File size: 10,813 Bytes
1d6f391
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
"""
Bertint V8 Dataset — Per-Residue Protein Embeddings for Cross-Attention

Like V7 but keeps per-residue ESM-C embeddings [L, D] instead of
mean-pooling to [D]. This enables token-level cross-attention between
glycan tokens and protein residues.

Changes from V7:
  - protein_emb: [Lp, 960] per-residue (not [960] mean-pooled)
  - collate_fn: pads protein sequences to max length in batch
  - Returns protein_mask for cross-attention padding
"""

import json
import logging
import os
from pathlib import Path
from typing import Dict, List, Optional, Tuple

import h5py
import numpy as np
import pandas as pd
import torch
from torch.utils.data import Dataset
from torch.nn.utils.rnn import pad_sequence

logger = logging.getLogger(__name__)


# ============================================================================
# BPE Tokenizer Loader (same as V7)
# ============================================================================

def load_bpe_tokenizer(vocab_path: str):
    """
    Load the Bertose BPE tokenizer directly from source.

    Bypasses downstream_tasks package imports. Adds utils
    directory to sys.path and imports WURCSBPETokenizer directly.

    Args:
        vocab_path: Path to BPE vocabulary JSON file.

    Returns:
        WURCSBPETokenizer instance.
    """
    import sys

    env_root = os.environ.get("BERTOSE_ROOT") or os.environ.get("BERTOSE_REPO_ROOT")
    candidate_roots = []
    if env_root:
        candidate_roots.append(Path(env_root).expanduser().resolve())
    candidate_roots.extend(Path(__file__).resolve().parents)
    candidate_roots.append(Path.cwd())

    utils_dir = None
    for root in candidate_roots:
        candidate = root / "bert_training_v4" / "downstream_tasks" / "utils"
        if candidate.exists():
            utils_dir = candidate
            break

    if utils_dir is None:
        utils_dir = Path(
            "/work/ratul1/supantha/glycan-SD-VS/bert_training_v3/"
            "v3.1_cluster_training/bert_training_v4/downstream_tasks/utils"
        )

    utils_dir = str(utils_dir)
    if utils_dir not in sys.path:
        sys.path.insert(0, utils_dir)

    from wurcs_bpe_tokenizer import WURCSBPETokenizer
    return WURCSBPETokenizer(vocab_path)


# ============================================================================
# Dataset
# ============================================================================

class BertintV8Dataset(Dataset):
    """
    Dataset for glycan-protein interaction with cross-attention support.

    Returns:
      - BPE-tokenized glycan sequences for live Bertose forward pass
      - Per-residue ESM-C protein embeddings [Lp, D] (NOT mean-pooled)
      - Masks for both sides (for cross-attention padding)

    Args:
        csv_path: Path to binding data CSV.
        split_path: Path to glycan-cold splits JSON.
        split: One of 'train', 'val', 'test'.
        protein_emb_path: Path to ESM-C embeddings HDF5.
        vocab_path: Path to BPE vocabulary JSON.
        max_glycan_length: Maximum glycan sequence length.
        max_protein_length: Maximum protein residues (truncate longer).
        target_col: Column name for regression target.
    """

    def __init__(
        self,
        csv_path: str,
        split_path: str,
        split: str,
        protein_emb_path: str,
        vocab_path: str,
        max_glycan_length: int = 256,
        max_protein_length: int = 1024,
        target_col: str = "target_rank",
    ):
        logger.info(f"Loading {split} dataset from {csv_path}")

        # Load splits
        with open(split_path) as f:
            splits_data = json.load(f)
        if "glycan_cold" in splits_data:
            splits_data = splits_data["glycan_cold"]
        split_glycans = set(splits_data[split])
        logger.info(f"  {split}: {len(split_glycans)} glycans in split")

        # Load and filter data
        df = pd.read_csv(csv_path)
        df = df[df["glycan_wurcs"].isin(split_glycans)].copy()
        df = df.dropna(subset=[target_col])
        logger.info(f"  {len(df):,} records after split + target filter")

        self.records = df.reset_index(drop=True)
        self.target_col = target_col
        self.max_protein_length = max_protein_length

        # Load BPE tokenizer
        logger.info(f"  Loading BPE tokenizer from {vocab_path}")
        self.tokenizer = load_bpe_tokenizer(vocab_path)
        self.max_glycan_length = max_glycan_length

        # Pre-tokenize all unique glycans
        unique_wurcs = df["glycan_wurcs"].unique()
        logger.info(f"  Pre-tokenizing {len(unique_wurcs)} unique glycans...")
        self.tokenized_cache: Dict[str, Dict[str, torch.Tensor]] = {}
        skipped = 0
        for wurcs in unique_wurcs:
            try:
                tok = self.tokenizer.tokenize(
                    wurcs, max_length=max_glycan_length
                )
                self.tokenized_cache[wurcs] = {
                    "token_ids": torch.tensor(
                        tok["token_ids"], dtype=torch.long
                    ),
                    "attention_mask": torch.tensor(
                        tok["attention_mask"], dtype=torch.long
                    ),
                    "branch_depths": torch.tensor(
                        tok["branch_depths"], dtype=torch.long
                    ),
                    "linkage_types": torch.tensor(
                        tok["linkage_types"], dtype=torch.long
                    ),
                }
            except (KeyError, ValueError) as exc:
                skipped += 1
                if skipped <= 5:
                    logger.warning(
                        f"    Tokenization failed for WURCS: "
                        f"{wurcs[:60]}... ({exc})"
                    )
        if skipped > 0:
            logger.warning(
                f"    Skipped {skipped} glycans with tokenization errors"
            )
            self.records = self.records[
                self.records["glycan_wurcs"].isin(self.tokenized_cache)
            ].reset_index(drop=True)
            logger.info(
                f"  {len(self.records):,} records after removing "
                f"un-tokenizable"
            )

        # Load protein embeddings — KEEP PER-RESIDUE (not mean-pooled!)
        logger.info(f"  Loading per-residue protein embeddings...")
        self.protein_embs: Dict[str, torch.Tensor] = {}
        with h5py.File(protein_emb_path, "r") as f:
            for key in f.keys():
                emb = torch.from_numpy(f[key][:]).float()
                # emb: [L, D] per-residue
                if emb.dim() == 1:
                    # Edge case: single-residue protein
                    emb = emb.unsqueeze(0)
                # Truncate very long proteins
                if emb.shape[0] > max_protein_length:
                    emb = emb[:max_protein_length]
                protein_id = key.replace("|", "/")
                self.protein_embs[protein_id] = emb
        logger.info(f"    {len(self.protein_embs)} proteins loaded")

        # Log protein length statistics
        lengths = [v.shape[0] for v in self.protein_embs.values()]
        logger.info(
            f"    Protein lengths: min={min(lengths)}, "
            f"max={max(lengths)}, mean={np.mean(lengths):.0f}"
        )

        # Filter to records with available embeddings
        available = set(self.protein_embs.keys())
        has_protein = self.records["protein_id"].isin(available)
        if not has_protein.all():
            missing = (~has_protein).sum()
            logger.warning(
                f"    {missing} records missing protein embeddings"
            )
            self.records = self.records[has_protein].reset_index(drop=True)

        logger.info(f"  Final {split} dataset: {len(self.records):,} records")

    def __len__(self) -> int:
        return len(self.records)

    def __getitem__(self, idx: int) -> Dict[str, torch.Tensor]:
        row = self.records.iloc[idx]
        wurcs = row["glycan_wurcs"]
        protein_id = row["protein_id"]

        # Glycan tokens (pre-cached, already padded to max_glycan_length)
        cached = self.tokenized_cache[wurcs]

        # Protein embedding — per-residue [Lp, D]
        protein_emb = self.protein_embs[protein_id]

        # Target
        target = torch.tensor(row[self.target_col], dtype=torch.float)

        # Concentration features
        has_conc = torch.tensor(row.get("has_conc", 0), dtype=torch.float)
        log_conc = torch.tensor(row.get("log_conc", 0.0), dtype=torch.float)

        return {
            "token_ids": cached["token_ids"],
            "attention_mask": cached["attention_mask"],
            "branch_depths": cached["branch_depths"],
            "linkage_types": cached["linkage_types"],
            "protein_emb": protein_emb,        # [Lp, D] variable-length!
            "protein_length": protein_emb.shape[0],
            "target": target,
            "has_conc": has_conc,
            "log_conc": log_conc,
        }


def collate_fn(
    batch: List[Dict[str, torch.Tensor]],
) -> Dict[str, torch.Tensor]:
    """
    Collate with variable-length protein padding.

    Glycan sequences are already padded (BPE tokenizer pads to
    max_glycan_length). Protein sequences need padding to the
    max length in the batch.
    """
    # Glycan: already fixed-length, just stack
    token_ids = torch.stack([item["token_ids"] for item in batch])
    attention_mask = torch.stack(
        [item["attention_mask"] for item in batch]
    ).float()
    branch_depths = torch.stack(
        [item["branch_depths"] for item in batch]
    )
    linkage_types = torch.stack(
        [item["linkage_types"] for item in batch]
    )

    # Protein: variable-length → pad to max in batch
    protein_embs = [item["protein_emb"] for item in batch]
    protein_padded = pad_sequence(protein_embs, batch_first=True)  # [B, Lp_max, D]

    # Protein mask: 1 for real residues, 0 for padding
    protein_lengths = [item["protein_length"] for item in batch]
    max_prot_len = protein_padded.shape[1]
    protein_mask = torch.zeros(len(batch), max_prot_len)
    for i, length in enumerate(protein_lengths):
        protein_mask[i, :length] = 1.0

    # Targets and metadata
    targets = torch.stack([item["target"] for item in batch])
    has_conc = torch.stack([item["has_conc"] for item in batch])
    log_conc = torch.stack([item["log_conc"] for item in batch])

    return {
        "token_ids": token_ids,
        "attention_mask": attention_mask,
        "branch_depths": branch_depths,
        "linkage_types": linkage_types,
        "protein_emb": protein_padded,    # [B, Lp_max, D]
        "protein_mask": protein_mask,      # [B, Lp_max]
        "target": targets,
        "has_conc": has_conc,
        "log_conc": log_conc,
    }