Reference
Tool reference
Find tools for your research and check their inputs, outputs, and terms.
Select a tool name to see input formats, settings, output metrics, and terms.
| Tool | What is it used for? | License at official distribution source |
|---|---|---|
| AbLang2 paired | Represents one paired antibody heavy- and light-chain sequence as 480 numerical features for sequence comparison and downstream analysis. These features do not predict structure, binding affinity, or efficacy. | Code BSD-3-Clause · Weights BSD-3-Clause-Clear |
| alchemlyb | Estimate free energy from molecular simulation results using TI, MBAR, or BAR. | Code BSD-3-Clause |
| AlphaFold | Predict the structure of a single protein chain in single-sequence mode (alphafold2_ptm). | Code MIT, Apache-2.0 · Weights CC-BY-4.0 · See the detail page for additional terms |
| ANARCI | Align antibody sequences and number their positions using schemes such as IMGT and Kabat. | Code BSD-3-Clause · Data CC-BY-4.0 |
| Autodock Vina | Search for binding poses between a protein and a small molecule and score them. Use the scores to compare candidates; they are not experimentally measured binding affinities. | Code Apache-2.0 |
| Boltz-2 | Predict complex structures containing proteins, nucleic acids and small molecules, with structural confidence metrics for each candidate. | MIT |
| bowtie2 | Aligns short sequencing reads to a reference sequence, allowing for insertions and deletions. | Code GPL-3.0-only |
| bwa | Finds where short sequencing reads align on a reference sequence. | Code GPL-3.0-only |
| Chai-1 | Predict the structure of complexes containing proteins, nucleic acids, and small molecules. | Apache-2.0 |
| DiffAb | Design new antibody CDRs based on an antigen structure. CDRs are antibody regions involved in target recognition. | Code Apache-2.0, LicenseRef-PyRosetta-NonCommercial · Weights Apache-2.0 · Optional components require a separate commercial agreement · See the detail page for additional terms |
| ESM2 35M | Represents one protein sequence as 480 numerical features for downstream classification and comparison, not structural coordinates, binding affinity or functional scores. | MIT |
| ESMFold | Predict a protein structure with the ESM2 language model. Start from a single sequence without an MSA of related sequences. | MIT |
| GROMACS | Simulate a protein in aqueous solution with the TIP3P water model. Supports energy minimization and molecular dynamics (MD). | Code LGPL-2.1-or-later, GPL-2.0-or-later |
| ImmuneBuilder | Predict variable-domain structures in antibodies, nanobodies, and TCRs. These domains are involved in target recognition. | Code BSD-3-Clause · Weights CC-BY-4.0 |
| K-Fold | An openly released model developed in Korea that predicts complex structures and interface confidence. | Code Apache-2.0, MIT, MPL-2.0 · Weights Apache-2.0, MIT |
| LigandMPNN | Design protein sequences while accounting for ligands (binding partners) and modified residues. | MIT |
| nvMolKit | 2D structural fingerprint similarity between a reference molecule and candidate molecules | Code Apache-2.0 |
| OpenMM | Run energy minimization and molecular dynamics (MD) from an input protein structure using nonperiodic conditions. | Code MIT AND LGPL-3.0-only |
| P2Rank | Find potential ligand-binding pockets in a protein structure and rank the candidate sites. | MIT |
| PharmacoNet | Model pharmacophores—chemical features relevant to binding—from a protein structure and use them to screen a molecular library. | MIT |
| PIGenet2 | Predict protein–ligand binding affinity, reporting the total binding energy and its component terms. | Code MIT, Apache-2.0, LicenseRef-PyMOL-Permissive · Weights MIT · Data CC-BY-4.0 |
| ProteinMPNN | Design amino-acid sequences for a protein backbone structure. Finding a sequence from a structure is called inverse folding. | MIT |
| RFantibody | Design new antibody and nanobody CDRs from an antigen structure and an antibody framework, proceeding through backbone design, sequence design, and structure filtering. | Code MIT · Weights MIT, CC-BY-4.0 |
| RFD4-Proteina | Generation-only RFD4-Proteina run that designs sequence and all-atom structure from an annotated CIF (up to 4 candidates, no scientific score) | BSD-3-Clause |
| RFdiffusion | Design new protein structures with seven protocols, including binder design, preservation of specified structural regions and symmetric complex design. | BSD-3-Clause |
| samtools | Convert, sort, and summarize SAM/BAM files, calculate depth, and create BAM/FASTA indexes. | Code MIT |
| SaProt | Score protein variants using both structure and sequence. Zero-shot scores require no additional training on variant data and are not stability ΔΔG values. | Code MIT, GPL-3.0-only · Weights MIT |
| shape-it | Find candidates with shapes similar to a reference molecule by overlaying 3D shapes represented with Gaussian functions. | Code MIT, GPL-2.0-only |
| ThermoMPNN | Suggest single amino-acid substitutions aimed at improving thermal stability, based on a protein structure. | MIT |
| TNP | Calculate developability metrics from nanobody (VHH) sequences. Use them to compare candidate properties; they do not guarantee successful drug development. | Code BSD-3-Clause, MIT AND LGPL-3.0-only · Weights CC-BY-4.0 · Data CC-BY-4.0 |
| USRCAT (RDKit) | Compare molecules using USR/USRCAT shape fingerprints to shortlist candidates from a large library for further review. | Code BSD-3-Clause |
Available tool versions and costs are shown in your project’s execution plan. This list also includes tools whose input formats are documented but which may not be available to run.