Spaces:
Running
Running
Update mtdna_tool_explainer_updated.html
Browse files- mtdna_tool_explainer_updated.html +135 -135
mtdna_tool_explainer_updated.html
CHANGED
|
@@ -1,135 +1,135 @@
|
|
| 1 |
-
<!DOCTYPE html>
|
| 2 |
-
<html lang="en">
|
| 3 |
-
<head>
|
| 4 |
-
<meta charset="UTF-8">
|
| 5 |
-
<meta name="viewport" content="width=device-width, initial-scale=1.0">
|
| 6 |
-
<title>
|
| 7 |
-
|
| 8 |
-
<style>
|
| 9 |
-
.custom-container {
|
| 10 |
-
background-color: #ffffff !important;
|
| 11 |
-
color: #222222 !important;
|
| 12 |
-
font-family: Arial, sans-serif !important;
|
| 13 |
-
line-height: 1.6 !important;
|
| 14 |
-
padding: 2rem !important;
|
| 15 |
-
max-width: 900px !important;
|
| 16 |
-
margin: auto !important;
|
| 17 |
-
}
|
| 18 |
-
|
| 19 |
-
.custom-container h1,
|
| 20 |
-
.custom-container h2,
|
| 21 |
-
.custom-container h3,
|
| 22 |
-
.custom-container strong,
|
| 23 |
-
.custom-container b,
|
| 24 |
-
.custom-container p,
|
| 25 |
-
.custom-container li,
|
| 26 |
-
.custom-container ol,
|
| 27 |
-
.custom-container ul,
|
| 28 |
-
.custom-container span {
|
| 29 |
-
color: #222222 !important;
|
| 30 |
-
font-weight: normal !important;
|
| 31 |
-
}
|
| 32 |
-
|
| 33 |
-
.custom-container h1,
|
| 34 |
-
.custom-container h2 {
|
| 35 |
-
font-weight: bold !important;
|
| 36 |
-
}
|
| 37 |
-
|
| 38 |
-
.custom-container img {
|
| 39 |
-
max-width: 100%;
|
| 40 |
-
border: 1px solid #ccc;
|
| 41 |
-
padding: 5px;
|
| 42 |
-
background: #fff;
|
| 43 |
-
}
|
| 44 |
-
|
| 45 |
-
.custom-container code {
|
| 46 |
-
background: none !important;
|
| 47 |
-
color: #222 !important;
|
| 48 |
-
font-family: inherit !important;
|
| 49 |
-
font-size: inherit !important;
|
| 50 |
-
padding: 0 !important;
|
| 51 |
-
border-radius: 0 !important;
|
| 52 |
-
}
|
| 53 |
-
|
| 54 |
-
|
| 55 |
-
.custom-container .highlight {
|
| 56 |
-
background: #ffffcc;
|
| 57 |
-
padding: 4px 8px;
|
| 58 |
-
border-left: 4px solid #ffcc00;
|
| 59 |
-
margin: 1rem 0;
|
| 60 |
-
color: #333 !important;
|
| 61 |
-
}
|
| 62 |
-
</style>
|
| 63 |
-
</head>
|
| 64 |
-
|
| 65 |
-
<body>
|
| 66 |
-
<div class="custom-container">
|
| 67 |
-
|
| 68 |
-
<h1>
|
| 69 |
-
|
| 70 |
-
<p>The <strong>
|
| 71 |
-
|
| 72 |
-
<h2>System Overview Diagram</h2>
|
| 73 |
-
<p>The figure below shows the core execution flow—from input accession to final output.</p>
|
| 74 |
-
<img src="https://huggingface.co/spaces/VyLala/mtDNALocation/resolve/main/flowchart.png" alt="
|
| 75 |
-
|
| 76 |
-
|
| 77 |
-
<h2>Key Steps</h2>
|
| 78 |
-
<ol>
|
| 79 |
-
<li><strong>Input</strong>: One or more GenBank accession numbers are submitted (e.g., via UI, CSV, or text).</li>
|
| 80 |
-
|
| 81 |
-
<li><strong>Metadata Collection</strong>: Using <code>fetch_ncbi_metadata</code>, the pipeline retrieves metadata like country, isolate, collection date, and reference title. If available, supplementary material and full-text articles are parsed using DOI, PubMed, or Google Custom Search.</li>
|
| 82 |
-
|
| 83 |
-
<li><strong>Text Extraction & Preprocessing</strong>:
|
| 84 |
-
<ul>
|
| 85 |
-
<li>All available documents are parsed and cleaned (tables, paragraphs, overlapping sections).</li>
|
| 86 |
-
<li>Text is merged into two formats: a smaller <code>chunk</code> and a full <code>all_output</code>.</li>
|
| 87 |
-
</ul>
|
| 88 |
-
</li>
|
| 89 |
-
|
| 90 |
-
<li><strong>LLM-based Inference (Gemini + RAG)</strong>:
|
| 91 |
-
<ul>
|
| 92 |
-
<li>Chunks are embedded with FAISS and stored for reuse.</li>
|
| 93 |
-
<li>The Gemini model answers specific queries like predicted country, sample type, and any niche label requested by the user.</li>
|
| 94 |
-
</ul>
|
| 95 |
-
</li>
|
| 96 |
-
|
| 97 |
-
<li><strong>Result Structuring</strong>:
|
| 98 |
-
<ul>
|
| 99 |
-
<li>Each output includes predicted fields + explanation text (methods used, quotes, sources).</li>
|
| 100 |
-
<li>Summarized and saved using <code>save_to_excel</code>.</li>
|
| 101 |
-
</ul>
|
| 102 |
-
</li>
|
| 103 |
-
</ol>
|
| 104 |
-
|
| 105 |
-
<h2>Output Format</h2>
|
| 106 |
-
<p>The final output is an Excel file with the following fields:</p>
|
| 107 |
-
<ul>
|
| 108 |
-
<li><code>Sample ID</code></li>
|
| 109 |
-
<li><code>Predicted Country</code> and <code>Country Explanation</code></li>
|
| 110 |
-
<li><code>Predicted Sample Type</code> and <code>Sample Type Explanation</code></li>
|
| 111 |
-
<li><code>Sources</code> (links to articles)</li>
|
| 112 |
-
<li><code>Time Cost</code></li>
|
| 113 |
-
</ul>
|
| 114 |
-
|
| 115 |
-
<h2>System Highlights</h2>
|
| 116 |
-
<ul>
|
| 117 |
-
<li>RAG + Gemini integration for improved explanation and transparency</li>
|
| 118 |
-
<li>Excel export for structured research use</li>
|
| 119 |
-
<li>Optional ethnic/location/language inference using isolate names</li>
|
| 120 |
-
<li>Quality check (e.g., fallback on short explanations, low token count)</li>
|
| 121 |
-
<li>Report Button – After results are displayed, users can submit errors or mismatches using the report text box below the output table</li>
|
| 122 |
-
</ul>
|
| 123 |
-
|
| 124 |
-
<h2>Citation</h2>
|
| 125 |
-
<div class="highlight">
|
| 126 |
-
Phung, V. (2025).
|
| 127 |
-
</div>
|
| 128 |
-
|
| 129 |
-
<h2>Contact</h2>
|
| 130 |
-
<p>If you are a researcher working with
|
| 131 |
-
|
| 132 |
-
</div>
|
| 133 |
-
</body>
|
| 134 |
-
</html>
|
| 135 |
-
|
|
|
|
| 1 |
+
<!DOCTYPE html>
|
| 2 |
+
<html lang="en">
|
| 3 |
+
<head>
|
| 4 |
+
<meta charset="UTF-8">
|
| 5 |
+
<meta name="viewport" content="width=device-width, initial-scale=1.0">
|
| 6 |
+
<title>BioMetadataAudit – System Overview</title>
|
| 7 |
+
|
| 8 |
+
<style>
|
| 9 |
+
.custom-container {
|
| 10 |
+
background-color: #ffffff !important;
|
| 11 |
+
color: #222222 !important;
|
| 12 |
+
font-family: Arial, sans-serif !important;
|
| 13 |
+
line-height: 1.6 !important;
|
| 14 |
+
padding: 2rem !important;
|
| 15 |
+
max-width: 900px !important;
|
| 16 |
+
margin: auto !important;
|
| 17 |
+
}
|
| 18 |
+
|
| 19 |
+
.custom-container h1,
|
| 20 |
+
.custom-container h2,
|
| 21 |
+
.custom-container h3,
|
| 22 |
+
.custom-container strong,
|
| 23 |
+
.custom-container b,
|
| 24 |
+
.custom-container p,
|
| 25 |
+
.custom-container li,
|
| 26 |
+
.custom-container ol,
|
| 27 |
+
.custom-container ul,
|
| 28 |
+
.custom-container span {
|
| 29 |
+
color: #222222 !important;
|
| 30 |
+
font-weight: normal !important;
|
| 31 |
+
}
|
| 32 |
+
|
| 33 |
+
.custom-container h1,
|
| 34 |
+
.custom-container h2 {
|
| 35 |
+
font-weight: bold !important;
|
| 36 |
+
}
|
| 37 |
+
|
| 38 |
+
.custom-container img {
|
| 39 |
+
max-width: 100%;
|
| 40 |
+
border: 1px solid #ccc;
|
| 41 |
+
padding: 5px;
|
| 42 |
+
background: #fff;
|
| 43 |
+
}
|
| 44 |
+
|
| 45 |
+
.custom-container code {
|
| 46 |
+
background: none !important;
|
| 47 |
+
color: #222 !important;
|
| 48 |
+
font-family: inherit !important;
|
| 49 |
+
font-size: inherit !important;
|
| 50 |
+
padding: 0 !important;
|
| 51 |
+
border-radius: 0 !important;
|
| 52 |
+
}
|
| 53 |
+
|
| 54 |
+
|
| 55 |
+
.custom-container .highlight {
|
| 56 |
+
background: #ffffcc;
|
| 57 |
+
padding: 4px 8px;
|
| 58 |
+
border-left: 4px solid #ffcc00;
|
| 59 |
+
margin: 1rem 0;
|
| 60 |
+
color: #333 !important;
|
| 61 |
+
}
|
| 62 |
+
</style>
|
| 63 |
+
</head>
|
| 64 |
+
|
| 65 |
+
<body>
|
| 66 |
+
<div class="custom-container">
|
| 67 |
+
|
| 68 |
+
<h1>Bio Metadata AUdit – Brief System Pipeline and Usage Guide</h1>
|
| 69 |
+
|
| 70 |
+
<p>The <strong>BioMetadataAudit Tool</strong> is a lightweight pipeline designed to help researchers extract metadata such as geographic origin, sample type (ancient/modern), and optional niche labels (e.g., ethnicity, specific location) from GenBank accession numbers. It supports batch input and produces structured Excel summaries.</p>
|
| 71 |
+
|
| 72 |
+
<h2>System Overview Diagram</h2>
|
| 73 |
+
<p>The figure below shows the core execution flow—from input accession to final output.</p>
|
| 74 |
+
<img src="https://huggingface.co/spaces/VyLala/mtDNALocation/resolve/main/flowchart.png" alt="BioMetadataAuditPipeline Flowchart">
|
| 75 |
+
|
| 76 |
+
|
| 77 |
+
<h2>Key Steps</h2>
|
| 78 |
+
<ol>
|
| 79 |
+
<li><strong>Input</strong>: One or more GenBank accession numbers are submitted (e.g., via UI, CSV, or text).</li>
|
| 80 |
+
|
| 81 |
+
<li><strong>Metadata Collection</strong>: Using <code>fetch_ncbi_metadata</code>, the pipeline retrieves metadata like country, isolate, collection date, and reference title. If available, supplementary material and full-text articles are parsed using DOI, PubMed, or Google Custom Search.</li>
|
| 82 |
+
|
| 83 |
+
<li><strong>Text Extraction & Preprocessing</strong>:
|
| 84 |
+
<ul>
|
| 85 |
+
<li>All available documents are parsed and cleaned (tables, paragraphs, overlapping sections).</li>
|
| 86 |
+
<li>Text is merged into two formats: a smaller <code>chunk</code> and a full <code>all_output</code>.</li>
|
| 87 |
+
</ul>
|
| 88 |
+
</li>
|
| 89 |
+
|
| 90 |
+
<li><strong>LLM-based Inference (Gemini + RAG)</strong>:
|
| 91 |
+
<ul>
|
| 92 |
+
<li>Chunks are embedded with FAISS and stored for reuse.</li>
|
| 93 |
+
<li>The Gemini model answers specific queries like predicted country, sample type, and any niche label requested by the user.</li>
|
| 94 |
+
</ul>
|
| 95 |
+
</li>
|
| 96 |
+
|
| 97 |
+
<li><strong>Result Structuring</strong>:
|
| 98 |
+
<ul>
|
| 99 |
+
<li>Each output includes predicted fields + explanation text (methods used, quotes, sources).</li>
|
| 100 |
+
<li>Summarized and saved using <code>save_to_excel</code>.</li>
|
| 101 |
+
</ul>
|
| 102 |
+
</li>
|
| 103 |
+
</ol>
|
| 104 |
+
|
| 105 |
+
<h2>Output Format</h2>
|
| 106 |
+
<p>The final output is an Excel file with the following fields:</p>
|
| 107 |
+
<ul>
|
| 108 |
+
<li><code>Sample ID</code></li>
|
| 109 |
+
<li><code>Predicted Country</code> and <code>Country Explanation</code></li>
|
| 110 |
+
<li><code>Predicted Sample Type</code> and <code>Sample Type Explanation</code></li>
|
| 111 |
+
<li><code>Sources</code> (links to articles)</li>
|
| 112 |
+
<li><code>Time Cost</code></li>
|
| 113 |
+
</ul>
|
| 114 |
+
|
| 115 |
+
<h2>System Highlights</h2>
|
| 116 |
+
<ul>
|
| 117 |
+
<li>RAG + Gemini integration for improved explanation and transparency</li>
|
| 118 |
+
<li>Excel export for structured research use</li>
|
| 119 |
+
<li>Optional ethnic/location/language inference using isolate names</li>
|
| 120 |
+
<li>Quality check (e.g., fallback on short explanations, low token count)</li>
|
| 121 |
+
<li>Report Button – After results are displayed, users can submit errors or mismatches using the report text box below the output table</li>
|
| 122 |
+
</ul>
|
| 123 |
+
|
| 124 |
+
<h2>Citation</h2>
|
| 125 |
+
<div class="highlight">
|
| 126 |
+
Phung, V. (2025). BioMetadataAudit. HuggingFace Spaces. https://huggingface.co/spaces/VyLala/mtDNALocation
|
| 127 |
+
</div>
|
| 128 |
+
|
| 129 |
+
<h2>Contact</h2>
|
| 130 |
+
<p>If you are a researcher working with genomic data or edge-case accessions and need scalable inference or logging, reach out through the HuggingFace space or email provided in the repo README.</p>
|
| 131 |
+
|
| 132 |
+
</div>
|
| 133 |
+
</body>
|
| 134 |
+
</html>
|
| 135 |
+
|