caddforge-docs 0.3.0__py3-none-any.whl

caddforge_docs/site/examples/quickstart/pipeline.yaml

@@ -0,0 +1,23 @@
+version: 1
+name: toy-pose-selection
+defaults:
+  backend: local
+stages:
+  - id: best_per_ligand
+    type: filter.tabular
+    config:
+      input_path: scores.csv
+      sort_by: score
+      ascending: true
+      group_by: ligand
+      top_n_per_group: 1
+      output_name: best_per_ligand.csv
+  - id: shortlist
+    type: filter.tabular
+    inputs:
+      table: best_per_ligand.filtered_table
+    config:
+      sort_by: score
+      ascending: true
+      top_n: 2
+      output_name: shortlist.csv

caddforge_docs/site/examples/quickstart/run.py

@@ -0,0 +1,18 @@
+"""Run from the directory containing diagnostics.yaml and values.csv."""
+from caddforge.core.execution import load_result_for_job, submit_workflow
+from caddforge.core.job import JobStatus
+from caddforge.plugins import get_tool
+
+spec = get_tool("datascience", "distribution-diagnostics")
+cfg = spec.config_cls.from_yaml("diagnostics.yaml")
+workflow = spec.workflow_cls(cfg)
+job = submit_workflow(
+    workflow, cfg, backend_name=cfg.backend,
+    input_ports=tuple(getattr(spec.plugin, "input_ports", ())),
+)
+result = load_result_for_job(job)
+if result is None or result.status != JobStatus.COMPLETED:
+    raise RuntimeError(f"Job {job.id} failed; inspect its logs")
+print(job.id)
+print(result.paths["report_json"])
+print(result.metrics["n_total"])

caddforge_docs/site/examples/quickstart/run_pipeline.py

@@ -0,0 +1,6 @@
+"""Run the toy selection pipeline from the example directory."""
+from caddforge.pipeline.executor import run_pipeline
+
+result = run_pipeline("pipeline.yaml", emit=print)
+print(result.pipeline_job.id)
+print(result.artifacts["shortlist.filtered_table"].primary_path())

caddforge_docs/site/examples/quickstart/scores.csv

@@ -0,0 +1,7 @@
+ligand,pose_id,score
+toy_a,a1,-3.0
+toy_a,a2,-5.0
+toy_b,b1,-4.0
+toy_b,b2,-2.0
+toy_c,c1,-6.0
+toy_c,c2,-1.0

caddforge_docs/site/examples/quickstart/values.csv

@@ -0,0 +1,31 @@
+sample_id,value
+sample_01,1.2
+sample_02,1.5
+sample_03,1.8
+sample_04,2.0
+sample_05,2.1
+sample_06,2.3
+sample_07,2.5
+sample_08,2.7
+sample_09,2.9
+sample_10,3.0
+sample_11,3.1
+sample_12,3.3
+sample_13,3.5
+sample_14,3.7
+sample_15,3.8
+sample_16,4.0
+sample_17,4.2
+sample_18,4.3
+sample_19,4.5
+sample_20,4.7
+sample_21,4.9
+sample_22,5.0
+sample_23,5.2
+sample_24,5.4
+sample_25,5.7
+sample_26,6.0
+sample_27,6.2
+sample_28,6.5
+sample_29,7.0
+sample_30,7.5

caddforge_docs/site/examples/run_tool.py

@@ -0,0 +1,40 @@
+"""Submit a public tool from a downloaded YAML using its declared input ports."""
+
+from __future__ import annotations
+
+import argparse
+from pathlib import Path
+
+from caddforge.core.execution import load_result_for_job, submit_workflow
+from caddforge.core.job import JobStatus
+from caddforge.plugins import get_tool
+
+
+def main() -> None:
+    parser = argparse.ArgumentParser(description=__doc__)
+    parser.add_argument("section")
+    parser.add_argument("tool")
+    parser.add_argument("config", type=Path)
+    args = parser.parse_args()
+    spec = get_tool(args.section, args.tool)
+    cfg = spec.config_cls.from_yaml(args.config)
+    workflow = spec.workflow_cls(cfg)
+    job = submit_workflow(
+        workflow, cfg, backend_name=cfg.backend,
+        input_ports=tuple(getattr(spec.plugin, "input_ports", ())),
+    )
+    print(job.id)
+    result = load_result_for_job(job)
+    if result is None:
+        if cfg.backend == "local":
+            raise RuntimeError("Local job has no result; inspect its logs")
+        print("Submitted; check status before loading completed results")
+        return
+    if result.status != JobStatus.COMPLETED:
+        raise RuntimeError(f"Job {job.id}: {result.status.value}; inspect its logs")
+    print(result.metrics)
+    print(result.paths)
+
+
+if __name__ == "__main__":
+    main()

caddforge_docs/site/examples/tools/datascience-csv-scatter.yaml

@@ -0,0 +1,17 @@
+# Configuration template: supply prepared inputs and required runtime.
+csv_path: data/metrics.csv
+x_column: feature_x
+y_column: feature_y
+color_column: feature_group
+smiles_column: smiles
+id_column: compound_id
+hover_columns: [compute_time]
+x_scale: linear
+y_scale: log
+palette: viridis
+thresholds_enabled: true
+x_positive_direction: low
+y_positive_direction: high
+point_size: 10
+alpha: 0.8
+title: Synthetic metrics

caddforge_docs/site/examples/tools/datascience-distribution-diagnostics.yaml

@@ -0,0 +1,10 @@
+# Configuration template: supply prepared inputs and required runtime.
+csv_path: data/assay_values.csv
+column: pIC50
+bins: 50
+clip_std: null
+sample_size: 5000
+random_seed: 0
+include_log: true
+plot_filename: distribution_diagnostics.png
+results_filename: distribution_report.json

caddforge_docs/site/examples/tools/descriptors-ani-conformers.yaml

@@ -0,0 +1,9 @@
+# Configuration template: supply prepared inputs and required runtime.
+smiles: "CCO"
+num_confs: 100
+top_n: 10
+rmsd_cluster_thresh: 0.5
+max_mmff_iters: 200
+model_name: ANI2x
+device: cpu
+output_sdf_name: ranked_conformers.sdf

caddforge_docs/site/examples/tools/descriptors-ani-psa.yaml

@@ -0,0 +1,9 @@
+# Configuration template: supply prepared inputs and required runtime.
+smiles: "CC(=O)Oc1ccccc1C(=O)O"
+num_confs: 100
+top_n: 10
+rmsd_cluster_thresh: 0.5
+max_mmff_iters: 200
+temperature: 298.15
+model_name: ANI2x
+device: cpu

caddforge_docs/site/examples/tools/descriptors-cluster-molecules.yaml

@@ -0,0 +1,11 @@
+# Configuration template: supply prepared inputs and required runtime.
+input_path: data/molecules.csv
+smiles_column: smiles
+id_column: compound_id
+algorithm: kmedoids
+fingerprint_radius: 2
+fingerprint_bits: 2048
+kmedoids_n_clusters: 100
+kmedoids_mode: auto
+kmedoids_max_exact_n: 5000
+kmedoids_max_exact_pairs: 25000000

caddforge_docs/site/examples/tools/descriptors-phesa.yaml

@@ -0,0 +1,7 @@
+# Configuration template: supply prepared inputs and required runtime.
+reference_smiles: "CCO"
+candidate_smiles:
+  - "CCCO"
+  - "CCCCO"
+max_confs: 200
+pp_weight: 0.5

caddforge_docs/site/examples/tools/docking-gnina.yaml

@@ -0,0 +1,12 @@
+# Configuration template: supply prepared inputs and required runtime.
+receptor_path: data/protein.pdb
+ligand_path: data/ligands.sdf
+autobox_ligand_path: data/reference_ligand.sdf
+flexres:
+  - A:194
+  - A:244
+  - A:252
+scoring: dkoes_fast
+cnn_scoring: rescore
+no_gpu: true
+output_format: sdf

caddforge_docs/site/examples/tools/docking-idockya.yaml

@@ -0,0 +1,8 @@
+# Configuration template: supply prepared inputs and required runtime.
+receptor_path: data/receptor.sdf
+native_ligand_path: data/native_ligand.sdf
+ligand_path: data/ligands.sdf
+output_format: sdf
+output_dir_name: docked_out
+num_workers: 0
+max_inflight_tasks: 0

caddforge_docs/site/examples/tools/docking-unidock.yaml

@@ -0,0 +1,12 @@
+# Configuration template: supply prepared inputs and required runtime.
+receptor_path: data/protein.pdbqt
+ligand_multisdf_path: data/ligands.sdf
+center_x: 0.0
+center_y: 0.0
+center_z: 0.0
+size_x: 20
+size_y: 20
+size_z: 20
+search_mode: fast
+exhaustiveness: 384
+batch_size: 50000

caddforge_docs/site/examples/tools/fep-openfe-abfe.yaml

@@ -0,0 +1,53 @@
+# Configuration template: supply prepared inputs and required runtime.
+ligand_sdf: data/ligand_neutral.sdf
+protein_pdb: data/protein_fixed.pdb
+ligand_index: 0
+fix_protein_pdb: false
+partial_charge_method: am1bcc
+off_toolkit_backend: ambertools
+host_min_distance_nm: 0.5
+host_max_distance_nm: 1.5
+protocol_repeats: 1
+settings_overrides:
+  complex_simulation_settings.real_time_analysis_interval: 10 picosecond
+  complex_equil_simulation_settings.equilibration_length: 0.2 nanosecond
+  complex_equil_simulation_settings.production_length: 0.5 nanosecond
+  complex_equil_simulation_settings.equilibration_length_nvt: 0.10 nanosecond
+  complex_simulation_settings.equilibration_length: 0.2 nanosecond
+  complex_simulation_settings.production_length: 2.0 nanosecond
+  complex_simulation_settings.n_replicas: 68
+  solvent_equil_simulation_settings.equilibration_length: 0.1 nanosecond
+  solvent_equil_simulation_settings.production_length: 0.5 nanosecond
+  solvent_equil_simulation_settings.equilibration_length_nvt: 0.05 nanosecond
+  solvent_simulation_settings.equilibration_length: 0.1 nanosecond
+  solvent_simulation_settings.production_length: 1 nanosecond
+  solvent_simulation_settings.real_time_analysis_interval: 10 picosecond
+  solvent_simulation_settings.n_replicas: 60
+  engine_settings.compute_platform: CUDA
+  complex_lambda_settings.lambda_elec:
+    [0, 0.05, 0.1, 0.14, 0.19, 0.24, 0.29, 0.33, 0.38, 0.43, 0.48, 0.52, 0.57, 0.62, 0.67, 0.71,
+      0.76, 0.81, 0.86, 0.9, 0.95, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
+      1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
+  complex_lambda_settings.lambda_vdw:
+    [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.06, 0.12, 0.18, 0.24,
+      0.28, 0.32, 0.36, 0.4, 0.44, 0.48, 0.52, 0.56, 0.6, 0.62, 0.64, 0.66, 0.68, 0.69, 0.7, 0.71,
+      0.72, 0.73, 0.74, 0.75, 0.76, 0.77, 0.78, 0.79, 0.8, 0.81, 0.82, 0.83, 0.83, 0.84, 0.85,
+      0.86, 0.87, 0.88, 0.89, 0.9, 0.91, 0.92, 0.94, 0.96, 0.98, 1]
+  complex_lambda_settings.lambda_restraints:
+    [0, 0, 0, 0.01, 0.01, 0.02, 0.03, 0.04, 0.06, 0.07, 0.09, 0.11, 0.13, 0.16, 0.18, 0.21, 0.24,
+      0.27, 0.3, 0.33, 0.37, 0.4, 0.44, 0.49, 0.53, 0.57, 0.62, 0.67, 0.72, 0.77, 0.83, 0.88,
+      0.94, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
+      1, 1, 1, 1, 1, 1, 1]
+  solvent_lambda_settings.lambda_elec:
+    [0, 0.01, 0.02, 0.03, 0.04, 0.07, 0.09, 0.11, 0.13, 0.15, 0.17, 0.22, 0.26, 0.3, 0.35, 0.39,
+      0.43, 0.48, 0.52, 0.57, 0.61, 0.65, 0.7, 0.74, 0.78, 0.83, 0.87, 0.91, 0.96, 1, 1, 1, 1,
+      1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
+  solvent_lambda_settings.lambda_vdw:
+    [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+      0.1, 0.18, 0.26, 0.32, 0.38, 0.42, 0.46, 0.5, 0.53, 0.56, 0.59, 0.62, 0.65, 0.68, 0.71,
+      0.74, 0.76, 0.78, 0.8, 0.81, 0.83, 0.84, 0.86, 0.88, 0.9, 0.92, 0.94, 0.96, 0.98, 1]
+  solvent_lambda_settings.lambda_restraints:
+    [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+      0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
+run_quickrun: true
+quickrun_extra_args: []

caddforge_docs/site/examples/tools/fep-openfe-rbfe-septop.yaml

@@ -0,0 +1,23 @@
+# Configuration template: supply prepared inputs and required runtime.
+operation_mode: run
+ligand_sdf: data/ligands.sdf
+ligand_sdfs: []
+protein_pdb: data/protein.pdb
+complexes: []
+project_compound_ids:
+  - proj_anchor_01
+  - proj_anchor_02
+export_network_bundle: true
+reuse_completed_edges: true
+partial_charge_method: am1bcc
+off_toolkit_backend: ambertools
+protocol_repeats: 3
+settings_overrides:
+  engine_settings.compute_platform: CUDA
+compatibility_threshold: 0.45
+project_assignment_threshold: 0.35
+local_cluster_threshold: 0.55
+max_clash_score: 0.35
+diagnostic_cycle_edges_per_component: 1
+run_quickrun: true
+quickrun_extra_args: []

caddforge_docs/site/examples/tools/md-center-and-align.yaml

@@ -0,0 +1,16 @@
+# Configuration template: supply prepared inputs and required runtime.
+backend: local
+topology_path: data/system.pdb
+trajectory_path: data/traj.xtc
+center_selection: protein or resname MOL
+keep_selection: protein or resname MOL
+align_selection: protein and backbone
+unwrap: true
+center: true
+wrap: true
+center_mode: geometry
+wrap_compound: residues
+align_weights: mass
+output_dir_name: output
+output_trajectory_filename: traj-centered.xtc
+output_structure_filename: traj-centered.pdb

caddforge_docs/site/examples/tools/md-cluster-representative.yaml

@@ -0,0 +1,16 @@
+# Configuration template: supply prepared inputs and required runtime.
+backend: local
+topology_path: data/traj-centered.pdb
+trajectory_path: data/traj-centered.xtc
+ligand_template_sdf: data/template.sdf
+ligand_resname: UNK
+cluster_selection: null
+extract_selection: protein or resname UNK
+last_ns: 10.0
+frame_slice: null
+distance_threshold_nm: 0.2
+output_dir_name: output
+output_complex_filename: largest_cluster_representative_complex.pdb
+output_protein_filename: largest_cluster_representative_protein.pdb
+output_ligand_sdf_filename: largest_cluster_representative_ligand.sdf
+clustering_summary_filename: clustering_summary.json

caddforge_docs/site/examples/tools/md-extract-frames.yaml

@@ -0,0 +1,17 @@
+# Configuration template: supply prepared inputs and required runtime.
+backend: local
+topology_path: data/traj-centered.pdb
+trajectory_path: data/traj-centered.xtc
+ligand_template_sdf: data/template.sdf
+ligand_resname: UNK
+extract_selection: protein or resname UNK
+frame_index: null
+last_ns: 10.0
+frame_slice: null
+write_per_frame_pdbs: false
+output_dir_name: output
+output_trajectory_filename: last-10ns.xtc
+output_structure_filename: last-10ns_first_complex.pdb
+protein_trajectory_filename: last-10ns_protein.xtc
+protein_structure_filename: last-10ns_first_protein.pdb
+ligand_sdf_filename: last-10ns_first_ligand.sdf

caddforge_docs/site/examples/tools/md-fix-structure.yaml

@@ -0,0 +1,20 @@
+# Configuration template: supply prepared inputs and required runtime.
+backend: local
+input_pdb: data/complex.pdb
+forcefields:
+  - amber14-all.xml
+  - amber14/tip3p.xml
+ph: 7.0
+protonation_policy: preserve
+termini_policy: charged
+fix_nonstandard_residues: auto
+strict_all: false
+membrane_lipid_resnames:
+  - POPC
+  - POPE
+validate_openmm_system: auto
+sanitize_mixed_residues: auto
+preserve_conect: true
+quiet: false
+output_dir_name: output
+output_filename: null

caddforge_docs/site/examples/tools/md-grand.yaml

@@ -0,0 +1,28 @@
+# Configuration template: supply prepared inputs and required runtime.
+backend: local
+complex_pdb_path: data/complex.pdb
+ligand_template_sdf: data/ligand_template.sdf
+ligand_resname: LIG
+sphere_radius_angstrom: 10.0
+n_ghost_waters: 150
+nonbonded_cutoff_nm: 0.9
+temperature_kelvin: 300.0
+initialization_passes: 7500
+max_production_passes: 100000
+ph: 7.4
+padding_nm: 1.2
+ionic_strength_molar: 0.15
+ligand_selection: null
+align_selection: null
+frame_analysis_interval: 1
+log_sync_interval_seconds: 30
+output_dir_name: output
+trajectory_filename: gcmc_trajectory.dcd
+ghost_water_filename: ghost_water_state.txt
+checkpoint_filename: gcmc_checkpoint.chk
+hydrated_complex_filename: hydrated_complex.pdb
+gcmc_summary_filename: gcmc_summary.json
+representative_complex_filename: representative_complex.pdb
+representative_protein_filename: representative_protein.pdb
+representative_ligand_filename: representative_ligand.sdf
+selection_summary_filename: selection_summary.json

caddforge_docs/site/examples/tools/md-inducia.yaml

@@ -0,0 +1,29 @@
+# Configuration template: supply prepared inputs and required runtime.
+mode: template
+backend: local
+receptor_pdb_path: data/receptor.pdb
+query_ligand_sdf_path: data/query.sdf
+template_ligand_sdf_path: data/known_binder.sdf
+ligand_resname: LIG
+max_local_workers: 1
+phesa:
+  max_confs: 200
+clustering:
+  rmsd_cutoff_angstrom: 1.0
+clash_detection:
+  allowed_vdw_overlap_angstrom: 0.4
+gnina:
+  cnn_scoring: rescore
+  pose_sort_order: CNNscore
+grand:
+  sphere_radius_angstrom: 10.0
+  n_ghost_waters: 150
+  initialization_passes: 7500
+  max_production_passes: 100000
+openbpmd:
+  max_input_complexes: null
+  nreps: 10
+  hill_height: 0.05
+  deposit_interval_ps: 1.0
+progress:
+  interval_seconds: 30

caddforge_docs/site/examples/tools/md-minimize.yaml

@@ -0,0 +1,13 @@
+# Configuration template: supply prepared inputs and required runtime.
+complex_pdb_path: data/complex.pdb
+ligand_path: data/ligand.sdf
+lig_resname: LIG
+mode: ligand_only
+pocket_radius_angstrom: 5.0
+shell_radius_angstrom: 5.0
+backbone_restraint_strength: moderate
+shell_restraint_strength: very_strong
+tolerance_kj_mol_nm: 10.0
+max_iterations: 1000
+platform: CPU
+run_directory: runs/minimize-one-complex

caddforge_docs/site/examples/tools/md-openbpmd.yaml

@@ -0,0 +1,11 @@
+# Configuration template: supply prepared inputs and required runtime.
+backend: local
+complex_pdb_path: data/complex.pdb
+lig_resname: MOL
+ligand_net_charge: 0
+nreps: 10
+hill_height: 0.05
+deposit_interval_ps: 1.0
+log_sync_interval_seconds: 30
+output_dir_name: output
+analysis_dir_name: analysis

caddforge_docs/site/examples/tools/md-plain-md.yaml

@@ -0,0 +1,28 @@
+# Configuration template: supply prepared inputs and required runtime.
+backend: local
+system_pdb_path: data/system.pdb
+molecule_sdf_paths:
+  - data/ligand.sdf
+ph: 7.4
+system_preparation_mode: solvate
+padding: 1.0
+ionic_strength: 0.15
+prepared_box_margin: 0.0
+nonbonded_cutoff: 1.0
+barostat: isotropic
+pressure: 1.0
+membrane_surface_tension: 0.0
+membrane_xy_mode: isotropic
+membrane_z_mode: free
+barostat_frequency: 25
+temperature: 300.0
+step_size_fs: 4
+simulation_time_ns: 1.0
+trajectory_filename: traj.xtc
+report_interval: 10000
+checkpoint_interval: 5000
+output_dir_name: output
+seed: null
+repeats: 1
+checkpoint_path: null
+max_restarts: 10

caddforge_docs/site/examples/tools/ml-explore-classifier.yaml

@@ -0,0 +1,5 @@
+# Configuration template: supply prepared inputs and required runtime.
+job_id: existing_model_job_id
+run_base: runs
+model_name: random_forest
+positive_class: 1

caddforge_docs/site/examples/tools/ml-model-factory.yaml

@@ -0,0 +1,32 @@
+# Configuration template: supply prepared inputs and required runtime.
+train_path: data/train.csv
+target_column: y
+task: regression
+feature_columns: [f1, f2]
+ignore_columns: [compound_id, measured_at]
+test_path: null
+smiles_column: smiles
+fingerprint_types: [morgan, atompair, featmorgan]
+fp_bits: 2048
+fp_radius: 2
+fp_use_chirality: true
+model_names: [ridge, random_forest, xgboost]
+model_params:
+  random_forest:
+    n_estimators: 500
+    random_state: 123
+calibrate: false
+calibrate_method: sigmoid
+test_size: 0.2
+random_state: 123
+predictions_filename: predictions.csv
+results_filename: results.json
+metrics_filename: metrics.json
+id_column: compound_id
+classification_thresholds: null
+time_column: measured_at
+standardize_targets: false
+positive_class: null
+target_transform: none
+drop_non_positive_targets: true
+# log_targets: false  # deprecated alias for target_transform: log

caddforge_docs/site/examples/tools/ml-model-zoo.yaml

@@ -0,0 +1,16 @@
+# Configuration template: supply prepared inputs and required runtime.
+train_path: data/train.csv
+target_column: y
+feature_columns: [f1, f2]
+model_name: random_forest
+task: regression
+test_size: 0.2
+random_state: 123
+standardize_targets: false
+target_transform: none
+positive_class: 1
+predictions_filename: predictions.csv
+results_filename: results.json
+metrics_filename: metrics.json
+mode: train
+model_path: artifacts/model.joblib

caddforge_docs/site/examples/tools/ml-pca.yaml

@@ -0,0 +1,10 @@
+# Configuration template: supply prepared inputs and required runtime.
+data_path: data/features.csv
+feature_columns: [f1, f2, f3]
+ignore_columns: [id]
+n_components: 5
+standardize: true
+drop_missing_rows: true
+scores_filename: pca_scores.csv
+components_filename: pca_components.csv
+results_filename: results.json

caddforge_docs/site/examples/tools/ml-simple-gp.yaml

@@ -0,0 +1,17 @@
+# Configuration template: supply prepared inputs and required runtime.
+train_path: data/train.csv
+target_column: y
+feature_columns: [f1, f2, f3]
+smiles_column: smiles
+ignore_columns: [id, comment]
+fingerprint_types: [morgan, atompair, featmorgan]
+kernel: tanimoto
+noise: 0.05
+test_path: data/test.csv
+save_report: true
+log_targets: false
+generate_scatter_plot: true
+scatter_filename: gp_scatter.html
+mode: train
+model_path: simple_gp_model.joblib
+id_column: id

caddforge_docs/site/examples/tools/qm-transfer-free-energy.yaml

@@ -0,0 +1,11 @@
+# Configuration template: supply prepared inputs and required runtime.
+ligand_sdf: data/ligand.sdf
+solvent_sdf: data/octanol.sdf
+n_confs: 3
+basis: def2-TZVP
+xc: BP86
+do_geomopt: true
+temperature_K: 298.15
+standard_state: x
+cosmo_backend: dft
+xtb_path: xtb