File size: 7,118 Bytes
5c3cfae
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
"""Collect trajectories with direct OpenEnv environment access."""

from __future__ import annotations

import argparse
import random
import uuid
from pathlib import Path
from typing import Dict, List, Sequence

from models import ActionType, ExperimentAction
from server.hackathon_environment import BioExperimentEnvironment
from training.evaluation import EvaluationSuite
from training.trajectory import Trajectory, TrajectoryDataset


HEURISTIC_SEQUENCE = [
    ActionType.COLLECT_SAMPLE,
    ActionType.PREPARE_LIBRARY,
    ActionType.SEQUENCE_CELLS,
    ActionType.RUN_QC,
    ActionType.FILTER_DATA,
    ActionType.NORMALIZE_DATA,
    ActionType.CLUSTER_CELLS,
    ActionType.TRAJECTORY_ANALYSIS,
    ActionType.MARKER_SELECTION,
    ActionType.SYNTHESIZE_CONCLUSION,
]


def parse_args() -> argparse.Namespace:
    parser = argparse.ArgumentParser(
        description="Run rollout episodes and persist trajectories."
    )
    parser.add_argument("--episodes", type=int, default=10, help="Number of episodes.")
    parser.add_argument(
        "--policy",
        choices=["random", "heuristic"],
        default="heuristic",
        help="Policy to use for rollouts.",
    )
    parser.add_argument(
        "--max-steps",
        type=int,
        default=None,
        help="Optional hard cutoff per episode (defaults to env limit).",
    )
    parser.add_argument(
        "--output-dir",
        default="training/rollouts",
        help="Directory for JSON trajectory outputs.",
    )
    parser.add_argument("--seed", type=int, default=None, help="RNG seed.")
    return parser.parse_args()


def heuristic_next_action(history: Sequence[ActionType], step_index: int) -> ActionType:
    seen = set(history)
    for action in HEURISTIC_SEQUENCE:
        if action not in seen:
            return action
    if step_index >= 2 and ActionType.VALIDATE_MARKER not in seen:
        return ActionType.VALIDATE_MARKER
    if ActionType.SYNTHESIZE_CONCLUSION in seen:
        return ActionType.SYNTHESIZE_CONCLUSION
    return ActionType.SYNTHESIZE_CONCLUSION


def pick_action(policy: str, step_index: int, history: Sequence[ActionType]) -> ActionType:
    if policy == "random":
        return random.choice(list(ActionType))
    return heuristic_next_action(history, step_index)


def default_comparison_name(conditions: Sequence[str]) -> str:
    normalized = {condition.lower() for condition in conditions}
    if {"healthy", "ipf"} <= normalized:
        return "IPF_vs_healthy"
    if any("treated" in condition for condition in normalized) and any(
        "untreated" in condition for condition in normalized
    ):
        return "treated_vs_untreated"
    if any("healthy" in condition for condition in normalized):
        return "disease_vs_healthy"
    return "disease_vs_healthy"


def build_experiment_action(

    action_type: ActionType,

    discovered_markers: Sequence[str],

    conditions: Sequence[str],

) -> ExperimentAction:
    method = None
    parameters: Dict[str, object] = {}

    if action_type == ActionType.COLLECT_SAMPLE:
        parameters = {"n_samples": 6}
    elif action_type == ActionType.PREPARE_LIBRARY:
        method = "10x_chromium"
    elif action_type == ActionType.RUN_QC:
        method = "scanpy.pp.calculate_qc_metrics"
    elif action_type == ActionType.FILTER_DATA:
        method = "scanpy.pp.filter_cells"
    elif action_type == ActionType.NORMALIZE_DATA:
        method = "scanpy.pp.normalize_total"
    elif action_type == ActionType.CLUSTER_CELLS:
        method = "scanpy.tl.leiden"
    elif action_type == ActionType.DIFFERENTIAL_EXPRESSION:
        method = "scanpy.tl.rank_genes_groups"
        parameters = {"comparison": default_comparison_name(conditions)}
    elif action_type == ActionType.TRAJECTORY_ANALYSIS:
        method = "scanpy.tl.dpt"
    elif action_type == ActionType.MARKER_SELECTION:
        method = "scanpy.tl.rank_genes_groups"
    elif action_type == ActionType.VALIDATE_MARKER:
        method = "qPCR"
        parameters = {"marker": discovered_markers[0] if discovered_markers else "SPP1"}
    elif action_type == ActionType.SYNTHESIZE_CONCLUSION:
        parameters = {"claims": []}

    return ExperimentAction(
        action_type=action_type,
        method=method,
        parameters=parameters,
        confidence=0.75,
    )


def run_episode(

    env: BioExperimentEnvironment,

    episode_id: str,

    policy: str,

    max_steps: int | None = None,

) -> Trajectory:
    structured_obs = env.reset()
    traj = Trajectory(
        episode_id=episode_id,
        task=structured_obs.task.model_dump(),
        metadata={
            "task_problem": structured_obs.task.problem_statement,
            "policy": policy,
        },
    )

    done = structured_obs.done
    step_num = 0
    while not done:
        if max_steps is not None and step_num >= max_steps:
            break

        history = [rec.action_type for rec in structured_obs.pipeline_history]
        action_type = pick_action(policy, step_num, history)
        experiment_action = build_experiment_action(
            action_type=action_type,
            discovered_markers=structured_obs.discovered_markers,
            conditions=structured_obs.task.conditions,
        )

        structured_obs = env.step(experiment_action)
        reward = structured_obs.reward
        done = structured_obs.done
        step_num += 1

        traj.add_step(
            action=experiment_action,
            observation=structured_obs,
            reward=reward,
            done=done,
            reward_breakdown=structured_obs.step_reward_breakdown,
        )

        print(
            f"  step={structured_obs.step_index:02d} "
            f"action={action_type.value:>28} "
            f"reward={reward:+.3f}"
        )

    return traj


def main() -> None:
    args = parse_args()
    if args.seed is not None:
        random.seed(args.seed)

    out_dir = Path(args.output_dir)
    out_dir.mkdir(parents=True, exist_ok=True)

    env = BioExperimentEnvironment()
    trajectories: List[Trajectory] = []

    print(
        f"Starting rollout collection: episodes={args.episodes}, policy={args.policy}"
    )
    for ep in range(args.episodes):
        print(f"Episode {ep + 1}/{args.episodes}")
        traj = run_episode(
            env=env,
            episode_id=str(uuid.uuid4()),
            policy=args.policy,
            max_steps=args.max_steps,
        )
        traj.save(out_dir / f"{traj.episode_id}.json")
        trajectories.append(traj)

    dataset = TrajectoryDataset(trajectories)
    stats = EvaluationSuite.online_metrics(trajectories)

    print("\nRun complete.")
    print(f"Saved trajectories to: {out_dir}")
    print("Online metrics:")
    for metric in stats:
        print(f"  - {metric.name}: {metric.value:.4f}")

    print(f"Summary: {dataset.summary()}")


if __name__ == "__main__":
    main()