Ethan Perlstein 1-to-N

I've met so many entrepreneurial rare disease parents over the years that I’ve lost count. They have moved or are moving medical mountains to save their kids and others like them. But rare parent founders get no love from institutional players. Those days are done. Science, talent and compute are no longer limiting. Priority Review Voucher alpha makes the economics work. The missing spark is access to cure capital. That's why I’m incredibly pumped to relaunch @1000cures with my cofounder @ryan_1000cures! Ryan and I teamed up to create a “YC for Rare” that unites our biotech houses with complementary expertises, experiences and networks. 1000 Cures is an accelerator for lean startups led by parents on mission to cure pediatric rare diseases. We ride at dawn. Let’s go!

Perlara 3.0 site launch coming soon here’s a data teaser

@BioCentury Other options exist from NGLY1 drug repurposing screens conducted years ago, including aripiprazole and GSK3beta, but have not been thoroughly pursued pubmed.ncbi.nlm.nih.gov/31615832/ journals.plos.org/plosgenetics/a…

Tiny biotech’s experience raises questions about FDA’s rare disease policies. Grace Science says it has been shut out of plausible mechanism framework, denied flexibility on CMC requirements buff.ly/J4GAy1c

This summer we're launching YC Paper Club to bring researchers & builders together. Every few weeks we'll host a small group dinner in Mountain View to share and discuss new research papers. Interested in both research & building the future? Sign up at: events.ycombinator.com/ycpaperclub

As I mentioned before, I am now sharing an example from GPT-5.5 Pro, also featured by OpenAI, that really left me stunned by what it is capable of in biomedical science. (full report on the website I created with Codex, link in the thread). To push GPT-5.5 Pro hard, I uploaded a real data set of immune subset (T cells) gene-expression spreadsheet: 62 sorted T cell samples, 27,906 gene columns, and millions of underlying data points across different T cell subsets. Importantly, this public dataset also had paired structure making it possible to separate true cell-state biology from donor-to-donor variation. I asked GPT-5.5 Pro not merely to summarize the spreadsheet, but to analyze it deeply: What can we learn from this dataset? What are the mechanistic insights? What are the most important biological questions that emerge? What follow-up experiments should we do next? It thought for about 100 minutes and produced a roughly 40-page report! What amazed me was not just the length or even the initial analysis, since previous models are also capable of doing this. What amazed me was the quality of the reasoning and insights it provided! The report recognized that this was not just a table of genes, but two overlapping experimental designs. It identified the major biological axis, which in plain language was that the cells were not just “different categories.” They formed a coherent differentiation landscape, moving from future potential toward immediate function. It also understood the caveats. It did not overclaim from bulk gene-expression data. It clearly explained that bulk transcriptomics cannot distinguish whether every cell in a sorted population has shifted or whether a smaller subpopulation is dominating the signal. It recommended the right next steps experiments, and integration with donor metadata. This is what made the report feel so special to me. It was not just doing statistics. It was reasoning like an expert systems immunologist. It saw the structure of the experiment, interpreted the patterns, built a mechanistic model, identified limitations, proposed causal hypotheses, and laid out a translational roadmap. Other advanced models have been able to generate excellent biomedical reports before, including previous GPT-5 models. So I don't want to claim this is an entirely new type of capability. But this one felt different in an important way. It had more scientific elegance, more restraint, more biological intuition, and more of the nuanced judgment that usually comes only from years of hands-on experience in the field. It felt like this AI model had crossed another threshold. This is the kind of analysis that could easily take a research team months to perform, refine, interpret, and write up. Even then, many teams might not produce something this integrated, this mechanistically coherent, and this useful as a launchpad for future experiments. I know a 40-page T-cell gene-expression analysis may not be exciting to everyone. To illustrate how good it is, also had Codex built a web site with it anyone can explore, link below. 😊 Those interested can go deeper into the report. I also wanted this example on the record because, because to me, it is evidence that we are entering a new stage in AI-assisted biomedical science. The important point is no longer that AI can "analyze data and write a report.” The important point is that AI can now help transform complex biological data into mechanistic understanding, experimental priorities, and testable hypotheses at a speed and depth that would have been almost unimaginable a short time ago. For biomedical science, this is a very big deal! Of course, this may vary across domains, and every analysis still needs expert review, validation, and experimental follow-up. But in my own field, with data I understand deeply, this felt like another inflection point. I feel strongly that we have crossed another milestone threshold in the age of AI, with the release of GPT-5.5.

curesmaxxing

@tokengobbler cuz fundraising and dating are the same thing

Being a founder in SF is the closest men will ever get to being a hot girl. Everything's free and everyone wants to grab coffee with you

PRV sales holding steady around ~$200M for anyone paying attention

@AppleHelix @OmicsOmicsBlog very interesting indeed!

Wow this is really interesting case. Sezaby is phenobarbital sodium. Phenobarbital has been used for over 100 years. There is even a USP monograph for it. FDA's argument is that because of this, Sezaby contains an active moiety had been previously approved. Sun Pharma sued that because the PRV legislation says "...previously approved in any other application under subsection (b)(1), (b)(2), or (j) of section 505’ of the FD&C Act". Phenobarbital approval predates FD&C act's 1962 amendments The court agreed and Sun Pharma was issued a PRV Take away here is that If your rare pediatric drug contains DESI (pre-1962) or "grandfathered" (pre-1938) API, and there are NO post-1962 approval of drugs containing the said API, then it can qualify for PRV. thefdalawblog.com/2025/12/when-i…

@zacxbt is pre-early code for masochism?

DeSci is still pre-early

@tech__unicorn 0 to 60 baby

peptides are now more popular in sf than claude why do cults form so quickly here?

@treypicou Kalshi for Cures

love the concept of fda getting real-time trial data (admittedly i haven’t dug into details yet) but also think people will inevitably trade on all this insider info esp with online betting markets for drug approvals coming online.

@omgjulissaa dudewipes to the rescue

Do you sniff your girls butthole?

@craigzLiszt that’s how it starts

make something rich people want

Excited to share our discovery of a new programmable RNA-guided DNA-targeting system hiding inside bacteriophages that predates CRISPR. We call it VIPR (Viral Interference Programmable Repeat), and it uses an entirely new logic to find its targets. Thread + link below.

Stealth mode is dumb. If no one knows you exist, you don’t exist. Build loud.

The mission of @1000cures is clear: Accelerate family-founded companies (FAMCOs) toward parent-powered cures

Just wrapped up an inspiring few days at the 2026 CDG Scientific & Family Conference in Orlando with @eperlste Huge thanks to the entire CDG community — families, researchers, clinicians, and advocates for the powerful conversations, shared insights, and relentless drive to advance treatments and care for CDG patients. The energy and collaboration at this conference reinforce why @1000cures exists: to equip rare disease families with everything they need to go from idea to impact faster. If you’re a CDG parent, researcher, or advocate and we didn’t connect yet — reach out. The next 1000 cures come from communities like these.

The reemergence of the global blockbuster asset class and the resulting competition among Big Pharma for market share are the demand drivers for PRVs. Two PRVs cleared $200M in Q1, up from an average of $150M last year. In fact PRV values have been trending upward since bottoming around $80M in 2018 📈

@orenjacob Don’t recall asking your opinion my man

@eperlste No. Being bicoastal means you don’t actually invest in either and stay on the surface. Honestly, long term, it’s not a winning strategy.

be bicoastal and you get the best of both worlds!

Shkreli derangement syndrome is a thing clearly. Again, I have every reason to hate this guy because he made my life a living hell for a while 10 years ago. Pharma wanted so badly to disown him but he’s always been one of them! He just did loudly what Horizon and many many other Pharma companies did (and still do) quietly. And have you listened to him talk about peptides recently? He’s super trad, in fact. His freaking mentor was Fred Hassan, people! But no one’s done their actual homework on the guy. Guess I’m just a sucker for a good comeback story 🤷

@Nicole_Paulk @eperlste Well i agree he's pretty smart. Just sometimes morally misguided! He slightly fills a communication type void in an industry that struggles on that front generally.

I'm begging all of you, please stop interviewing this idiot and platforming him. It's beneath you and makes you look pathetic. There are real science + business experts on any topic you can dream up who'd be better than this 💩