AndrewArmour

[AndrewArmour @ArmourAndrw]

@SteveBakerFRSA @LoftusSteve @MaggiesMole Any chance you'll come back @SteveBakerFRSA? We could do with more sensible voices like your in parliament.

[AndrewArmour @ArmourAndrw]

@TrentTelenko A great test will be how quickly they can produce their own Patriots.

[AndrewArmour @ArmourAndrw]

@kelvmackenzie Sounds like a soup kitchen?

[AndrewArmour @ArmourAndrw]

@VincentGeloso I've always thought infant mortality was a good measure over time, although its so low now in developed countries its hard to measure further small gains.

[AndrewArmour @ArmourAndrw]

@LoftusSteve Steve, what about if we devolved it even further down? Everything bar defence, law, foreign policy down, not to PC level, but family level?

[AndrewArmour @ArmourAndrw]

@dim0kq I think at Waterloo 75% of the British/Allied casualties were from artillery. Just waiting on the ridge getting shot at. The column and cavalry charges would have been welcome relief!

[AndrewArmour @ArmourAndrw]

@fmfclips I took 20g each morning on a multi day run where I only had 90 minutes of sleep for 2 nights. I didn't feel mentally tired during the day at all. I haven't done a comparator but I would usually feel a lot worse after one bad night's sleep.

[AndrewArmour @ArmourAndrw]

@Louise_m_perry The lady at the top of the table looks so happy!

[AndrewArmour @ArmourAndrw]

@BojanRadojici10 Looks interesting, I'd be interested in a copy. Thanks

[Lucas Paulo de Lima Camillo @lucascamillomd]

AI Virtual Cell vs Linear Model—who wins? 🤖 ⚔️ 📈

Our preprint, entitled "𝘋𝘦𝘦𝘱 𝘓𝘦𝘢𝘳𝘯𝘪𝘯𝘨-𝘉𝘢𝘴𝘦𝘥 𝘎𝘦𝘯𝘦𝘵𝘪𝘤 𝘗𝘦𝘳𝘵𝘶𝘳𝘣𝘢𝘵𝘪𝘰𝘯 𝘔𝘰𝘥𝘦𝘭𝘴 𝘋𝘰 𝘖𝘶𝘵𝘱𝘦𝘳𝘧𝘰𝘳𝘮 𝘜𝘯𝘪𝘯𝘧𝘰𝘳𝘮𝘢𝘵𝘪𝘷𝘦 𝘉𝘢𝘴𝘦𝘭𝘪𝘯𝘦𝘴 𝘰𝘯 𝘞𝘦𝘭𝘭-𝘊𝘢𝘭𝘪𝘣𝘳𝘢𝘵𝘦𝘥 𝘔𝘦𝘵𝘳𝘪𝘤𝘴", seeks to answer this question.

Paper ▸ https://t.co/7RE7xGZT3g
Code ▸ https://t.co/ig19iB4Z3A

🎮 𝐋𝐚𝐜𝐤 𝐨𝐟 𝐜𝐨𝐧𝐭𝐫𝐨𝐥𝐬
Every wet-lab biologist knows that positive and negative controls are fundamental to assess whether an assay or experiment worked. However, the genetic-perturbation modeling field has been lacking these anchors to judge whether a model is actually learning the task. While the dataset mean is often used as a negative control, we propose an 𝐢𝐧𝐭𝐞𝐫𝐩𝐨𝐥𝐚𝐭𝐞𝐝-𝐝��𝐩𝐥𝐢𝐜𝐚𝐭𝐞 baseline as a positive control, approximating the best achievable performance for a given dataset.

📐 𝐌𝐞𝐭𝐫𝐢𝐜 𝐦𝐢𝐬𝐜𝐚𝐥𝐢𝐛𝐫𝐚𝐭𝐢𝐨𝐧
With positive and negative controls, we analysed 14 perturbation datasets to see which metrics best separate the two. We call this difference the 𝐃𝐲𝐧𝐚𝐦𝐢𝐜 𝐑𝐚𝐧𝐠𝐞 𝐅𝐫𝐚𝐜𝐭𝐢𝐨𝐧 (𝐃𝐑𝐅). Strikingly, widely used metrics like MSE and Pearson Δ (relative to control) often show low DRF, indicating limited sensitivity to perturbation signals. Weighted MSE and normalized inverse ranking perform well.

🧠 𝐃𝐞𝐞𝐩 𝐥𝐞𝐚𝐫𝐧𝐢𝐧𝐠 𝐩𝐞𝐫𝐟𝐨𝐫𝐦𝐚𝐧𝐜𝐞
Using well-calibrated metrics, most deep-learning models outperform linear baselines—and even additive models on combinatorial tasks. This holds from GEARS and scGPT to MLPs built on foundation-model embeddings.

Recently, a 𝐭𝐫𝐨���𝐞 of papers has cast doubt on the utility of deep learning for building the so-called AI Virtual Cell. Here, we show these models learn useful biology when evaluated with well-calibrated metrics. Looking forward to the bright future of the field!

Congrats to the first authors @Henrymiller2012, @g27182818, and @Fleblanc_3 for the absolutely fantastic work at @ShiftBioscience, alongside @BrendanMSwain and @BoWang87! 🔥

[Daniel Ives @dives86]

@SheekeyScience breaks down the @ShiftBioscience preprint 'A single factor for safer cellular rejuvenation' highlighting both the progress and caveats. Thanks @EleanorSheekey for opening up the frontlines of cell rejuvenation to a larger audience! https://t.co/A4miiG1SMG

[Prof Steve Horvath @prof_horvath]

@dives86 Wear this T shirt- it guarantees a romantic, intelligent date in less than 10 days!

[Daniel Ives @dives86]

@prof_horvath Thanks Steve and built on the shoulders of the methylation clocks, your manuscript in T-shirt form for our celebration today!

[Prof Steve Horvath @prof_horvath]

Genuine epigenetic rejuvenation in primary cells has long been the holy grail. A groundbreaking preprint reveals that over-expression of a single (secret) gene overcomes this barrier: greatly reduced age estimates across in fibroblasts and keratinocytes according to validated epigenetic clocks including the Skin&Blood clock (Horvath 2018) and the original pan-tissue clock (Horvath 2013). In keratinocytes, this gene decreased the pan-tissue clock by nearly ten years for each month of treatment! Longitudinal sampling confirmed age REVERSAL. This gene seems to outperform even the Yamanaka factors (OSKM) while crucially avoiding pluripotency induction and its associated cancer risks. 
Lucas Paulo de Lima Camillo,  Daniel Ives,  Brendan M. Swain (2025) A single factor for safer cellular rejuvenation. https://t.co/xjtoo7OQ6J

[AndrewArmour @ArmourAndrw]

@MartinSLewis We mostly have it heating at night when it's cheap electricity.

[AndrewArmour @ArmourAndrw]

@ZubyMusic It's a luxury belief.

[AndrewArmour @ArmourAndrw]

@JayinKyiv A European NATO would want Ukraine as a key player.

[AndrewArmour @ArmourAndrw]

@DrNeilStone 👍

[AndrewArmour @ArmourAndrw]

@benleo Economy - US. Security/Ukraine looks like we need to work with Europe.

[AndrewArmour @ArmourAndrw]

@berlin_bridge Completely agree. It's time for Europe to step up. The size of the European economies vs Russia should make it very one sided. Then our own security pact with Ukraine.