Genomics + immunology + ML = personalized cancer immunotherapy | https://xitter.cf/t.co/nReVwtVHPq | https://xitter.cf/t.co/8DWibdfDWa
Durham, NC
Joined June 2007
- Tweets23K
- Following5.3K
- Followers7.4K
- Likes102K
Pinned Tweet
Slides from a talk I gave in September at the Lunenfeld-Tanenbaum Research Institute in Toronto.
Machines of Loving Hype: Let's get specific about "curing cancer with AI"
(secretly, personalized TCR therapies for NUT carcinoma and beyond)
alex rubinsteyn retweeted
If your Author Accepted Manuscript was supported by @NIH funding, it must be posted publicly to PMC without an embargo. There's no cost and it does not require buying expensive open access plans. Take steps to upload your Author Accepted Manuscript here: nihms.nih.gov/login/?next=/s…
.@JAMAInternalMed recently published a thoughtful piece on public access calling for NIH to assert its position regarding compliance with the NIH Public Access Policy.
NIH has the right to make the Author Accepted Manuscript, which has been supported by taxpayers, public in PubMed Central at time of publication; a right which is independent from any publisher agreement.
This is a free path to compliance for authors, helping us ensure rapid public access to NIH-supported research results.
alex rubinsteyn retweeted
Two years of work, and PySR v2 is finally out!
If you haven't used it before: PySR is a machine learning library that finds short equations that fit your data.
I've always wanted a PyTorch for symbolic learning. PySR v2 is a big step towards that:
alex rubinsteyn retweeted
🇨🇳 China IND Tracker (October 12–18)
16 novel drugs received their first IND clearances in China during the week, according to China’s Center for Drug Evaluation (CDE) disclosures.
Notable INDs:
1. $ANL Adlai Nortye (阿诺生物) — AN4035 Injection
MOA: CEACAM5-targeting ADC conjugated with a highly potent pan-RAS(ON) inhibitor
Indication: Advanced or metastatic solid tumors with RAS mutations and enriched CEACAM5 expression, including colorectal cancer, pancreatic ductal adenocarcinoma, and non-small cell lung cancer
2. Yuekang Pharma (悦康药业) — YKYY036 Injection
MOA: INHBE-targeting siRNA conjugated with GalNAc ligand
Indication: Obesity or overweight
3. Precision Biotech (精准生物) — TC-13-183 Cell Therapy
MOA: Cell therapy
Indication: CEA-positive advanced peritoneal metastatic colorectal cancer
4. CSPC (石药集团) — SYS6088 Injection
MOA: PD-1/VEGFA/CTLA-4 trispecific antibody
Indication: Advanced or metastatic solid tumors
5. Qilu Pharma (齐鲁制药) — QLS2401 Injection
MOA: PSMA/STEAP1/CD3 trispecific antibody
Indication: Advanced prostate cancer
6. Institute of Biophysics, Chinese Academy of Sciences / Sinovac Biotech (中科院生物物理所/科兴集团) — SNA01 Injection
MOA: Long-acting anti-RSV mab for intramuscular administration
Indication: Prevention of RSV lower respiratory tract infections in neonates and infants
7. Essight Biotech (灵识质源) — ES502 Injection
MOA: RAS G12V-targeting TCR-TCE
Indication: RAS G12V positive advanced solid tumors
8. Chipscreen (微芯生物) — NW001 for Injection
MOA: Epigenetic immune-modulating antibody-drug conjugate (EIMAC), comprising a humanized anti-PD-L1 mab conjugated to an engineered HDACi payload
Indication: Advanced malignancies, including solid tumors and lymphomas
9. Innostellar Biotherapeutics (朗昇生物) — LX111 Injection
MOA: Gene therapy
Indication: RVO-ME and DME
10. Metis TechBio (剂泰科技) — MTS109 Injection
MOA: mRNA encoding a CD3×CD19×BCMA trispecific T-cell engager (TCE), delivered via LNPs
Indication: SLE
alex rubinsteyn retweeted
We now have prospective data with TOPO1 ADC sequencing from:
- SATEEN (#ESMOBreast26)
- HER3-DXd (#ESMOBreast26)
- SWITCH (upcoming #ESMO26)
All validate prior retrospective data, showing that TOPO1 ADC resistance is not overcome by target switch.
New payloads urgently needed.
#ESMO26 | SWITCH – Phase II
In mBC progressing after ADC therapy, switching the target antigen while continuing with the same TOP1 inhibitor payload class resulted in ORRs of only 0–8.3%.
Although the sample size was small and the patient population heterogeneous, changing the target antigen alone does not appear sufficient to overcome resistance.
alex rubinsteyn retweeted
We're working on an interactive book about cells, and how they work.
Our next installment, "A Recipe for Cells," is out today. It's about what cells are made from and why, despite us *knowing* what they are made from, we are not able to create life synthetically.
Read: press.asimov.com/books/burri…
alex rubinsteyn retweeted
I've always been bothered by how inefficiently most genomics software handle 1-hots. Many use 32 bits to store each 0/1 (128 bits/position!). High memory use slows down everything: modifying a sequence, generating shuffles, reading from/writing to disk, transfer to a GPU, etc.
alex rubinsteyn retweeted
BindCraft2 v1.0.4 has been released: with significantly improved VHH, scFv, ARP, and induced fit targeting. WE also improved speed and code stability. Try your difficult campaigns again. Great work by Erik Mäeots, Leonardo Tredese and Elizaveta Chernova.
alex rubinsteyn retweeted
underdiscussed background to GLPs is the lack of murine work that fueled its success - anglerfish? yes! gila monsters? yes! mouse ko models? luckily no!!!
alex rubinsteyn retweeted
lol sclerostin inhibitors rebuilding my mom’s skeleton and GLPs solving the obesity crisis and gene therapies that keep SMA kids alive and at little league practice is 1e283x cooler than a flying car, idk where you’ve been in biotech lately
Thesis defense by @DhuviKarthikey1
“Towards Personalized T Cell Therapies”
Has anyone published proteomics data for which uORFs (and more broadly ncORFs) are translated in dogs?
alex rubinsteyn retweeted
Structural variant detection across sequencing technologies nature.com/articles/s41587-0…
Which domain for the Initiative for Generative Immunotherapy
58%igi.bio
7%genimm.org
26%genimmuno.org
9%Other (reply)
85 votes • Final results alex rubinsteyn retweeted
This work is not getting enough attention. These are pretty massive leaps in modeling splicing. Very excited about this. Need to do a deep read but the performance on diverse splicing related tasks looks really good.
#SpliceAI2 splice variant effect benchmarks. Considerably improved performance in 9 evaluations spanning cryptic splicing, sQTLs, MPRAs, population genetics, plasma proteins, and rare disease. 🧬✂️🧵
