user avatar
Andrew Beam
@AndrewLBeam
We can only see a short distance ahead, but we can see plenty there that needs to be done. CTO, @LilaSciences Prof, @Harvard | Cofounder @generate_biomed
Boston, MA
Joined March 2013
1,902
Following
10.1K
Followers
Posts
  • Pinned
    user avatar
    Andrew Beam
    @AndrewLBeam
    Oct 14, 2025
    Today we’re excited to share additional support in the Series A for Lila: $350M in total for the round and $550M raised to date. I’m grateful for our team, our early partners, and the investors who believe in this mission. In an earlier post I asked whether science can create
    user avatar
    Lila Sciences
    @LilaSciences
    Oct 14, 2025
    We’ve closed our Series A. With $550M total raised since launch, we’re ready to scale. 🚀Learn how our Series A is fueling our next chapter: lila.ai/news/announcin…
    19K
  • user avatar
    Andrew Beam
    @AndrewLBeam
    Aug 1, 2018
    If I were to sum up the challenges in machine learning for healthcare in a single XKCD, this would definitely be the one:
  • user avatar
    Andrew Beam
    @AndrewLBeam
    Jan 26, 2022
    Explaining my dissertation to current grad students
  • user avatar
    Andrew Beam
    @AndrewLBeam
    Nov 15, 2023
    1/n: We are excited to share that our paper on Chroma, a general purpose diffusion model for proteins, is out today in @Nature! nature.com/articles/s4158… A couple of my favorite highlights in the 🧵below 👇
    00:00
    362K
  • user avatar
    Andrew Beam
    @AndrewLBeam
    Jan 9, 2020
    Replying to @edwardhkennedy
    GIF
  • user avatar
    Andrew Beam
    @AndrewLBeam
    Nov 30, 2021
    Posting the preprint Getting the paper published
  • user avatar
    Andrew Beam
    @AndrewLBeam
    Apr 5, 2018
    Our preprint that creates embeddings for over 100k medical concepts using data from 60 million patients, 1.7 million journal articles and 20 million notes is up: bit.ly/2HbYoyx Pretrained embeddings: bit.ly/2GvqQ0X Interactive explorer bit.ly/2GVNu1U
  • user avatar
    Andrew Beam
    @AndrewLBeam
    Feb 12, 2019
    This shouldn't surprise anyone. If you have tabular data, a small number of variables, and a modest sample size there is *no* reason to expect ML to be superior. However, I don't think this is the scenario most have in mind when thinking about potential for ML in medicine
    user avatar
    Muin J. Khoury
    @MuinJKhoury
    Feb 12, 2019
    Machine learning/artificial intelligence are viewed as the future of predictive analytics. This systematic review shows no performance benefit of machine learning over logistic regression in clinical prediction models. jclinepi.com/article/S0895-…
  • user avatar
    Andrew Beam
    @AndrewLBeam
    Jul 28, 2020
    Language models are known to exhibit bias and it seems that GPT-3 is no different in this regard, but it is always shocking to see. I gave it the first prompt and had it generate the rest.
  • user avatar
    Andrew Beam
    @AndrewLBeam
    Apr 17, 2018
    Self-driving cars are often used an example of how adversarial attacks can do harm in the real world. In our new preprint, @samfin55, @zakkohane, and I argue that medicine is the perfect storm of incentive + opportunity for adversarial attacks: arxiv.org/abs/1804.05296
  • user avatar
    Andrew Beam
    @AndrewLBeam
    May 29, 2019
    A few nuggets from @geoffreyhinton's talk from earlier today at the #ml4h unconference. First up, the distinction between statistics and AI (and presumably ML by implication). Overall, I think these are pretty clean contrasts:
  • user avatar
    Andrew Beam
    @AndrewLBeam
    Aug 12, 2024
    We are building one of the largest GPU clusters in biotech and are recruiting ML engineers! If you have experience making GPUs go brr and would like work on exciting problems at the intersection of AI and autonomous science, please consider applying: job-boards.greenhouse.io/flagshippionee…
    28K
  • user avatar
    Andrew Beam
    @AndrewLBeam
    Feb 16, 2021
    One of the things I've learned from straddling the worlds of machine learning, statistics, and epidemiology is that everyone has their own definition for what "nonparametric" means
  • user avatar
    Andrew Beam
    @AndrewLBeam
    Sep 1, 2019
    Something that the machine learning for healthcare community has needed for a long time: A library for transforming MIMIC-III data into meaningful ML prediction tasks. Big 🙏 to @TristanNaumann, @MarzyehGhassemi, et al. for putting this together: Repo:
    GitHub - MLforHealth/MIMIC_Extract: MIMIC-Extract:A Data Extraction, Preprocessing, and Represent...
    From github.com