Similarity scores and representative covers#

Compare ligands and protein interfaces, explore similarity scores, and find representative clusters. Similarity scores defines the metrics and files.

import pandas as pd

from plinder.core import PlinderRelease, query_table
from plinder.core.scores import (
    reconstruct_interface_similarity_scores,
    reconstruct_similarity_scores,
)

release = PlinderRelease()

/home/runner/micromamba/envs/plinder/lib/python3.12/site-packages/vcs_versioning/_backends/_git.py:709: UserWarning: "/home/runner/work/plinder/plinder" is shallow and may cause errors
  pre_parse(wd)

ligand_system_id = "4agi__1__1.C__1.R"
ligand_id = "4agi__1__1.R"
interface_id = "7cm8__1__1.A--2.A"

Compare ligand similarities#

reconstruct_similarity_scores() reads the files needed for the requested query and target IDs. This example uses a one-pair self-comparison to keep execution small.

ligand_scores = reconstruct_similarity_scores(
    query_system_ids=[ligand_system_id],
    target_system_ids=[ligand_system_id],
    query_ligand_ids=[ligand_id],
    target_ligand_ids=[ligand_id],
)
ligand_scores

	query_system	query_ligand_id	target_system	target_ligand_id	protein_mapping	mapping	protein_mapper	source	metric	similarity

For larger neighborhoods, read selected columns and rows from the complete ligand score table.

def read_ligand_neighborhood(system_id, ligand_id):
    return pd.read_parquet(
        release.fetch("ligand_similarity_scores"),
        columns=[
            "query_system",
            "query_ligand_id",
            "target_system",
            "target_ligand_id",
            "pocket_qcov",
            "pocket_fident_qcov",
            "pli_qcov",
            "sucos_shape",
        ],
        filters=[
            ("query_system", "==", system_id),
            ("query_ligand_id", "==", ligand_id),
        ],
    )

Compare protein-interface similarities#

The interface API likewise accepts selected query and target IDs.

interface_scores = reconstruct_interface_similarity_scores(
    query_interface_ids=[interface_id],
    target_interface_ids=[interface_id],
)
interface_scores

	query_system	target_system	mapping	source	metric	iface1_qcov	iface2_qcov	similarity

Representative covers#

Request cover columns through query_table() just like annotation columns. Representative covers describes their construction and long-form files.

pocket_cover = "pocket_qcov__70__ligand__directed_set_cover"
ligand_cover = query_table(
    columns=[
        "system_id",
        "ligand_id",
        pocket_cover,
        f"{pocket_cover}__is_centroid",
    ],
    filters=[("ligand_id", "==", ligand_id)],
)
ligand_cover.T

	0
system_id	4agi__1__1.C__1.R
ligand_id	4agi__1__1.R
pocket_qcov__70__ligand__directed_set_cover	c3554
pocket_qcov__70__ligand__directed_set_cover__is_centroid	False

interface_cover = query_table(
    "interface_annotations",
    columns=[
        "system_id",
        "interface_qcov__70__directed_set_cover",
    ],
    filters=[("system_id", "==", interface_id)],
)
interface_cover.T

	0
system_id	7cm8__1__1.A--2.A
interface_qcov__70__directed_set_cover	c2668

Matched molecular pairs#

Use ligand_mmp_pairs to look up transformations involving the selected ligand chemistry.

smiles_id = query_table(
    columns=["ligand_smiles_id"],
    filters=[("ligand_id", "==", ligand_id)],
).iloc[0, 0]
mmp_neighbors = query_table(
    "ligand_mmp_pairs",
    filters=[[
        ("ligand_smiles_id_1", "==", smiles_id),
        ("ligand_smiles_id_2", "==", smiles_id),
    ]],
)
mmp_neighbors.head()

	ligand_smiles_id_1	ligand_smiles_id_2	ligand_smiles_1	ligand_smiles_2	transformation	shared_core_smiles	num_cuts	shared_core_num_heavy_atoms	ligand_1_num_heavy_atoms	ligand_2_num_heavy_atoms	ligand_1_shared_core_fraction	ligand_2_shared_core_fraction
0	182	33748	C#CCO[C@@H]1O[C@@H](C)[C@@H](O)[C@@H](O)[C@@H]1O	C[Se][C@@H]1O[C@@H](C)[C@@H](O)[C@@H](O)[C@@H]1O	[:1]OCC#C>>[:1][Se]C	[*:1][C@@H]1O[C@@H](C)[C@@H](O)[C@@H](O)[C@@H]1O	1	10	14	12	0.714286	0.833333
1	232	33748	C#C[C@@H]1N[C@@H](C)[C@@H](O)[C@H]1O	C[Se][C@@H]1O[C@@H](C)[C@@H](O)[C@@H](O)[C@@H]1O	[:1][C@@H]1[C@H]([:2])[C@H](C)N[C@H]1C#C>>[*...	[:1]O.[:2]O	2	2	10	12	0.200000	0.166667
2	232	33748	C#C[C@@H]1N[C@@H](C)[C@@H](O)[C@H]1O	C[Se][C@@H]1O[C@@H](C)[C@@H](O)[C@@H](O)[C@@H]1O	[:1][C@@H]1[C@H]([:2])[C@H](C)N[C@H]1C#C>>[*...	[:1]O.[:2]O	2	2	10	12	0.200000	0.166667
3	232	33748	C#C[C@@H]1N[C@@H](C)[C@@H](O)[C@H]1O	C[Se][C@@H]1O[C@@H](C)[C@@H](O)[C@@H](O)[C@@H]1O	[:1][C@@H]1[C@H]([:2])[C@H](C)N[C@H]1C#C>>[*...	[:1]O.[:2]O	2	2	10	12	0.200000	0.166667
4	232	33748	C#C[C@@H]1N[C@@H](C)[C@@H](O)[C@H]1O	C[Se][C@@H]1O[C@@H](C)[C@@H](O)[C@@H](O)[C@@H]1O	[:1][C@@H]1[C@H](O)[C@H]([:2])N[C@H]1C#C>>[*...	[:2]C.[:1]O	2	2	10	12	0.200000	0.166667