Diversity Filtering
-
Upload
christos-kannas -
Category
Technology
-
view
84 -
download
1
description
Transcript of Diversity Filtering
![Page 1: Diversity Filtering](https://reader036.fdocuments.us/reader036/viewer/2022082920/554ea78bb4c905977e8b49f0/html5/thumbnails/1.jpg)
Diversity FilteringChristos KannasUniversity of Cyprus
![Page 2: Diversity Filtering](https://reader036.fdocuments.us/reader036/viewer/2022082920/554ea78bb4c905977e8b49f0/html5/thumbnails/2.jpg)
2nd
RDKi
t UG
M
Outline• Introduction• Methodology• Implementation
3rd
Oct
ober
, 201
3
2
![Page 3: Diversity Filtering](https://reader036.fdocuments.us/reader036/viewer/2022082920/554ea78bb4c905977e8b49f0/html5/thumbnails/3.jpg)
2nd
RDKi
t UG
M
Introduction• The need to select all the diverse molecules from a dataset
(based on a threshold).
• Divide the dataset into diverse molecules and similar molecules .
3rd
Oct
ober
, 201
3
3
![Page 4: Diversity Filtering](https://reader036.fdocuments.us/reader036/viewer/2022082920/554ea78bb4c905977e8b49f0/html5/thumbnails/4.jpg)
2nd
RDKi
t UG
M
Methodology• 2D Fingerprints
• Similarity Metric: Tanimoto, Dice• Similarity Matrix• Diagonal has 1…
• Make diagonal 0, or• Skip it…
• Max/Mean/Min Similarity (row/column based)
• Divide molecules in to 2 datasets• One with diverse molecules (below similarity threshold)• One with similar molecules (above similarity threshold)
3rd
Oct
ober
, 201
3
4
![Page 5: Diversity Filtering](https://reader036.fdocuments.us/reader036/viewer/2022082920/554ea78bb4c905977e8b49f0/html5/thumbnails/5.jpg)
2nd
RDKi
t UG
M
Implementation 1/4• Diversity Score Function [O(n2)]• Inputs:
• Query Molecules == Reference Molecules• Similarity Metric [Tanimoto, Dice]• Scoring Method [Max, Mean, Min]
• Output:• Diversity Score
3rd
Oct
ober
, 201
3
5
![Page 6: Diversity Filtering](https://reader036.fdocuments.us/reader036/viewer/2022082920/554ea78bb4c905977e8b49f0/html5/thumbnails/6.jpg)
2nd
RDKi
t UG
M
Implementation 2/4• Show source code for fingerprint similarity/diversity…
3rd
Oct
ober
, 201
3
6
![Page 7: Diversity Filtering](https://reader036.fdocuments.us/reader036/viewer/2022082920/554ea78bb4c905977e8b49f0/html5/thumbnails/7.jpg)
2nd
RDKi
t UG
M
Implementation 3/4• Filtering Engine [O(n)]• Inputs:
• Molecules + Diversity Score• Threshold
• Outputs:• Diverse Molecules• Similar Molecules
3rd
Oct
ober
, 201
3
7
![Page 8: Diversity Filtering](https://reader036.fdocuments.us/reader036/viewer/2022082920/554ea78bb4c905977e8b49f0/html5/thumbnails/8.jpg)
2nd
RDKi
t UG
M
Implementation 4/4• Show source code for diversity filtering…
3rd
Oct
ober
, 201
3
8
![Page 9: Diversity Filtering](https://reader036.fdocuments.us/reader036/viewer/2022082920/554ea78bb4c905977e8b49f0/html5/thumbnails/9.jpg)
2nd
RDKi
t UG
M3r
d O
ctob
er, 2
013
9