CNS Multiparameter Optimisation (MPO) Score Predictor

    The following manual gives you a walk-through on how to use the CNS MPO Score Predictor.

    Table of Contents


    Central Nervous System (CNS) drugs are special in the sense that they have to penetrate the Blood-Brain Barrier (BBB) in order to have any effect on their target. It is also known that they exhibit physico-chemical properties from certain ranges, forming a smaller subset in the large property space of orally available drugs.

    Wager and his co-researchers at Pfizer built a CNS Multiparameter Optimization (MPO) algorithm for generating a score that used 6 common physico-chemical properties (molecular weight (MW), logP, logD at pH 7.4, topological polar surface area (TPSA), the number of H-bond donors (HBD) and the pKa of the most basic center of the molecule) to build a relationship between this smaller CNS property space and CNS drug-likeness. The research revealed that CNS drugs already on the market and potential candidates show high MPO score values (so called desirability score values ≥ 4.0 on a scale between 0 and 6), making this a useful tool at the design stage to accelerate the identification of compounds with increased probability of success. Since the publication of the research the CNS MPO Score has become a generally accepted algorithm in the CNS-oriented medicinal chemistry community.

    Chemaxon's CNS MPO Score Predictor is able to calculate the CNS MPO score using the algorithm published by Wager et al.


    The CNS MPO Score prediction has been available since v. 20.21. in the following Chemaxon products.


    In MarvinSketch the CNS MPO Score prediction is available under the Calculations » Other » CNS MPO score menu item.



    To predict the CNS MPO Score with cxcalc, use the mpo function:

    cxcalc -N ih mpo aspirine

    From v. 24.1 the properties and their contributions to the CNS MPO Score can also be returned with the -c option:

    cxcalc -N i mpo -c true aspirine
    5.75        1.24  -2.16 180.16  63.60   1.00    -7.14   1.00    1.00    1.00    1.00    0.75    1.00

    Chemical Terms

    To predict the MPO Score with Chemical Terms, use the mpo() function:

    evaluate -e "mpo()" aspirine

    From v. 24.1 the properties and their contributions to the CNS MPO Score can also be returned. For example:

    evaluate -e "mpo('MW')" aspirine
    evaluate -e "mpo('MW_SCORE')" aspirine


    From v. 22.20 the MPO Score prediction is available via the public API. It can also be used via the Calculations Web Services API.

    Accuracy report

    We tested the CNS MPO Score Predictor on a test set of 119 molecules available in the references. We plotted the number of test molecules for which the predicted CNS MPO score falls within the delta range of 0-0.5, 0.5-1.0 and 1.0-1.5, respectively.



    From v. 24.1 the CNS MPO Score prediction requires an ADMET license. However, Protonation, Partitioning and Structural Calculations licenses are required to get the CNS MPO properties and their contributions. See the details here.

    NOTE: Predicting the CNS MPO Score in MarvinSketch requires ONLY the MarvinBeans license. In other Chemaxon tools the above licensing applies.


    1. Wager, Travis T. et al. (2010). Moving beyond Rules: The Development of a Central Nervous System Multiparameter Optimization (CNS MPO) Approach To Enable Alignment of Druglike Properties, ACS Chem. Neurosci., 1(6), 435-449.
    2. Wager, Travis T. et al. (2016). Central Nervous System Multiparameter Optimization Desirability: Application in Drug Discovery, ACS Chem. Neurosci., 7(6), 767-775.