Excited for the upcoming @midl_conference at #Paris 🇫🇷 !
Welcome to our *oral* presentation "Infinite spatial transcriptomic editing in a generated gigapixel 🐭"!
Github: github.com/CTPLab/IST-edi…
Program: Oral 2.3 - Synthesis
Time: Thursday from 16:30-16:45
🎇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: github.com/CTPLab/IST-edi…
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
thelancet.com/journals/lanon…
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... sciencedirect.com/science/articl…
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 medrxiv.org/cgi/content/sh…#medRxiv
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.
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!
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 doi.org/10.1093/bioinf…
Code github.com/CTPLab/SST-edi…
Liver tumor->normal cells
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 doi.org/10.1093/bioinf…
Code github.com/CTPLab/SST-edi…
Liver tumor->normal cells
🎇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: github.com/CTPLab/IST-edi…
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 aacrjournals.org/clincancerres/…
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:
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. scim.ag/2lO
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)
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.
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 github.com/CTPLab/LEA for more detail. #Covid#drug
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 github.com/CTPLab/LEA,
@ViktorKoelzer, @Unispital_USZ, @UZH_en
12K Followers 2K FollowingBruker Spatial Biology provides best‑in‑class solutions for capturing the full complexity of biology through a portfolio of instruments, software, and services.
398 Followers 206 FollowingDefeating the curse of dimensionality one algorithm at a time. 7M+ pageviews so far..Also the Advanced Matrix Factorization Jungle page https://t.co/dpQgesm8SY
68K Followers 60 FollowingStudent of mind and nature, libertarian, chess player, cancer survivor. @ Keen, UAlberta, Amii, https://t.co/u8za2Kod54, The Royal Society, Turing Award
308K Followers 480 FollowingPython's BDFL-emeritus, Distinguished Engineer at Microsoft, Computer History Fellow, fully vaccinated. Opinions are my own. He/him.
1K Followers 559 FollowingCompSci + ML + Healthcare. @AWSCloud, @StanfordAIMI, @Mila_Quebec. Director of https://t.co/gYWXTejyJb, https://t.co/N7PzI3ikhU, and https://t.co/1DBZ8BiID8.
802 Followers 513 FollowingLee Placito Fellow of Gastrointestinal Cancer 👨🏻🎓 @UniofOxford 👨🏼🔬🎓 Oncology🔬 Precision Medicine 🧬 All genes expressed are my Eoghan
6K Followers 31 FollowingDecoding biology to radically improve lives.
Décrypter la biologie pour radicalement améliorer les vies.
Powered by | Propulsé par @recursionpharma.
61K Followers 418 FollowingThe Lancet Oncology is the global leader in clinical oncology publishing peer-reviewed research and reviews, comment, news, and Commissions. IF=35·9.
29K Followers 667 FollowingEnabling researchers to answer biology’s hardest and most elusive questions with innovative #singlecell, #spatialbiology & #insitu technology
12K Followers 2K FollowingBruker Spatial Biology provides best‑in‑class solutions for capturing the full complexity of biology through a portfolio of instruments, software, and services.
62K Followers 652 FollowingUniversity Distinguished Professor (Emeritus), Oregon State Univ.; Former President, AAAI; Currently Chair CS Section of ArXiv
26K Followers 800 FollowingMeta MSL. I led PoT, MMMU, MMLU-Pro, ClawBench, MAmmoTH, General-Reasoner, VL-Rethinker, VLM2Vec. I contributed to Gemini-2.5 and Muse Spark series.
17K Followers 1K FollowingResearch news on @Wikipedia @Wikidata @Wikimedia, hot off the press. Volunteer-curated by @tilmanbayer & @mad_astronaut. Read our newsletter for full coverage
140K Followers 2K FollowingNYT Asia tech columnist 不明白播客主持人 Views here are my own 联系请用li.yuan AT nytimes. com 或者 FreeFrom公匙npub1nc3azwxkfaj96n85sujpcvy5mmn72hm3rzxklqqaklmzrwlljrqsfgsyca
2K Followers 604 FollowingResearch Scientist @ Idiap Research Institute. @Idiap_ch
Adjunct lecturer @ Australian Institute for ML. @TheAIML
Occasionally cycling across continents.
165K Followers 1K FollowingCell Press partners with scientists across all disciplines to publish and share work that will inspire future directions in research. #ScienceThatInspires
110K Followers 425 Followingprofessor of computer science @Stanford @stanfordnlp, co-founder of @togethercompute, creator of https://t.co/7R5THVogW2, co-founder of @simile_ai, pianist