Top-level API

The top-level package provides convenience imports for the most common TMol objects and workflows. Their full documentation lives in the owning packages, such as tmol.io, tmol.pose, and tmol.score.

Core objects

CanonicalOrdering	The canonical ordering class describes the integer ordering of residue types and for atoms within those residue types for the collection of available residue types defined by a PatchedChemicalDatabase.
CartesianMoveMap	Move map for Cartesian-space minimization.
ConstraintEnergyTerm	Score coordinate and geometric constraints attached to a pose stack.
ConstraintSet	Immutable batched coordinate constraints and their tensor storage.
EdgeType	Kinds of directed connections represented in a fold forest.
FoldForest	The fold forest will define the fold trees for the poses in a PoseStack.
KinematicModuleData	Topology and traversal tensors required by a pose kinematics module.
MoveMap	Hierarchical internal-coordinate degrees of freedom for a pose stack.
PackedBlockTypes	A class to aggregate the properties for a collection of residue types.
ParameterDatabase	Immutable chemical and scoring parameter container used by tmol.
PoseStack	Batch of molecular systems with shared residue-type definitions.
ScoreFunction	Weighted collection of energy terms rendered for a pose topology.
ScoreType	Stable indices for energy terms in score-function weight tensors.

Structure and chemistry

atom_records_from_pose_stack	Create a numpy array holding the atom records needed to write a PDB file from a PoseStack.
canonical_form_from_openfold	The canonical form is intended to represent a stable, serializable intermediate format for a structure so that it can be created today and then be read in years from now and be used to construct a PoseStack in tmol.
canonical_form_from_pdb	Create a canonical form from either the contents of a PDB file as one long string or a list of individual lines from the file or by providing the name/path of a PDB file
canonical_form_from_rosettafold2	The canonical form is intended to represent a stable, serializable intermediate format for a structure so that it can be created today and then be read in years from now and be used to construct a PoseStack in tmol.
canonical_ordering_for_openfold	Construct the CanonicalOrdering object that will be used for the subset of residue types that are used by OpenFold; this will be stable so that the entries in "coords" tensor member of the canonical form dictionary will be interpretable indefinitely and thus a canonical form dictionary can be serialized to disk and read again after an arbitrary amount of time
canonical_ordering_for_rosettafold2	Construct the CanonicalOrdering object that will be used for the subset of residue types that are used by RoseTTAFold2; this will be stable so that the entries in "coords" tensor member of the canonical form dictionary will be interpretable indefinitely and thus a canonical form dictionary can be serialized to disk and read again after an arbitrary amount of time
default_canonical_ordering	Create a CanonicalOrdering object from the default set of residue types
default_packed_block_types	Create a PackedBlockTypes object from the default set of residue types
extended_pose_stack_from_sequences	Build a PoseStack from sequences with ideal geometry and extended backbone torsions.
one2three	Return the three-letter amino acid code given its one-letter code, or None if not a valid one-letter code.
packed_block_types_for_openfold	Construct the PackedBlockTypes (PBT) object that will be used for the subset of residue types that are used by OpenFold.
packed_block_types_for_rosettafold2	Construct the PackedBlockTypes (PBT) object that will be used for the subset of residue types that are used by RoseTTAFold2.
pose_stack_from_canonical_form	Build a pose stack from tensors in canonical atom ordering.
pose_stack_from_openfold	Build a PoseStack from the output generated by openfold
pose_stack_from_pdb	Construct a PoseStack given the contents of a PDB file or the name of a PDB file, using the full set of residue types contained in tmol's chemical.yaml file.
pose_stack_from_rosettafold2	Build a PoseStack from the output generated by RoseTTAFold2
pose_stack_to_pdb_string	Convert a PoseStack into PDB text suitable for molecular viewers.
selection_gallery	Return one interactive viewer for several labeled AtomArray selections.
switchable_view	Return HTML that switches one 3Dmol viewer among labeled structures.
three2one	Return the one-letter amino acid code given its three letter code, or None if not a valid three-letter code
view	Create a draggable py3Dmol viewer for a molecular structure.
write_pose_stack_pdb	Write a PDB-formatted file to disk given an input PoseStack.

Scoring and optimization

beta2016_score_function	Return a ScoreFunction implementing the beta_nov2016_cart score function of Rosetta3.
build_kinforest_network	Build a differentiable kinematic scoring network for a pose stack.
create_mainchain_coordinate_constraints	Add coordinate constraints for every declared polymer main-chain atom.
fast_relax	Relax poses through repeated side-chain packing and minimization.
get_named_torsions	Measure named torsions.
get_torsion_names	Names of the torsions defined on a block's type, in database order.
run_cart_min	Run minimization on a PoseStack in Cartesian coordinate space.
run_kin_min	Run minimization on a PoseStack in internal DOF space.
run_min	Run minimization on any sfxn module (Cartesian or KinForest).
set_named_torsions	Set named torsions, returning a new PoseStack.

C++ and CUDA integration

TMol: GPU-accelerated molecular modeling with PyTorch.

tmol.include_paths()

C++/CUDA include paths for tmol components.

Defined before other imports because JIT extension loading (tmol.utility._cpp_extension) imports this during module init.