Jiqing Wu

Postdoc @UniSpital_USZ

[Jiqing Wu @IID_learning]

🔊A novel study 'Tera-MIND: Tera-scale mouse brain simulation via spatial mRNA-guided diffusion'!
Using spatial mRNA as input, we generated tera-scale 3D 🐭 brain.
Web: https://t.co/OmCGLn2t6E
Code: https://t.co/gsKEgk4HXX
Paper: https://t.co/virjbcoUC5
#GenAI #diffusion

[Jiqing Wu @IID_learning]

Excited for the upcoming @midl_conference at #Paris 🇫🇷 !

Welcome to our *oral* presentation "Infinite spatial transcriptomic editing in a generated gigapixel 🐭"!

Github: https://t.co/tGK8UGewPj
Program: Oral 2.3 - Synthesis
Time: Thursday from 16:30-16:45

[Jiqing Wu @IID_learning]

🎇For the first time ever, we propose Infinite #SpatialTranscriptomic editing using #GenerativeAI.

Our approach enables algorithmic gene expression-guided editing in a generated gigapixel mouse pup🐭.

Code, preprint and generated 106496 x 53248 WSIs: https://t.co/zZcCIMvXLq

[Nanda Horeweg @NandaHoreweg]

Age is an independent prognostic and causal risk factor for worse outcome after curative tx for stage I-III endometrial cancer pts. A multi-method study using data of the PORTEC -1/2/3 trials by Famke Wakkerman. Presented at #ESTRO24 by prof Creutzberg

https://t.co/ZJSZoojKQo

[Nanda Horeweg @NandaHoreweg]

Older women with #endometrialcancer should not be excluded from (molecular) diagnostic assessments and treatment based on their age alone.
Read in our Lancet Oncology paper why:

Prognostic impact and causality of age on oncological outcomes in wome... https://t.co/fChJPt0rwT

[Jiqing Wu @IID_learning]

@AdrianoAguzzi Hope you recover soon, Dr. Aguzzi.

[medRxiv @medrxivpreprint]

Prognostic impact and causality of age on oncological outcomes in women with endometrial cancer: a multimethod analysis of the randomised PORTEC-1, -2 and -3 trials https://t.co/qr3LInyhKo #medRxiv

[Marc Aubreville @MAubreville]

Since the regular paper #reviews+decisions for @midl_conference 2024 in Paris are now out (and publicly accessible), I did a brief analysis of the data using the OpenReview API.
➡️ https://t.co/6ffD8wKivv ⬅️

[Patrick Malone, MD PhD @patricksmalone]

one important reason we haven't reached an "alphafold moment" for biological data beyond protein structures:

datasets for protein structure are consistent and uniform. x-ray crystallography or cryo-EM data provide absolute atomic coordinates, meaning that the data is standardized and directly comparable across different experiments and studies.

datasets in other areas, such as RNA-seq or cell painting, suffer from batch effects and differences in normalization strategies, making it challenging to aggregate and harmonize data across labs at sufficient scale to achieve alphafold-level capabilities.

big reason why data standardization initiatives like @czbiohub are so important to computational biology.

[Jiqing Wu @IID_learning]

@PathologoP Thanks a lot😄

[Jiqing Wu @IID_learning]

This SST-editing study was developed upon advanced spatial transcriptomic platforms #CosMx (@nanostringtech) and #Xenium(@10xGenomics)

Many thanks to the researchers for curating the data!
Many thanks to @ViktorKoelzer for supervising the project!

[Jiqing Wu @IID_learning]

Can we simulate tumor->normal cell transition using gene expression?

SST-editing (@OUPBioinfo) enables in silico gene expression-guided editing at single-cell resolution. #GAN #GenAI

Accepted paper https://t.co/LTvzw91bqX
Code https://t.co/6bLkYRdjaJ

Liver tumor->normal cells

[Jiqing Wu @IID_learning]

Can we simulate tumor->normal cell transition using gene expression?

SST-editing (@OUPBioinfo) enables in silico gene expression-guided editing at single-cell resolution. #GAN #GenAI

Accepted paper https://t.co/LTvzw91bqX
Code https://t.co/6bLkYRdjaJ

Liver tumor->normal cells

[bioRxiv Bioinfo @biorxiv_bioinfo]

IST-editing: Infinite spatial transcriptomic editing in a generated gigapixel mouse pup https://t.co/SzuEhF8MY3 #biorxiv_bioinfo

[Jiqing Wu @IID_learning]

🎇For the first time ever, we propose Infinite #SpatialTranscriptomic editing using #GenerativeAI.

Our approach enables algorithmic gene expression-guided editing in a generated gigapixel mouse pup🐭.

Code, preprint and generated 106496 x 53248 WSIs: https://t.co/zZcCIMvXLq

[Nanda Horeweg @NandaHoreweg]

Can low grade endometrial cancer be p53 abnormal? Does the p53abn status matter for prognosis? Largest & most comprehensive study now in CCR: Clinical Behavior and Molecular Landscape of Stage I p53-abnormal Low-Grade Endometrioid Endometrial Carcinomas https://t.co/EyOA6NJXSL

[PHD Comics @PHDcomics]

Thank you ☕️

[Robert Scoble @Scobleizer]

This is the scariest tweet I've made in a long time.

On Friday I met with a psychiatrist, @MundinMd and did a 30 minute session, where I was her patient.

These are the notes that the system she was using, which uses @OpenAI's GPT as back end, made.

Wow. Thread:

[Science Magazine @ScienceMagazine]

Using #CRISPR engineering, researchers in @ScienceTM have manufactured hypoimmune pancreatic islet transplants that can control #diabetes in mice while avoiding destruction by immune cells, removing the need for immunosuppressive drugs. https://t.co/MR8Q3HFKiH

[Dan Shipper 📧 @danshipper]

GPT-4 does drug discovery.

Give it a currently available drug and it can:

- Find compounds with similar properties
- Modify them to make sure they're not patented
- Purchase them from a supplier (even including sending an email with a purchase order)

[Gary Marcus @GaryMarcus]

No. Tesla recall, MSFT Bing fail, and Google Bard fail are NOT independent; each reflect the fact that you cannot build AI in the real world from Big Data and deep learning alone.

Too many edge cases and not enough reasoning. We need new approaches; current AI has been oversold.

[Jiqing Wu @IID_learning]

Our 'LEA' pre-print study is released this week. we

a. propose a robust quantification score (e.g., hit score for phenotypic drug screening)

b. support the biologically plausible simulation of phenotypic changes.

See https://t.co/Z9gbm6cAQ6 for more detail. #Covid #drug

[Jiqing Wu @IID_learning]

How do we quantify #drug effects (e.g. #COVID) on cell-based essays? Keywords: eigenvalue comparison.

How do we explain the quantification? Demo: VERO cell population.

Follow the project update via https://t.co/8jQmjd3dCn,
@ViktorKoelzer, @Unispital_USZ, @UZH_en