Top Tweets for #igloo
GM igloo. charts are red today and the penguins are still waddling. what got you into Pudgy in the first place, the art, the toys or the people?
GM Polly. charts are red, the igloo stays warm
fireplace in an igloo?
If you haven't caught on yet, The Huddle is the new Portal. It's becoming the central hub for everything IGLOO.
IGLOO is growing up. Abstract was an ambitious first chapter, but growing up means making tough business decisions and recognizing when something is no longer financially sustainable.
The Huddle represents the next stage of maturity: a leaner, more sustainable foundation built for long-term growth.
I wouldn't be surprised to see games, apps, and an entire ecosystem of experiences built around it.
Growing up isn't about holding on to everything you built. It's about knowing what to leave behind so you can build something bigger.
The Huddle is an ever-evolving hub connecting Pudgy Penguins fans to the NFT and $PENGU ecosystems, while creating a dedicated home that celebrates our holders.
Access holder benefits, discover events, and stay connected to what’s next.
Join here: huddle.pudgypenguins.com
Hey, i have a fat ass aunt dm
My youngest sister is most of the time nakd
I have 3 sisters
Do protein representations encode variant function? Diagnosing residue-level protein attributions via embedding-space gradients
1. The paper introduces IGLOO, a benchmarking framework to test whether residue-level attributions (via Integrated Gradients on protein language model embeddings) actually recover functionally important residues, rather than merely producing plausible-looking heatmaps.
2. IGLOO’s core idea is to create synthetic fitness landscapes where per-residue “ground-truth importance” is known, enabling direct scoring of attribution fidelity. It builds 9 protein–landscape settings using 3 proteins (GB1, T4 lysozyme, p53) × 3 landscape types (additive, epistatic, nonlinear “cliff”), and systematically sweeps label noise to decouple accuracy from interpretability.
3. A central finding: predictive accuracy (held-out Spearman correlation on fitness) weakly tracks attribution quality. Models can predict variant fitness well while producing residue attributions that are near-random relative to known important sites—an explicit demonstration of the prediction–explanation fallacy in pLM-based variant effect prediction.
4. The work diagnoses why this happens using cascading parameter randomization: in common “pool-first” architectures (attention pooling on per-residue embeddings before the MLP head), attributions barely change when randomizing most of the predictor head, but collapse when randomizing the pooling layer—showing the pooling module largely determines residue-level attribution patterns.
5. A practical architectural intervention improves attribution: moving learned computation before pooling (“pool-later” via per-residue processing + pooling) substantially strengthens the link between model learning and residue attributions. In one example (GB1 additive), the correlation between attribution quality and predictive accuracy increases dramatically (Pearson r from 0.23 to 0.83).
6. Backbone choice matters for interpretability: across seven pLMs from ESM-C, Profluent E1, and Ankh families, Ankh models yield the most consistent attribution quality across landscapes, and bigger is not always better (Ankh-base can outperform Ankh-large).
7. Intermediate layers can predict “well” but attribute poorly: for Ankh-base, attribution quality collapses when using intermediate hidden states (even when prediction Spearman can reach ~0.6), while final-layer representations give the best attribution. The paper argues this may relate to scaling/normalization properties of intermediate residual streams.
8. Ensembling improves stability of interpretability: averaging attributions across independently seeded predictor heads reduces attribution variance roughly at the expected 1/sqrt(K) rate, making residue-level interpretations more reliable without major added cost.
9. Real-protein case studies mirror synthetic conclusions. On FLIP2 α-amylase splits, the split with best predictive performance does not necessarily yield best recovery of annotated functional categories; pool-later heads outperform pool-first heads for attribution across splits. On TEM-1 β-lactamase datasets, top-attributed sites show partial agreement with known functional residues, and in silico checks (stability and binding proxies) match attribution sign in ~2/3 of tested mutant–ligand combinations.
💻Code: github.com/chemcognition-lab…
📜Paper: biorxiv.org/content/10.64898…
#ProteinEngineering #ProteinLanguageModels #Interpretability #IntegratedGradients #DeepLearning #ComputationalBiology #MachineLearning #VariantEffectPrediction

Dm me I trib
Dm me ill trib
@Igloocola give a follow back
yes dm me, you have to follow for it to send though
dm me
Go to chat private my cuck
Follow
İ cant
Most Popular Users

Elon Musk 
@elonmusk
240.3M followers

Barack Obama 
@barackobama
118.6M followers

Cristiano Ronaldo 
@cristiano
114.4M followers

Donald J. Trump 
@realdonaldtrump
111.8M followers

Narendra Modi 
@narendramodi
106.9M followers

Rihanna 
@rihanna
98.7M followers

NASA 
@nasa
92.2M followers

Justin Bieber 
@justinbieber
91.7M followers

KATY PERRY 
@katyperry
89.9M followers

Taylor Swift 
@taylorswift13
83.9M followers

Lady Gaga 
@ladygaga
75.4M followers

Virat Kohli 
@imvkohli
73.3M followers

Kim Kardashian 
@kimkardashian
70.8M followers

YouTube 
@youtube
68.6M followers

Neymar Jr 
@neymarjr
66.3M followers

Bill Gates 
@billgates
65.2M followers

Selena Gomez 
@selenagomez
63M followers

The Ellen Show
@theellenshow
62.1M followers

CNN 
@cnn
61.7M followers

X 
@x
60.6M followers















