Scientific task · Molecular interaction

Molecular interaction and binding

Predict or analyze interactions

分子相互作用与结合

ProteinRNASmall moleculeMolecular interaction

Definition and search aliases

Permanent ID
molecular-interaction-analysis
Aliases
molecular binding
Deprecated aliases
None
Hierarchy
Parent task; benchmark coverage below includes its leaf tasks.

Coverage

8 benchmark families cover this task

suitecomplete

Biology-Instructions

A multi-omics sequence-instruction suite with 21 formal predictive tasks across DNA, RNA, protein, and multi-molecule inputs; the final paper reports task-specific held-out evaluations rather than a single aggregate score.

Antibody-antigen interactionRNA-protein interaction prediction
trackcomplete

CASP17 Immune Complexes

Dedicated CASP17 category for blind prediction of antibody-antigen, nanobody-antigen, and T-cell receptor complex structures.

Antibody-antigen interaction
datasetpartial

ProteinLMBench

A creator-curated set of 944 protein-science multiple-choice questions with answer explanations, generated from research literature and released for evaluating text LLM protein understanding.

Molecular interaction and binding
suitecomplete

ATOM3D

A living collection of eight curated 3D molecular-learning tasks spanning small molecules, protein interactions and mutations, ligand binding, and protein/RNA structure ranking.

Protein-protein interface predictionProtein-complex mutation stability predictionProtein-ligand binding affinityProtein-ligand functional efficacy prediction
competitionpartial

CASP

Biennial blind community experiments that assess macromolecular structure, complex, ligand, and model-accuracy prediction against experimental structures withheld during prediction.

Protein-ligand pose predictionProtein-ligand binding affinity
trackcomplete

CASP Protein-Ligand Prediction

Formal CASP track for blind prediction of protein-ligand binding poses, binding affinity or rank, binding pockets, and pose confidence.

Protein-ligand pose predictionProtein-ligand binding affinity
suitepartial

MoleculeNet

The original molecular-machine-learning benchmark of 17 dataset collections and more than 800 prediction endpoints spanning quantum, physicochemical, biophysical, and physiological properties.

Protein-ligand binding affinity
suitepartial

ProteinGym

Versioned deep-mutational-scanning and clinical-variant benchmarks for protein fitness prediction and design in zero-shot and supervised regimes.

Protein-ligand binding prediction
competitionpartial

CAMEO

Weekly, automated, independent, blind evaluation of registered macromolecular structure-prediction servers on complete PDB entries whose experimental structures are withheld during prediction.

Protein-ligand pose prediction
suitepartial

LAB-Bench

A practical biology-research suite of 2,457 multiple-choice questions across eight broad categories and 31 versioned task files, with public and private contamination-monitoring splits.

Protein-protein interaction prediction

Evidence-backed count claims

Each row keeps its original unit and basis. Rows with different units or overlapping mappings are never added.

BenchmarkMapped taskCoverageCountVersionEvidence
Biology-Instructions
root: bioinstruction
Antibody-antigen interaction
official-track · high
explicitly-in-scope1 tracks
Formal evaluation tracks (Antibody-Antigen Neutralization).
emnlp-2025bioinstruction-evidence-paper
Biology-Instructions Antibody-Antigen Neutralization
root: bioinstruction
Antibody-antigen interaction
official-track · high
explicitly-in-scope26902 examples
distinct examples across the published train, validation, and test splits
emnlp-2025bioinstruction-aan-evidence-paper
CASP17 Immune Complexes
root: casp
Antibody-antigen interaction
official-track · high
explicitly-in-scopeNot reported
CASP17 immune-complex targets.
CASP17
as of 2026-07-21
casp-immune-evidence-category
ProteinLMBench
root: proteinlmbench
Molecular interaction and binding
official-taxonomy · high
observedNot reported
Released ProteinLMBench question records.
hf-f139796proteinlmbench-evidence-paper
ATOM3D
root: atom3d
Protein-complex mutation stability prediction
official-track · high
explicitly-in-scope1 tasks
Curated 3D benchmark datasets.
v0.2.6
as of 2026-07-22
atom3d-paper-definition-evidence
ATOM3D
root: atom3d
Protein-ligand binding affinity
official-track · high
explicitly-in-scope1 tasks
Curated 3D benchmark datasets.
v0.2.6
as of 2026-07-22
atom3d-paper-definition-evidence
CASP
root: casp
Protein-ligand binding affinity
official-track · high
explicitly-in-scopeNot reported
CASP17 protein-ligand targets.
CASP17
as of 2026-07-21
casp-evidence-casp17-protocol
CASP Protein-Ligand Prediction
root: casp
Protein-ligand binding affinity
official-track · high
explicitly-in-scopeNot reported
CASP17 protein-ligand targets.
CASP17
as of 2026-07-21
casp-ligand-evidence-casp17
MoleculeNet
root: moleculenet
Protein-ligand binding affinity
official-taxonomy · high
explicitly-in-scope1 other
Original paper dataset collections.
original-2017moleculenet-paper-definition-evidence
LifeSciBench
root: lifescibench
Protein-ligand binding prediction
official-taxonomy · high
explicitly-in-scopeNot reported
Expert-authored benchmark tasks.
initial-releaselifescibench-evidence-taxonomy
ProteinGym
root: proteingym
Protein-ligand binding prediction
official-taxonomy · high
observedNot reported
DMS assays in the official generic Binding function category.
1.3proteingym-evidence-taxonomy
ATOM3D
root: atom3d
Protein-ligand functional efficacy prediction
official-track · high
explicitly-in-scope1 tasks
Curated 3D benchmark datasets.
v0.2.6
as of 2026-07-22
atom3d-paper-definition-evidence
CAMEO
root: cameo
Protein-ligand pose prediction
official-taxonomy · high
explicitly-in-scopeNot reported
Ligand-containing targets in the current rolling service.
current-complex-3d
as of 2026-07-21
cameo-evidence-2024-study
CASP
root: casp
Protein-ligand pose prediction
official-track · high
explicitly-in-scopeNot reported
CASP17 protein-ligand targets.
CASP17
as of 2026-07-21
casp-evidence-casp17-protocol
CASP Protein-Ligand Prediction
root: casp
Protein-ligand pose prediction
official-track · high
explicitly-in-scopeNot reported
CASP17 protein-ligand targets.
CASP17
as of 2026-07-21
casp-ligand-evidence-casp17
LAB-Bench
root: lab-bench
Protein-protein interaction prediction
official-track · high
explicitly-in-scope50 questions
Viral PPI formal-task questions.
repository-998a8e0lab-bench-evidence-paper
LAB-Bench DbQA — Viral protein–protein interactions
root: lab-bench
Protein-protein interaction prediction
official-track · high
explicitly-in-scope50 questions
questions across public and private splits
repository-998a8e0lab-bench-dbqa-viral-ppi-evidence-paper
LifeSciBench
root: lifescibench
Protein-protein interaction prediction
official-taxonomy · high
explicitly-in-scopeNot reported
Expert-authored benchmark tasks.
initial-releaselifescibench-evidence-taxonomy
ATOM3D
root: atom3d
Protein-protein interface prediction
official-track · high
explicitly-in-scope1 tasks
Curated 3D benchmark datasets.
v0.2.6
as of 2026-07-22
atom3d-paper-definition-evidence
Biology-Instructions
root: bioinstruction
RNA-protein interaction prediction
official-track · high
explicitly-in-scope1 tracks
Formal evaluation tracks (RNA-Protein Interaction Prediction).
emnlp-2025bioinstruction-evidence-paper
Biology-Instructions RNA-Protein Interaction Prediction
root: bioinstruction
RNA-protein interaction prediction
official-track · high
explicitly-in-scope20824 examples
distinct examples across the published train, validation, and test splits
emnlp-2025bioinstruction-rpi-evidence-paper

Official evaluations connected to these benchmarks

Runs are included only for benchmark records mapped here (and formal child tracks when a mapped suite is the root). A task mapping does not imply that every run isolates this task.

WorkProvider / classRelated runs
ATOM3D: Tasks On Molecules in Three DimensionsStanford University
benchmark_creator
atom3d-creator-full
Biology-Instructions: A Dataset and Benchmark for Multi-Omics Sequence Understanding Capability of Large Language ModelsShanghai Artificial Intelligence Laboratory, University of Science and Technology of China, University of Sydney, University of Toronto, Chinese University of Hong Kong, Shanghai Jiao Tong University, Fudan University, Shanghai Innovation Institute
benchmark_creator
bioinstruction-aan-closed-baselines
bioinstruction-aan-creator-systems
bioinstruction-aan-open-baselines
bioinstruction-apa-closed-baselines
bioinstruction-apa-creator-systems
bioinstruction-apa-open-baselines
bioinstruction-cpd-closed-baselines
bioinstruction-cpd-creator-systems
bioinstruction-cpd-open-baselines
bioinstruction-crispr-on-target-closed-baselines
bioinstruction-crispr-on-target-creator-systems
bioinstruction-crispr-on-target-open-baselines
bioinstruction-ea-closed-baselines
bioinstruction-ea-creator-systems
bioinstruction-ea-open-baselines
bioinstruction-ec-closed-baselines
bioinstruction-ec-creator-systems
bioinstruction-ec-open-baselines
bioinstruction-emp-closed-baselines
bioinstruction-emp-creator-systems
bioinstruction-emp-open-baselines
bioinstruction-epi-closed-baselines
bioinstruction-epi-creator-systems
bioinstruction-epi-open-baselines
bioinstruction-fluorescence-closed-baselines
bioinstruction-fluorescence-creator-systems
bioinstruction-fluorescence-open-baselines
bioinstruction-modification-closed-baselines
bioinstruction-modification-creator-systems
bioinstruction-modification-open-baselines
bioinstruction-mrl-closed-baselines
bioinstruction-mrl-creator-systems
bioinstruction-mrl-open-baselines
bioinstruction-ncrna-closed-baselines
bioinstruction-ncrna-creator-systems
bioinstruction-ncrna-open-baselines
bioinstruction-pd300-closed-baselines
bioinstruction-pd300-creator-systems
bioinstruction-pd300-open-baselines
bioinstruction-prs-closed-baselines
bioinstruction-prs-creator-systems
bioinstruction-prs-open-baselines
bioinstruction-rpi-closed-baselines
bioinstruction-rpi-creator-systems
bioinstruction-rpi-open-baselines
bioinstruction-sirna-closed-baselines
bioinstruction-sirna-creator-systems
bioinstruction-sirna-open-baselines
bioinstruction-solubility-closed-baselines
bioinstruction-solubility-creator-systems
bioinstruction-solubility-open-baselines
bioinstruction-stability-closed-baselines
bioinstruction-stability-creator-systems
bioinstruction-stability-open-baselines
bioinstruction-tb-human-closed-baselines
bioinstruction-tb-human-creator-systems
bioinstruction-tb-human-open-baselines
bioinstruction-tb-mouse-closed-baselines
bioinstruction-tb-mouse-creator-systems
bioinstruction-tb-mouse-open-baselines
bioinstruction-thermostability-closed-baselines
bioinstruction-thermostability-creator-systems
bioinstruction-thermostability-open-baselines
Beyond Single Chains: Benchmarking Macromolecular Complex Prediction Methods With the Continuous Automated Model EvaluatiOn (CAMEO)SIB Swiss Institute of Bioinformatics, Biozentrum University of Basel
benchmark_creator
cameo-2024-antibody-three-server-common
cameo-2024-ligand-baseline-common
cameo-2024-ppi-three-server-common
Assessment of Pharmaceutical Protein-Ligand Pose and Affinity Predictions in CASP16University of California San Diego, University of Basel, University of California Davis
benchmark_creator
casp16-ligand-affinity-stage1
casp16-ligand-affinity-stage2
casp16-ligand-pose-regular
CASP16 Protein Monomer Structure Prediction AssessmentUniversity of Texas Southwestern Medical Center, University of California Davis
benchmark_creator
casp16-monomer-regular-official
Assessment of Protein Complex Predictions in CASP16: Are We Making Progress?University of Texas Southwestern Medical Center, University of California Davis, Stanford University
benchmark_creator
casp16-multimer-phase1-regular
Claude Sonnet 4.5 System CardAnthropic
official_model_provider
lab-bench-cloning-scenarios-anthropic-sonnet45-system-card
lab-bench-figqa-anthropic-sonnet45-system-card
lab-bench-protocolqa-anthropic-sonnet45-system-card
lab-bench-seqqa-anthropic-sonnet45-system-card
LAB-Bench: Measuring Capabilities of Language Models for Biology ResearchFutureHouse
benchmark_creator
lab-bench-cloning-scenarios-creator-mcq
lab-bench-cloning-scenarios-creator-mcq-llama-context
lab-bench-cloning-scenarios-creator-open-response
lab-bench-dbqa-viral-ppi-creator-mcq
lab-bench-figqa-creator-mcq
lab-bench-figqa-creator-open-response
lab-bench-litqa2-creator-mcq
lab-bench-protocolqa-creator-mcq
lab-bench-protocolqa-creator-open-response
lab-bench-suppqa-creator-mcq
lab-bench-tableqa-creator-mcq
Claude Sonnet 4.6 System CardAnthropic
official_model_provider
lab-bench-figqa-crop-tool
lab-bench-figqa-no-tools
Claude for Life SciencesAnthropic
official_model_provider
lab-bench-protocolqa-anthropic
MoleculeNet: a benchmark for molecular machine learningStanford University, DeepChem
benchmark_creator
moleculenet-creator-full
ProteinGym: Large-Scale Benchmarks for Protein Fitness Prediction and DesignUniversity of Oxford, Harvard Medical School, Seismic Therapeutic, Harvard University, Centre for Genomic Regulation, Universitat Pompeu Fabra, Broad Institute
benchmark_creator
proteingym-v10-dms-substitutions-zero-shot
A Fine-tuning Dataset and Benchmark for Large Language Models for Protein UnderstandingToursun Synbio, Johns Hopkins University, University of Cambridge, Shanghai Institute for Biomedical and Pharmaceutical Technologies, Shanghai AI Laboratory, Shanghai Jiao Tong University, UNSW Sydney
benchmark_creator
proteinlmbench-creator-full