Bender Group Meeting
What is Compound Combination Modelling, and how can it help?
Compound combinations are 'mixtures' of two or more constituent compounds.
The properties of the combination tend to often be non-linearly dependent on the properties of the constituent compounds
This deviation of a biological response from additive is a phenomenon known as synergy.
Medicinal (both western and traditional)
Toxicity considerations for industrial products and intermediates
Flavourings and perfumes
There are many reasons to study combinations:
Combinations are much more common and relevant to the real world than purified single agents commonly considered in chemistry.
The relevant combinations in Nature tend to be tens of compounds.
For example, TCM remedies combine many herbs together, each of which have multiple active compounds in.
This is very complicated to study, and datasets have tended to focus very much on pairwise interaction.
Drug vs All
All vs All
One compound combined with a library
Compounds in a library combined together
Most useful for exploring synergy in general
Most useful for finding partners for an already identified compound
Many different compounds
There are two main techniques for assessing the activity and synergy of combinations of compounds.
Deviation from Gaddum's Non Interaction model (Highest Single agent model
Maximal distance from additive line
More measurements required
Fewer Measurements required
Replicates less costly
Replicates more costly
Survey different dose ratios
Only look at one dose ratio
The shape of the surface may encode information
No extra information encoded
Any plots need to visualise the compounds and their interactions.
In the literature, there have been two main approaches:
Reasonably straightforward for drug vs all, as there is a 1:1 ratio of compounds to interactions.
More difficult for all vs all datasets: the number of combinations is proportional to the square of the compounds
Compounds are positioned on edges
Combinations are patches in the heat map
The colour of the patches indicates the degree of synergy of the combination.
Can order the compounds according to properties
Examples for the malaria database.
Nodes are compounds.
Edges are combinations.
Degree of synergy indicated by thickness/colour of the edges.
Node positioning can be done using a layout algorithm dependent of the edge weights.
Lewis et. al. Synergy Maps: exploring compound combinations using network-based visualisation J.Chem.Inf. 2015 (submitted)
Drug vs All and All vs All datasets are structured to suggest two different paradigms of model building.
All vs All pairwise data suggests a general model of the synergy between two given compounds
Drug vs All however suggests a more simple model, as one compound is kept constant, so the model can be simplified to the familiar QSAR problem:
Using the predicted target log-probabilities from PIDGIN as compound features for the MIPE compounds, and negative log Gamma as an output, a Leave One Out cross validation was performed with Random Forest Regressor models.
Discretise the continuous space to transform to a classification problem
Filter the data to remove bad surfaces
Try out new synergy metrics
Try removing additive data from the training set
Use more detailed features, such as fusion fingerprints
Dr. Andreas Bender
CCM 'task force'
All the Bender Group
Dr. Rajarshi Guha
EPSRC and Department of Chemistry for funding