rewire.it
Task

FLIP THERMOSTABILITY-HUMAN: Thermostability fitness prediction, Human split

Thermostability fitness prediction, Human split. Scored with Spearman correlation on FLIP Thermostability, Human split. Trained on the split's training set with ten percent held out for validation, scored on its test set.

8 evaluations · 8 metric rows

Overview

Thermostability fitness prediction, Human split. Scored with Spearman correlation on FLIP Thermostability, Human 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.

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 THERMOSTABILITY-HUMAN: Thermostability fitness prediction, Human split

spearman (correlation) · Higher values are better for this metric.

Every method FLIP reports on Thermostability fitness prediction, Human split, scored with Spearman correlation on FLIP Thermostability, Human split.

Evaluation protocol · FLIP Thermostability, Human split (FLIP split)

  1. ESM-1b (per AA) · Configuration · Author-reported evaluation0.71
  2. ESM-1b (mean) · Configuration · Author-reported evaluation0.70
  3. ESM-1v (per AA) · Configuration · Author-reported evaluation0.77
  4. ESM-1v (mean) · Configuration · Author-reported evaluation0.75
  5. ESM-untrained (per AA) · Configuration · Author-reported evaluation0.44
  6. ESM-untrained (mean) · Configuration · Author-reported evaluation0.48
  7. Ridge · Method · Author-reported evaluation0.15
  8. CNN · Method · Author-reported evaluation0.50

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 6, column(Human)
Values, uncertainty and evidence
spearman: original source values
Tested entityPrinted valueUncertaintyEvidence
ESM-1b (per AA) · Configuration0.71 correlationNot reportedAuthor-reported evaluation · source checkedflip primary benchmark evidence · Table 6, row(ESM-1b (per AA)), column(Human)
ESM-1b (mean) · Configuration0.70 correlationNot reportedAuthor-reported evaluation · source checkedflip primary benchmark evidence · Table 6, row(ESM-1b (mean)), column(Human)
ESM-1v (per AA) · Configuration0.77 correlationNot reportedAuthor-reported evaluation · source checkedflip primary benchmark evidence · Table 6, row(ESM-1v (per AA)), column(Human)
ESM-1v (mean) · Configuration0.75 correlationNot reportedAuthor-reported evaluation · source checkedflip primary benchmark evidence · Table 6, row(ESM-1v (mean)), column(Human)
ESM-untrained (per AA) · Configuration0.44 correlationNot reportedAuthor-reported evaluation · source checkedflip primary benchmark evidence · Table 6, row(ESM-untrained (per AA)), column(Human)
ESM-untrained (mean) · Configuration0.48 correlationNot reportedAuthor-reported evaluation · source checkedflip primary benchmark evidence · Table 6, row(ESM-untrained (mean)), column(Human)
Ridge · Method0.15 correlationNot reportedAuthor-reported evaluation · source checkedflip primary benchmark evidence · Table 6, row(Ridge), column(Human)
CNN · Method0.50 correlationNot reportedAuthor-reported evaluation · source checkedflip primary benchmark evidence · Table 6, row(CNN), column(Human)
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 · 8 evaluations · 8 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.

Results grouped by the exact reported evaluation
Metric and findingCoverage and uncertaintyEvidence
CNN on FLIP THERMOSTABILITY-HUMAN: Thermostability fitness prediction, Human 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

0.50 spearman

Unit: correlation · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedflip primary benchmark evidence · Table 6, row(CNN), column(Human)

Source checking is not independent reproduction.

ESM-1b (mean) on FLIP THERMOSTABILITY-HUMAN: Thermostability fitness prediction, Human 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 6, row(ESM-1b (mean)), column(Human)

Source checking is not independent reproduction.

ESM-1b (per AA) on FLIP THERMOSTABILITY-HUMAN: Thermostability fitness prediction, Human 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 6, row(ESM-1b (per AA)), column(Human)

Source checking is not independent reproduction.

ESM-1v (mean) on FLIP THERMOSTABILITY-HUMAN: Thermostability fitness prediction, Human 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 6, row(ESM-1v (mean)), column(Human)

Source checking is not independent reproduction.

ESM-1v (per AA) on FLIP THERMOSTABILITY-HUMAN: Thermostability fitness prediction, Human 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

0.77 spearman

Unit: correlation · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedflip primary benchmark evidence · Table 6, row(ESM-1v (per AA)), column(Human)

Source checking is not independent reproduction.

ESM-untrained (mean) on FLIP THERMOSTABILITY-HUMAN: Thermostability fitness prediction, Human 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

0.48 spearman

Unit: correlation · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedflip primary benchmark evidence · Table 6, row(ESM-untrained (mean)), column(Human)

Source checking is not independent reproduction.

ESM-untrained (per AA) on FLIP THERMOSTABILITY-HUMAN: Thermostability fitness prediction, Human 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 6, row(ESM-untrained (per AA)), column(Human)

Source checking is not independent reproduction.

Ridge on FLIP THERMOSTABILITY-HUMAN: Thermostability fitness prediction, Human 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

0.15 spearman

Unit: correlation · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedflip primary benchmark evidence · Table 6, row(Ridge), column(Human)

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

Claims, original sources and review scope · Release 2026-09-17-134cd1815de8
Property and statementOriginal source and locationReview and provenance
Relationship: part of

discovery-benchmark-flip

Individual claims
flip primary benchmark evidence

Original source ↗

Table 6, column(Human)

Version: 2021 manuscript
Retrieved: 2026-09-16T21:07:13.889041+00:00

source checked

automated source review · 2026-09-18

Audit details

Primary-source transcription with no human sign-off and no independent reproduction.

Field: links:part_of:discovery-benchmark-flip

Claim: flip-association-thermostability-human

Source artifact SHA-256: afcf360c88a7a4ae153b3c2d8d4fa6d4ac0abe84f2131b94409abff6447ce363

Hash scope: Exact retrieved primary paper artifact bytes.

Inspected artifact

Sources and history

Release 2026-09-17-134cd1815de8 · Record review: source checked

1 source records and release historyDownload this release
Technical metadata and extraction receipts

Stable ID: flip-task-thermostability-human

areas
proteins-complexes
tasks
Thermostability fitness prediction, Human split
metric
Spearman correlation
metric direction
higher
dataset
FLIP Thermostability, Human split
protocol
Trained on the split's training set with ten percent held out for validation, scored on its test set.
source locator
Table 6, column(Human)
comparison panels
id: flip-panel-thermostability-human; title: FLIP THERMOSTABILITY-HUMAN: Thermostability fitness prediction, Human split; protocol id: flip-task-thermostability-human; dataset id: flip-dataset-flip-thermostability-human-split; metric: spearman; unit: correlation; direction: higher; result ids: flip-result-esm-1b-per-aa-thermostability-human-spearman; flip-result-esm-1b-mean-thermostability-human-spearman; flip-result-esm-1v-per-aa-thermostability-human-spearman; flip-result-esm-1v-mean-thermostability-human-spearman; flip-result-esm-untrained-per-aa-thermostability-human-spearman; flip-result-esm-untrained-mean-thermostability-human-spearman; flip-result-ridge-thermostability-human-spearman; flip-result-cnn-thermostability-human-spearman; source ids: expansion-p3-flip; source locator: Table 6, column(Human); context: Every method FLIP reports on Thermostability fitness prediction, Human split, scored with Spearman correlation on FLIP Thermostability, Human 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

Suggest a correction