@BioAI_Neuro
@BioAI_NeuralNet

@MIT trained Neuroscientist interested #Neural_Nets, #BioAI, #NeuroAI 🧠⚡🤖 substack.com/@bioai2neuro 🎯 aibio28ai@gmail.com

 Texas, United States
Joined April 2023
414 Photos and videos
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
88
587
74,243
Article

Synthetic Data for BioAI and NeuroAI: From Mechanistic Simulators to Foundation Models

Abstract Synthetic data is only as good as the model that generates it, and in biology the best generators are mechanistic simulators whose parameters mean something. Foundation models for neural

1
3
12
1,919
more replies
Fig-5
1
40
fig-6
40
@BioAI_Neuro retweeted
J Brew
@BrewNeuron
2h
🧠Great post on Neuronal modeling, with refs and code "Synthetic data will be part of every serious BioAI and NeuroAI foundation model, because real data cannot cover the space these models are asked to predict. The open question is not whether to use it but how to keep it honest.
@BioAI_Neuro
@BioAI_NeuralNet
9h
Article

Synthetic Data for BioAI and NeuroAI: From Mechanistic Simulators to Foundation Models

Abstract Synthetic data is only as good as the model that generates it, and in biology the best generators are mechanistic simulators whose parameters mean something. Foundation models for neural

1
1
3
213
@BioAI_Neuro retweeted
@BioAI_Neuro
@BioAI_NeuralNet
9h
Article

Synthetic Data for BioAI and NeuroAI: From Mechanistic Simulators to Foundation Models

Abstract Synthetic data is only as good as the model that generates it, and in biology the best generators are mechanistic simulators whose parameters mean something. Foundation models for neural

1
3
12
1,919
@BioAI_Neuro retweeted
@BioAI_Neuro
@BioAI_NeuralNet
9h
Curious about synthetic data in BioAI and NeuroAI? Simulators, virtual cells, model collapse, and one model that went from R² 0.999 to 0.15 on real neurons. Here it is 👇 nitter.net/BioAI_NeuralNet/status… #BioAI #NeuroAI #Foundationmodels
@BioAI_Neuro
@BioAI_NeuralNet
9h
Article

Synthetic Data for BioAI and NeuroAI: From Mechanistic Simulators to Foundation Models

Abstract Synthetic data is only as good as the model that generates it, and in biology the best generators are mechanistic simulators whose parameters mean something. Foundation models for neural
6
14
909
A multimodal, all-optical platform for linking cell identity to metabolic function in intact tissues nature.com/articles/s41592-0…

A multimodal, all-optical platform for linking cell identity to metabolic function in intact tissues

Nature Methods - REDCAT is a multimodal, all-optical platform that maps metabolic activity alongside cell identity in intact tissues at single-cell and subcellular resolution. By integrating Raman...

nature.com
1
2
550
ResolVI: addressing noise and bias in spatial transcriptomics nature.com/articles/s41592-0…

ResolVI: addressing noise and bias in spatial transcriptomics

Nature Methods - Segmentation and quantification of spatial transcriptomics data is plagued by specific noise and bias. ResolVI tackles this challenge by generating error- and batch-corrected...

nature.com
2
7
585
A foundation model of vision, audition, and language for in-silico neuroscience arxiv.org/abs/2605.04326 #Foundation_models, #NeuroAI, #NeuralNets
7
584
Sentience and the Origins of Consciousness: From Cartesian Duality to Markovian Monism mdpi.com/1099-4300/22/5/516
1
5
11
610
Oligodendrocytes Across the Spectrum of Central Nervous System Health and Disease
Cell@CellCellPress
Sep 24
Now online! Oligodendrocytes in central nervous system health and disease dlvr.it/TVdRRp
1
1
550
nature.com/articles/s42256-0…

Steering machine reasoning with brain signals

Nature Machine Intelligence - Representational alignment can reveal similarities between human brain activity and language models. Work now demonstrates that it can also guide learning, improving...

nature.com
3
5
508
nature.com/articles/s42256-0…

Implicit-bias-like patterns in reasoning models

Nature Machine Intelligence - Lee and Lai study bias-like processing differences in large language reasoning models and find that, for most models, processing stereotypical information takes less...

nature.com
3
3
482
nature.com/articles/s42256-0…

Causal evidence that language models use confidence to drive behaviour

Nature Machine Intelligence - Kumaran et al. show that large language models making decisions on when to answer a question or abstain from answering can be influenced by boosting or suppressing...

nature.com
2
4
482
nature.com/articles/s42256-0…

Guiding large language models to predict edit sequences for molecular synthesizability optimization

Nature Machine Intelligence - Computational drug design often generates molecules that cannot be synthesized. Li and Lai show how large language models can predict precise structural edits to fix...

nature.com
3
2
489
So cool!!
David van Dijk
@david_van_dijk
Sep 25
LLMs can play two roles in biology. Co-scientist: What experiment should we run? Simulator: What happens to a cell or tissue if we run it? At CellType, we build the latter: specialized LLMs trained on pharma's own data and run on-prem to predict biological responses.
CellType graphic comparing two uses of LLMs in biology. As a co-scientist, an LLM helps choose the next experiment. As a simulator, an LLM predicts how a cell or tissue responds to an intervention. CellType builds specialized simulators trained on partner data and run on-prem.

ALT CellType graphic comparing two uses of LLMs in biology. As a co-scientist, an LLM helps choose the next experiment. As a simulator, an LLM predicts how a cell or tissue responds to an intervention. CellType builds specialized simulators trained on partner data and run on-prem.
3
11
1,811
Load more