Bài kiểm tra có liên kết hướng dẫn · Trung bình Cấp độ

AI trong bài kiểm tra tối ưu hóa khách hàng tiềm năng

Các thử nghiệm dẫn đến chu trình tối ưu hóa, đánh đổi nhiều thuộc tính, dự đoán so với đo lường, phân tách xác thực và giám sát nhà hóa học.

Đường dẫn hướng dẫn liên quanAI trong tối ưu hóa khách hàng tiềm năng
Câu hỏi 1 của 8

What does a model-predicted potency improvement establish?

Xem trước mọi câu hỏi8 câu hỏi

Câu trả lời và giải thích xuất hiện khi bạn làm bài kiểm tra.

  1. What does a model-predicted potency improvement establish?
    • That synthesis will be straightforward
    • A hypothesis to verify with synthesized compounds and assays
    • A confirmed improvement in patients
    • That exposure and toxicity are acceptable
  2. Why can a more potent analogue be a worse lead?
    • A lead is judged only by potency
    • A model score measures every clinical property
    • It may have poor solubility, exposure, selectivity, or safety
    • Potency always worsens solubility
  3. Which sequence describes a design-make-test cycle?
    • Propose structures, synthesize selected compounds, and measure outcomes
    • Train a model once and skip experiments
    • Select a target and begin clinical use
    • Rank compounds only by literature frequency
  4. Why split test data by scaffold or time?
    • To make all compounds chemically identical
    • To avoid measuring potency
    • To increase predicted scores
    • To reduce leakage from close analogues and better assess novelty
  5. How should a chemist handle an AI-generated structure?
    • Use the predicted score as a lab result
    • Review its plausibility and test it experimentally
    • Assume the model guarantees synthesis
    • Advance it because the structure is novel
  6. Which measurement should be considered alongside potency?
    • Solubility, metabolic stability, selectivity, and exposure
    • Only the number of atoms
    • Only a preferred scaffold name
    • The model’s training loss
  7. How can chemist preference data inform a learning-to-rank model?
    • It proves which compound works in patients
    • It replaces biological assays
    • It automatically predicts every ADME property
    • It can train a model to prioritize compounds according to expert comparisons
  8. Why preserve negative experimental results?
    • They are unusable once a model is trained
    • They prove the target is invalid
    • They inform future model updates and explain rejected designs
    • They make every candidate look active