Sai Raghavendra Maddhuri

Research Scientist at Meta. Previously PhD CS at Purdue. BITSian.

[Jay Alammar @JayAlammar]

The Illustrated Stable Diffusion

https://t.co/sbjKHP4Pol

New post!

Over 30 visuals explaining how Stable Diffusion works (diffusion, latent diffusion, CLIP, and a lot more).

[Kihara Laboratory @kiharalab]

Our paper out from Nature Methods! Residue-wise local quality estimation for protein models from cryo-EM maps" by @GTerashi @XiaoWangzyy @tesmer_john @sai_ragh4. & Kihara. DAQ identifies potential wrong regions in protein models using deep learning.
https://t.co/5CUC1nshKb

[Kihara Laboratory @kiharalab]

Had a great time with two new PhDs, Lyman and Sai, who depart our lab to make difference in the real world! @Monroe_Lyman @sai_ragh4

[Daisuke Kihara @d_kihara]

A new PhD from our lab!

[Sai Raghavendra Maddhuri @sai_ragh4]

Successfully defended my PhD!😀

[Kihara Laboratory @kiharalab]

Sai successfully defended his PhD thesis today. Congratulations, Dr. Maddhuri!!

[Kihara Laboratory @kiharalab]

Sai successfully defended his PhD thesis today. Congratulations, Dr. Maddhuri!!

[Andrej Karpathy @karpathy]

The ongoing consolidation in AI is incredible. Thread: ➡️ When I started ~decade ago vision, speech, natural language, reinforcement learning, etc. were completely separate; You couldn't read papers across areas - the approaches were completely different, often not even ML based.

[Genki Terashi @GTerashi]

Our latest research Emap2sec+ has just been published in @NatureComms .

https://t.co/4n6UebNbYM

[Sai Raghavendra Maddhuri @sai_ragh4]

New paper from our lab has just been published in @NatureComms !!
Emap2sec+ extends our earlier work Emap2sec to also detect DNA/RNA from cryo-EM maps
https://t.co/LbnHGIinPE
@PurdueCS @kiharalab

[Kihara Laboratory @kiharalab]

New paper from our lab released today: "VESPER: global and local cryo-EM map alignment using local density vectors" in Nature Communications. Xusi Han, @GTerashi et al. https://t.co/icGUvWtu02

[Sai Raghavendra Maddhuri @sai_ragh4]

My new paper published in Bioinformatics journal!

[Kihara Laboratory @kiharalab]

New paper "Protein Contact Map Refinement for Improving Structure Prediction Using Generative Adversarial Networks" in Bioinformatics now released online! https://t.co/iye1PDRycw @PurdueCS

[Kihara Laboratory @kiharalab]

New paper "Protein Contact Map Refinement for Improving Structure Prediction Using Generative Adversarial Networks" in Bioinformatics now released online! https://t.co/iye1PDRycw @PurdueCS

[Sai Raghavendra Maddhuri @sai_ragh4]

Thank you for the shout out, Alessandro!! Glad to know you find our method helpful.

[AlessandroBorsellini @ABorsellini]

I have been trying the SuperEM method from @kiharalab @sai_ragh4. Not only improved the resolution, but it is extremely good at showing poorly resolved areas. #CryoEM
https://t.co/wiLQl0ZVF8

[Kihara Laboratory @kiharalab]

This week we have another paper accepted: " Protein Contact Map Refinement for Improving Structure Prediction Using Generative Adversarial Networks" for publication in Bioinformatics, @sai_ragh4, @GTerashi, Aashish Jain, Yuki Kagaya & Kihara.

[Sai Raghavendra Maddhuri @sai_ragh4]

An abridged version of our Emap2sec work is just published
https://t.co/ysoPwuSSTW

[Kihara Laboratory @kiharalab]

A summary of Emap2sec cryo-EM software by @sai_ragh4 et al.
https://t.co/ZWvvperOBR

[bioRxiv @biorxivpreprint]

Super-Resolution Cryo-EM Maps With 3D Deep Generative Networks https://t.co/KYz8pIBsDx #bioRxiv

[Daisuke Kihara @d_kihara]

The CASP14 meeting is now over. In the closing remark, John Moult declared that the single chain protein structure prediction is solved. This is a strong and historical statement.

[Oriol Vinyals @OriolVinyalsML]

Biology's ImageNet moment has arrived: #AlphaFold2 solves Protein Folding at the #CASP14 competition!

Blog: https://t.co/KH9g8FFXvS

[Mohammed AlQuraishi @MoAlQuraishi]

CASP14 #s just came out and they’re astounding—DeepMind looks to have solved protein structure prediction. Median GDT_TS went from 68.5 (CASP13) to 92.4!!!! Cf. their 2nd best CASP13 struct scored 92.8 (out of 100). Median RMSD is 2.1Å. I think it's over https://t.co/dQ1BOJWuwn