A Machine Learning Framework Identifies Plastid-Encoded Proteins Harboring C3 and C4 Distinguishing Sequence Information
Bibliographic record
Abstract
C4 photosynthesis is known to have at least 61 independent origins across plant lineages making it one of the most notable examples of convergent evolution. Of the >60 independent origins, a predicted 22-24 origins, encompassing greater than 50% of all known C4 species, exist within the Panicoideae, Arundinoideae, Chloridoideae, Micrairoideae, Aristidoideae, and Danthonioideae (PACMAD) clade of the Poaceae family. This clade is therefore primed with species ideal for the study of genomic changes associated with the acquisition of the C4 photosynthetic trait. In this study, we take advantage of the growing availability of sequenced plastid genomes and employ a machine learning (ML) approach to screen for plastid genes harboring C3 and C4 distinguishing information in PACMAD species. We demonstrate that certain plastid-encoded protein sequences possess distinguishing and informative sequence information that allows them to train accurate ML C3/C4 classification models. Our RbcL-trained model, for example, informs a C3/C4 classifier with greater than 99% accuracy. Accurate prediction of photosynthetic type from individual sequences suggests biologically relevant, and potentially differing roles of these sequence products in C3 versus C4 metabolism. With this ML framework, we have identified several key sequences and sites that are most predictive of C3/C4 status, including RbcL, subunits of the NAD(P)H dehydrogenase complex, and specific residues within, further highlighting their potential significance in the evolution and/or maintenance of C4 photosynthetic machinery. This general approach can be applied to uncover intricate associations between other similar genotype-phenotype relationships.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
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 teacher head, 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".