Tools & Resources
Imageomics Institute is developing open-access tools and resources for the biological community and beyond.
Democratizing science through open-source biological tools and resources represents a powerful paradigm shift in the world of scientific research. This movement champions the idea that knowledge should be freely accessible and sharable, transcending the traditional boundaries of academia. By making cutting-edge biological tools, resources, and data openly available to researchers, citizen scientists, and enthusiasts alike, we are fostering a more inclusive and collaborative scientific community. This approach empowers individuals from diverse backgrounds to actively participate in research, driving innovation and accelerating discoveries. It not only enhances scientific transparency but also holds the potential to address global challenges more effectively, from advancing biological knowledge to addressing environmental concerns. As open-source biological tools and resources continue to evolve and gain traction, they pave the way for a future where science is more accessible, equitable, and impactful for the betterment of society as a whole.
Open-Access Tools & Resources
The Imageomics Institute GitHub organization hosts the development and distribution of a collection of open-source ML tools used to study the biological information encoded in images and videos integrated with structured biological knowledge.
The Imageomics Hugging Face organization is an extension of the Institute GitHub, hosting the open-source models, datasets, and demos developed.
General-use, data exploration software for high-dimensional image data. Andromeda is a website that allows a user to perform dimensional reduction on an uploaded CSV file. To learn more visit the imageomics GitHub.
There is a lot of available data, but determining its level of usefulness (via exploratory data analysis) can be a very time-consuming process. To facilitate the exploration of new data, we developed a dashboard to visualize distribution information and samples of datasets efficiently and with no coding required.
Our current version is focused on plant and animal images (being hard-coded for information about samples from species through type of view), though images aren’t required to gather distribution statistics. We are actively working to expand the functionality for a more general audience as a way to quickly generate visuals for data or explore whether new data would be suitable for experiments without having to invest large amounts of time into EDA.
To learn more about the project, visit the GitHub Repository.