA) - new citations for unconstrained GNNs - clarifications on the universality of GemNet - and this hand-drawn figure PDF: arxiv.org/abs/2312.07511

Tweet Image 1

Felipe Engelberger Reposted

Stoked that our @pb3lab @iibm_uc @ibiochile is among the recipients of one of the Garden Grants from @HomeworldBio 🎉

Homeworld Collective is thrilled to announce the results of our inaugural Garden Grants Program. TLDR; $1.3M to 16 awesome teams to take their best shots at “big, if true” ideas for climate biotech. homeworld.bio/blog/announcin… 🧵



Loading...

Something went wrong.


Something went wrong.