gerstung-lab/Delphi

• hightopics#1

  Add specific topics to improve categorization

  Why:

  COPY-PASTE FIX

  Copy

  health-trajectories, generative-ai, transformers, disease-progression, longitudinal-data, deep-learning, pytorch, causal-inference, biomedicine

  OpenDoneDismiss
• highreadme#2

  Add a concise project summary immediately after the main title

  Why:

  CURRENT

  ## Learning the natural history of human disease with generative transformers
  
  [`Paper`] [[`BibTeX`](#Citation)]
  
  Artem Shmatko*, Alexander Wolfgang Jung*, Kumar Gaurav*, Søren Brunak, Laust Mortensen, Ewan Birney, Tom Fitzgerald, Moritz Gerstung (*Equal Contribution)

  COPY-PASTE FIX

  Copy

  ## Learning the natural history of human disease with generative transformers
  
  Delphi is a PyTorch-based generative transformer model designed to learn and simulate the natural history of human disease from longitudinal patient data, enabling insights into health trajectories and disease progression.
  
  [`Paper`] [[`BibTeX`](#Citation)]
  
  Artem Shmatko*, Alexander Wolfgang Jung*, Kumar Gaurav*, Søren Brunak, Laust Mortensen, Ewan Birney, Tom Fitzgerald, Moritz Gerstung (*Equal Contribution)

  OpenDoneDismiss
• mediumhomepage#3

  Add a homepage URL to the repository metadata

  Why:

  COPY-PASTE FIX

  Copy

  https://www.nature.com/articles/s41586-024-07179-w (or the official paper URL)

  OpenDoneDismiss

Category GEO backends resolved for this scan: google/gemini-2.5-flash, deepseek/deepseek-v4-flash

• CATEGORY QUERY

  What are effective generative AI models for simulating and predicting human health trajectories?

  you: not recommended
  AI recommended (in order):

  1. AlphaFold
  2. Generative Adversarial Networks (GANs)
  3. Conditional GANs (cGANs)
  4. Time-series GANs (T-GANs)
  5. MedGAN
  6. Variational Autoencoders (VAEs)
  7. Conditional VAEs (CVAEs)
  8. Recurrent VAEs (RVAEs)
  9. Recurrent Neural Networks (RNNs)
  10. LSTMs
  11. GRUs
  12. Transformers
  13. Diffusion Models
  14. Denoising Diffusion Probabilistic Models (DDPMs)
  15. Reinforcement Learning (RL)
  16. Deep Q-Networks (DQN)
  17. Proximal Policy Optimization (PPO)

  AI recommended 17 alternatives but never named gerstung-lab/Delphi. This is the gap to close.

  Show full AI answer
• CATEGORY QUERY

  How can I apply transformer models to analyze longitudinal patient data for disease progression?

  you: not recommended
  AI recommended (in order):

  1. Hugging Face Transformers
  2. PyTorch
  3. TensorFlow
  4. Keras
  5. DeepMind's AlphaFold
  6. Google's Trajectory Transformer

  AI recommended 6 alternatives but never named gerstung-lab/Delphi. This is the gap to close.

  Show full AI answer

• Metadata completeness

  warn

  Suggestion:

• README presence

  pass

• Compared to common alternatives in this category, what is the core differentiator of gerstung-lab/Delphi?

  pass
  ✓AI named gerstung-lab/Delphi explicitly

  AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

• If a team adopts gerstung-lab/Delphi in production, what risks or prerequisites should they evaluate first?

  pass
  ✓AI named gerstung-lab/Delphi explicitly

  AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

• In one sentence, what problem does the repo gerstung-lab/Delphi solve, and who is the primary audience?

  pass
  ✓AI named gerstung-lab/Delphi explicitly

  AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?