Geonomic commited on
Commit
22aac61
·
verified ·
1 Parent(s): 1c919fb

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +2 -2
app.py CHANGED
@@ -234,7 +234,7 @@ with gr.Blocks(theme=gr.themes.Soft(), title="🧬 The Genomic Oracle 🧬") as
234
  """
235
  <div style="text-align: center; padding-bottom: 10px;">
236
  <h1 style="font-size: 3.5rem; font-weight: bold; margin-bottom: 0.2rem;">🧬 The Genomic Oracle 🧬</h1>
237
- <h3 style="margin-top: 0; font-weight: normal;"><b>University of Maryland Global Campus (UMGC)</b> | Bioinformatics Capstone Project</h3>
238
  </div>
239
  <hr>
240
  """
@@ -245,7 +245,7 @@ with gr.Blocks(theme=gr.themes.Soft(), title="🧬 The Genomic Oracle 🧬") as
245
  """
246
  Welcome to the official interface for **The Genomic Oracle**, a cascaded machine learning pipeline designed for high-precision DNA sequence classification.
247
 
248
- ### 🧠 The 4-Stage Architecture
249
  1. **The Gatekeeper:** Logistic Regression model rapidly screens native k-mer vectors to identify protein-coding vs. non-coding potential.
250
  2. **Structural Mapper:** LightGBM model classifies the sequence into 1 of 7 structural features (e.g., Exons, UTRs, Enhancers).
251
  3. **Phenotype Prediction:** Sequences flagged as Coding are passed through a custom ALiBi BERT transformer model to predict specific traits.
 
234
  """
235
  <div style="text-align: center; padding-bottom: 10px;">
236
  <h1 style="font-size: 3.5rem; font-weight: bold; margin-bottom: 0.2rem;">🧬 The Genomic Oracle 🧬</h1>
237
+ <h3 style="margin-top: 0; font-weight: normal;"><b>University of Maryland Global Campus</b> | Bioinformatics Capstone</h3>
238
  </div>
239
  <hr>
240
  """
 
245
  """
246
  Welcome to the official interface for **The Genomic Oracle**, a cascaded machine learning pipeline designed for high-precision DNA sequence classification.
247
 
248
+ ### The 4-Stage Cascading Architecture
249
  1. **The Gatekeeper:** Logistic Regression model rapidly screens native k-mer vectors to identify protein-coding vs. non-coding potential.
250
  2. **Structural Mapper:** LightGBM model classifies the sequence into 1 of 7 structural features (e.g., Exons, UTRs, Enhancers).
251
  3. **Phenotype Prediction:** Sequences flagged as Coding are passed through a custom ALiBi BERT transformer model to predict specific traits.