Required skills: All of our existing models are built for PyTorch, so experience with Python and PyTorch/Tensorflow workflows is preferred. The ability to work with datasets, such as segmenting video and generating graph visualizations is essential. An ability to build web interfaces, UI design, basic knowledge of biology, open-source practices, and applied mathematical tools will also be useful.
About: The DevoWorm group has developed an open-source Graph neural network (GNN) framework for embryogenetic data called DevoGraph. Developmental GNNs (D-GNNs) allow us to characterize a growing network that undergoes shape transformations along with increases in size. This is ultimately important for understanding formation of the connectome and the origins of embodied behavior.
Aims: For this year’s project, the successful applicant will work on extending our two outcomes from last year:
The first direction involves working with Neural Developmental Programs to build growing neural networks. This provides a means to model the function of embryogenetic networks, developing connectomes, and other growth processes
The second direction involves working with hyper graph representations, enabling multiscale modeling from a network perspective.
We aim to tie our D-GNN work into the group’s ongoing theoretical and computational work. As such, this project will require the ability to work with mathematical models and
associated algorithms. Knowledge of graph and/or network theory is helpful, but not
required.
What can I do before GSoC?
You can ask one of the mentors to direct you to the data source and you can start working on it. Please feel free to join the Openworm Slack or attend our meetings to raise questions/discussions regarding your approach to the problem.
My name is Nakshatra Piplad, I am an undergraduate student from IIT Kharagpur, and I found this project very interesting and wanted to contribute to it.
I have gone through the provided links and also submitted the form to join the OpenWorm Slack community. While I wait to be added, is there anything else I can do to get started? I am eager to begin contributing and exploring the dataset. I especially found the work around Developmental GNNs and hypergraph representations very interesting. However, I noticed that the following links didn’t open for me:
I’d love to go through these resources as well—please let me know if there are alternative links or any additional reading materials that would help me better understand the project.
To clarify, I’m not a mentor, but I wanted to let you know that the project website https://devoworm.weebly.com/ works fine for me as well. However, I can confirm that the DevoWorm.AI link isn’t working on my end either.
I’d recommend going through the project website for now, as it has plenty of useful information. Hopefully, the DevoWorm.AI link will get sorted out soon!
Feel free to reach out if you have any questions or need help getting started. Looking forward to collaborating!
You’re welcome! Here is the DevoWorm.AI Link. It’s working fine.
Regarding the right platform for discussions, I personally think that email might be a more effective way to reach out, as the mentors are professors and working professionals who may not always have time to check Neurostars frequently. Checking emails could be more feasible for them. However, this is just my personal opinion and not an official stance from any mentor, so I’d recommend being patient, as replies may take some time.
Yes, even i tried using this link, It did not work. Also, I was not able to join the slack channel to attend the meeting. If anyone has any information. Please let me know.
Hi Everyone, I’m Priyanka Gautam, a Ph.D. student at Kansas State University. My research focuses on dynamic networks, specifically using graph neural networks (GNNs) to study influence propagation and identify critical components. I explore their applications in diverse domains including infrastructure, social systems, and neuroscience. I also started working with hypergraphs, which resonates with the project’s interest in multiscale modeling. I’m excited about the potential of applying these techniques to understand growing biological networks within the DevoGraph project.
I’ve been exploring the existing DevoGraph codebase along with the previously proposed notebooks on hypergraph construction and visualization. I noticed that some approaches, like spatial threshold-based and lineage-based hypergraphs, have already been explored.
I’m curious — are these hypergraph models considered complete in their current form, or is there room to further expand or generalize them? For example, could there be other biologically meaningful ways to define hyperedges beyond spatial proximity and lineage relationships?
Additionally, I’m really intrigued by the idea of evolving graph and hypergraph structures over time. Tis question may be for you @mehul arora. Has there been any prior work or experimentation on dynamic hypergraphs within DevoGraph? If not, I’d love to understand your thoughts on potential directions for modeling the temporal evolution of cell relationships — perhaps even aligning it with neural development.
My name is Jiya Gupta, and I am an undergraduate student at IIT Kharagpur. I recently submitted my proposal for the Project Idea #4 OpenWorm DevoWorm :: DevoGraph and wanted to express my enthusiasm for the opportunity to contribute.
I’ve thoroughly enjoyed exploring the project materials and discussions, and I find the intersection of developmental biology, graph theory, and AI particularly compelling. I’ve also submitted the form to join the OpenWorm Slack community and look forward to engaging with the team there.
In the meantime, please let me know if there’s anything further I can do to prepare or if there are additional resources you would recommend reviewing. I’m eager to begin contributing and learning from the community.
Thank you for your time and consideration—I look forward to your feedback on my proposal!
