ACS Spring 2016, Ed Griffen from MedChemica on extracting pharmacophores and toxophores form large data sets

1. Ed Griffen, MedChemica Ltd
Extracting actionable
knowledge from large
scale in vitro
pharmacology data

2. MedChemica
Why improve medicinal chemistry practice?
For an aging population and emerging pathogens
“Eroom’s Law” – The cost of discovering a new drug has
doubled every 9 years consistently for the last 60 years.1
= cost  8%/year
2
1. Scannell et al Nature Reviews Drug Discovery (2012), 11, 191-200
2. Paul et al Nature Reviews Drug Discovery (2010), 9, 203-214
Cost /
$million
Cost/Launch(2010): $873m
Capitalised: $1.8Bn2
0
50
100
150
200
250
300
350
400
450
500
Cost / project
Cost/Launch
Cost/Launch (capitalized)

3. MedChemica
Actionable knowledge
Critical information that the user can immediately choose
a course of action from:
3
ADME
– ways to ‘fix’ your molecule
Toxicology
– sub structures to avoid
Pharmacology
– substructural leads built for
practical design

4. MedChemica
Roche
Data
rule
finder
Roche
Database
Genentech
Data
rule
finder
Genentech
Data
AZ
Data
rule
finder
AZ
Database
Grand Rule
Database
ADMET Rule database
Better medicinal chemistry by combining knowledge
MedChemica
Grand Rule
Database
Grand Rule
Database
Grand Rule
Database
AZ
Exploitation
Roche
Exploitation
Genentech
Exploitation
Pharma 4
Data
rule
finder
Pharma 4
Data
Grand Rule
Database
Pharma 4
Exploitation
Grand Rule
Database
Pharma 5
Data
rule
finder
Pharma 5
Data
Grand Rule
Database
Pharma 5
Exploitation
Grand Rule
Database
>500 million pairs
from companies
+ 12 million from
public data

5. Current Knowledge sets – GRDv3
Numbers of statistically valid transforms
Grouped Datasets Number of Rules
logD7.4 153449
Merged solubility 46655
In vitro microsomal clearance:
Human, rat ,mouse, cyno, dog
88423
In vitro hepatocyte clearance :
Human, rat ,mouse, cyno, dog
26627
MCDK permeability A-B / B – A efflux 1852
Cytochrome P450 inhibition:
2C9, 2D6 , 3A4 , 2C19 , 1A2 40605
Cardiac ion channels
NaV 1.5 , hERG ion channel inhibition
15636
Glutothione Stability 116
plasma protein or albumin binding
Human, rat ,mouse, cyno, dog
64622

6. MedChemica
Actionable knowledge
Critical information that the user can immediately choose
a course of action from:
6
ADME
– ways to ‘fix’ your molecule
Toxicology
– substructures to avoid
Pharmacology
– substructural leads built for
practical design

7. MedChemica
Clear structural direction from Big Data
Example
Dopamine Transporter inhibitors
7
0
30
60
90
120
4 6 8 10
pIC50
count
Pharmacophore
0
1
pKi
Predicted 8.6
Measured 9.1
Mean with Pharmacophore 8.3
Mean without 6.7
n examples 27
Odds ratio : ChEMBL 407
What do I want?:
• Substructures associated with potency
• Specificity of model
• Predictions
• Domain of Applicability
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
● ●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
● ●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
● ●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
● ●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
● ●
●
●
●
●
●
●
●
●●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
4
6
8
5 6 7 8 9
pIC50_pred
pIC50
CHEMBL538405

8. MedChemica
MedChemica Principles of Pharmacophore Extraction
• Pharmacophores must be clear and understandable
• Pharmacophore generation must be transparent to allow checking and
validation
• Use as much measured data as possible
• Look for key elements influencing potency
• Don’t base pharmacophores on a few compounds
• Pharmacophore must be specific
• (not like phenyl + amine = hERG inhibitor)
• Can be applied quickly (to large libraries)
8
Cation
HyAr
HyAr
How do I
actually use
this?

9. MedChemica
QSAR and Knowledge extraction
Model as filter or knowledge?
9
substructures Physical chemistry
descriptors(Hansch,
Taft, Fujita, Abraham)
Atomic, pair, triplet
descriptors
Indices
(M)LR Free Wilson
PLS
Trees / Forests
SVM
Bayesian NN
Deep Learning Dark
Black
Descriptors
Method

10. MedChemica
• Identify key potency giving changes by matched molecular pair analysis on large datasets
• Extract fragments that are associated with potency
• Find pairs of fragments and linkers that are specific to potent compound subsets
•  easy to use 2D pharmacophores
• 2 potency enhancing fragments joined by a specific linker
Specific Pharmacophore extraction from MMPA
10
Model
1470 compounds
CHEMBL339
Dopamine
transporter
Pharmacophore
Identification CHEMBL538405 pKi 9.1
Example
0
200
400
5 6 7 8 9
pIC50
count
All D2 Compounds
Fragment I
Fragment 2
Linker
pKi
Predicted 8.6
Measured 9.1
Mean with Pharmacophore 8.3
Mean without 6.7
n examples 27
Odds ratio : ChEMBL 407
Predict potency
and show
Pharmacophore
match
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
● ●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
● ●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
● ●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
● ●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
● ●
●
●
●
●
●
●
●
●●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
4
6
8
5 6 7 8 9
pIC50_pred
pIC50
Public
Data
Find
Matched
Pairs
Pharmacophores
Find
Pharmacophore
dyads
Find
Potent
Fragments

11. MedChemica
Matched Molecular Pairs
• Molecules that differ only by a particular,
well-defined structural transformation
Transformation with environment
capture
• MMPs can be recorded as transformations from
A B
• Environment is essential to understand chemistry
Statistical analysis
• Learn what effect the transformation has had on properties in the past
Griffen, E. et al. Matched Molecular Pairs as a Medicinal Chemistry Tool. Journal of Medicinal Chemistry.
2011, 54(22), pp.7739-7750.
Advanced MMPA
Δ Data A-
B
1
2
2
3
3
3
4
4
4
12
23
3
34
4
4
A B
Public
Data
Find
Matched
Pairs
Fragments

12. MedChemica
Matched pair methodology
because MCSS and F&I each find different pairings
A – CHEMBL156639 B - CHEMBL2387702
A – CHEMBL100461 B –CHEMBL103900
MCSS ✓, F&I ✗ MCSS ✗ , F&I ✓
MCSS ✓, F&I ✗
MCSS ✓, F&I ✗
MCSS ✗, F&I ✗ MCSS ✗, F&I ✗
MCSS ✗ , F&I ✓
MCSS ✓, F&I ✗

13. MedChemica
Does the Matched Pair method really matter?
Using only one technique will miss between 12% and 56% of pairings
13
Pairings Pairings
number of
compounds common FI only MCSS only total FI only % common % MCSS only %
VEGF 4466 14631 17172 14823 46626 37 31 32
Dopamine
Transporter 1470 4480 8930 3497 16907 53 26 21
GABAA 848 2500 1722 4205 8427 20 30 50
D2 human 3873 12995 13811 13098 39904 35 33 33
D2 rat 1807 5408 6595 7346 19349 34 28 38
Acetylcholine
esterase 383 536 725 1434 2695 27 20 53
Monoamine
oxidase 264 653 1156 246 2055 56 32 12
min 20 20 12
max 56 33 53
FI MCSS
common

14. MedChemica
Mining transform sets to find potent fragments
Identify the ‘A’ fragments associated with a significant
number `of potency decreasing changes – irrespective
of what they are replaced with
‘A’ is ‘better than anything you replace it with’
Fragment A Fragment B
Change in binding
measurement
• One-tailed binomial test with Holm–
Bonferonni correction at 95%
confidence identifies potent
fragments
• Compare the mean of the
compounds that contain the
fragment with the mean of the
remaining compounds
Statistics:
pKi/
pIC50
Compounds
containing potent
fragment
Remaining
compounds
Effect size =
Cohen’s d test
A
B
C ED
+2.1+2.2
+1.4
+0.4 F
+1.8
Public
Data
Find
Matched
Pairs
Find
Potent
Fragments
Cohen’s d
Effect sizes:
Large >= 0.8
Medium 0.5 – 0.8
Small 0.2 - 0.5
Trivial 0.1 – 0.2
No effect < 0.1
d = A
m -
B
m
1
s
s ' = A
2
s + B
2
s
2

15. MedChemica
Mining transform sets to find destructive fragments
Identify the ‘Z’ fragments associated with a significant
number `of potency increasing changes – irrespective of
what they are replaced with
‘Z’ is ‘worse than anything you replace it with’
Fragment A Fragment B
Change in binding
measurement
Public
Data
Find
Matched
Pairs
Find
Potent
Fragments
+2.7
+3.2
+0.6
+0.6
Z
pKi/
pIC50
Compounds containing
destructive fragment
Remaining
compounds

16. MedChemica
Mining transform sets to find influential fragments
Identify the ‘Z’ fragments associated with a significant
number `of potency increasing changes – irrespective of
what they are replaced with
‘Z’ is ‘worse than anything you replace it with’
Fragment A Fragment B
Change in binding
measurement
Public
Data
Find
Matched
Pairs
Find
Potent
Fragments
+2.7
+3.2
+0.6
+0.6
Identify the ‘A’ fragments associated with a significant
number `of potency decreasing changes – irrespective
of what they are replaced with
‘A’ is ‘better than anything you replace it with’
A
+2.1+2.2
+1.4
+0.4
+1.8
Z
pKi/
pIC50
Compounds with
destructive fragment
Compounds with
constructive fragments

17. MedChemica
Building Pharmacophores from potent Fragments
But individual Fragments are small and often non – specific so…
• Permutate all the pairs of fragments and find the the shortest
path between them (pharmacophore dyads) in the training set
• shortest path between them encodes distance & geometry
• select pharmacophore dyads with PLS to identify the dyads that
are explaining most of the potency
• check for significance and effect size with Cohen’s d and Welch’s
t-test.
17
• But what about specificity?
Path
Fragment 1
Fragment 2
[CH2]CN
Public
Data
Find
Matched
Pairs
Pharmacophores
Find
Pharmacophore
dyads
Find
Potent
Fragments

18. MedChemica
Testing for specificity - pharmacophores
• How selective is the pharmacophore?
• What are the odds of it hitting a molecule in the test set vs
CHEMBL?
• Odds of finding in potency set =
n(pharmacophore hits in potency set)
n(in potency set)
• Odds of finding in CHEMBL =
n(pharmacophore hits in CHEMBL not in potency set)
n(in CHEMBL)
• Odds ratio = selectivity =
Odds of finding in potency set_______
Odds of finding in CHEMBL(not potency set)
18
27
1470
62
1351211
27/1470
62/1351211
=407
(95% confidence limits: 259-642)
Odds of hitting a potent compound are 407 times greater than a random compound in CHEMBL
Path
Fragment 1
Fragment 2
[CH2]CN

19. MedChemica
How specific is a Pharmacophore?
What does a bad odds ratio look like?
What is the odds ratio?
Found in CHEMBL 565658/1352681
Found in CHEMBL240 – hERG where pIC50 >=5 1985/2451
OR = 1985/2451 = 0.81
565658/1352681 0.42
=1.94 (95% conf 1.83 – 2.05)
19
Lipophilic base, usually a tertiary amine
X = 2-5 atom chain, may include rings, heteroatoms
or polar groups
X
N
R1
R2
e. g. sertindole: 14nM vs hERG
[$([NX3;H2,H1,H0;!$(N[C,S]=[O,N])]~*~*~*~c),$([NX3;H2,H1,H0;!$(N[C,S]=[O,N])]~*~*~c),$([NX3;H2,H1,H0;!$(N[C,S]=[O,N])]~*~*~*~*~c),$([NX3;H2,H1,H0;!$(N[C,S]=[O,N])]~*~*~*~*~*~c)]
Early simple hERG model
Ar-linker-base has only been found 1.9x more often in
hERG inhibitors than at random in ChEMBL

20. MedChemica
Domain of Applicability
“Whereof one cannot speak, thereof one must be silent.”1
Claiming to have extracted knowledge or making a prediction when we know don’t have
enough evidence is:
• Delusional
• Dangerous
• it would be more productive to act on a different hypothesis or at random
• Degrades using rational analysis at all
Compound activity prediction should have three classes of output:
• Active
• Inactive
• Out of domain – no prediction possible
Only fragments with sufficient evidential base are used to form into
pharmacophore dyads
In turn only pharmcophore dyads that have enough support are used in the
model
20
1. Wittgenstein, Tractatus Logico-Philosophicus, 1922

21. MedChemica
Model activity from presence of Pharmacophores
21
0
20
40
60
80
0
20
40
60
80
01
4 6 8 10
pIC50
count
Matches
0
1
0
30
60
90
120
4 6 8 10
pIC50
count
Matches
0
1
Identify and group Fragment SMARTS from
MMPA
If n ≥ 8, perform a one-tailed binomial test with
Holm-Bonferroni adjustment
Remove non significant ‘Biophores’
Compare the mean of the compounds containing
the biophore with the mean of the remaining
compounds for significance (Welch’s t test and
effect size Cohen’s d)
Permutate all the significant Biophores and
determine the shortest paths between them in
the training set = Pharmacophore dyads
Select Pharmacophore dyads with n >=6
examples
Use presence /absence of
Pharmacophore dyad as an indicator
variable in PLS modelling
Dopamine Transport +/- pharmacophores

22. MedChemica
Modelling critical safety targets
22
1. J. Bowes, A. J. Brown, J. Hamon, W. Jarolimek, A. Sridhar, G. Waldron, and S. Whitebread, “Reducing safety-related
drug attrition: the use of in vitro pharmacological profiling,” Nat. Rev. Drug Discov., vol. 11, no. 12, pp. 909–922, Nov.
2012
Public Data
Find
Matched
Pairs
Pharmacophores
Find
Pharmacophore
dyads
Find Potent
Fragments
Target Class Effect Number of compounds
Acetylcholine esterase - human enzyme CV: drop in BP, drop in HR, bronchioconstriction 383
b 1 adrenergic receptor GPCR CV: change in HR, BP, bronchiodilation, vasodilation, tremor 505
Androgen receptor NHR
Endocrine: agonism: androgenicity / gynecomastia, prostrate /
breast carcinoma
1064
CB1 canabinnoid receptor GPCR
CNS: euphoria, dysphoria, anxiety, memory impairment, analgesia,
hypothermia, weight loss, emesis, depression
1104
CB2 canabinnoid receptor GPCR increased inflammation 1112
Dopamine D2 receptor - human GPCR
CNS: hallucinations, drowsiness, confusion, emesis,
CV drop in heart rate
3873
Dopamine D2 receptor - rat GPCR As human 1807
Dopamine Transporter Transporter
CNS: addictive psychostimulation, depression , parkinsonism,
seizures
1470
GABA A receptor Ion channel CNS: anxiolysis, ataxia, sedation, depression, amnesia 848
hERG ion channel Ion channel CV: QT prolongation 4189
5HT2a receptor GPCR CNS:drop in body temp, anxiogenic 642
Monoamine oxidase enzyme CV increase BP, DDI potential CNS: dizziness, nausea 264
Muscarinic acetyl choline receptor
M1
GPCR CNS: proconvulsant, drop in cognitive function, vision impairment 628
m opioid receptor GPCR CNS: sedation, abuse liability, respiratory depression, hypothermia 1128

23. MedChemica
Target
Number of
compounds
Number of
compound
pairs
Number of
Fragments
Number of
Pharmacophore
dyads after
filtering
R2 RMSEP ROC
odds_ratio
(geomean)
Acetylcholine esterase - human 383 27755 44 10 0.43 1.57 0.80 4
b 1 adrenergic receptor 505 145447 276 313 0.64 0.70 0.96 833
Androgen receptor 1064 113163 186 46 0.47 0.77 0.86 140
CB1 canabinnoid receptor 1104 88091 165 90 0.61 1.02 0.87 96
CB2 canabinnoid receptor 1112 82130 194 158 0.19 0.85 0.64 5.7
Dopamine D2 receptor - human 3873 230962 483 602 0.42 0.88 0.69 110
Dopamine D2 receptor - rat 1807 118736 267 377 0.29 0.85 0.78 125
Dopamine Transporter 1470 106969 282 336 0.58 0.73 0.88 141
GABA A receptor 848 39494 106 167 0.70 0.76 0.97 560
hERG ion channel 4189 242261 392 76 0.61 0.96 0.92 55
5HT2a receptor 642 50870 197 267 0.61 0.59 0.83 600
Monoamine oxidase 264 15439 44 11 0.12 1.25 0.48 181
Muscarinic acetylcholine receptor M1 628 48200 97 510 0.62 0.94 0.89 48
m opioid receptor 1128 37184 33 11 0.69 1.30 0.87 81
Modelling critical safety targets
• Build models using 10-fold cross validated PLS
• Assess using ROC / BEDROC, R2 vs 100 fold y-scrambled R2 and geomean odds ratio
23
Public Data
Find
Matched
Pairs
Pharmacophores
Find
Pharmacophore
dyads
Find Potent
Fragments

24. MedChemica
Toxophore examples
Detailed, specific & transparent
24
Dopamine D2 receptor human
Actual: 9.5
Predicted: 9.1
Mean with: 8.0
Mean without: 6.6
Odds Ratio: 340
Dopamine Transporter
Actual: 9.1
Predicted: 8.6
Mean with: 8.3
Mean without: 6.7
Odds Ratio: 407
GABA-A
Actual: 9.0
Predicted: 8.7
Mean with: 8.0
Mean without: 6.8
Odds Ratio: 1506
b1 adrenergic receptor
Actual: 7.8
Predicted: 7.7
Mean with: 6.5
Mean without: 5.7
Odds Ratio: 1501

25. MedChemica
Safety Target Conclusions
• We can model safety critical targets and extract both predictive models and
useful ligand structural information
• Clear areas to action
• Clearly defined domain of applicability
• No prediction where there is insufficient evidence (conservative method)
• The method relies on having large data sets >= 500 data points
• MMPA is computationally intense phase
• But of course molecules only need pairing once…
25

26. MedChemica
Actionable knowledge
Critical information that the user can immediately choose
a course of action from:
26
ADME
– ways to ‘fix’ your molecule
Toxicology
– sub structures to avoid
Pharmacology
– substructural leads built for
practical design

27. MedChemica
Prediction of unseen new molecules
The acid test…
• Vascular endothelial growth factor receptor 2 tyrosine kinase (KDR)
• Inhibitors have oncology and ophthalmic indications
• Large dataset in CHEMBL
• 10 fold cross validated PLS model
• Selected model by minimised RMSEP
27
Compounds 4466
Matched Pairs 288100
Fragments 678
Pharmacophore dyads 787
RMSEP 0.8
R2 0.64
Y-scrambled R2 0.0
ROC 0.95
Geomean odds ratio 80
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
● ●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
● ●
●
●
●
●
●
●●
●
●
●
●
● ●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
● ●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
● ●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
● ●
●
●
●
●
●
●
●
●●
●
●
●
● ●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●●
●
●
●
● ●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●●
●●
●
●
●
●
● ●●
●●●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
● ●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●●
●●
●
●
●
●●●●
●
●
●●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
● ●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●●●
●
●●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
4
6
8
10
5 7 9
pIC50_pred
pIC50

28. MedChemica
Novartis Predictions From Our Model
Domain of Applicabiltiy….
Actual: 8.4[1]
Predicted: 7.5
28
Actual: 7.6[1]
Predicted: 7.5
1. J MedChem(2016), Bold et al.
2. MedChem Lett (2016), Mainolfi et al.
Actual: 7.7[2]
Predicted: 7.1
Actual: 9.0[2]
Predicted: Out of Domain

29. MedChemica
Value of Potency prediction from MMPA:
Clear substructures enable rapid actions
29
Compounds +
data
Safety
data
Potency
data
HTS
data
Toxicity alerts
Virtual Library prioritisation
Virtual Library design
Fragment set design
Retest prioritisation
Hit re-mining / analogue hunting
Substructure modification
Lead design
Fast Follower design
26 examples in
training set
Mean without
pharmacophore
Mean with
pharmacophore
0
2
4
6
6 7 8 9 10
pIC50
count

30. MedChemica
The MedChemica team
Andrew G Leach
Al Dossetter
Shane Montague
Lauren Reid*
Jess Stacey*
*Royal Society of Chemistry Industrial Placements Grant Scheme

31. MedChemica
A Collaboration of the willing
Craig Bruce OE
David Cosgrove GalCoz
Andy Grant★
Martin Harrison Elixir
Paul Faulder Elixir
Andrew Griffin Elixir
Huw Jones Base360
Al Rabow
David Riley AZ
Graeme Robb AZ
Attilla Ting AZ
Howard Tucker retired
Dan Warner Myjar
Steve St-Galley Sygnature
David Wood JBA Risk
Management
Phil Jewsbury AZ
Mike Snowden AZ
Peter Sjo AZ
Martin Packer AZ
Manos Perros AZ
Nick Tomkinson AZ
Martin Stahl Roche
Jerome Hert Roche
Martin Blapp Roche
Torsten Schindler Roche
Paula Petrone Roche
John Cumming Roche
Jeff Blaney Genentech
Hao Zheng Genentech
Slaton Lipscomb Genentech
James Crawford Genentech