MOLGENIS/connect: a system for semi-automatic integration of heterogeneous phenotype data with applications in biobanks
Bibliographic record
Abstract
MOTIVATION: While the size and number of biobanks, patient registries and other data collections are increasing, biomedical researchers still often need to pool data for statistical power, a task that requires time-intensive retrospective integration. RESULTS: To address this challenge, we developed MOLGENIS/connect, a semi-automatic system to find, match and pool data from different sources. The system shortlists relevant source attributes from thousands of candidates using ontology-based query expansion to overcome variations in terminology. Then it generates algorithms that transform source attributes to a common target DataSchema. These include unit conversion, categorical value matching and complex conversion patterns (e.g. calculation of BMI). In comparison to human-experts, MOLGENIS/connect was able to auto-generate 27% of the algorithms perfectly, with an additional 46% needing only minor editing, representing a reduction in the human effort and expertise needed to pool data. AVAILABILITY AND IMPLEMENTATION: Source code, binaries and documentation are available as open-source under LGPLv3 from http://github.com/molgenis/molgenis and www.molgenis.org/connect CONTACT: : m.a.swertz@rug.nl SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.
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 | 0.006 | 0.019 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.005 | 0.004 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.003 | 0.003 |
| Open science | 0.003 | 0.006 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.025 | 0.010 |
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".