Decoding the cannabis tissue culture puzzle: Machine learning analysis of cannabis in vitro morpho-physiological disorders expands the potential for precision micropropagation
Bibliographic record
Abstract
Cannabis sativa L. (cannabis) has recently re-emerged as an economically important crop, fueling research focused on enhancing production practices to meet market demands. The developing cannabis industry can be improved by overcoming certain production hurdles using micropropagation to maintain and multiply pathogen-free plants in confined spaces at high volumes. However, developing efficient micropropagation systems for cannabis have been hampered by the prevalence of various morpho-physiological disorders, resulting in low multiplication rates, culture decline, and overall low efficiency rates. While progress in cannabis micropropagation has been made, nutrient imbalances and various disorders are still common. Successful micropropagation is species specific and dependent on a variety of interconnected factors related to abiotic conditions and nutrient availability, which represent challenges in the refinement and execution of effective methods. Micropropagation media represent the exclusive sources of macro- and micro-nutrients for cultured plant tissues, inadequacies of which can result in the emergence of morpho-physiological symptoms. This work represents the first in-depth analysis of multiple morpho-physiological disorders in micropropagated cannabis arising from media nutrient content. Additionally, we present machine learning as an effective tool for assessing nutrient-associated symptoms in cultured cannabis and identifying which components are responsible. Results will help with troubleshooting cannabis micropropagation systems to prevent or correct undesirable outcomes, while introducing new methods to assess in vitro cannabis disorders.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".