@BioAI_Neuro

Friends and colleagues often ask, “What are the top 100 important "AI in Biology" papers that provide broad insights into the field?” 📚🔬 While narrowing it down to exactly 100 is no small feat, I’ve curated a list of foundational and impactful #BioAI papers. I'm sure the list would exceed more than 100 given the relentless expansion of this thrilling field! Please follow this thread for key insights, and please feel free to suggest any papers I may have missed! With my background and interests, I prioritize papers in #AgingBiology, #CellBiology, and #Neuroscience. I’ll keep this thread pinned to my profile and update it regularly. I encourage everyone to add more papers from their own expertise—let’s make this interactive and foster engaging discussions! Here is a collection of essential #AIbio papers. #100_AIBio_Papers #AIBio_papers #AIBio_Chat #AIneuro_papers #AI_AgingBio_papers

Backlash against AI is mounting!!

@usepapertrace @NatureNeuro @AgingCell I will revisit. Thank you!

@BioAI_Pharma @NatureNeuro @AgingCell Cool pick. Thornburg et al.'s JCVI-syn3A whole-cell model is wild. If you only skim one thing, check how they validated against growth curves and RNA-seq. Quick way to judge realism.

Friends and colleagues often ask, “What are the top 100 important "AI in Biology" papers that provide broad insights into the field?” 📚🔬 While narrowing it down to exactly 100 is no small feat, I’ve curated a list of foundational and impactful #BioAI papers. I'm sure the list would exceed more than 100 given the relentless expansion of this thrilling field! Please follow this thread for key insights, and please feel free to suggest any papers I may have missed! With my background and interests, I prioritize papers in #AgingBiology, #CellBiology, and #Neuroscience. I’ll keep this thread pinned to my profile and update it regularly. I encourage everyone to add more papers from their own expertise—let’s make this interactive and foster engaging discussions! Here is a collection of essential #AIbio papers. #100_AIBio_Papers #AIBio_papers #AIBio_Chat #AIneuro_papers #AI_AgingBio_papers

47/ Next top 100 #BioAI paper in this series : Bringing the genetically minimal cell to life on a computer in 4D sciencedirect.com/science/articl… Thornburg et al. 2026 developed a full 4D whole-cell model of the genetically minimal bacterium JCVI-syn3A, simulating its entire 100-minute cell cycle across both space and time. The model integrates genetic information processing, metabolism, growth, chromosome replication, and cell division into a single computational framework. Using hybrid simulations and experimental constraints, it captures dynamic cellular morphology, membrane growth, and chromosome organization driven by SMC- and topoisomerase-like proteins. Remarkably, the system reproduces real experimental measurements including doubling time, mRNA half-lives, ribosome counts, protein distributions, and DNA replication patterns. Because the model incorporates stochasticity, every simulated cell behaves uniquely, enabling prediction not only of average cellular behavior but also the heterogeneity passed to daughter cells. This represents a major step toward predictive whole-cell simulations that connect molecular-scale processes to complete cellular life cycles. #WholeCellModeling #DigitalCell #MinimalCell #AIforScience #MolecularBiology #JCVISyn3A #Top100BioAI_Papers #FutureOfBiology

46/ Next top 100 #BioAI paper in this series : A foundation model of transcription across human cell types nature.com/articles/s4158… Flash Summary: The General Expression Transformer (GET) is a foundation model that predicts gene expression across diverse human cell types by integrating DNA sequence and chromatin accessibility. It learns a universal “regulatory grammar” of transcription and can generalize to unseen cell types with near-experimental accuracy. GET identifies long-range regulatory elements and transcription factor interactions, revealing mechanisms of gene control. It also uncovers disease-relevant disruptions, such as how PAX5 mutations alter regulatory networks in leukemia. Follow this thread to learn more about this super important BioAI paper: x.com/NeuroAI_Nexus/… #Foundation_models, #Transcription, #BioAI #Top100_BioAI_papers

@UrnovFyodor That’s cool! How accurate are citations and references?

I prompted the “deep literature” mode of Edison Scientific to write a comprehensive review on the biology of a gene that I know well. Twenty five min later it sent a 17 page PDF. It was, as best as I can tell, flawless. Folks, we are not in Kansas anymore. Don’t at me - try it.

Why heart never get cancer ?

@KaiXCreator Just curious, why ? Tokenomics is the reason?

Why is everyone making a shift from Claude to Codex?

Super important paper also for #Bioelectricity enthusiasts

@earthcurated Patch-clamp electrophysiology!!! It is super F….. hard to carry it even in live animals or any tissue!!!

Name one job AI will never be able to replace. 👇

@thekevinmcp My physical library is also similar size but my digital one is crazy—pilled up things from undergrad, phd . Postdoctoral and stuff later

It's beautiful. Mine are away in boxes as I prepare to move, so I'll just be moved by this picture of yours.

This is a fascinating tool for neuro and cell bio folks !! As a patch clamp ephys person, I love electrical synapses and coupling !!! Long-term editing of brain circuits using an engineered electrical synapse | Nature nature.com/articles/s4158…

Growth charts reveal how the brain’s ‘communication highways’ change throughout life nature.com/articles/d4158…

@movielover93582 I want to see other neuroscientists perspective on this because in my field experiments have complex design and so many variables can go awry!!

@BioAI_Pharma Ai hypothesis is slowly becoming same level to human hypothesis

What happens when we outsource hypothesis generation to a machine ? Check this paper. What’s your hypothesis? | Nature Methods nature.com/articles/s4159…

Double robustness | Nature Methods nature.com/articles/s4159…

Please check this exciting study from @Yang_zy223 . Here is my summary: 1️⃣ Scalable training for discovery-LLMs We provide the first complexity analysis showing why directly training P(h|b) is intractable, then introduce a decomposed recipe reducing complexity from O(Nᵏ) → O(log N). A post-trained 7B model reaches near-frontier inspiration retrieval accuracy: • MS-7B: 54.4% • Gemini-3 Pro: 54.9% • GPT-5.4: 51.5% • Base 7B: 28.4% 2️⃣ Sample-efficient test-time scaling ~9,500 unguided brute-force samples still can’t match what MS-7B achieves with just 1–3 guided samples. Brute force plateaus early; guided sampling keeps scaling.

Platonic representation of foundation machine learning interatomic potentials | Nature Machine Intelligence nature.com/articles/s4225…

A generative artificial intelligence approach for peptide antibiotic optimization | Nature Machine Intelligence nature.com/articles/s4225…

Pretraining a foundation model for small-molecule natural products | Nature Machine Intelligence nature.com/articles/s4225…

Alex, We often glorify successful people and assume that simply following their path is enough to succeed. But in reality, success is different for everyone. We should also study failures and use “inversion thinking” to understand why something failed, not just why something worked. We may need to share our failures as well; not just successes!!!

Hello everyone 👋 I'm Alex, a 5-time failed startup founder, I hope one day I'll be able to make it... But today, I'd like to connect with: 🎨 Designers 📱 Developers ✨ Indie makers 🖌️ UI/UX 🤖 Vibe coders 📊 Growth hackers 📦 Etc.. If you want to connect, just say hi 👋 #saas #buildinpublic #startup #tech