Transcript - Lorentz Center

Desirability Indexes for Soft
Constraint Modeling in Drug Design
Johannes Kruisselbrink
E-mail: [email protected]
Leiden University. The university to discover.
Scope
Context:
- Quality measures for candidate molecular
structures for automated optimization
Contents:
- Using the concept of Desirability for modeling
soft or fuzzy constraints
- The applicability in automated drug design and
examples for integration within a scoring
function
Leiden University. The university to discover.
Uncertainty and noise in optimization problems
Uncertainty and noise can arise in various parts of
the optimization model:
Input X
System
(Model)
Output Y
G
O
A
L
S
f1max / min
f2max / min
|
fmmax / min
Objectives
g1 ≤ 0
g2 ≤ 0
|
gn ≤ 0
Constraints
External (uncontrollable)
parameters A
A) Uncertainty and noise in the design variables
C) Uncertain and/or noisy system output
B) Uncertainty and noise environmental parameters
D) Vagueness / fuzziness in the constraints
Leiden University. The university to discover.
Our setup for Automated
Molecule Evolution
Leiden University. The university to discover.
Automated molecule design
- Search for molecular structures with specific
pharmacological or biological activity
- Objectives: Maximization of potency of drug
(and minimization of side-effects)
- Constraints: Stability, synthesizability, druglikeness, etc.
- Aim: provide a set of molecular structures that
can be promising candidates for further
research
Leiden University. The university to discover.
Molecule Evolution
-
‘Normal’ evolution cycle
Graph based mutation and
recombination operators
Deterministic elitist (μ+λ) parent
selection (NSGA-II with Niching)
Initialize population P0
Fragments extracted from
From Drug Databases
While not terminate do
Pt+1= select from (P U O)
Evaluate O
Generate offspring O from P
“The molecule evoluator. An interactive evolutionary
algorithm for the design of drug-like molecules.“,
E.-W. Lameijer, J.N. Kok, T. Bäck, A.P. IJzerman,
J. Chem. Inf. Model., 2006, 46(2): 545-552.
Leiden University. The university to discover.
Objectives and constraints
Objectives
-
Activity predictors based on support vector machines:
- f1: activity predictor based on ECFP6 fingerprints
- f2: activity predictor based on AlogP2 Estate Counts
- f3: activity predictor based on MDL
Constraints
-
Bounds based on Lipinski’s rule of five and the minimal energy
confirmation:
-
Number of Hydrogen acceptors
Number of Hydrogen donors
Molecular solubility
Molecular weight
AlogP value
Minimized energy
Leiden University. The university to discover.
Soft constraints in drug design
Leiden University. The university to discover.
Soft constraints in Drug Design
- Estimating the feasibility of candidate structures
can be done using boundary values for certain
molecule properties
- Examples are Lipinski’s rule-of-five and
estimations of the minimal energy
conformations
- But…, how strict are those rules?
- Sometimes violations are easy to fix manually
- Sometimes violations are not violations in practice
Leiden University. The university to discover.
Molecules failing Lipinski
MW
Atorvastatin
log P
log P
(5.088)
MW
Ethopropazine
Bexarotene
Liothyronine
HA / HD
Doxycycline
MW / HA
Olmesartan
MW / HA
Acarbose
Leiden University. The university to discover.
Modeling constraints using
desirability functions
Leiden University. The university to discover.
The real nature of the constraints
The constraints are of the following forms:
Where
-
x denotes a candidate structure
g(x) denotes the property value of x
Aj is the lower bound of the property filter
Bj is the upper bound of the property filter
reads: A is preferred to be smaller than B
Leiden University. The university to discover.
Modeling constraints as objectives
Constraints can be transformed into ‘objectives’ by mapping
their values onto a function with the domain <0,1> where:
- Values close to 0 correspond to undesirable results
- Values close to 1 correspond to desirable results
- Values between 0 and 1 fall into the grey area
1
1
Cutoff bound
Constraint bound
0
0
violated
grey area
One-sided
satisfied
violated grey area
satisfied
grey area violated
Two-sided
There are multiple ways to create such mappings!
Leiden University. The university to discover.
Constraints in our studies
Fuzzy constraint scores based on Lipinski’s rule of five
and bounds on the minimal energy confirmation:
Descriptor
LB
A
B
UB
Num H-acceptors
0
1
6
10
Num H-donors
0
1
3
5
Molecular solubility
-6
-4
NA
NA
Molecular weight
150
250
450
600
ALogP
0
1
4
5
Minimized energy
NA
NA
80
150
* Bounds settings were determined based on chemical intuition
Leiden University. The university to discover.
Harrington Desirability Functions
One-sided:
Two-sided:
d (Y ' )  exp(  exp( Y ' ))
d (Y ' )  exp(  Y ' )
Y '  ln(  ln d )  b0  b1Y
2Y  (U  L)
Y '
U L
n
Leiden University. The university to discover.
Example one-sided Harrington DF
Molecular solubility:
-
Soft constraint: Y > -4
Absolute cutoff: Y < -6
0.99  exp(  exp( (b0  b1  4))
d (Y ' )  exp(  exp( Y ' ))
d (Y )  exp(  exp(16.8548  3.0637  Y )))
Y '  ln(  ln d )  b0  b1Y
0.01  exp(  exp( (b0  b1  6))
 ln(  ln( 0.99))   b0  b1  4
 ln(  ln( 0.01))   b0  b1  6
4.6001  b0  4  b1
- 1.5272  b0  6  b1
b0  16.8548
b1  3.0637
violated
grey area
satisfied
Leiden University. The university to discover.
Example two-sided Harrington DF
Molecular weight:
-
d (Y ' )  exp(  Y ' )
n
Absolute lower cutoff: Y < 150
Lower bound constraint: Y > 250
Upper bound constraint: Y < 450
Absolute upper cutoff: Y > 600
2Y  (U  L)
Y '
U L
Problematic!
- No support for non-symmetric boundaries
- No explicit support for ‘completely satisfied’ intervals
Leiden University. The university to discover.
Example two-sided Harrington DF
One possibility:
-
Make symmetric
Base d(Y) on cutoff bounds
Tune n using a constraint bound
d (Y ' )2Y exp(
 Y150
' ) ) 7.8273 
(600
n
d (Y )  exp 


2Y  (U  L)
Y '
U L
 2  250  (600  150) n 

d (250)  exp  


600

150



0.99  exp  0.5556
n
 ln 0.99  0.5556
600  150



n
n  log 0.5556  ln 0.99  7.8273
violated
grey
area
satisfied
grey
area
violated
Leiden University. The university to discover.
Example two-sided Harrington DF
Or:
-
Make symmetric
Base d(Y) on constraint bounds
Tune n using a cutoff bound
d (Y ' )2Y exp(
 Y 250
' ) ) 2.2033 
(450
n
d (Y )  exp 


2Y  (U  L)
Y '
U L
 2 150  (450  250) n 

d (150)  exp  


450

250



0.01  exp  2 
 ln 0.01  2 n
n
450  250

n  log 2  ln 0.01  2.2033
violated
grey
area
satisfied
grey
area
violated
Leiden University. The university to discover.


Example two-sided Harrington DF
Or:
-
Make symmetric
Base d(Y) on average between
constraint bounds and cutoff bounds
Tune n using a cutoff bound
d (Y ' )2Yexp(
Y ' ) )5.6927
(525 200
n
d (Y )  exp 


2Y  (U  L)
Y '
U L
 2 150  (525  200 ) n 

d (150 )  exp  


525  200



0.01  exp  1.3077 n
 ln 0.01  1.3077 n
525  200





n  log1.3077  ln 0.01  5.6927
violated
grey
area
satisfied
grey
area
violated
Leiden University. The university to discover.
Harrington
- Advantages:
- Maps onto a continuous function
- Strictly monotonous mapping
- Distinction between completely violated points
- Downsides:
- Tuning the DF is somewhat arbitrary
- Distinction between completely satisfied solutions
- Not really suited for ‘completely satisfied intervals’
- Does not allow non-symmetric constraints
Leiden University. The university to discover.
Derringer Desirability Functions
One-sided:
1
l

 Y  U 
d (Y )  

B

U



0
Two-sided:
,Y  B
,B Y U
,Y  U
0
 Y

 T
d (Y )  
 Y
 T
0

,Y  L
L

L
u
U 

U 
l
,L Y T
,T  Y  U
,Y  U
Leiden University. The university to discover.
Example one-sided Derringer DF
Molecular solubility:
-
Soft constraint: Y > -4
Absolute cutoff: Y < -6
1
 Y  6 l
d (Y )  

  4  6 
0
1
l

 Y  U 
d (Y )  

B

U




0
,Y  B
,B Y U
,Y  U
, Y  4
,4  Y  6
, Y  6
Note: l=1linear
violated
grey area
satisfied
Leiden University. The university to discover.
Example two-sided Derringer DF
Molecular weight:
-
Absolute cutoff: Y < 150
Soft constraint: Y > 250
Soft constraint: Y < 450
Absolute cutoff: Y > 600
0
 Y  150 l


 250  150 
d (Y )  1
 Y  600 u


450

600


0
, Y  150
0
 Y

 T
d (Y )  
 Y
 T
0

,Y  L
L

L
u
U 

U 
l
,L Y T
,T  Y  U
,Y  U
,150  Y  250
,250  Y  450
,450  Y  600
, Y  600
violated grey
area
satisfied
grey
area
violated
Leiden University. The university to discover.
Derringer
- Advantages:
- Easy straightforward implementation
- Control for modeling non-symmetric constraints
- Easy integration for ‘completely satisfied’ intervals
- No distinction between completely satisfied solutions
- Downsides:
- Maps onto a discontinuous function
- Not strictly monotonous (just monotonous)
- No distinction between solutions after lower cutoff
Leiden University. The university to discover.
Aggregating the Desirability
Functions into score functions
Leiden University. The university to discover.
Many objective optimization
- Modeling fuzzy constraints using DFs generates
many additional objective functions
- In our case:
- 3 original objectives + 6 constraints  9 objectives
- The possibilities:
- Pareto optimization
- Aggregation
- A combination of the both
Leiden University. The university to discover.
Aggregation
- Desirability functions can be easily integrated into one
single scoring function, e.g.:
-
Weighted sum
Min performance
Geometrical mean
Average
The Desirability Index
k
F  x    ai  Di  g i  x 
i 1
 k

F  x     Di  g i  x 
 i 1

1
k
F x   min Di g i  x 
i 1... k
1 k
F x    Di  g i  x 
k i 1
Leiden University. The university to discover.
Remodeling the objectives
- Desirability index aggregation of the objectives requires
a normalization function that maps the objective function
values to the interval [0,1]
- One possibility:
 

fˆi x   exp d i  f i*  f i x   max
Original objective function minimization
- Or…, use Harrington or Derringer DFs
Leiden University. The university to discover.
The aggregation possibilities
- Full aggregation:
- Aggregate the constraints and the objectives into one
quality score (1 objective)
- Partial aggregation:
- Aggregate the constraints into one constraint score
(1 extra objective  4 objectives)
- Aggregate the constraints and the objectives into two
separate scoring function (2 objectives)
Leiden University. The university to discover.
A case study
Leiden University. The university to discover.
Experiments
Comparison of:
- Complete aggregation (1 objective)
- Separate aggregation of objectives and constraints (2
objectives)
- Only aggregate constraint scores (4 objectives)
Objectives:
- three activity prediction models for estrogen receptor
antagonists
EA settings:
-
NSGA-II for the multi-objective test-cases
80 parents / 120 offspring
1000 generations
No niching
Leiden University. The university to discover.
4D Pareto fronts
Optimization direction
Complete aggregation (1 objective)
Only aggregate constraint scores (4 objectives)
The Pareto fronts obtained using
three different scoring methods
Aggregate constraints and objectives separately (2 objectives)
Leiden University. The university to discover.
Random subsets of the results
Leiden University. The university to discover.
Separate constraints and objectives
Tamoxifen
Color: constraint scores
(white = 0  black = 1)
f3: MDL max (=1)
f2: ECFP max (=1)
f1: AlogP2 EC  max (=1)
Leiden University. The university to discover.
Conclusions
Leiden University. The university to discover.
Discussion - Ranking issues
- DFs that can yield 0 values will generate 0 values for
the performance when aggregating using the geometric
mean
- DFs that make distinctions between completely satisfied
constraints might be involved in unnecessary further
optimization (maximization while already satisfied)
An ideal DF?
Never 0 (distinction on the degree
of constraint)
1
When satisfied 1 (no distinction
between satisfied regions)
0
violated
grey area
satisfied
Leiden University. The university to discover.
Conclusions
- Desirability Functions and Desirability Indexes
for modeling soft / fuzzy constraints:
- Are intuitive and easy to incorporate
- Allow for easy integration of additional constraints
- Incorporate the concept of vagueness present in all
rule-of-thumb measures
- Prevent the optimization method from ruling out
promising candate structures
Leiden University. The university to discover.
Thank you!
Johannes Kruisselbrink
Natural Computing Group
LIACS, Universiteit Leiden
e-mail: [email protected]
http://natcomp.liacs.nl
Leiden University. The university to discover.
Matlab codes
(no presentation stuff, just
for creating the DF plots)
Leiden University. The university to discover.
Harrington one-sided example
clf
x = [0:.1:10];
y = exp(-exp(-(-8 + 2 * x)));
plot(x, y)
ylim([-.1 1.1])
xlabel('Y')
ylabel('d(Y)')
Leiden University. The university to discover.
Harrington two-sided example
clf
x = [0:.01:10];
y = exp(-abs((2 * x - (6 + 4))/(6 - 4)).^(3));
plot(x, y)
ylim([-.1 1.1])
xlabel('Y')
ylabel('d(Y)')
Leiden University. The university to discover.
One-sided Harrington DF in MATLAB
clf
x = [-8:.1:-2];
y = exp(-exp(-(16.8548 + 3.0637 * x)));
plot(x, y)
hold on
plot([-8 -6 -4 -2],[0 0 1 1], '-.r')
ylim([-.1 1.1])
xlabel('Y')
ylabel('d(Y)')
legend('Harrington DF', 'Linear DF', 'Location', 'NorthWest')
Leiden University. The university to discover.
Two-sided Harrington DF 1 in MATLAB
clf
x = [0:1:800];
y = exp(-abs((2 * x - (600 + 150))/(600 - 150)).^(7.8273));
plot(x, y)
hold on
plot([0 150 250 450 600 850], [0 0 1 1 0 0], '-.r')
ylim([-.1 1.1])
xlabel('Y')
ylabel('d(Y)')
legend('Harrington DF', 'Linear DF', 'Location', 'NorthEast')
Leiden University. The university to discover.
Two-sided Harrington DF 2 in MATLAB
clf
x = [0:1:800];
y = exp(-abs((2 * x - (450 + 250))/(450 - 250)).^(2.2033));
plot(x, y)
hold on
plot([0 150 250 450 600 850], [0 0 1 1 0 0], '-.r')
ylim([-.1 1.1])
xlabel('Y')
ylabel('d(Y)')
legend('Harrington DF', 'Linear DF', 'Location', 'NorthEast')
Leiden University. The university to discover.
Two-sided Harrington DF 3 in MATLAB
clf
x = [0:1:800];
y = exp(-abs((2 * x - (525 + 200))/(525 - 200)).^(5.6927));
plot(x, y)
hold on
plot([0 150 250 450 600 850], [0 0 1 1 0 0], '-.r')
ylim([-.1 1.1])
xlabel('Y')
ylabel('d(Y)')
legend('Harrington DF', 'Linear DF', 'Location', 'NorthEast')
Leiden University. The university to discover.
One-sided Derringer DF in MATLAB
clf
hold on
x = [-8:.01:-2];
y1 = (x >= -4) * 1 + (x < -4) .* (x >= -6) .* ((x + 6)/(-4 + 6)).^0.5;
plot(x, y1, '-.b')
y2 = (x >= -4) * 1 + (x < -4) .* (x >= -6) .* ((x + 6)/(-4 + 6)).^1;
plot(x, y2, '--r')
y3 = (x >= -4) * 1 + (x < -4) .* (x >= -6) .* ((x + 6)/(-4 + 6)).^2;
plot(x, y3, 'g')
ylim([-.1 1.1])
xlabel('Y')
ylabel('d(Y)')
legend('Derringer DF (l=0.5)', 'Derringer DF (l=1)', 'Derringer DF (l=2)',
'Location', 'NorthWest')
Leiden University. The university to discover.
Two-sided Derringer DF in MATLAB
clf
hold on
x = [0:.1:800];
y1 = (x >= 150) .* (x < 250) .* ((x - 150) / (250 - 150)).^(0.5) + (x >= 250) .* (x
<= 450) .* 1 + (x > 450) .* (x <= 600) .* ((x - 600) / (450 - 600)).^(0.5);
plot(x, y1, '-.b')
y2 = (x >= 150) .* (x < 250) .* ((x - 150) / (250 - 150)).^(1) + (x >= 250) .* (x <=
450) .* 1 + (x > 450) .* (x <= 600) .* ((x - 600) / (450 - 600)).^(1);
plot(x, y2, '--r')
y3 = (x >= 150) .* (x < 250) .* ((x - 150) / (250 - 150)).^(2) + (x >= 250) .* (x <=
450) .* 1 + (x > 450) .* (x <= 600) .* ((x - 600) / (450 - 600)).^(2);
plot(x, y3, 'g')
ylim([-.1 1.1])
xlabel('Y')
ylabel('d(Y)')
legend('Derringer DF (l=0.5)', 'Derringer DF (l=1)', 'Derringer DF (l=2)',
'Location', 'NorthEast')
Leiden University. The university to discover.