Alex Telford

@draparente We do! :) Thanks for the extra detail on the indications too, we'll look into it

@Atelfo btw - love what you guys are doing! Wish you guys had individual accounts :)

This is really cool/necessary! First two indications I looked up had the wrong prevalence labels, though. Both diseases are more common than the assigned rare/ultra-rare labels. They were originally thought to be small populations, but higher prevalence numbers were published within the last few years.

@RessyM @Convokebio @DrSamuelBHume Here's how a burden of 4 is described in our rubric (impact on day to day life): Independent in self-care but symptoms prevent sustained full-time activity. Employment precarious, requires major accommodations, part-time status, or role reassignment. Karnofsky Status 60-70

@Convokebio @DrSamuelBHume Yikes. Looking at Endometriosis numbers, I can tell that nobody involved has, know anyone with, or had patients with the disease. Women are getting maid because there's no way to stop the pain, and the burden is only a 4. And it's not just a pelvic issue. Goddamn.

Today we're publishing our index of unmet needs in human disease: 2443 indications scored and ranked on burden of disease, prevalence, pipeline activity, and treatment burden. We hope this will help drug developers identify overlooked medical problems convoke.bio/blog/introduci…

@alibrocato We did internal human review, but not formally with e.g. patient groups or KOLs. That's something we might add in a future iteration. I consider this a proof of concept

@Atelfo How is this validated / verified

We ran an experiment to see if LLMs could help map, identify, and prioritize unmet medical needs across thousands of diseases. I've found it pretty educational to browse through; I've worked in biopharma for a while now and there are still so many big problems I've never heard of

@_buggles Let's do it! My email is alex@convoke.bio

@Atelfo This is fascinating. I’m at Pfizer leading applied AI in commercial. We should talk

@connorlandgraf Our definition of uncommon was "Affects between 1 in 2,000 and 1 in 100 people". The LLM's estimate of the prevalence for HFrEF was 1 in 270

@Atelfo Heart failure is uncommon?? uhh..

@adic_9 @dr_alphalyrae We have an entry under CFS

@Atelfo @dr_alphalyrae sad to see myalgic encephalitis is not on there Cool work nonetheless I do wish there was a toggle to scale by # of affected people

This is amazing. We need so many more biotechs in the world to address these diseases.

@antonioregalado Oops, you're right! That's a typo. Thanks & will fix

@Atelfo guide says the opposite. It is interesting there are zero, and it's also cool the summary identifies what's needed is a preventive measure. (no curing this one).

@antonioregalado Yeah it's an unusual one. In that case it's the burden of disease driving the score. Pipeline = 7 means that there's probably no drugs in development (higher need)

@Atelfo pretty interesting to see hydranencephaly @ #2. It says pipeline=7 but i couldnt find an outlink to any trial.

@MartinBJensen Will check and get back to you!

@Atelfo Would be curious how this overlaps with mostly manual version for age-related diseases - can your LLM answer? norn.group/age-related-di…

Biology is one of the most interesting domains where I'm seeing AI being applied. @Convokebio is hosting a small event with lightning talks to introduce the space to a technical audience without a bio background. There's a few spots left, DM me if you'd like to be added.

Check out the index here: insights.convoke.bio/unmet-needs

I'm joining the OpenAI Foundation to lead the Life Sciences & Curing Diseases program. We're starting with three areas of grantmaking: * AI for Alzheimer's * Public Data for Health * Accelerating Progress on High-Mortality and High-Burden Diseases Time to get to work!

Going Founder Mode On Cancer centuryofbio.com/p/sid Sid Sijbrandij is a generational founder. He founded and led GitLab, one of the largest remote companies in the world, from idea-stage startup to NASDAQ-listed software giant. But in 2022, a six centimeter mass growing from his upper spine threatened to end all of that. He had cancer. What happened next is nothing short of remarkable. Sid went founder mode on his care journey. In the years since, he's deployed cutting-edge genomics to profile his disease. Based on this data, he's developed a growing armamentarium of personalized therapies. As a result, his disease is now undetectable. A simplistic version of this story could be, “Wow! A brilliant billionaire seemingly cured his cancer. Good for him!” But as I’ve gotten to know Sid, it’s become abundantly clear to me that there is more to the story than that. In an in-depth profile for The Century of Biology, I explore Sid's journey and what this might mean for the future of cancer care.

@NickADobos Cookie clicker

What will the ideal AI agent orchestrator look like? - starcraft, age of empires, factorio - list of chats, aka cursor - CLI tabs - linear ???

There's no guarantee that Kendall square is going to remain a biotech hub. Every 20-30 years or so a new industry has replaced the previously dominant one; before biotech it was AI, before that it was minicomputers, hard candy, and soap

Dave Ricks on @stripe's podcast is the best pharma exec interview I've listened to in a good while. My notes on the conversation, Lilly's DTC strategy, and how they're using the capital influx from GLP-1s to build a new type of pharma business model: atelfo.github.io/2025/12/07/goi…

Ask not why would you work in biology, but rather: why wouldn't you? owlposting.com/p/ask-not-why-… openai/gemini gave this essay an A- for evocative imagery. claude gave it a C- for being emotionally manipulative. both are probably right. i feel a little sick re-reading it