David Fischer
@davidsebfischer
Followers
2K
Following
828
Media
8
Statuses
367
I develop mechanistic machine learning tools for single-cell and spatial omics data to understand the regulatory patterns underlying human disease dynamics.
Cambridge, MA
Joined September 2014
Agentic AI systems are becoming available for use in science – but can we trust them?
1
2
9
kai: Notebook-based alignment of human and agentic reasoning in single-cell biology https://t.co/pLYjvX5gaP
1
2
4
kai is an assistant for single-cell biology optimized for human-agent collaboration. Like AI assistants in other domains, kai enhances human efficiency while maintaining accountability – a key advantage over fully autonomous systems in science.
1
0
1
We compared kai with one-shot analysis generation by LLMs by scoring the generated Jupyter notebooks based on various criteria. kai consistently outperforms one-shot analysis generation.
1
0
0
We tested kai on complex scenarios in single-cell biology. kai consistently completed analyses and reasoned (LLM reasoning + analysis execution) for longer than 20 minutes.
1
0
0
The output of kai’s reasoning process is this Jupyter notebook: a transparent documentation of all analyses performed and decisions made. Human scientists can inspect, modify, and give feedback on each step of the analysis.
1
0
0
kai interacts with human scientists through a chat interface in VS Code and directly edits and executes Jupyter notebooks. This design enables kai to autonomously perform analyses while maintaining full accountability.
1
0
0
This motivated us to build kai: an agentic AI that uses Jupyter notebooks – the same interface that humans use to collaborate.
1
0
0
We started by asking: how do humans build trust with each other? In collaborations, they document their reasoning in computational notebooks, e.g. Jupyter notebooks.
1
0
0
For example, how can I verify the product of 20 minutes of autonomous work by an agent without blindly hoping that it didn’t hallucinate at a key decision point at minute 5?
1
0
0
In cell biology, agentic AI systems need to reason over text, code, and analysis results. How do we ensure accountability in this complex multimodal setting to inspire trust in the predictions made by agents?
1
0
0
Our featured article: Adapting systems biology to address the complexity of human disease in the single-cell era https://t.co/gCUDoWkgqP
#Review by @davidsebfischer, @mav_tweets, @peterswinter & @shaleklab
@broadinstitute @mit @ragoninstitute
0
2
4
A shift in perspective: #systemsbiology and single-cell genomics are transforming how we study disease. Learn more in a new Nature Reviews Genetics perspective by @Schmdit_Center alum @davidsebfischer, Martin Villanueva, @peterswinter, and @shaleklab. #omics @broadinstitute
Currently, there's a lot of interest in quantitative models that would help us understand and predict features of the complex cellular systems that underlie human health and disease - think about virtual cells, for example.
1
8
13
This review is the product of a great team effort together with Martin Villanueva, Peter Winter @peterswinter and Alex Shalek @shaleklab! https://t.co/XSDaC8fyK7 &
nature.com
Nature Reviews Genetics - Differences between humans and experimental models create a translational gap that makes it difficult to extrapolate research findings. The authors review systems-focused...
0
1
4
In summary, we outline how systems biology is being adapted to the multiscale dynamics of human health and disease in omics-driven as what is effectively a two-loop cycle over discovery and validation.
1
0
1
We review strategies that can manage this distance and dissect how it relates to understanding cellular systems at specific spatiotemporal scales - e.g. the cellular scale often considered in single-cell-resolved experiments or the tissue niche scale in spatial omics experiments.
1
0
0
However, the usage of two distinct systems incurs a "translational distance" that complicates systems biology approaches that utilize information from the two.
1
0
0
We leverage that insight to describe how one can translate between discovery efforts in human tissues and validation efforts in experimental model systems. Both are needed to build quantitative models are faithful to human biology and validated through perturbation experiments.
1
0
0
In this review, we discuss how one can rationalize what information about a multiscale cellular system is actually captured by on omics study.
1
0
0