Spaces:
Running
Running
Upload 2 files
Browse files
.gitattributes
CHANGED
|
@@ -35,3 +35,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
credentials.json filter=crypt diff=crypt
|
| 37 |
|
|
|
|
|
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
credentials.json filter=crypt diff=crypt
|
| 37 |
|
| 38 |
+
A_flowchart_in_the_image_illustrates_a_data_proces.png filter=lfs diff=lfs merge=lfs -text
|
A_flowchart_in_the_image_illustrates_a_data_proces.png
ADDED
|
Git LFS Details
|
mtdna_tool_explainer_updated.html
ADDED
|
@@ -0,0 +1,81 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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>mtDNA Tool – System Overview</title>
|
| 7 |
+
<style>
|
| 8 |
+
body { font-family: Arial, sans-serif; line-height: 1.6; padding: 2rem; max-width: 900px; margin: auto; background-color: #f9f9f9; color: #333; }
|
| 9 |
+
h1, h2 { color: #2c3e50; }
|
| 10 |
+
img { max-width: 100%; border: 1px solid #ccc; padding: 5px; background: #fff; }
|
| 11 |
+
code { background: #eee; padding: 2px 4px; border-radius: 4px; }
|
| 12 |
+
.highlight { background: #ffffcc; padding: 4px 8px; border-left: 4px solid #ffcc00; margin: 1rem 0; }
|
| 13 |
+
</style>
|
| 14 |
+
</head>
|
| 15 |
+
<body>
|
| 16 |
+
|
| 17 |
+
<h1>mtDNA Location Classifier – Brief System Pipeline and Usage Guide</h1>
|
| 18 |
+
|
| 19 |
+
<p>The <strong>mtDNA 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 mtDNA GenBank accession numbers. It supports batch input and produces structured Excel summaries.</p>
|
| 20 |
+
|
| 21 |
+
<h2>System Overview Diagram</h2>
|
| 22 |
+
<p>The figure below shows the core execution flow—from input accession to final output.</p>
|
| 23 |
+
<img src="./A_flowchart_in_the_image_illustrates_a_data_proces.png" alt="mtDNA Pipeline Flowchart">
|
| 24 |
+
|
| 25 |
+
<h2>Key Steps</h2>
|
| 26 |
+
<ol>
|
| 27 |
+
<li><strong>Input</strong>: One or more GenBank accession numbers are submitted (e.g., via UI, CSV, or text).</li>
|
| 28 |
+
|
| 29 |
+
<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>
|
| 30 |
+
|
| 31 |
+
<li><strong>Text Extraction & Preprocessing</strong>:
|
| 32 |
+
<ul>
|
| 33 |
+
<li>All available documents are parsed and cleaned (tables, paragraphs, overlapping sections).</li>
|
| 34 |
+
<li>Text is merged into two formats: a smaller <code>chunk</code> and a full <code>all_output</code>.</li>
|
| 35 |
+
</ul>
|
| 36 |
+
</li>
|
| 37 |
+
|
| 38 |
+
<li><strong>LLM-based Inference (Gemini + RAG)</strong>:
|
| 39 |
+
<ul>
|
| 40 |
+
<li>Chunks are embedded with FAISS and stored for reuse.</li>
|
| 41 |
+
<li>The Gemini model answers specific queries like predicted country, sample type, and any niche label requested by the user.</li>
|
| 42 |
+
</ul>
|
| 43 |
+
</li>
|
| 44 |
+
|
| 45 |
+
<li><strong>Result Structuring</strong>:
|
| 46 |
+
<ul>
|
| 47 |
+
<li>Each output includes predicted fields + explanation text (methods used, quotes, sources).</li>
|
| 48 |
+
<li>Summarized and saved using <code>save_to_excel</code>.</li>
|
| 49 |
+
</ul>
|
| 50 |
+
</li>
|
| 51 |
+
</ol>
|
| 52 |
+
|
| 53 |
+
<h2>Output Format</h2>
|
| 54 |
+
<p>The final output is an Excel file with the following fields:</p>
|
| 55 |
+
<ul>
|
| 56 |
+
<li><code>Sample ID</code></li>
|
| 57 |
+
<li><code>Predicted Country</code> and <code>Country Explanation</code></li>
|
| 58 |
+
<li><code>Predicted Sample Type</code> and <code>Sample Type Explanation</code></li>
|
| 59 |
+
<li><code>Sources</code> (links to articles)</li>
|
| 60 |
+
<li><code>Time Cost</code></li>
|
| 61 |
+
</ul>
|
| 62 |
+
|
| 63 |
+
<h2>System Highlights</h2>
|
| 64 |
+
<ul>
|
| 65 |
+
<li>RAG + Gemini integration for improved explanation and transparency</li>
|
| 66 |
+
<li>Excel export for structured research use</li>
|
| 67 |
+
<li>Optional ethnic/location/language inference using isolate names</li>
|
| 68 |
+
<li>Quality check (e.g., fallback on short explanations, low token count)</li>
|
| 69 |
+
<li>Report Button – After results are displayed, users can submit errors or mismatches using the report text box below the output table</li>
|
| 70 |
+
</ul>
|
| 71 |
+
|
| 72 |
+
<h2>Citation</h2>
|
| 73 |
+
<div class="highlight">
|
| 74 |
+
Phung, V. (2025). mtDNA Location Classifier. HuggingFace Spaces. https://huggingface.co/spaces/VyLala/mtDNALocation
|
| 75 |
+
</div>
|
| 76 |
+
|
| 77 |
+
<h2>Contact</h2>
|
| 78 |
+
<p>If you are a researcher working with historical mtDNA 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>
|
| 79 |
+
|
| 80 |
+
</body>
|
| 81 |
+
</html>
|