# Screen, dock, and rank small molecules

Prepare the target, screen your library, dock with several methods, and flag ADMET risk before you order compounds.

[Try it free](https://proteiniq.io/app/workflows/templates?template=structure-based-virtual-screening)[Browse tools](https://proteiniq.io/use-cases/molecular-docking)

![EGFR kinase with gefitinib, a GNINA result on ProteinIQ](https://proteiniq.io/_next/image?url=%2Fimages%2Fsolutions%2Fheroes%2Fsmall-molecule.webp&w=1920&q=75&dpl=dpl_J8tu6aF3F41kEvMFgYtuMXes1ynJ)

1. ## Target and library preparation

   Repair the target, identify plausible pockets, review protonation, and standardize ligand structures before screening.

   [![PDBFixer](https://proteiniq.io/_next/image?url=%2Fimages%2Ftools%2Fpdb-fixer-featured.webp&w=96&q=75&dpl=dpl_J8tu6aF3F41kEvMFgYtuMXes1ynJ) ### PDBFixer Fix PDB and mmCIF structures by adding missing atoms, residues, hydrogens, and solvent.](https://proteiniq.io/app/pdb-fixer)[![fpocket](https://proteiniq.io/_next/image?url=%2Fimages%2Ftools%2Ffpocket.webp&w=96&q=75&dpl=dpl_J8tu6aF3F41kEvMFgYtuMXes1ynJ) ### fpocket Identify protein pockets and ligand binding sites with druggability scores.](https://proteiniq.io/app/fpocket)[![PROPKA 3](https://proteiniq.io/_next/image?url=%2Fimages%2Ftools%2Fpropka-3.webp&w=96&q=75&dpl=dpl_J8tu6aF3F41kEvMFgYtuMXes1ynJ) ### PROPKA 3 Predict pKa values of ionizable groups in proteins based on 3D structure.](https://proteiniq.io/app/propka)[![Ligand fixer](https://proteiniq.io/_next/image?url=%2Fimages%2Ftools%2Fligand-fixer.webp&w=96&q=75&dpl=dpl_J8tu6aF3F41kEvMFgYtuMXes1ynJ) ### Ligand fixer Repair SDF, MOL, and MOL2 ligands for RDKit, Meeko, and docking preparation workflows.](https://proteiniq.io/app/ligand-fixer)[![SMILES to SDF](https://proteiniq.io/_next/image?url=%2Fimages%2Ftools%2Fsmiles-to-sdf.webp&w=96&q=75&dpl=dpl_J8tu6aF3F41kEvMFgYtuMXes1ynJ) ### SMILES to SDF Generate 3D SDF files from SMILES strings with batch conversion and downloadable combined outputs.](https://proteiniq.io/app/smiles-to-sdf)
2. ## Generation and early filtering

   Generate candidates from the pocket or purchasable chemical space, rank a library against the target, and remove compounds with unsuitable properties or structural liabilities.

   [![GenMol](https://proteiniq.io/_next/image?url=%2Fimages%2Ftools%2Fgenmol.webp&w=96&q=75&dpl=dpl_J8tu6aF3F41kEvMFgYtuMXes1ynJ) ### GenMol Generate novel drug-like molecules using NVIDIA's discrete diffusion AI model.](https://proteiniq.io/app/genmol)[![BoltzMol-1](https://proteiniq.io/_next/image?url=%2Fimages%2Ftools%2Fboltzmol-1.webp&w=96&q=75&dpl=dpl_J8tu6aF3F41kEvMFgYtuMXes1ynJ) ### BoltzMol-1 Small-molecule design against a protein target from purchasable chemical space.](https://proteiniq.io/app/boltzmol-1)[![Boltz Small Molecule Screen](https://proteiniq.io/_next/image?url=%2Fimages%2Ftools%2Fboltz-small-molecule-screen.webp&w=96&q=75&dpl=dpl_J8tu6aF3F41kEvMFgYtuMXes1ynJ) ### Boltz Small Molecule Screen Rank your SMILES library against a protein target.](https://proteiniq.io/app/boltz-small-molecule-screen)[![Lipinski's rule of 5](https://proteiniq.io/_next/image?url=%2Fimages%2Ftools%2Flipinskis-rule-of-5.webp&w=96&q=75&dpl=dpl_J8tu6aF3F41kEvMFgYtuMXes1ynJ) ### Lipinski's rule of 5 Screen compounds for oral bioavailability using molecular weight, LogP, hydrogen bond donor, and acceptor limits.](https://proteiniq.io/app/lipinskis-rule-of-5)[![PAINS filter](https://proteiniq.io/_next/image?url=%2Fimages%2Ftools%2Fpains-filter.webp&w=96&q=75&dpl=dpl_J8tu6aF3F41kEvMFgYtuMXes1ynJ) ### PAINS filter Screen compounds for Pan-Assay Interference patterns using PAINS_A, PAINS_B, and PAINS_C filters.](https://proteiniq.io/app/pains-filter)[![Lead-likeness filter](https://proteiniq.io/_next/image?url=%2Fimages%2Ftools%2Flead-likeness-filter.webp&w=96&q=75&dpl=dpl_J8tu6aF3F41kEvMFgYtuMXes1ynJ) ### Lead-likeness filter Screen for lead-like compounds using stricter molecular descriptor criteria for early optimization.](https://proteiniq.io/app/lead-likeness-filter)
3. ## Docking and pose review

   Use complementary docking methods, preserve their native scores, profile the contacts each pose makes, and check whether proposed complexes are physically plausible.

   [![GNINA](https://proteiniq.io/_next/image?url=%2Fimages%2Ftools%2Fgnina.webp&w=96&q=75&dpl=dpl_J8tu6aF3F41kEvMFgYtuMXes1ynJ) ### GNINA Dock small molecules into proteins using CNN scoring and physics-based pose optimization.](https://proteiniq.io/app/gnina)[![AutoDock Vina](https://proteiniq.io/_next/image?url=%2Fimages%2Ftools%2Fautodock-vina-announcement.webp&w=96&q=75&dpl=dpl_J8tu6aF3F41kEvMFgYtuMXes1ynJ) ### AutoDock Vina Dock ligands into protein structures and estimate binding modes, poses, and affinity scores.](https://proteiniq.io/app/autodock-vina)[![SMINA](https://proteiniq.io/_next/image?url=%2Fimages%2Ftools%2Fsmina.webp&w=96&q=75&dpl=dpl_J8tu6aF3F41kEvMFgYtuMXes1ynJ) ### SMINA Enhanced molecular docking with custom scoring functions and fast minimization](https://proteiniq.io/app/smina)[![DiffDock-L](https://proteiniq.io/_next/image?url=%2Fimages%2Ftools%2Fdiffdock-featured-image.webp&w=96&q=75&dpl=dpl_J8tu6aF3F41kEvMFgYtuMXes1ynJ) ### DiffDock-L Predict protein-ligand binding poses and confidence scores without a predefined binding site.](https://proteiniq.io/app/diff-dock)[![PLIP](https://proteiniq.io/_next/image?url=%2Fimages%2Ftools%2Fplip.webp&w=96&q=75&dpl=dpl_J8tu6aF3F41kEvMFgYtuMXes1ynJ) ### PLIP Profile protein-ligand interactions from a PDB complex structure.](https://proteiniq.io/app/plip)[![PoseBusters](https://proteiniq.io/_next/image?url=%2Fimages%2Ftools%2Fposebusters.webp&w=96&q=75&dpl=dpl_J8tu6aF3F41kEvMFgYtuMXes1ynJ) ### PoseBusters Validate generated and docked ligand poses with structure, chemistry, and reference-pose checks.](https://proteiniq.io/app/posebusters)
4. ## ADMET and lead refinement

   Review pharmacokinetic and toxicity risk, then apply simulation or free-energy methods to the smaller set that survives triage.

   [![ADMET-AI](https://proteiniq.io/_next/image?url=%2Fimages%2Ftools%2Fadmet-ai.webp&w=96&q=75&dpl=dpl_J8tu6aF3F41kEvMFgYtuMXes1ynJ) ### ADMET-AI Predict absorption, distribution, metabolism, excretion, and toxicity properties for compound libraries.](https://proteiniq.io/app/admet-ai)[![Boltz ADME](https://proteiniq.io/_next/image?url=%2Fimages%2Ftools%2Fboltz-adme.webp&w=96&q=75&dpl=dpl_J8tu6aF3F41kEvMFgYtuMXes1ynJ) ### Boltz ADME LogD, permeability and solubility predictions for small molecules.](https://proteiniq.io/app/boltz-adme)[![Structural alert screening](https://proteiniq.io/_next/image?url=%2Fimages%2Ftools%2Ftoxicity-prediction.webp&w=96&q=75&dpl=dpl_J8tu6aF3F41kEvMFgYtuMXes1ynJ) ### Structural alert screening Screen compounds for structural toxicity alerts using PAINS filters, BRENK filters, and NIH filters for safer drug discovery.](https://proteiniq.io/app/toxicity-prediction)[![OpenMM](https://proteiniq.io/_next/image?url=%2Fimages%2Ftools%2Fopenmm.webp&w=96&q=75&dpl=dpl_J8tu6aF3F41kEvMFgYtuMXes1ynJ) ### OpenMM Molecular dynamics, minimization, and energy calculations with classical or ML potentials](https://proteiniq.io/app/openmm)[![gmx_MMPBSA](https://proteiniq.io/_next/image?url=%2Fimages%2Ftools%2Fgmx-mmpbsa.webp&w=96&q=75&dpl=dpl_J8tu6aF3F41kEvMFgYtuMXes1ynJ) ### gmx_MMPBSA Calculate binding free energies with MM/PBSA and MM/GBSA](https://proteiniq.io/app/gmx-mmpbsa)

## Small-molecule use cases

Pick the method that fits your question and evidence. Each one comes with a workflow you can open and edit.

[See all use cases](https://proteiniq.io/use-cases)

- [Virtual screening Rank a compound library against your target online with docking and similarity tools, check the poses and ADMET predictions, and export a shortlist for testing. See workflow](https://proteiniq.io/use-cases/virtual-screening)
- [High-throughput virtual screening Prepare and partition a large compound library, apply staged filters, run reproducible batches, and aggregate ranked results without losing failures or method settings. See workflow](https://proteiniq.io/use-cases/high-throughput-virtual-screening)
- [Structure-based virtual screening Prepare a target structure, review a compound library, generate ranked poses with GNINA, and inspect pose-quality and ADMET results in one editable workflow. See workflow](https://proteiniq.io/use-cases/structure-based-virtual-screening)
- [Ligand-based virtual screening Compare a compound library with known active ligands using molecular descriptors, fingerprints, pharmacophores, or learned features, then review and export a traceable shortlist. See workflow](https://proteiniq.io/use-cases/ligand-based-virtual-screening)
- [Pharmacophore-based virtual screening Define a three-dimensional interaction-feature model, prepare candidate conformers, rank feature matches, and review a chemically diverse shortlist. See workflow](https://proteiniq.io/use-cases/pharmacophore-based-virtual-screening)
- [Molecular docking Dock a ligand into a protein online with AutoDock Vina, GNINA or DiffDock-L, or dock two proteins with LightDock, then check every pose before you trust its score. See workflow](https://proteiniq.io/use-cases/molecular-docking)
- [Blind docking Search broadly across a prepared protein when the ligand-binding site is unknown or poorly characterized. See workflow](https://proteiniq.io/use-cases/blind-docking)
- [AI molecular docking Use AI docking models to generate protein–ligand poses, compare their confidence, and check whether the predicted structures are chemically plausible. See workflow](https://proteiniq.io/use-cases/ai-molecular-docking)

## Guides for small-molecule work

Background guides on the methods, scores, and numbers behind these workflows.

[See all guides](https://proteiniq.io/guides)

- [![Small molecule in a protein pocket with dotted contacts and a magnified contact detail.](https://proteiniq.io/_next/image?url=%2Fimages%2Fguides%2Fvina-score%2Ffeatured.webp&w=1920&q=75&dpl=dpl_J8tu6aF3F41kEvMFgYtuMXes1ynJ) Docking · October 11, 2026 ### What is a Vina score, and what counts as good The AutoDock Vina score is a docking score in kcal/mol, not a measured binding energy. Learn what the output columns mean, why there is no universal good score, and how far Vina tracks experimental affinity.](https://proteiniq.io/guides/vina-score)
- [![Superimposed protein folds with dotted connectors showing differences at corresponding positions.](https://proteiniq.io/_next/image?url=%2Fimages%2Fguides%2Frmsd%2Ffeatured.webp&w=1920&q=75&dpl=dpl_J8tu6aF3F41kEvMFgYtuMXes1ynJ) Structures · October 11, 2026 ### What is RMSD, and what counts as a good value RMSD is the average distance between matched atoms of two structures, in ångströms. Learn the formula, when to superimpose, and what values count as good for proteins, docked poses and molecular dynamics.](https://proteiniq.io/guides/rmsd)
- [![Capsule, antibody, and DNA illustrations representing different drug discovery approaches.](https://proteiniq.io/_next/image?url=%2Fimages%2Fguides%2Fdrug-discovery-statistics%2Ffeatured.webp&w=1920&q=75&dpl=dpl_J8tu6aF3F41kEvMFgYtuMXes1ynJ) Drugs · July 30, 2026 ### Drug discovery statistics [2026] Current drug discovery statistics on FDA novel drug approvals, clinical success rates, development cost, biosimilars, cell and gene therapies, AAV products, and CRISPR trials.](https://proteiniq.io/guides/drug-discovery-statistics)
- [![DNA, a folded protein, and a small ligand beside its binding pocket.](https://proteiniq.io/_next/image?url=%2Fimages%2Fguides%2Fdruggable-genome%2Ffeatured.webp&w=1920&q=75&dpl=dpl_J8tu6aF3F41kEvMFgYtuMXes1ynJ) Drugs · October 23, 2026 ### How many druggable genes are there? About 4,500 human genes are considered part of the druggable genome. A major analysis counted 4,479 drugged or druggable genes, equal to 22% of protein-coding genes.](https://proteiniq.io/guides/druggable-genome)
- [![Ink illustration of a computational network connected to a protein binding pocket and candidate molecules.](https://proteiniq.io/_next/image?url=%2Fimages%2Fguides%2Fai-drug-discovery-statistics%2Ffeatured.webp&w=1920&q=75&dpl=dpl_J8tu6aF3F41kEvMFgYtuMXes1ynJ) Drugs · October 23, 2026 ### AI drug discovery statistics [2026] AI drug discovery statistics for 2026: 117 AI-enabled drugs had entered clinical trials by mid-2025, three computationally designed drugs are in Phase 3 or under FDA review, and none is approved yet. Plus FDA submissions, funding, and the data models train on.](https://proteiniq.io/guides/ai-drug-discovery-statistics)

## Ready to discover small molecules?

### Free

$0

The perfect starting place for your first project.

- All tools
- 200 credits, then 100/mo
- 3 jobs per day
- Up to 1,000 residues per job
- Academic license

[Get Free](https://proteiniq.io/sign-up)

### Plus

$23 per user per month, billed annually

Everything an academic lab needs to scale.

- Everything in Free
- 24,000 credits/user/year
- No daily job limit
- Batches & workflows
- API access

### Pro

Popular

$79 per user per month, billed annually

More compute and a commercial license for industry.

- Everything in Plus
- 96,000 credits/user/year
- Commercial license

### Enterprise

Contact us Custom annual terms

Custom credits, seats, and security review.

- Everything in Pro
- Custom credit allocation
- Shared seats and admin controls
- Invoice billing and security review

[Contact sales](https://proteiniq.io/contact)

[View all plans and compare features](https://proteiniq.io/pricing)

## Frequently asked questions

AI answers from our docs. No sign-in needed.

## More solutions

The same workspace, set up for other kinds of discovery.

- [RNA discovery See how your RNA folds and binds Explore](https://proteiniq.io/solutions/rna-discovery)
- [Antibody engineering Antibodies, checked before synthesis Explore](https://proteiniq.io/solutions/antibody-engineering)
- [Peptide discovery Send only your best peptides to the lab Explore](https://proteiniq.io/solutions/peptide-discovery)
- [Enzyme engineering Know which enzyme variants to make Explore](https://proteiniq.io/solutions/enzyme-engineering)