A path towards AI-scale, interoperable biological data
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912642344419328 |
|---|---|
| author | Aevermann, Brian Califano, Andrea Chiu, Chi-Li Clack, Nathan Clemons Jr., William M. D'Orazi, Jonah Cool Florence D. DeRisi, Joseph L. Elias, Joshua E. Fahsbender, Elizabeth Fraser, Scott E. Gonzalez, Carlos G. Haury, Matthias Karaletsos, Theofanis Kelley, Shana O. Khan, Aly A. Lowe, Alan R. Lundberg, Emma McClure, Ryan A. Otte, Stephani Paull, Evan O. Royer, Loïc A. Sadgat, Dana Schmid, Sandra L. Scovanner, Samantha Stolitzka, Cathy Swedlow, Jason R. Wong, Joan Yeretssian, Garabet Brennan, Patricia Carr, Ambrose J. |
| author_facet | Aevermann, Brian Califano, Andrea Chiu, Chi-Li Clack, Nathan Clemons Jr., William M. D'Orazi, Jonah Cool Florence D. DeRisi, Joseph L. Elias, Joshua E. Fahsbender, Elizabeth Fraser, Scott E. Gonzalez, Carlos G. Haury, Matthias Karaletsos, Theofanis Kelley, Shana O. Khan, Aly A. Lowe, Alan R. Lundberg, Emma McClure, Ryan A. Otte, Stephani Paull, Evan O. Royer, Loïc A. Sadgat, Dana Schmid, Sandra L. Scovanner, Samantha Stolitzka, Cathy Swedlow, Jason R. Wong, Joan Yeretssian, Garabet Brennan, Patricia Carr, Ambrose J. |
| contents | Biology is at the precipice of a new era where AI accelerates and amplifies the ability to study how cells operate, organize, and work as systems, revealing why disease happens and how to correct it. Organizations globally are prioritizing AI to accelerate basic research, drug discovery, personalized medicine, and synthetic biology. However, despite these opportunities, scientific data have proven a bottleneck, and progress has been slow and fragmented. Unless the scientific community takes a technology-led, community-focused approach to scaling and harnessing data, we will fail to capture this opportunity to drive new insights and biological discovery. The data bottleneck presents a unique paradox. It is increasingly simple to generate huge data volumes, thanks to expanding imaging datasets and plummeting sequencing costs, but scientists lack standards and tooling for large biological datasets, preventing integration into a multimodal foundational dataset that unlocks generalizable models of cellular and tissue function. This contradiction highlights two interrelated problems: abundant data that's difficult to manage, and a lack of data resources with necessary quality and utility to realize AI's potential in biology. Science must forge a collective approach enabling distributed contributions to combine into cohesive, powerful datasets transcending individual purposes. Here, we present a technological and data generation roadmap for scaling scientific impact. We outline AI's opportunity, mechanisms to scale data generation, the need for multi-modal measurements, and means to pool resources, standardize approaches, and collectively build the foundation enabling AI's full potential in biological discovery. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_09757 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A path towards AI-scale, interoperable biological data Aevermann, Brian Califano, Andrea Chiu, Chi-Li Clack, Nathan Clemons Jr., William M. D'Orazi, Jonah Cool Florence D. DeRisi, Joseph L. Elias, Joshua E. Fahsbender, Elizabeth Fraser, Scott E. Gonzalez, Carlos G. Haury, Matthias Karaletsos, Theofanis Kelley, Shana O. Khan, Aly A. Lowe, Alan R. Lundberg, Emma McClure, Ryan A. Otte, Stephani Paull, Evan O. Royer, Loïc A. Sadgat, Dana Schmid, Sandra L. Scovanner, Samantha Stolitzka, Cathy Swedlow, Jason R. Wong, Joan Yeretssian, Garabet Brennan, Patricia Carr, Ambrose J. Other Quantitative Biology Biology is at the precipice of a new era where AI accelerates and amplifies the ability to study how cells operate, organize, and work as systems, revealing why disease happens and how to correct it. Organizations globally are prioritizing AI to accelerate basic research, drug discovery, personalized medicine, and synthetic biology. However, despite these opportunities, scientific data have proven a bottleneck, and progress has been slow and fragmented. Unless the scientific community takes a technology-led, community-focused approach to scaling and harnessing data, we will fail to capture this opportunity to drive new insights and biological discovery. The data bottleneck presents a unique paradox. It is increasingly simple to generate huge data volumes, thanks to expanding imaging datasets and plummeting sequencing costs, but scientists lack standards and tooling for large biological datasets, preventing integration into a multimodal foundational dataset that unlocks generalizable models of cellular and tissue function. This contradiction highlights two interrelated problems: abundant data that's difficult to manage, and a lack of data resources with necessary quality and utility to realize AI's potential in biology. Science must forge a collective approach enabling distributed contributions to combine into cohesive, powerful datasets transcending individual purposes. Here, we present a technological and data generation roadmap for scaling scientific impact. We outline AI's opportunity, mechanisms to scale data generation, the need for multi-modal measurements, and means to pool resources, standardize approaches, and collectively build the foundation enabling AI's full potential in biological discovery. |
| title | A path towards AI-scale, interoperable biological data |
| topic | Other Quantitative Biology |
| url | https://arxiv.org/abs/2510.09757 |