week 12

Question 1

machine learning

Answer 1

• “thing-labeler”
• input: description of something
• output: what label the thing should get
• once machine has learned on the training set of data, you ask the machine to label new things for you
• well suited to “ineffable” things

Question 2

ineffable

Answer 2

• too great or extreme to be expressed or described in words

Question 3

AI for in silico drug discovery

Answer 3

• model a “good” inhibitor (antagonist) for a protein compared to non-inhibitors
• start with what we know to train computers

Question 4

AI to study protein-protein interactions

Answer 4

• disrupt those protein-protein interactions
• analyze

Question 5

AI at u of t

Answer 5

• vector institute
• independent, not-for-profit
• dedicated to research field of AI

Question 6

using computers to model the pharmacokinetics of a drug

Answer 6

• mathematical predictions of a drugs pharmacokinetics
• imputs: physiology variables, drugs chemical properties, drug-specific preclinical information
• outputs: Absorption, distribution, metabolism, elimination
• exploring effects of other medications taken at the same time, food or empty stomach, disease status

Question 7

digital health in clinical trials

Answer 7

• devices monitor blood pressure
• vast amounts of data

Question 8

clinical trials inside computer

Answer 8

• in silico clinical trials
• HumMod - “the most complete mathematical model of human physiology ever created”

Question 9

trial pathfinder

Answer 9

• open source
• goal is to expand inclusion criteria for cancer clinical trials
• uses electronic medical records
• uses patient data to optimize the selection of eligibility criteria