true chen true

Bioinformatics, Metagenomics, Immunology，Statistics，Deep learning

[AI Will @FinanceYF5]

https://t.co/gnn1F65v1i
AutoGPT 案例帖子一览 应该是目前最全的了

[Kevin K. Yang 楊凱筌 @KevinKaichuang]

Diffusion for protein structure is actually pretty popular!

Folding Diffusion: https://t.co/fGdHqLTi5U
Genie: https://t.co/pnNlcojurZ
ProteinSGM: https://t.co/3z1hbBm8ci
FrameDiff: https://t.co/IQ7QrfaSO5
Chroma: https://t.co/ijbfZitdWf
RFDiffusion: https://t.co/1y8y9QFoqx

[Jakob Nikolas Kather @jnkath]

Very happy to share this: We teamed up with 3 professional societies in 🇩🇪 (@dgho_eV, @gmdsEV, @informatikradar) and put together "an overview and a roadmap for #AI in hematology and oncology" https://t.co/URST2P7TPn & https://t.co/61fTTJVId9 @ottoadelheid @NCT_UCC_DD @NCT_HD

[Sam Altman @sama]

here is GPT-4, our most capable and aligned model yet. it is available today in our API (with a waitlist) and in ChatGPT+.

https://t.co/2ZFC36xqAJ

it is still flawed, still limited, and it still seems more impressive on first use than it does after you spend more time with it.

[Kevin K. Yang 楊凱筌 @KevinKaichuang]

A novel enzyme, Huc, consumes atmospheric levels of hydrogen gas and transfers the derived electrons for aerobic respiration.

@Rhys__G @Ashleigh_Kropp @greeninglab

https://t.co/NsTGs07MOR

[Leonardo V. Castorina @DrLeucine]

Hi everyone! While preparing for a journal club, I wrote an article about how @DeepMind #AlphaFold works! I dig deeper into the network architecture and explain AlphaFold's biological significance. #deeplearning #proteinfolding

https://t.co/dt2IfAPNMn

[Nazim Bouatta @NazimBouatta]

The recording of my third lecture @HarvardCMSA is now available. I discuss #AlphaFold2's limitations and a possible way forward. Retraining AF2 with inductive biases reflecting the physics/geometry of the problem could be the key. 1/2
https://t.co/PoMTGm5NbA

[Kevin K. Yang 楊凱筌 @KevinKaichuang]

Use sequence fitness predictions, structure-based features, and distances between mutated and wild-type residues to predict antibody escape mutations.

@NthadaniN @sarahgurev @NotinPascal @nooryoussef03 @_nathanrollins @sandercbio @yaringal @deboramarks

https://t.co/0uhgomt5gm

[Kevin K. Yang 楊凱筌 @KevinKaichuang]

Finetune a pretrained protein masked language model to predict whether each residue in a sequence is disordered.

@ananthannambiar @sergei_maslov

https://t.co/H2c41GzQ2p

[Mark Tenenholtz @marktenenholtz]

Some papers that were rejected:

• PPO (used to train ChatGPT)
• SVM
• SIFT
• YOLO
• GELU
• LSTM
• Dropout
• RoBERTa
• MinTrace
• PageRank
• Kalyan Filters
• Transformer-XL
• Word2Vec (poster)
• Viola-Jones Face Detector

And that’s why open research is good.

[Nazim Bouatta @NazimBouatta]

This Thursday, for my third lecture on deep learning for proteins at @HarvardCMSA, I'll describe AlphaFold2 limitations and how our OpenFold could help move forward. And how AF2 could impact our thinking about cells and organisms-expanding on N&V https://t.co/Go6ZiC09vz. 1/2

[bioRxiv Bioinfo @biorxiv_bioinfo]

MIDAS: a deep generative model for mosaic integration and knowledge transfer of single-cell multimodal data https://t.co/4SHV4wMwt7 #biorxiv_bioinfo

[Jordan Burgess @jordnb]

It's Time to Build (with ChatGPT)

Collecting the best APIs, hacks and extensions to get the most out of ChatGPT and to build next-gen product experiences ✨ —

[Yann LeCun @ylecun]

PyTorch 2.0 is announced!
Main new feature:
cmodel = torch.compile(model)
Faster training with no code modification.
Available in nightly build.
Stable release scheduled for early March

[Gustaf Ahdritz @gahdritz]

Our preprint on OpenFold, our trainable reproduction of AlphaFold2, is finally up (https://t.co/3EoTzE3Xdb)! Since we open-sourced parameters in June, we've trained the model to high accuracy more than 50 times, on a variety of datasets. Here's what we learned (a lot) -> (1/19)

[Pau Labarta Bajo @paulabartabajo_]

Wanna learn Reinforcement Learning?

Here is a step-by-step, hands-on course, that takes you from the fundamentals to Deep RL

And it is FREE ↓↓↓
https://t.co/PHKQloFqHG

[Turing Post @TheTuringPost]

A thread with the latest AI news is mindblowing 🤯🧵⬇️

[Snehanshu Saha@Hessian @SahaSnehanshu]

I'm teaching Computational Learning Theory based out of Shalev and Ben David's classic text 'Understanding Machine Learning: From theory to Algorithms'. In response to multiple requests, I've decided to make class/lecture notes open to public.

[AI Conference DL Countdown @DlCountdown]

IJCAI 2023 (abstract): 57 days.
IJCAI 2023 (paper): 64 days.
ACL 2023: 66 days.
ICML 2023: 73 days.
IROS 2023: 106 days.
ICCV 2023: 114 days.

[Moran Yassour @MoranYassour]

Pls RT: Any computational (micro)biologists out there looking for a #postdoc position? 🦠👩‍🎓👩‍💻 We’d love to have you in our lab in Jerusalem studying the infant gut #microbiome. There is a 2-week window for a great postdoc fellowship application, so pls talk to me asap.