CSE 494/CSE 598/CBS 598Application of AI to molecular Biology(4:40 – 5: 55 PM, BYAC 190)

Instructor: Chitta BaralOffice hours: TTh 3 to 4 PM

Four Great Questions The nature of matter. The origins of the universe. The nature of life. The workings of mind (simulating

“intelligence” artificially).

Meaning of the word: “intelligence”

1. (a) The capacity to acquire and apply knowledge. (b) The faculty of thought and reason. (c) Superior powers of mind. See Synonyms at mind.

2. An intelligent, incorporeal being, especially an angel.

3. Information; news. See Synonyms at news.

4. (a) Secret information, especially about an actual or potential enemy. …

Source: The American Heritage® Dictionary

Meaning of the word: “intelligence”

n. 1. The capacity to acquire and apply knowledge,

especially toward a purposeful goal.

2. An individual's relative standing on two quantitative indices, namely measured intelligence, as expressed by an intelligence quotient, and effectiveness of adaptive behavior.

The American Heritage® Stedman's Medical Dictionary

Meaning of the word: “intelligence”n.1 a : the ability to learn or understand or to deal with new or

trying situations

b : the ability to apply knowledge to manipulate one's environment or to think abstractly as measured by objective criteria (as tests)

2 : mental acuteness

Merriam-Webster's Medical Dictionary

Meaning of the word: “intelligence”n.1. the ability to comprehend; to understand and profit from

experience [ant: stupidity]

2. a unit responsible for gathering and interpreting intelligence

3. secret information about an enemy (or potential enemy); “we sent out planes to gather intelligence on their radar coverage”

Source: WordNet ® 1.6, © 1997 Princeton University

The key features of an intelligent entity it can acquire knowledge through various

means such as learning from experience, observations, reading and processing natural language text, from discussion with others

it can reason with this knowledge to make plans, explain observations, achieve goals, etc.

AI and molecular biology This course is about the application of the

above science and engineering (referred to as AI) to molecular biology.

Molecular Biology molecular biology n.

The branch of biology that deals with the formation, structure, and function of macromolecules essential to life, such as nucleic acids and proteins, and especially with their role in cell replication and the transmission of genetic information.

The branch of biology that deals with the manipulation of DNA so that it can be sequenced or mutated. If mutated, the DNA is often inserted into the genome of an organism to study the biological effects of the mutation.

Source: The American Heritage® Dictionary of the English Language, Fourth Edition Copyright © 2000 by Houghton Mifflin Company. Published by Houghton Mifflin Company. All rights reserved.

n : the branch of biology that studies the structure and activity of macromolecules essential to life (and especially with their genetic role) Source: WordNet ® 1.6, © 1997 Princeton University

Nature of life Source of diseases and disorders -- often traced to

activities inside cells. The activities inside cells are often regulated by

proteins (enzymes, ligands on cell surfaces, etc.) Central Dogma: DNA (genes) RNA Proteins Genome: The whole set of genes Differential gene expression Q: When are particular genes expressed in a cell Q: The details of the various interactions Q: Reasoning about the interactions

Main themes of the course

How to acquire/learn molecular biology knowledge?

How to do various kinds of reasoning with such knowledge?

(Why reason with such knowledge?)

Learning biological knowledge and meta-knowledge (ontologies) From observations (microarray, gene profile data) From reading

Intex (protein-gene1 interacts with protein-gene2) Other kinds of information extraction

TREC-Genomics BioQA

From discussing CBioc, CBioc-I Collaborative filtering

Signal Pathways(from http://www.afcs.org/cm2/)

                                     

Reasoning-I Reasoning about interactions

Prediction Side effects of drugs

Planning Drug and therapy design

Explanation, Diagnosis Explaining unusual behavior of cells

Hypothesizing missing knowledge about cell behavior

Reasoning - II Reasoning about consistency of Ontologies Reasoning across various kinds of knowledge

From interaction knowledge, gene disease relationship, drug effect data and other knowledge to drug-disease predictions.

Tentative topics to be covered Introduction Overview of Molecular Biology Ontologies Learning Knowledge (from text)

Learning interactions, etc. Learning Ontologies

Learning Knowledge (from data) Learning causality Dynamic Bayes nets

Representation and reasoning with biological knowledge Reasoning with ontologies Overview of other applications of AI to molecular biology

More on Hidden Markov Models Use of decision trees, inductive Logic programming (Progol), etc. for classification

and prediction. Gene finding, protein folding, kernel methods, protein 3D structure prediction

Grading and Modus Operandi project + paper + class presentations 80%

Chance to collaborate with my Ph.D students Expected to be of publication quality

Class Test (April 3rd week) 20% Modus Operandi:

There will be 8-9 groups each of 1-2 students Groups select project asap (in two weeks) First 5 classes I will present We will have some guest lectures Other classes presented by my Ph.D students Group discussion on PSB topics.

Projects Each project is of research interest to ASU

and TGen researchers, particularly to me. Students will work closely with me, my

colleague Dr. Graciela Gonzalez and my Ph.D students

Tentative list of projects – 1 AI, KR and Ontology issues in BioPAX and possible

solutions. – Luis, Nam, Jicheng Various kinds of knowledge extraction from natural language

text (abstracts and articles) -- Luis, Graciela Protein/gene Interactions Knowledge about images Etc. Extracting ontologies

Hypothesis formation/generation -- Nam Reasoning with various kinds of data – Luis, Xin, Nam Modeling of pathways – Nam, Jicheng

Qualitative modeling Quantitative modeling

Tentative list of projects – 2 Biological Question answering -- Luis Learning gene interactions (as Bayes nets or a

similar structure) -- Xin from time series micro-array data From gene profile data From multiple data types

Any idea from PSB topics. You may suggest and discuss a topic, but need to do

it asap

My current projects Biosignet: http://www.biosignet.org CBioC: http://www.cbioc.org

InteEx BioQA: http://www.bioqa.org

TREC-Genomics Biogenenet: http://www.biogenenet.org