Excited to our new paper in PLOS Genetics doi.org/10.1371/journa……Nihar worked tirelessly to get this across the line with much support and collaboration from NZ, Nathaniel Hafford Tear Amanda Sadan, Christina Zarouchlioti, Aaron Jeffries, Anita Szabo, Ismail Moghul, Szi Kay, and many others!

Hot off the press 👇‼️ jamanetwork.com/journals/jamao… Very proud to see the first AI-enabled analysis of Geographic Atrophy OCT feature changes over 24 months from the phase III DERBY & OAKS studies published by our team in JAMA Ophthalmology 😀NIHR Moorfields BRC UCL Institute of Ophthalmology 🙌

The result of exceptional team efforts and tireless work by our wonderful team #BalaskasLab 🙏 Special thanks to Dun Jack Fu for his talent, skill and dedication that made this work possible. Most proud of our amazing team Ismail Moghul Nikolas Pontikos

Very excited to see Nihar image on the front cover of PLOS Genetics this month. Amazing work Nihar! journals.plos.org/plosgenetics/a…

Pegcetacoplan associated with slower growth of photoreceptor degeneration (PRD), RPE-loss, PRD in isolation, and RPE and Outer Retinal Atrophy. Our analysis of automatically-segmented quantitative OCT biomarkers out in JAMA Ophthalmology based on OAKS & DERBY Apellis Pharma data.

Delighted to report that our paper 'Expert CONsensus on Visual Evaluation in Retinal disease manaGEment: the CONVERGE study' is now published in the British Journal of Ophthalmology. bjo.bmj.com/content/early/…

At the height of One Million Checkboxes's popularity I thought I'd been hacked. A few hours later I was tearing up, extraordinarily proud of some brilliant teens. A thread about my favorite story from running OMCB....

Excellent talk from Shahida Moosa #StopTheGenocide highlighting the need for a global reference for phenotype variability in rare disease diagnosis. Featured Symposium (session 35) on AI to improve clinical diagnoses in Four Seasons Ballroom 2&3 #ASHG24 #AI #rarediseases

Eye2Gene for next generation phenotyping of inherited retinal diseases using AI was highlighted by Ismail Moghul UCL Institute of Ophthalmology during the great Featured Symposium on Advanced in AI (session 35). #ASHG24 ASHG #AI Nikolas Pontikos

Elfride De Baere Eye2Gene UCL Institute of Ophthalmology ASHG Thank you Elfride De Baere ! It certainly looked like a great session, I am sure Ismail Moghul enjoyed it!

Apple released a hearing aids feature for the AirPods Pro a while ago. I bought a pair for grandma, but then realized that the feature was geoblocked in India So we at Lagrange Point decided to unblock it. It ended up involving a leaky microwave and building a Faraday cage:

Make your Mac think faster 🧠🧠 Tomorrow I'll show you how to cancel your copilot subscription.

A.I. is improving the accuracy of medical diagnoses. Today for inherited retinal diseases [IRD] (Eye2Gene vs retinal experts) nature.com/articles/s4225…

DeepMind just dropped a 106-page paper unveiling AlphaGenome. This single model could completely redefine how we discover disease-causing mutations and drug targets. This is massive. 🧵

Hieu Pham lmaaooo, need more of this in ML papers. I loved the writing style of yolov3, intro was hilarious also the graph literally just goes off the y axis and they just leave it to flex 😂

1⃣A comprehensive assessment of organ-specific proteomic aging clocks In an analysis of UK Biobank proteomic data, this study tested at scale the previously described organ-specific proteomic aging clocks. People with 8+ aged organs (>1.5SD for the respective clock) had a

3⃣An AI multi-agent for bioinformatics PromptBio promises to offer a comprehensive AI pipeline for bioinformatic data analyses including standardized omics pipelines. Interested to see how successful these efforts to automate big data analyses are going to be.

5⃣Foundation Models of Behavioral Data from Apple Wearables Using data from 160,000 participants in the Apple Heart and Movement Study, this manuscript describes the development of foundation models for the analyses of 27 behavioral variables collected over 2.5B hours of

We've been developing a small standalone tool for viewing & calculating frequency from modification tags in BAM files. This call is for brave users to test. github.com/warp9seq/minim… written by Suneth in C, based on mod tag parsing we did for realfreq doi.org/10.1093/bioinf…

No driver mutations could be identified in 181 tumors. The authors do not know why. Perhaps, it's an algorithmic failure. Perhaps, it reflects non genetic contributions to carcinogenesis. What do you think ?