1 / 15

Relational Data

Relational Data. Inductive Logic Programming (ILP). Can use ILP to find a set of rules capturing a property that the positive graphs have in common that no negative graph has.

kaplan
Download Presentation

Relational Data

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Relational Data

  2. Inductive Logic Programming (ILP) • Can use ILP to find a set of rules capturing a property that the positive graphs have in common that no negative graph has. • This property is a kind of disjunction of subgraphs, where we allow one node in the graph to possibly play the role of multiple nodes in the subgraph.

  3. Rule

  4. Pharmacophores • A drug is a (typically) small organic molecule capable of binding to a target protein. • Binding depends on shape and on locations of charged groups, hydrophobic groups, etc. • If exact structure of target site is known, drug design is relatively easy -- but this is rarely known.

  5. Example of Binding

  6. Typical Practice • Test many molecules (1,000,000) to find some that bind to target (ligands). • Infer (induce) shape of target site from 3D structural similarities. • Shared 3D substructure is called a pharmacophore. • Perfect example of a machine learning task with spatial target.

  7. Pharmacophore expressed in English A Molecule M is active against Pseudomonas Aeruginosa if it has a conformation B such that: M has a hydrophobic group C, M has a hydrogen acceptor D, the distance between C and D in conformation B is 11.7 Angstroms M has a positively-charged atom E, the distance between C and E in conformation B is 4 Angstroms the distance between D and E in conformation B is 9.4 Angstroms M has a positively-charged atom F, the distance between C and F in conformation B is 11.1 Angstroms the distance between D and F in conformation B is 12.6 Angstroms the distance between E and F in conformation B is 8.7 Angstroms Tolerance 1.5 Angstroms

  8. Obvious Question 1 • Why don’t we just use one of the ligands (hits) as the drug? • Typically they don’t meet all the other requirements for drugs: • Non-toxic (other side effects) • Active enough (drink 2 gallons) • Metabolism (lasts long enough but not too long in the body) • Take by mouth? (gut-bloodstream)

  9. Obvious Question 2 • Why doesn’t a chemist just look at the ligands and figure out what they have in common? • Each molecule has many different shapes (conformers), any one of which might be the active one. Multiple instance problem (Dietterich, Lathrop, Lozano-Perez) • May be many molecules.

  10. The Logical Representation of a Pharmacophore

  11. ACE Pharmacophore • Molecule A is an ACE inhibitor if: • molecule A contains a zinc-site B, • molecule A contains a hydrogen acceptor C, • the distance between B and C is 7.89 +/- 0.75 A, • molecule A contains a hydrogen acceptor D, • the distance between B and D is 8.48 +/- 0.75 A, • the distance between C and D is 2.13 +/- 0.75 A, • molecule A contains a hydrogen acceptor E, • the distance between B and E is 4.89 +/- 0.75 A, • the distance between C and E is 3.11 +/- 0.75 A, • the distance between D and E is 3.75 +/- 0.75 A.

  12. Molecule 1

  13. Gene/Protein Level Interactions Gene Expression Gene Sequence Structural Motifs FUNCTION Protein Interactions Chromosomal Location Protein Function

More Related