Computational evaluation of exome sequence data using human and model organism phenotypes improves diagnostic efficiency
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
PURPOSE: Medical diagnosis and molecular or biochemical confirmation typically rely on the knowledge of the clinician. Although this is very difficult in extremely rare diseases, we hypothesized that the recording of patient phenotypes in Human Phenotype Ontology (HPO) terms and computationally ranking putative disease-associated sequence variants improves diagnosis, particularly for patients with atypical clinical profiles. METHODS: Using simulated exomes and the National Institutes of Health Undiagnosed Diseases Program (UDP) patient cohort and associated exome sequence, we tested our hypothesis using Exomiser. Exomiser ranks candidate variants based on patient phenotype similarity to (i) known disease-gene phenotypes, (ii) model organism phenotypes of candidate orthologs, and (iii) phenotypes of protein-protein association neighbors. RESULTS: Benchmarking showed Exomiser ranked the causal variant as the top hit in 97% of known disease-gene associations and ranked the correct seeded variant in up to 87% when detectable disease-gene associations were unavailable. Using UDP data, Exomiser ranked the causative variant(s) within the top 10 variants for 11 previously diagnosed variants and achieved a diagnosis for 4 of 23 cases undiagnosed by clinical evaluation. CONCLUSION: Structured phenotyping of patients and computational analysis are effective adjuncts for diagnosing patients with genetic disorders.Genet Med 18 6, 608-617.
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.
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 | 0.001 | 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 it