fix: main page links

notebooks_tutorials/01_tracks_prediction.ipynb

@@ -108,7 +108,233 @@
     },
     {
       "cell_type": "code",
-      "execution_count": 4,
+      "execution_count": null,
+      "id": "6193fd37",
+      "metadata": {},
+      "outputs": [
+        {
+          "data": {
+            "text/html": [
+              "<div>\n",
+              "<style scoped>\n",
+              "    .dataframe tbody tr th:only-of-type {\n",
+              "        vertical-align: middle;\n",
+              "    }\n",
+              "\n",
+              "    .dataframe tbody tr th {\n",
+              "        vertical-align: top;\n",
+              "    }\n",
+              "\n",
+              "    .dataframe thead th {\n",
+              "        text-align: right;\n",
+              "    }\n",
+              "</style>\n",
+              "<table border=\"1\" class=\"dataframe\">\n",
+              "  <thead>\n",
+              "    <tr style=\"text-align: right;\">\n",
+              "      <th></th>\n",
+              "      <th>file_id</th>\n",
+              "      <th>biosample_type</th>\n",
+              "      <th>tissue</th>\n",
+              "      <th>assay</th>\n",
+              "      <th>strand</th>\n",
+              "      <th>experiment_target</th>\n",
+              "      <th>specie</th>\n",
+              "      <th>dataset</th>\n",
+              "    </tr>\n",
+              "  </thead>\n",
+              "  <tbody>\n",
+              "    <tr>\n",
+              "      <th>0</th>\n",
+              "      <td>SRX20249461</td>\n",
+              "      <td>tissue</td>\n",
+              "      <td>Leaf (17 days)</td>\n",
+              "      <td>TF ChIP-seq</td>\n",
+              "      <td>NaN</td>\n",
+              "      <td>JMJ20</td>\n",
+              "      <td>glycine_max</td>\n",
+              "      <td>ncbi_chrom_acc</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>1</th>\n",
+              "      <td>SRX20249462</td>\n",
+              "      <td>tissue</td>\n",
+              "      <td>Leaf (17 days)</td>\n",
+              "      <td>TF ChIP-seq</td>\n",
+              "      <td>NaN</td>\n",
+              "      <td>FLAG</td>\n",
+              "      <td>glycine_max</td>\n",
+              "      <td>ncbi_chrom_acc</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>2</th>\n",
+              "      <td>SRX21859141</td>\n",
+              "      <td>tissue</td>\n",
+              "      <td>Seed (60 days)</td>\n",
+              "      <td>Histone ChIP-seq</td>\n",
+              "      <td>NaN</td>\n",
+              "      <td>H3K27me3</td>\n",
+              "      <td>glycine_max</td>\n",
+              "      <td>ncbi_chrom_acc</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>3</th>\n",
+              "      <td>SRX21859142</td>\n",
+              "      <td>tissue</td>\n",
+              "      <td>Seed (60 days)</td>\n",
+              "      <td>Histone ChIP-seq</td>\n",
+              "      <td>NaN</td>\n",
+              "      <td>H3K27me3</td>\n",
+              "      <td>glycine_max</td>\n",
+              "      <td>ncbi_chrom_acc</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>4</th>\n",
+              "      <td>SRX21859143</td>\n",
+              "      <td>tissue</td>\n",
+              "      <td>Seed (60 days)</td>\n",
+              "      <td>Histone ChIP-seq</td>\n",
+              "      <td>NaN</td>\n",
+              "      <td>H3K4me3</td>\n",
+              "      <td>glycine_max</td>\n",
+              "      <td>ncbi_chrom_acc</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>...</th>\n",
+              "      <td>...</td>\n",
+              "      <td>...</td>\n",
+              "      <td>...</td>\n",
+              "      <td>...</td>\n",
+              "      <td>...</td>\n",
+              "      <td>...</td>\n",
+              "      <td>...</td>\n",
+              "      <td>...</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>15884</th>\n",
+              "      <td>GSM874952</td>\n",
+              "      <td>Unknown</td>\n",
+              "      <td>NaN</td>\n",
+              "      <td>TF ChIP-seq</td>\n",
+              "      <td>NaN</td>\n",
+              "      <td>RPB2</td>\n",
+              "      <td>mouse</td>\n",
+              "      <td>geo</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>15885</th>\n",
+              "      <td>GSM874953</td>\n",
+              "      <td>Unknown</td>\n",
+              "      <td>NaN</td>\n",
+              "      <td>TF ChIP-seq</td>\n",
+              "      <td>NaN</td>\n",
+              "      <td>RPB2</td>\n",
+              "      <td>mouse</td>\n",
+              "      <td>geo</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>15886</th>\n",
+              "      <td>GSM874954</td>\n",
+              "      <td>Unknown</td>\n",
+              "      <td>NaN</td>\n",
+              "      <td>TF ChIP-seq</td>\n",
+              "      <td>NaN</td>\n",
+              "      <td>RPB2</td>\n",
+              "      <td>mouse</td>\n",
+              "      <td>geo</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>15887</th>\n",
+              "      <td>GSM874955</td>\n",
+              "      <td>Unknown</td>\n",
+              "      <td>NaN</td>\n",
+              "      <td>TF ChIP-seq</td>\n",
+              "      <td>NaN</td>\n",
+              "      <td>RPB2</td>\n",
+              "      <td>mouse</td>\n",
+              "      <td>geo</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>15888</th>\n",
+              "      <td>GSM874956</td>\n",
+              "      <td>Unknown</td>\n",
+              "      <td>NaN</td>\n",
+              "      <td>TF ChIP-seq</td>\n",
+              "      <td>NaN</td>\n",
+              "      <td>RPB2</td>\n",
+              "      <td>mouse</td>\n",
+              "      <td>geo</td>\n",
+              "    </tr>\n",
+              "  </tbody>\n",
+              "</table>\n",
+              "<p>15889 rows × 8 columns</p>\n",
+              "</div>"
+            ],
+            "text/plain": [
+              "           file_id biosample_type          tissue             assay strand  \\\n",
+              "0      SRX20249461         tissue  Leaf (17 days)       TF ChIP-seq    NaN   \n",
+              "1      SRX20249462         tissue  Leaf (17 days)       TF ChIP-seq    NaN   \n",
+              "2      SRX21859141         tissue  Seed (60 days)  Histone ChIP-seq    NaN   \n",
+              "3      SRX21859142         tissue  Seed (60 days)  Histone ChIP-seq    NaN   \n",
+              "4      SRX21859143         tissue  Seed (60 days)  Histone ChIP-seq    NaN   \n",
+              "...            ...            ...             ...               ...    ...   \n",
+              "15884    GSM874952        Unknown             NaN       TF ChIP-seq    NaN   \n",
+              "15885    GSM874953        Unknown             NaN       TF ChIP-seq    NaN   \n",
+              "15886    GSM874954        Unknown             NaN       TF ChIP-seq    NaN   \n",
+              "15887    GSM874955        Unknown             NaN       TF ChIP-seq    NaN   \n",
+              "15888    GSM874956        Unknown             NaN       TF ChIP-seq    NaN   \n",
+              "\n",
+              "      experiment_target       specie         dataset  \n",
+              "0                 JMJ20  glycine_max  ncbi_chrom_acc  \n",
+              "1                  FLAG  glycine_max  ncbi_chrom_acc  \n",
+              "2              H3K27me3  glycine_max  ncbi_chrom_acc  \n",
+              "3              H3K27me3  glycine_max  ncbi_chrom_acc  \n",
+              "4               H3K4me3  glycine_max  ncbi_chrom_acc  \n",
+              "...                 ...          ...             ...  \n",
+              "15884              RPB2        mouse             geo  \n",
+              "15885              RPB2        mouse             geo  \n",
+              "15886              RPB2        mouse             geo  \n",
+              "15887              RPB2        mouse             geo  \n",
+              "15888              RPB2        mouse             geo  \n",
+              "\n",
+              "[15889 rows x 8 columns]"
+            ]
+          },
+          "execution_count": 15,
+          "metadata": {},
+          "output_type": "execute_result"
+        }
+      ],
+      "source": [
+        "import pandas as pd\n",
+        "\n",
+        "df = pd.read_csv(\"/Users/b.dealmeida/Downloads/Supplementary_tables - Post-training functional tracks.tsv\", sep=\"\\t\")"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 17,
+      "id": "5f686ba9",
+      "metadata": {},
+      "outputs": [
+        {
+          "data": {
+            "text/plain": [
+              "2765"
+            ]
+          },
+          "execution_count": 17,
+          "metadata": {},
+          "output_type": "execute_result"
+        }
+      ],
+      "source": [
+        "len(df.tissue.unique())"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
       "id": "795a576f",
       "metadata": {},
       "outputs": [],
@@ -122,9 +348,9 @@
         "species = \"human\"  # will use for condition the model on species\n",
         "assembly = \"hg38\"  # will use for fetching the chromosome sequence\n",
         "chrom = \"chr19\"\n",
-        "start = 6_700_000\n",
-        "end   = 6_765_536\n",
-        "# Limiting to 65kb to work on Google Colab T4 GPU -> increase up to 1 million nucleotides if you have a better GPU\n",
+        "start = 6_749_152\n",
+        "end   = 6_781_920\n",
+        "# Using center 32kb window (32,768 bp) for faster inference\n",
         "\n",
         "# Optional\n",
         "HF_TOKEN = os.getenv(\"HF_TOKEN\", None)"

tabs/home.html

@@ -49,30 +49,30 @@
           <th>Size</th>
           <th>Pre-training</th>
           <th>Post-training</th>
-          <th>Tasks</th>
+          <th>Usage</th>
         </tr>
       </thead>
       <tbody>
         <tr>
           <td><strong>NTv3-8M</strong></td>
           <td>8M params</td>
-          <td>MLM</td>
+          <td><span class="checkmark">✅</span></td>
           <td>❌</td>
           <td>Embeddings, light inference</td>
         </tr>
         <tr>
           <td><strong>NTv3-100M</strong></td>
           <td>100M params</td>
-          <td>MLM</td>
           <td><span class="checkmark">✅</span></td>
-          <td>Tracks, annotation</td>
+          <td><span class="checkmark">✅</span></td>
+          <td>Embeddings, Tracks, annotation</td>
         </tr>
         <tr>
           <td><strong>NTv3-650M</strong></td>
           <td>650M params</td>
-          <td>MLM</td>
           <td><span class="checkmark">✅</span></td>
-          <td>Tracks, annotation, best accuracy</td>
+          <td><span class="checkmark">✅</span></td>
+          <td>Embeddings, Tracks, annotation, best accuracy</td>
         </tr>
       </tbody>
     </table>
@@ -86,7 +86,8 @@
         <li><a href="https://huggingface.co/spaces/InstaDeepAI/ntv3/blob/main/notebooks_tutorials/01_tracks_prediction.ipynb" target="_blank" rel="noopener noreferrer">📊 01 — Tracks prediction</a></li>
         <li><a href="https://huggingface.co/spaces/InstaDeepAI/ntv3/blob/main/notebooks_tutorials/02_fine_tuning.ipynb" target="_blank" rel="noopener noreferrer">🎯 02 — Fine-tune on bigwig tracks</a></li>
         <li><a href="https://huggingface.co/spaces/InstaDeepAI/ntv3/blob/main/notebooks_tutorials/03_model_interpretation.ipynb" target="_blank" rel="noopener noreferrer">🔍 03 — Model interpretation</a></li>
-        <li>🧪 04 — Training NTv3 generative </li>
+        <li>🧪 04 — Training NTv3-generative <em>(coming soon)</em></li>
+        <li>🧪 04 — Generating enhancer sequences <em>(coming soon)</em></li>
       </ul>
     </div>
     <div class="card">
@@ -95,7 +96,7 @@
         <li><a href="https://huggingface.co/spaces/InstaDeepAI/ntv3/blob/main/notebooks_pipelines/01_functional_track_prediction.ipynb" target="_blank" rel="noopener noreferrer">🎯 01 — Generate bigwig predictions for certain tracks</a></li>
         <li>🎯 02 — Fine-tune on bigwig tracks</li>
         <li>🔍 03 — Interpret a given genomic region</li>
-        <li>🧪 04 — Sequence generation</li>
+        <li>🧪 04 — Sequence generation <em>(coming soon)</em></li>
       </ul>
     </div>
     <div class="card">