File size: 13,291 Bytes
ae75aa1
 
 
 
3367165
ae75aa1
 
b7abdc5
ae75aa1
66b0297
3367165
df00fce
1094a5f
3367165
 
 
 
 
3e64e9c
 
b7abdc5
ae75aa1
 
 
 
76bb74c
ae75aa1
 
76bb74c
3367165
 
 
 
 
 
 
 
 
 
ae75aa1
 
3367165
 
1094a5f
3367165
ae75aa1
3367165
 
 
 
 
 
 
 
 
 
ae75aa1
3367165
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ae75aa1
 
 
 
3367165
 
 
76bb74c
3367165
 
 
 
 
 
 
 
 
df00fce
3367165
ae75aa1
3367165
 
66b0297
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3367165
 
66b0297
 
 
3367165
 
66b0297
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3367165
 
 
 
66b0297
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3367165
 
 
ae75aa1
df00fce
3367165
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ae75aa1
 
 
 
3367165
 
 
76bb74c
3367165
1094a5f
3367165
 
1094a5f
 
3367165
 
1094a5f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3367165
1094a5f
 
3367165
 
 
 
 
 
ae75aa1
3367165
 
 
 
 
 
 
 
 
 
 
ae75aa1
1094a5f
 
 
3367165
1094a5f
 
3367165
1094a5f
 
 
3367165
1094a5f
 
3367165
1094a5f
 
3367165
 
df00fce
1094a5f
df00fce
1094a5f
df00fce
1094a5f
ae75aa1
 
 
 
3367165
 
 
 
 
ae75aa1
3367165
 
 
 
 
 
 
 
 
 
ae75aa1
 
 
3367165
ae75aa1
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
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
{
  "cells": [
    {
      "cell_type": "markdown",
      "id": "024bb8a8",
      "metadata": {},
      "source": [
        "# 🚀 NTv3 Quickstart — Pre-trained and Post-trained models\n",
        "\n",
        "This notebook demonstrates how to run **quick inference** with both the pre- and post-trained NTv3 checkpoints:\n",
        "\n",
        "- **Pre-trained (MLM-focused):** `InstaDeepAI/NTv3_8M_pre`, `InstaDeepAI/NTv3_100M_pre`, `InstaDeepAI/NTv3_650M_pre`\n",
        "- **Post-trained (functional tracks and genome annotation):** `InstaDeepAI/NTv3_100M_pos`, `InstaDeepAI/NTv3_650M_pos`\n",
        "\n",
        "We show how to:\n",
        "\n",
        "1. Load tokenizers + models\n",
        "2. Run a forward pass on a DNA sequence window\n",
        "3. Inspect key outputs\n",
        "\n",
        "> 📝 **Note for Google Colab users:** This notebook is compatible with Colab! For faster inference, make sure to enable GPU: Runtime → Change runtime type → GPU (T4 or better recommended)."
      ]
    },
    {
      "cell_type": "markdown",
      "id": "5827af7e",
      "metadata": {},
      "source": [
        "## 0) 📦 Imports + setup"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "id": "38cc32a9",
      "metadata": {},
      "outputs": [],
      "source": [
        "!pip -q install \"transformers>=4.40\" \"huggingface_hub>=0.23\" safetensors torch numpy"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 3,
      "id": "d56c105b",
      "metadata": {},
      "outputs": [
        {
          "name": "stdout",
          "output_type": "stream",
          "text": [
            "device: cpu\n",
            "torch_dtype: torch.float32\n"
          ]
        }
      ],
      "source": [
        "import os\n",
        "import torch\n",
        "import numpy as np\n",
        "\n",
        "from transformers import AutoConfig, AutoModel, AutoTokenizer, AutoModelForMaskedLM\n",
        "\n",
        "# Optional: if the model is gated/private, set HF_TOKEN to a PERSONAL token (hf_...)\n",
        "HF_TOKEN = os.getenv(\"HF_TOKEN\", None)\n",
        "\n",
        "# -----------------------------\n",
        "# Device\n",
        "# -----------------------------\n",
        "device = \"cuda\" if torch.cuda.is_available() else \"cpu\"\n",
        "print(\"device:\", device)\n",
        "\n",
        "# Choose dtype (bf16 if supported; else fp16 on GPU; else fp32)\n",
        "if device == \"cuda\":\n",
        "    major, minor = torch.cuda.get_device_capability(0)\n",
        "    torch_dtype = torch.bfloat16 if major >= 8 else torch.float16\n",
        "else:\n",
        "    torch_dtype = torch.float32\n",
        "\n",
        "print(\"torch_dtype:\", torch_dtype)"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "82146876",
      "metadata": {},
      "source": [
        "## 1) 🎯 Pre-trained checkpoint (MLM-focused)\n",
        "\n",
        "This shows the simplest usage: load model + tokenizer, then run a forward pass.\n",
        "\n",
        "Expected output:\n",
        "- `logits`: masked language modeling logits"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "id": "336bb40c",
      "metadata": {},
      "outputs": [
        {
          "data": {
            "application/vnd.jupyter.widget-view+json": {
              "model_id": "411ee47e94ae467f9685c35b65e3e52d",
              "version_major": 2,
              "version_minor": 0
            },
            "text/plain": [
              "tokenizer_config.json:   0%|          | 0.00/1.48k [00:00<?, ?B/s]"
            ]
          },
          "metadata": {},
          "output_type": "display_data"
        },
        {
          "data": {
            "application/vnd.jupyter.widget-view+json": {
              "model_id": "30447edb44b849bd936290f3a6b1b863",
              "version_major": 2,
              "version_minor": 0
            },
            "text/plain": [
              "tokenization_ntv3.py:   0%|          | 0.00/12.0k [00:00<?, ?B/s]"
            ]
          },
          "metadata": {},
          "output_type": "display_data"
        },
        {
          "name": "stderr",
          "output_type": "stream",
          "text": [
            "A new version of the following files was downloaded from https://huggingface.co/InstaDeepAI/ntv3_base_model:\n",
            "- tokenization_ntv3.py\n",
            ". Make sure to double-check they do not contain any added malicious code. To avoid downloading new versions of the code file, you can pin a revision.\n"
          ]
        },
        {
          "data": {
            "application/vnd.jupyter.widget-view+json": {
              "model_id": "766f183dcc84421588e5cf0241d3efe7",
              "version_major": 2,
              "version_minor": 0
            },
            "text/plain": [
              "vocab.json:   0%|          | 0.00/138 [00:00<?, ?B/s]"
            ]
          },
          "metadata": {},
          "output_type": "display_data"
        },
        {
          "data": {
            "application/vnd.jupyter.widget-view+json": {
              "model_id": "b0db83f7cb824d3288a30bebf7891a63",
              "version_major": 2,
              "version_minor": 0
            },
            "text/plain": [
              "special_tokens_map.json:   0%|          | 0.00/149 [00:00<?, ?B/s]"
            ]
          },
          "metadata": {},
          "output_type": "display_data"
        },
        {
          "data": {
            "application/vnd.jupyter.widget-view+json": {
              "model_id": "33cf5391dcc549f088e4e927651d1cdb",
              "version_major": 2,
              "version_minor": 0
            },
            "text/plain": [
              "config.json:   0%|          | 0.00/1.70k [00:00<?, ?B/s]"
            ]
          },
          "metadata": {},
          "output_type": "display_data"
        },
        {
          "data": {
            "application/vnd.jupyter.widget-view+json": {
              "model_id": "85772d5369234ca286cfa518e1725b12",
              "version_major": 2,
              "version_minor": 0
            },
            "text/plain": [
              "configuration_ntv3.py:   0%|          | 0.00/5.90k [00:00<?, ?B/s]"
            ]
          },
          "metadata": {},
          "output_type": "display_data"
        },
        {
          "name": "stderr",
          "output_type": "stream",
          "text": [
            "A new version of the following files was downloaded from https://huggingface.co/InstaDeepAI/ntv3_base_model:\n",
            "- configuration_ntv3.py\n",
            ". Make sure to double-check they do not contain any added malicious code. To avoid downloading new versions of the code file, you can pin a revision.\n"
          ]
        },
        {
          "data": {
            "application/vnd.jupyter.widget-view+json": {
              "model_id": "ec1153d073e444c5b255ee5adea6ba68",
              "version_major": 2,
              "version_minor": 0
            },
            "text/plain": [
              "modeling_ntv3_base.py:   0%|          | 0.00/33.9k [00:00<?, ?B/s]"
            ]
          },
          "metadata": {},
          "output_type": "display_data"
        },
        {
          "name": "stderr",
          "output_type": "stream",
          "text": [
            "A new version of the following files was downloaded from https://huggingface.co/InstaDeepAI/ntv3_base_model:\n",
            "- modeling_ntv3_base.py\n",
            ". Make sure to double-check they do not contain any added malicious code. To avoid downloading new versions of the code file, you can pin a revision.\n"
          ]
        },
        {
          "data": {
            "application/vnd.jupyter.widget-view+json": {
              "model_id": "94b9bb7fe0da4f4994adb9127d9af7e6",
              "version_major": 2,
              "version_minor": 0
            },
            "text/plain": [
              "model.safetensors:   0%|          | 0.00/30.8M [00:00<?, ?B/s]"
            ]
          },
          "metadata": {},
          "output_type": "display_data"
        },
        {
          "name": "stdout",
          "output_type": "stream",
          "text": [
            "torch.Size([2, 128, 11])\n",
            "16\n",
            "2\n",
            "MLM logits shape: (2, 128, 11)\n"
          ]
        }
      ],
      "source": [
        "pretrained_model_name = \"InstaDeepAI/NTv3_8M_pre\"\n",
        "\n",
        "# Load tokenizer/model\n",
        "tok_pre = AutoTokenizer.from_pretrained(pretrained_model_name, trust_remote_code=True)\n",
        "model_pre = AutoModelForMaskedLM.from_pretrained(pretrained_model_name, trust_remote_code=True)\n",
        "\n",
        "# Example: human sequence\n",
        "seqs = [\"ATCGNATCG\", \"ACGT\"]\n",
        "batch = tok_pre(seqs, add_special_tokens=False, padding=True, pad_to_multiple_of=128, return_tensors=\"pt\")\n",
        "out = model_pre(**batch, output_hidden_states=True, output_attentions=True)\n",
        "\n",
        "print(out.logits.shape)       # (B, L, V = 11)\n",
        "print(len(out.hidden_states)) # convs + transformers + deconvs\n",
        "print(len(out.attentions))\n",
        "\n",
        "# Access MLM logits\n",
        "mlm_logits = out[\"logits\"]\n",
        "print(\"MLM logits shape:\", tuple(mlm_logits.shape))"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "60a01798",
      "metadata": {},
      "source": [
        "## 2) 🧠 Post-trained checkpoint (task heads: BigWig + BED)\n",
        "\n",
        "Post-trained checkpoints add task-specific heads for functional track prediction and genome annotation.\n",
        "\n",
        "In particular:\n",
        "- `species_tokenizer` is used to tokenize a species condition like `\"human\"`\n",
        "- `species_ids` passes the species tokens to the model\n",
        "\n",
        "Expected outputs:\n",
        "- `bigwig_tracks_logits`: functional track predictions\n",
        "- `bed_tracks_logits`: genome annotation predictions\n",
        "- `logits`: masked language modeling logits"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 9,
      "id": "bdb8c4d1",
      "metadata": {},
      "outputs": [
        {
          "name": "stdout",
          "output_type": "stream",
          "text": [
            "Model supported species: TO BE DONE\n"
          ]
        }
      ],
      "source": [
        "# Inspect config and supported species\n",
        "post_trained_model_name = \"InstaDeepAI/NTv3_100M_pos\"\n",
        "\n",
        "cfg_post = AutoConfig.from_pretrained(post_trained_model_name, trust_remote_code=True)\n",
        "\n",
        "species = \"TO BE DONE\"\n",
        "print(\"Model supported species:\", species)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "id": "6cc5f2df",
      "metadata": {},
      "outputs": [
        {
          "name": "stdout",
          "output_type": "stream",
          "text": [
            "torch.Size([1, 768, 7362])\n",
            "torch.Size([1, 768, 21, 2])\n",
            "torch.Size([1, 2048, 11])\n"
          ]
        }
      ],
      "source": [
        "tok_post = AutoTokenizer.from_pretrained(post_trained_model_name, trust_remote_code=True)\n",
        "cond_tok_post = AutoTokenizer.from_pretrained(post_trained_model_name, subfolder='species_tokenizer', trust_remote_code=True)\n",
        "model_post = AutoModel.from_pretrained(post_trained_model_name, trust_remote_code=True)\n",
        "\n",
        "# Prepare inputs\n",
        "batch = tok_post([\"ATCGNATCG\", \"ACGT\"], add_special_tokens=False, padding=True, pad_to_multiple_of=128, return_tensors=\"pt\")\n",
        "\n",
        "# Condition tokens (e.g., species)\n",
        "species = 'human'\n",
        "species_ids = cond_tok_post([species] * len(batch['input_ids']), add_special_tokens=False, return_tensors='pt')\n",
        "\n",
        "# Forward pass\n",
        "out = model_post(\n",
        "    input_ids=batch[\"input_ids\"],\n",
        "    species_ids=species_ids['input_ids'],\n",
        "    return_dict=True\n",
        ")\n",
        "\n",
        "# 7k human tracks over 37.5 % center region of the input sequence\n",
        "print(\"bigwig_tracks_logits:\", tuple(out[\"bigwig_tracks_logits\"].shape))\n",
        "# Location of 21 genomic elements over 37.5 % center region of the input sequence\n",
        "print(\"bed_tracks_logits:\", tuple(out[\"bed_tracks_logits\"].shape))\n",
        "# Language model logits for whole sequence over vocabulary\n",
        "print(\"language model logits:\", tuple(out[\"logits\"].shape))\n"
      ]
    }
  ],
  "metadata": {
    "kernelspec": {
      "display_name": "hf-finetune",
      "language": "python",
      "name": "python3"
    },
    "language_info": {
      "codemirror_mode": {
        "name": "ipython",
        "version": 3
      },
      "file_extension": ".py",
      "mimetype": "text/x-python",
      "name": "python",
      "nbconvert_exporter": "python",
      "pygments_lexer": "ipython3",
      "version": "3.10.18"
    }
  },
  "nbformat": 4,
  "nbformat_minor": 5
}