# Interested in starting a new project? Interested in AI? **URL:** \ **Category:** AWG Discussions\ **Tags:** aiml, cell, paper, read-it\ **Created:** [August 21, 2026, 6:23am UTC](https://awg.osdr.space/t/interested-in-starting-a-new-project-interested-in-ai/4501 "2026-08-21T06:23:49Z")\ **Posts on this page:** 6\ **Page:** 1
**Author:** ![rtscott2001](https://sea1.discourse-cdn.com/flex001/user_avatar/awg.osdr.space/rtscott2001/32/5_2.png) [@rtscott2001](https://awg.osdr.space/u/rtscott2001)\ **Post date:** [August 21, 2026, 6:23am UTC](https://awg.osdr.space/t/interested-in-starting-a-new-project-interested-in-ai/4501/1 "2026-08-21T06:23:49Z")
Hi [@AWGall](https://awg.osdr.space/groups/awgall) There have been a number of questions about which projects could be carried out mining the biological and/or environmental telemetry (CO2, RH, Temp, Radiation) data accessible and maximally open via OSDR-GeneLab There also is a TON of interest lately in AI/ML approaches. I urge AWGers to check out all the data, dashboard, viz & analysis tools, APIs, etc at the [About page](https://awg.osdr.space/about). Then I suggest AWG members read this recent paper ⬇ by Dupire et al 2026 on “ Fifteen challenges for generative AI applications to cell biology” — there are lots and lots of ideas on approaches to consider pursuing, and determining if these OSDR/GeneLab may be ripe to conduct a collaborative AWG investigation 🙂 ## Summary Generative AI (Gen-AI) has shown a remarkable impact in several biological research areas, from protein folding and _de novo_ design to pathogenic mutation prediction. However, it remains unclear whether these molecular-level successes can translate to cellular and multicellular insights relevant to fields ranging from immunology to cancer and neurodegeneration. This arises from the intricate nature of the molecular mechanisms that determine cellular and organismal behavior, the lack of sufficient training data, and the multicellular nature of most pathophysiologic phenotypes. Novel Gen-AI frameworks are likely needed to integrate prior biological knowledge, such as molecular interaction networks, as well as guiding principles focusing the community’s attention on solving biologically and translationally relevant problems. Drawing inspiration from Hilbert’s list of 23 mathematical problems that have focused the mathematical community’s attention for more than a century, we propose fifteen grand AI challenges to focus the biomedical community’s attention on critically relevant questions, most of which still lack effective predictive methodologies. ![image](https://us1.discourse-cdn.com/flex001/uploads/osdr/original/2X/0/09d12e0fd5542aef540a3deaaff0fad579341756.jpeg) Dupire L, Khan A, Karaletsos T, et al. **Fifteen challenges for generative AI applications to cell biology**. Cell, 2026; 0. [https://doi.org/10.1016/j.cell.2026.07.004](https://doi.org/10.1016/j.cell.2026.07.004) > **[Redirecting](https://linkinghub.elsevier.com/retrieve/pii/S0092867426008020)** ---
**Author:** ![jessicadurbano](https://sea1.discourse-cdn.com/flex001/user_avatar/awg.osdr.space/jessicadurbano/32/61_2.png) [@jessicadurbano](https://awg.osdr.space/u/jessicadurbano)\ **Post date:** [August 21, 2026, 6:36am UTC](https://awg.osdr.space/t/interested-in-starting-a-new-project-interested-in-ai/4501/2 "2026-08-21T06:36:19Z")
Thank you @rtscott2001 ---
**Author:** ![rtscott2001](https://sea1.discourse-cdn.com/flex001/user_avatar/awg.osdr.space/rtscott2001/32/5_2.png) [@rtscott2001](https://awg.osdr.space/u/rtscott2001)\ **Post date:** [August 21, 2026, 9:07am UTC](https://awg.osdr.space/t/interested-in-starting-a-new-project-interested-in-ai/4501/3 "2026-08-21T09:07:30Z")
My honor to help share key new papers and help enable the AWGs to be as fruitful as possible 🙂 Cheers and thanks for all you do @jessicadurbano ---
**Author:** ![fuganti](https://sea1.discourse-cdn.com/flex001/user_avatar/awg.osdr.space/fuganti/32/4777_2.png) [@fuganti](https://awg.osdr.space/u/fuganti)\ **Post date:** [September 17, 2026, 12:15am UTC](https://awg.osdr.space/t/interested-in-starting-a-new-project-interested-in-ai/4501/4 "2026-09-17T00:15:32Z")
Dear Ryan and AWG members, I would like to propose an initial project idea inspired by your invitation to explore AI/ML approaches using the biological and environmental telemetry available through OSDR/GeneLab. ### AI-Assisted 3D Digital Twin for Environmental Telemetry in Space Biology Experiments The idea is to develop an interactive 3D Digital Twin capable of representing an experimental space-biology environment and reproducing environmental conditions using OSDR telemetry data, initially focusing on temperature, relative humidity, CO₂, and radiation. Rather than using 3D visualization only for presentation, the Digital Twin would serve as an analytical and simulation environment. The proposed workflow would be: **OSDR environmental telemetry → time-series processing → AI/ML modeling → anomaly/pattern detection → 3D Digital Twin visualization and simulation** The first prototype could contain virtual environmental sensors positioned within a 3D experimental chamber. Historical or selected OSDR datasets could drive the virtual environment over time, allowing users to visualize how environmental conditions evolve during an experiment. An AI/ML layer could then be incorporated to identify unusual patterns, detect anomalies, model temporal behavior, and eventually predict environmental changes. A later research phase could investigate whether environmental patterns identified by the model are associated with biological responses available in OSDR/GeneLab datasets. This could potentially provide an intuitive computational environment for exploring relationships between environmental telemetry and biological experimental outcomes. The research question could initially be formulated as: **“Can an AI-assisted 3D Digital Twin reproduce, detect, and visualize anomalous environmental telemetry patterns in space-biology experiments using OSDR data?”** The project could begin as a relatively small proof of concept using only environmental telemetry and subsequently evolve toward multimodal integration with biological data. Possible components include: - interactive 3D experimental environment; - virtual temperature, humidity, CO₂, and radiation sensors; - temporal visualization of OSDR telemetry; - AI/ML-based anomaly detection; - comparison between observed and predicted environmental conditions; - simulation of alternative environmental scenarios; - explainable visualization of detected anomalies; - future integration of environmental and biological datasets. From a computational perspective, I am particularly interested in exploring the combination of Digital Twins, time-series analysis, machine learning, simulation, and interactive scientific visualization. I would be very interested in hearing whether you think this idea would fit the objectives of the OSDR AWGs and whether there are specific OSDR datasets, existing subgroups, or collaborators that would be particularly appropriate for developing such a proof of concept. If the idea is considered useful, I would be happy to prepare a more structured project proposal and an initial prototype for discussion with the group. Best regards, Lissandra Kruse Fuganti Master’s Researcher in Applied Computing Brazil ---
**Author:** ![fuganti](https://sea1.discourse-cdn.com/flex001/user_avatar/awg.osdr.space/fuganti/32/4777_2.png) [@fuganti](https://awg.osdr.space/u/fuganti)\ **Post date:** [September 17, 2026, 12:29am UTC](https://awg.osdr.space/t/interested-in-starting-a-new-project-interested-in-ai/4501/5 "2026-09-17T00:29:23Z")
Dear Ryan and AWG members, Following the discussion about potential AI/ML investigations using OSDR environmental telemetry, I developed an initial interactive proof of concept: **Orbital Cell Twin — An AI-Assisted Environmental–Cellular Digital Twin** [https://orbital-cell-twin-osdr.fuganti.chatgpt.site](https://orbital-cell-twin-osdr.fuganti.chatgpt.site/) The browser-based prototype explores how temperature, relative humidity, CO₂ concentration, and radiation could be represented within an interactive Digital Twin for space-biology experiments. The current prototype includes: - an animated virtual-cell environment; - adjustable temperature, humidity, CO₂, and radiation inputs; - baseline, heat, CO₂-spike, and radiation scenarios; - environmental telemetry visualization; - simulated cellular-stability prediction; - anomaly detection and model explanations; - a proposed workflow connecting environmental telemetry, time-series AI, cellular-response hypotheses, and future biological validation. At this stage, the data and cellular responses are explicitly synthetic and conceptual. The purpose of this first version is to demonstrate the interface, research workflow, and potential analytical role of a Digital Twin—not to make biological conclusions. A future research version could integrate selected OSDR/GeneLab datasets, document data provenance and uncertainty, compare forecasting and anomaly-detection approaches, and investigate whether environmental patterns are associated with biological responses. The initial research question is: **Can an AI-assisted 3D Digital Twin reproduce, detect, and explain anomalous environmental telemetry patterns—and support testable hypotheses about cellular response—in space-biology experiments?** I would greatly appreciate your feedback regarding whether this concept could fit the objectives of an OSDR AWG investigation, which datasets might be suitable for an initial case study, and whether an existing subgroup or potential collaborators would be interested in developing it further. Best regards, Lissandra Kruse Fuganti Master’s Researcher in Applied Computing Brazil ---
**Author:** ![rtscott2001](https://sea1.discourse-cdn.com/flex001/user_avatar/awg.osdr.space/rtscott2001/32/5_2.png) [@rtscott2001](https://awg.osdr.space/u/rtscott2001)\ **Post date:** [September 17, 2026, 12:39am UTC](https://awg.osdr.space/t/interested-in-starting-a-new-project-interested-in-ai/4501/6 "2026-09-17T00:39:08Z")
Hi Lissandra. I would slow this down a bit, and present your ideas to others in the [@AIMLawg](https://awg.osdr.space/groups/aimlawg) at their monthly meetings @james.casaletto @vaishnavi.nagesh @frank.soboczenski @lauren.sanders