A strategy for scalable data collection of soluble protein expression in diverse hosts
Bibliographic record
Abstract
Recombinant protein expression is central to academic exploration as well as biotechnology’s advancement of human health, climate applications and the bioeconomy in general. However, not all proteins can be expressed in all organisms, and the field lacks a predictive model of soluble protein expression that could replace laborious experimental trial-and-error. This project aims to design and test an extensible experimental platform and standardized data ontology for collecting soluble recombinant protein expression data across organisms. The resulting dataset will be used in building increasingly generalizable predictive models of protein expression. In this document, we have roadmapped data collection techniques, designed experiments to assess their feasibility, and outlined a proof-of-concept pilot study that would be conducted prior to full-scale data acquisition. Here, we propose a plan of action that will establish the feasibility of gathering ML-ready soluble protein expression data in two organisms commonly-used in biomanufacturing and protein expression: Escherichia coli and Pichia pastoris. Results of the feasibility study will inform decisions about the specifics of future pilot and full-scale data acquisition. We encourage the reader to reference our review, “Can protein expression be ‘solved’?” for details on soluble protein expression. Once gathered, the dataset proposed here will adhere to FAIR principals, be publically available, and “living” – researchers can freely use it and it will continue to grow over time. Subsequent experiments (beyond those outlined in this proposal) will include examining more protein sequences and expression in different organisms (e.g. Bacillus subtilis, Aspergillus niger) to make the model more extensible.
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 | 0.019 | 0.040 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.003 |
| Bibliometrics | 0.004 | 0.006 |
| Science and technology studies | 0.002 | 0.002 |
| Scholarly communication | 0.005 | 0.007 |
| Open science | 0.004 | 0.009 |
| Research integrity | 0.002 | 0.006 |
| Insufficient payload (model declined to judge) | 0.003 | 0.005 |
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".