Model type
Gradient-boosted-tree pipeline; this record is the paper-specific evaluated configuration.
Configuration
PMF (LASSO)
The PMF-only LASSO model is a sparse linear binding-affinity baseline in the fingerprint-scoring study.
Sources
Machine-Learning- and Knowledge-Based Scoring Functions Incorporating Ligand and Protein Fingerprints · Conclusions (paragraph 3); Methods/Machine Learning with LASSO and LightGBM (paragraph 1)How it worksEvaluated procedure (conceptual)
Conceptual input–method–output guide. Check the procedure text and linked evaluation for fitted components, additional inputs and exact settings.
Sources
Machine-Learning- and Knowledge-Based Scoring Functions Incorporating Ligand and Protein Fingerprints · Methods/Computational Details (paragraph 2); Methods/Computational Details (paragraph 4)At a glance
Biological inputs
PMF protein–ligand interaction descriptors
Sources
Machine-Learning- and Knowledge-Based Scoring Functions Incorporating Ligand and Protein Fingerprints · Methods (paragraph 1); Results and Discussion/Comparison of Binding Affinities Calculated by New Scoring Functions with Experimental Values (paragraph 2)Outputs
Predicted protein–ligand binding affinity
Sources
Machine-Learning- and Knowledge-Based Scoring Functions Incorporating Ligand and Protein Fingerprints · Introduction (paragraph 4); Results and Discussion/Comparison of Binding Affinities Calculated by New Scoring Functions with Experimental Values (paragraph 1)limited source coverage · Automated source review, 2026-09-16. All specifications and missing details
Evaluations and results
Release 2026-09-17-d277315f7d76 · 1 evaluation · 1 metric row. Different protocols are not a single leaderboard.
| Metric and finding | Coverage and uncertainty | Evidence |
|---|---|---|
| PMF (LASSO): Protein–ligand binding energy prediction Configuration: PMF (LASSO)Task: Protein–ligand binding energy predictionDataset: Fingerprint-scoring benchmark PMF-only LASSO baseline evaluated by the same authors. Author-reported evaluation · Evaluation metadata: needs review | ||
| 0.67 Pearson R Unit: unitless · Direction: unknown | Uncertainty: not reported in legacy extract Scored: Not reported · Eligible: Not reported | source checkedMachine-Learning- and Knowledge-Based Scoring Functions Incorporating Ligand and Protein Fingerprints · Table 1, PMF / LASSO row, R column Source checking is not independent reproduction. |
How it works
How the evaluated method works
LASSO regression fits binding affinities from potential-of-mean-force descriptors alone, without the ECFP and protein-fingerprint features used by the combined LightGBM configuration.
Sources
Machine-Learning- and Knowledge-Based Scoring Functions Incorporating Ligand and Protein Fingerprints · Methods/Computational Details (paragraph 2); Methods/Computational Details (paragraph 4)What was evaluated
The linked evaluation record identifies PMF (LASSO): Protein–ligand binding energy prediction. Its dataset, split, adaptation and evidence origin remain attached to the reported results.
Sources
Machine-Learning- and Knowledge-Based Scoring Functions Incorporating Ligand and Protein Fingerprints · The named evaluation’s methods and comparison table; exact preserved evaluation IDs: evaluation-lit-b3-051Strengths and limitations
Strengths and considerations
- Offers both a sparse linear control and a nonlinear tree-based model over explicitly defined chemical descriptors.
Sources
Machine-Learning- and Knowledge-Based Scoring Functions Incorporating Ligand and Protein Fingerprints · Methods/Machine Learning with LASSO and LightGBM (paragraph 2); Results and Discussion/Analysis of Descriptors Affecting the Scoring Function (paragraph 1)
Limitations and conditions
- The descriptor set and regression algorithm differ between rows; performance cannot be assigned to PMF or fingerprinting in isolation.
Sources
Machine-Learning- and Knowledge-Based Scoring Functions Incorporating Ligand and Protein Fingerprints · Results and Discussion/Analysis of Descriptors Affecting the Scoring Function (paragraph 1); Results and Discussion/Systems with Improved and Unimproved Scores (paragraph 1)
Profile review details
Primary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction.
Stable record: reported-model-8100b3de6c7811Specifications
Inputs, training, access and other details
Explanatory profile: limited source coverage · Automated source review, 2026-09-16. Review applies to the cited claims; unresolved fields are listed below. Numerical results retain their own review status.
| Property | Description and evidence |
|---|---|
| Model type | Gradient-boosted-tree pipeline; this record is the paper-specific evaluated configuration.SourcesMachine-Learning- and Knowledge-Based Scoring Functions Incorporating Ligand and Protein Fingerprints · Methods/Computational Details (paragraph 2); Methods/Computational Details (paragraph 4) |
| Architecture / procedure | LASSO regression fits binding affinities from potential-of-mean-force descriptors alone, without the ECFP and protein-fingerprint features used by the combined LightGBM configuration.SourcesMachine-Learning- and Knowledge-Based Scoring Functions Incorporating Ligand and Protein Fingerprints · Methods/Computational Details (paragraph 2); Methods/Computational Details (paragraph 4) |
| Biological inputs | PMF protein–ligand interaction descriptorsSourcesMachine-Learning- and Knowledge-Based Scoring Functions Incorporating Ligand and Protein Fingerprints · Methods (paragraph 1); Results and Discussion/Comparison of Binding Affinities Calculated by New Scoring Functions with Experimental Values (paragraph 2) |
| Outputs | Predicted protein–ligand binding affinitySourcesMachine-Learning- and Knowledge-Based Scoring Functions Incorporating Ligand and Protein Fingerprints · Introduction (paragraph 4); Results and Discussion/Comparison of Binding Affinities Calculated by New Scoring Functions with Experimental Values (paragraph 1) |
| Parameters | A sparse set of fitted linear coefficients on potential-of-mean-force descriptors; a pretrained neural parameter count is inapplicable. · Not applicableSourcesMachine-Learning- and Knowledge-Based Scoring Functions Incorporating Ligand and Protein Fingerprints · Methods/Machine Learning with LASSO and LightGBM (paragraph 2); Results and Discussion/Analysis of Descriptors Affecting the Scoring Function (paragraph 1) |
| Known versions / configuration | PMF (LASSO) is the comparison-table label; that label does not specify an immutable weight revision. · Not reported in inspected sourcesSourcesMachine-Learning- and Knowledge-Based Scoring Functions Incorporating Ligand and Protein Fingerprints · Model identification in the comparison table and corresponding Methods; immutable checkpoint revision is not supplied by the table label. |
| Training data / fitting | Of 6,271 PDBbind complexes, 4,933 are training, 1,234 are pretest for hyperparameter selection, and 104 are test. LASSO and LightGBM are fitted on interaction fingerprints.SourcesMachine-Learning- and Knowledge-Based Scoring Functions Incorporating Ligand and Protein Fingerprints · Back/Availability notes (paragraph 2); Back/Availability notes (paragraph 1) |
| Context limits | Protein–ligand interaction fingerprints from supplied complex structures; sequence-token context length is inapplicable.SourcesMachine-Learning- and Knowledge-Based Scoring Functions Incorporating Ligand and Protein Fingerprints · Methods/PMF Score (paragraph 1); Methods/Computational Details (paragraph 2) |
| Access | The paper links the public RDKit, scikit-learn and LightGBM libraries and provides hyperparameters in its Supporting Information. Additional study data are available from the authors; a complete study-specific checkpoint release is not established.SourcesMachine-Learning- and Knowledge-Based Scoring Functions Incorporating Ligand and Protein Fingerprints · Back / Notes, data and software availability |
| Code licence | No explicit code licence was established from the paper’s availability statement and inspected repository-root documentation. · Not reported in inspected sourcesSourcesMachine-Learning- and Knowledge-Based Scoring Functions Incorporating Ligand and Protein Fingerprints · Back/Availability notes (paragraph 2); Back/Availability notes (paragraph 1) |
| Weights licence | Not applicable to pretrained weights; coefficients are fitted from the study training complexes. · Not applicableSourcesMachine-Learning- and Knowledge-Based Scoring Functions Incorporating Ligand and Protein Fingerprints · Results and Discussion/Comparison of Binding Affinities Calculated by New Scoring Functions with Experimental Values (paragraph 1); Methods/Computational Details (paragraph 5) |
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.
19 evidence rows matching the loaded filters
| Property and statement | Original source and location | Review and provenance |
|---|---|---|
| Diagram caption Conceptual input–method–output guide. Check the procedure text and linked evaluation for fitted components, additional inputs and exact settings. Individual claims | Machine-Learning- and Knowledge-Based Scoring Functions Incorporating Ligand and Protein Fingerprints Methods/Computational Details (paragraph 2); Methods/Computational Details (paragraph 4) Version: PMC archival version PMC9178954.1 | source checked automated source review · 2026-09-16 Audit detailsPrimary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Diagram steps ["PMF protein–ligand interaction descriptors","PMF (LASSO)","Predicted protein–ligand binding affinity"] Individual claims | Machine-Learning- and Knowledge-Based Scoring Functions Incorporating Ligand and Protein Fingerprints Methods/Computational Details (paragraph 2); Methods/Computational Details (paragraph 4) Version: PMC archival version PMC9178954.1 | source checked automated source review · 2026-09-16 Audit detailsPrimary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Diagram title Evaluated procedure (conceptual) Individual claims | Machine-Learning- and Knowledge-Based Scoring Functions Incorporating Ligand and Protein Fingerprints Methods/Computational Details (paragraph 2); Methods/Computational Details (paragraph 4) Version: PMC archival version PMC9178954.1 | source checked automated source review · 2026-09-16 Audit detailsPrimary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Model type Gradient-boosted-tree pipeline; this record is the paper-specific evaluated configuration. Individual claims | Machine-Learning- and Knowledge-Based Scoring Functions Incorporating Ligand and Protein Fingerprints Methods/Computational Details (paragraph 2); Methods/Computational Details (paragraph 4) Version: PMC archival version PMC9178954.1 | source checked automated source review · 2026-09-16 Audit detailsPrimary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Architecture / procedure LASSO regression fits binding affinities from potential-of-mean-force descriptors alone, without the ECFP and protein-fingerprint features used by the combined LightGBM configuration. Individual claims | Machine-Learning- and Knowledge-Based Scoring Functions Incorporating Ligand and Protein Fingerprints Methods/Computational Details (paragraph 2); Methods/Computational Details (paragraph 4) Version: PMC archival version PMC9178954.1 | source checked automated source review · 2026-09-16 Audit detailsPrimary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Weights licence Not applicable to pretrained weights; coefficients are fitted from the study training complexes. Individual claims | Machine-Learning- and Knowledge-Based Scoring Functions Incorporating Ligand and Protein Fingerprints Results and Discussion/Comparison of Binding Affinities Calculated by New Scoring Functions with Experimental Values (paragraph 1); Methods/Computational Details (paragraph 5) Version: PMC archival version PMC9178954.1 | inapplicable automated source review · 2026-09-16 Audit detailsPrimary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Biological inputs PMF protein–ligand interaction descriptors Individual claims | Machine-Learning- and Knowledge-Based Scoring Functions Incorporating Ligand and Protein Fingerprints Methods (paragraph 1); Results and Discussion/Comparison of Binding Affinities Calculated by New Scoring Functions with Experimental Values (paragraph 2) Version: PMC archival version PMC9178954.1 | source checked automated source review · 2026-09-16 Audit detailsPrimary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Outputs Predicted protein–ligand binding affinity Individual claims | Machine-Learning- and Knowledge-Based Scoring Functions Incorporating Ligand and Protein Fingerprints Introduction (paragraph 4); Results and Discussion/Comparison of Binding Affinities Calculated by New Scoring Functions with Experimental Values (paragraph 1) Version: PMC archival version PMC9178954.1 | source checked automated source review · 2026-09-16 Audit detailsPrimary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Parameters A sparse set of fitted linear coefficients on potential-of-mean-force descriptors; a pretrained neural parameter count is inapplicable. Individual claims | Machine-Learning- and Knowledge-Based Scoring Functions Incorporating Ligand and Protein Fingerprints Methods/Machine Learning with LASSO and LightGBM (paragraph 2); Results and Discussion/Analysis of Descriptors Affecting the Scoring Function (paragraph 1) Version: PMC archival version PMC9178954.1 | inapplicable automated source review · 2026-09-16 Audit detailsPrimary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Known versions / configuration PMF (LASSO) is the comparison-table label; that label does not specify an immutable weight revision. Individual claims | Machine-Learning- and Knowledge-Based Scoring Functions Incorporating Ligand and Protein Fingerprints Model identification in the comparison table and corresponding Methods; immutable checkpoint revision is not supplied by the table label. Version: PMC archival version PMC9178954.1 | unreported automated source review · 2026-09-16 Audit detailsPrimary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
Sources and history
Release 2026-09-17-d277315f7d76 · Record review: needs review
1 source records and release history
- Machine-Learning- and Knowledge-Based Scoring Functions Incorporating Ligand and Protein Fingerprints · Original source · PMC archival version PMC9178954.1
Technical metadata and extraction receipts
Stable ID: reported-model-8100b3de6c7811
- areas
- molecular-interactions
- entity level
- method
- version
- Not reported
- reported name
- PMF (LASSO)
- historical missing metadata
- version: not_reported_in_legacy_extract; checkpoint revision: not_reported_in_legacy_extract; training data: not_reported_in_legacy_extract; licence: not_reported_in_legacy_extract
- metadata review scope
- historical_missing_metadata preserves the original discovery state. Current descriptive evidence and missingness are recorded in profile.facts; numerical-result review is separate.
- legacy kinds
- model
- entity classification
- review date: 2026-09-17; rationale: This source-scoped entry preserves the method/configuration actually named in an evaluation. It is neither a global family identity nor proof of an immutable checkpoint; the linked evaluation retains adaptation, fitting and scoring details.; source ids: fingerprint-scoring-2022; source locator: Methods/Computational Details (paragraph 2); Methods/Computational Details (paragraph 4) | Conclusions (paragraph 3); Methods/Machine Learning with LASSO and LightGBM (paragraph 1); ambiguities: Configuration means the source-labelled evaluated identity. It does not establish missing checkpoint hashes, default settings or equivalence to same-named records in other papers.