FLIP AAV-DES-MUT: AAV fitness prediction, Des-Mut split
AAV fitness prediction, Des-Mut split. Scored with Spearman correlation on FLIP AAV, Des-Mut split. Trained on the split's training set with ten percent held out for validation, scored on its test set.
Overview
AAV fitness prediction, Des-Mut split. Scored with Spearman correlation on FLIP AAV, Des-Mut split. Trained on the split's training set with ten percent held out for validation, scored on its test set.
Consult the linked sources for architecture or protocol details. Missing evidence is not evidence of a missing capability.
Evaluation design
Benchmarks bring together tasks and protocols. A task describes the biological question; a protocol defines a particular test.
Benchmarks
These source-backed links do not make different protocols or scores interchangeable.
Recorded evaluations
Each evaluation records what was tested and under which conditions.
- CNN on FLIP AAV-DES-MUT: AAV fitness prediction, Des-Mut split
- ESM-1b (mean) on FLIP AAV-DES-MUT: AAV fitness prediction, Des-Mut split
- ESM-1b (mut mean) on FLIP AAV-DES-MUT: AAV fitness prediction, Des-Mut split
- ESM-1v (mean) on FLIP AAV-DES-MUT: AAV fitness prediction, Des-Mut split
- ESM-1v (mut mean) on FLIP AAV-DES-MUT: AAV fitness prediction, Des-Mut split
- ESM-untrained (mean) on FLIP AAV-DES-MUT: AAV fitness prediction, Des-Mut split
- ESM-untrained (mut mean) on FLIP AAV-DES-MUT: AAV fitness prediction, Des-Mut split
- Levenshtein on FLIP AAV-DES-MUT: AAV fitness prediction, Des-Mut split
- Ridge on FLIP AAV-DES-MUT: AAV fitness prediction, Des-Mut split
Run instructions
No runnable recipe has been reviewed for this task. Dataset access, model requirements, licences and compute requirements must be checked against its sources before execution.
A task describes a biological question. Choose a linked protocol to obtain concrete split and scoring instructions.
Published comparisons
Explore the results reported under one evaluation protocol. Each figure keeps its source, dataset and metric together; it is not a ranking across studies. The pooled view gathers every source table that reports the same metric and names what it does not hold constant.
FLIP AAV-DES-MUT: AAV fitness prediction, Des-Mut split
spearman (correlation) · Higher values are better for this metric.
Every method FLIP reports on AAV fitness prediction, Des-Mut split, scored with Spearman correlation on FLIP AAV, Des-Mut split.
- ESM-1b (mean) · Configuration · Author-reported evaluation0.59
- ESM-1b (mut mean) · Configuration · Author-reported evaluation0.70
- ESM-1v (mean) · Configuration · Author-reported evaluation0.44
- ESM-1v (mut mean) · Configuration · Author-reported evaluation0.71
- ESM-untrained (mean) · Configuration · Author-reported evaluation0.34
- ESM-untrained (mut mean) · Configuration · Author-reported evaluation0.64
- Ridge · Method · Author-reported evaluation0.53
- CNN · Method · Author-reported evaluation0.75
- Levenshtein · Method · Author-reported evaluation-0.07
Source order is preserved. Plotted marks show point estimates; uncertainty, where reported, is retained in the printed values and table. Differences do not establish statistical significance.
flip primary benchmark evidence · Table 5, column(Des-Mut)Values, uncertainty and evidence
| Tested entity | Printed value | Uncertainty | Evidence |
|---|---|---|---|
| ESM-1b (mean) · Configuration | 0.59 correlation | Not reported | Author-reported evaluation · source checkedflip primary benchmark evidence · Table 5, row(ESM-1b (mean)), column(Des-Mut) |
| ESM-1b (mut mean) · Configuration | 0.70 correlation | Not reported | Author-reported evaluation · source checkedflip primary benchmark evidence · Table 5, row(ESM-1b (mut mean)), column(Des-Mut) |
| ESM-1v (mean) · Configuration | 0.44 correlation | Not reported | Author-reported evaluation · source checkedflip primary benchmark evidence · Table 5, row(ESM-1v (mean)), column(Des-Mut) |
| ESM-1v (mut mean) · Configuration | 0.71 correlation | Not reported | Author-reported evaluation · source checkedflip primary benchmark evidence · Table 5, row(ESM-1v (mut mean)), column(Des-Mut) |
| ESM-untrained (mean) · Configuration | 0.34 correlation | Not reported | Author-reported evaluation · source checkedflip primary benchmark evidence · Table 5, row(ESM-untrained (mean)), column(Des-Mut) |
| ESM-untrained (mut mean) · Configuration | 0.64 correlation | Not reported | Author-reported evaluation · source checkedflip primary benchmark evidence · Table 5, row(ESM-untrained (mut mean)), column(Des-Mut) |
| Ridge · Method | 0.53 correlation | Not reported | Author-reported evaluation · source checkedflip primary benchmark evidence · Table 5, row(Ridge), column(Des-Mut) |
| CNN · Method | 0.75 correlation | Not reported | Author-reported evaluation · source checkedflip primary benchmark evidence · Table 5, row(CNN), column(Des-Mut) |
| Levenshtein · Method | -0.07 correlation | Not reported | Author-reported evaluation · source checkedflip primary benchmark evidence · Table 5, row(Levenshtein), column(Des-Mut) |
Scope and limitations
- Author-reported numbers, source checked but not independently reproduced.
- The split is the task here. Figures from different splits of the same landscape are not comparable.
- The random sampled splits in Table 7 are the authors' own illustration of an optimistic evaluation, not a headline result.
- NA marks a baseline that cannot be applied to that landscape, and is recorded as no result rather than as a zero.
Source transcription and grouping reviewed by automated source review on 2026-09-18. These experiments were not independently reproduced by rewire.
Tested entities and results
Release 2026-09-17-134cd1815de8 · 9 evaluations · 9 metric rows. Different protocols are not a single leaderboard. Where several source tables report the same metric, the published comparisons above offer a pooled view that names what it does not hold constant.
| Metric and finding | Coverage and uncertainty | Evidence |
|---|---|---|
| CNN on FLIP AAV-DES-MUT: AAV fitness prediction, Des-Mut split Method: CNNTask: FLIP AAV-DES-MUT: AAV fitness prediction, Des-Mut splitDataset subset: FLIP AAV, Des-Mut split (FLIP split) Trained on the split's training set with ten percent held out for validation, scored on its test set. Author-reported evaluation · Evaluation metadata: source checked | ||
| 0.75 spearman Unit: correlation · Direction: higher | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedflip primary benchmark evidence · Table 5, row(CNN), column(Des-Mut) Source checking is not independent reproduction. |
| ESM-1b (mean) on FLIP AAV-DES-MUT: AAV fitness prediction, Des-Mut split Configuration: ESM-1b (mean)Task: FLIP AAV-DES-MUT: AAV fitness prediction, Des-Mut splitDataset subset: FLIP AAV, Des-Mut split (FLIP split) Trained on the split's training set with ten percent held out for validation, scored on its test set. Author-reported evaluation · Evaluation metadata: source checked | ||
| 0.59 spearman Unit: correlation · Direction: higher | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedflip primary benchmark evidence · Table 5, row(ESM-1b (mean)), column(Des-Mut) Source checking is not independent reproduction. |
| ESM-1b (mut mean) on FLIP AAV-DES-MUT: AAV fitness prediction, Des-Mut split Configuration: ESM-1b (mut mean)Task: FLIP AAV-DES-MUT: AAV fitness prediction, Des-Mut splitDataset subset: FLIP AAV, Des-Mut split (FLIP split) Trained on the split's training set with ten percent held out for validation, scored on its test set. Author-reported evaluation · Evaluation metadata: source checked | ||
| 0.70 spearman Unit: correlation · Direction: higher | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedflip primary benchmark evidence · Table 5, row(ESM-1b (mut mean)), column(Des-Mut) Source checking is not independent reproduction. |
| ESM-1v (mean) on FLIP AAV-DES-MUT: AAV fitness prediction, Des-Mut split Configuration: ESM-1v (mean)Task: FLIP AAV-DES-MUT: AAV fitness prediction, Des-Mut splitDataset subset: FLIP AAV, Des-Mut split (FLIP split) Trained on the split's training set with ten percent held out for validation, scored on its test set. Author-reported evaluation · Evaluation metadata: source checked | ||
| 0.44 spearman Unit: correlation · Direction: higher | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedflip primary benchmark evidence · Table 5, row(ESM-1v (mean)), column(Des-Mut) Source checking is not independent reproduction. |
| ESM-1v (mut mean) on FLIP AAV-DES-MUT: AAV fitness prediction, Des-Mut split Configuration: ESM-1v (mut mean)Task: FLIP AAV-DES-MUT: AAV fitness prediction, Des-Mut splitDataset subset: FLIP AAV, Des-Mut split (FLIP split) Trained on the split's training set with ten percent held out for validation, scored on its test set. Author-reported evaluation · Evaluation metadata: source checked | ||
| 0.71 spearman Unit: correlation · Direction: higher | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedflip primary benchmark evidence · Table 5, row(ESM-1v (mut mean)), column(Des-Mut) Source checking is not independent reproduction. |
| ESM-untrained (mean) on FLIP AAV-DES-MUT: AAV fitness prediction, Des-Mut split Configuration: ESM-untrained (mean)Task: FLIP AAV-DES-MUT: AAV fitness prediction, Des-Mut splitDataset subset: FLIP AAV, Des-Mut split (FLIP split) Trained on the split's training set with ten percent held out for validation, scored on its test set. Author-reported evaluation · Evaluation metadata: source checked | ||
| 0.34 spearman Unit: correlation · Direction: higher | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedflip primary benchmark evidence · Table 5, row(ESM-untrained (mean)), column(Des-Mut) Source checking is not independent reproduction. |
| ESM-untrained (mut mean) on FLIP AAV-DES-MUT: AAV fitness prediction, Des-Mut split Configuration: ESM-untrained (mut mean)Task: FLIP AAV-DES-MUT: AAV fitness prediction, Des-Mut splitDataset subset: FLIP AAV, Des-Mut split (FLIP split) Trained on the split's training set with ten percent held out for validation, scored on its test set. Author-reported evaluation · Evaluation metadata: source checked | ||
| 0.64 spearman Unit: correlation · Direction: higher | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedflip primary benchmark evidence · Table 5, row(ESM-untrained (mut mean)), column(Des-Mut) Source checking is not independent reproduction. |
| Levenshtein on FLIP AAV-DES-MUT: AAV fitness prediction, Des-Mut split Method: LevenshteinTask: FLIP AAV-DES-MUT: AAV fitness prediction, Des-Mut splitDataset subset: FLIP AAV, Des-Mut split (FLIP split) Trained on the split's training set with ten percent held out for validation, scored on its test set. Author-reported evaluation · Evaluation metadata: source checked | ||
| -0.07 spearman Unit: correlation · Direction: higher | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedflip primary benchmark evidence · Table 5, row(Levenshtein), column(Des-Mut) Source checking is not independent reproduction. |
| Ridge on FLIP AAV-DES-MUT: AAV fitness prediction, Des-Mut split Method: RidgeTask: FLIP AAV-DES-MUT: AAV fitness prediction, Des-Mut splitDataset subset: FLIP AAV, Des-Mut split (FLIP split) Trained on the split's training set with ten percent held out for validation, scored on its test set. Author-reported evaluation · Evaluation metadata: source checked | ||
| 0.53 spearman Unit: correlation · Direction: higher | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedflip primary benchmark evidence · Table 5, row(Ridge), column(Des-Mut) Source checking is not independent reproduction. |
Evidence table
Inspect claims, sources and review details
Trace each statement to its source and review. A context-only reference supports the record generally; it does not verify an individual field. Source checking does not reproduce an experiment.
One row per statement and cited source. Multiple citations are not independent evaluations. Shared locators are labelled explicitly.
1 evidence row matching the loaded filters
| Property and statement | Original source and location | Review and provenance |
|---|---|---|
| Relationship: part of discovery-benchmark-flip Individual claims | flip primary benchmark evidence Table 5, column(Des-Mut) Version: 2021 manuscript | source checked automated source review · 2026-09-18 Audit detailsPrimary-source transcription with no human sign-off and no independent reproduction. Field: Claim: flip-association-aav-des-mut Source artifact SHA-256: Hash scope: Exact retrieved primary paper artifact bytes. |
Sources and history
Release 2026-09-17-134cd1815de8 · Record review: source checked
1 source records and release history
- flip primary benchmark evidence · Original source · 2021 manuscript
Technical metadata and extraction receipts
Stable ID: flip-task-aav-des-mut
- areas
- proteins-complexes
- tasks
- AAV fitness prediction, Des-Mut split
- metric
- Spearman correlation
- metric direction
- higher
- dataset
- FLIP AAV, Des-Mut split
- protocol
- Trained on the split's training set with ten percent held out for validation, scored on its test set.
- source locator
- Table 5, column(Des-Mut)
- comparison panels
- id: flip-panel-aav-des-mut; title: FLIP AAV-DES-MUT: AAV fitness prediction, Des-Mut split; protocol id: flip-task-aav-des-mut; dataset id: flip-dataset-flip-aav-des-mut-split; metric: spearman; unit: correlation; direction: higher; result ids: flip-result-esm-1b-mean-aav-des-mut-spearman; flip-result-esm-1b-mut-mean-aav-des-mut-spearman; flip-result-esm-1v-mean-aav-des-mut-spearman; flip-result-esm-1v-mut-mean-aav-des-mut-spearman; flip-result-esm-untrained-mean-aav-des-mut-spearman; flip-result-esm-untrained-mut-mean-aav-des-mut-spearman; flip-result-ridge-aav-des-mut-spearman; flip-result-cnn-aav-des-mut-spearman; flip-result-levenshtein-aav-des-mut-spearman; source ids: expansion-p3-flip; source locator: Table 5, column(Des-Mut); context: Every method FLIP reports on AAV fitness prediction, Des-Mut split, scored with Spearman correlation on FLIP AAV, Des-Mut split.; caveats: Author-reported numbers, source checked but not independently reproduced.; The split is the task here. Figures from different splits of the same landscape are not comparable.; The random sampled splits in Table 7 are the authors' own illustration of an optimistic evaluation, not a headline result.; NA marks a baseline that cannot be applied to that landscape, and is recorded as no result rather than as a zero.; review: method: automated_source_review; date: 2026-09-18
Related records
- part of: FLIP
- subject: FLIP AAV-DES-MUT: part of discovery-benchmark-flip
- benchmark: CNN on FLIP AAV-DES-MUT: AAV fitness prediction, Des-Mut split
- benchmark: ESM-1b (mean) on FLIP AAV-DES-MUT: AAV fitness prediction, Des-Mut split
- benchmark: ESM-1b (mut mean) on FLIP AAV-DES-MUT: AAV fitness prediction, Des-Mut split
- benchmark: ESM-1v (mean) on FLIP AAV-DES-MUT: AAV fitness prediction, Des-Mut split
- benchmark: ESM-1v (mut mean) on FLIP AAV-DES-MUT: AAV fitness prediction, Des-Mut split
- benchmark: ESM-untrained (mean) on FLIP AAV-DES-MUT: AAV fitness prediction, Des-Mut split
- benchmark: ESM-untrained (mut mean) on FLIP AAV-DES-MUT: AAV fitness prediction, Des-Mut split
- benchmark: Levenshtein on FLIP AAV-DES-MUT: AAV fitness prediction, Des-Mut split
- benchmark: Ridge on FLIP AAV-DES-MUT: AAV fitness prediction, Des-Mut split