# Systematic quantitative characterization of cellular responses induced by multiple signals

- 5.1k Downloads
- 27 Citations

## Abstract

### Background

Cells constantly sense many internal and environmental signals and respond through their complex signaling network, leading to particular biological outcomes. However, a systematic characterization and optimization of multi-signal responses remains a pressing challenge to traditional experimental approaches due to the arising complexity associated with the increasing number of signals and their intensities.

### Results

We established and validated a data-driven mathematical approach to systematically characterize signal-response relationships. Our results demonstrate how mathematical learning algorithms can enable systematic characterization of multi-signal induced biological activities. The proposed approach enables identification of input combinations that can result in desired biological responses. In retrospect, the results show that, unlike a single drug, a properly chosen combination of drugs can lead to a significant difference in the responses of different cell types, increasing the differential targeting of certain combinations. The successful validation of identified combinations demonstrates the power of this approach. Moreover, the approach enables examining the efficacy of all lower order mixtures of the tested signals. The approach also enables identification of system-level signaling interactions between the applied signals. Many of the signaling interactions identified were consistent with the literature, and other unknown interactions emerged.

### Conclusions

This approach can facilitate development of systems biology and optimal drug combination therapies for cancer and other diseases and for understanding key interactions within the cellular network upon treatment with multiple signals.

## Keywords

A549 Cell Drug Combination AG02603 Cell Neural Network Structure GF109203X## Background

Understanding how multiple signals affect cellular functions is necessary in order to be able to understand and control these functions. Extensive studies have been done to address how the activation/inhibition of a particular cellular signaling pathway leads to a specific response. Several challenges limit the ability to study the simultaneous effects of multiple signaling. The complexity and lack of detailed knowledge of cellular systems prevent, in many cases, accounting for the effects of some unknown interactions among pathways or among non-primary signal targets. In addition, genetic or epigenetic alterations between otherwise similar cells can cause a significant difference in their responses. This places additional constraints on the experimental outcomes obtained by analyzing individual components. Furthermore, a critical challenge in the investigation of the effects of multiple signals is the arising complexity associated with the increasing number of signals and their various intensities. Without a systematic approach to replace a large number of time and resource consuming experimental tests, it is difficult to characterize the effects of these signals, to identify appropriate signal combinations.

There has been an increasing interest in examining how various biological activities are regulated by multiple interacting signals [1, 2, 3, 4]. Berenbaum introduced a direct search method to optimize cancer chemotherapy regimens [5]. Recently, a method based on stepwise direct search for identifying optimal combination of drugs for pain treatment has been introduced [6]. The method can also be applied in clinical research. More recently, a biased random walk approach called the "modified Gur game" approach was introduced to identify potent drug combinations [7, 8]. It is applied towards an objective with a "small" number of experimental trials. While the goal of these studies is to achieve optimization with minimal number of tests, the approach in these studies has several limitations including sensitivity to the design of the automatons driving the random walk and sensitivity to initial conditions. Its capacity to compare the performance of multiple systems will be limited due to the limited amount of obtained information. Moreover, the approach does not guarantee convergence to local or global maxima. In [8], the modified Gur game approach was used to identify a wide range of drug concentrations for which a stochastic search algorithm, differential evolution, was used to maximize an objective function. Although this approach converges to better combinations, the determination of the range of drugs to be used in the combination is sensitive to initial conditions. Another recent and very similar approach uses a deterministic search algorithm for optimization of drug combinations [9]. Determining optimal combinations for systems where a mechanistic model based on mass-action kinetics was recently presented [10]. The use of search algorithms as well as other systems approaches that include the mechanistic mass-action models were reviewed in [11]. Another limitation of these approaches is that they require repetition of the experiment in case the optimization parameters are to be modified or there is a change in the objective function. This limitation becomes significant when considering multi-objective optimization functions in which the objective function is dependent on subjective parameters, resulting in the need to carry over several experiments to determine a suitable set of parameters. Additionally, the convergence of the experimentally applied search algorithms depends on the appropriate selection of the algorithm's parameters. In the absence of a model to enable reasonable selection of the algorithm's parameters, convergence of these algorithms might be compromised. Furthermore, the experimentally applied algorithms can converge to an optima (local or global) that is not very robust to "small" variations in the input signals.

Other recent work on identifying drug combination focuses on identifying mixtures of drugs where the the search space is reduced to use only a single concentration while the search space is increased by searching through a larger number of potential drugs [12, 13]. The latter example describes an approach and applies it towards finding promising mixtures for lung cancer.

*in silico*experiments, the model enables analyzing the response of the system to various combinations and determining or selecting subsets of signal combinations that can yield desired cellular responses. The determination of these subsets can be achieved using tools such as stochastic search algorithms and cluster analysis. The proposed approach will facilitate the understanding of fundamental cellular responses, which are system responses reflecting the activity of a complex signaling network controlled by multiple internal and external signals. This approach can promote efficient understanding of cellular functions without intermediates. In addition, the approach allows multiple cell types or other biological systems to be quantitatively characterized, modeled, and compared in parallel. The maximal difference or similarity can be identified using a computational search. It can facilitate the development of drug combination therapies for various types of cancers [14, 15].

In comparison to the approaches previously mentioned, the approach introduced in this work overcomes their limitations by identification of the complete response function and carrying out the optimization *in silico*. The cost of carrying such *in silico* experiments is significantly less and is generally faster. The identification of the system response function also provides additional information regarding the potential of using a smaller number of drugs and on key system-level signaling interactions.

## Results

We utilize mathematical tools to characterize the effects of three and four agents on the differential response of cancer and normal cells. The cellular ATP levels of a non-small cell lung cancer cells A549 and primary lung fibroblast culture of AG02603 cells in response to combinations of three chemical agents are measured. Mathematical tools are used to construct predictive models of the cellular ATP levels in response to the combinations. We examine the ability to utilize relatively small numbers of combinations for model generation. The results are extended to study systems of higher complexity with the addition of a fourth chemical agent. The resulting models are used to compare the responses of normal and cancer cell to the same set of combinations. We show that a properly selected combination can result in a significant difference in the respective performance of normal and cancer cells. We also experimentally validate the selected combinations. Furthermore, we show that a combination of chemical agents, if properly chosen, can be more effective than a single agent in inducing a differential response between normal and cancer cells. Using the models, we will examine all the possible lower order mixtures of the four drugs. Moreover, we extract key system-level signaling interactions and compare these interactions between different cell types. We also compare these interactions to known interactions between the drugs.

### Signal-Cellular Response Modeling with a Complete Data Set

One of the goals of this work is to identify differences in the responses between cancer and non-cancer cells upon the drug treatment. The interactions in Figure 2 are an oversimplified set of interactions of the drugs used. The simplified diagram serves to illustrate some of the known interactions within the cell upon treatment with various drugs. AG490 is a tyrosine kinase inhibitor; U0126 is a MEK inhibitor; and indirubin-3'-monoxime is a cyclin-dependent kinase inhibitor. The drugs are also known to inhibit other targets in addition to the intended target enzymes and as such can lead to unknown interactions. Moreover, each pathway has various interactions with more pathways that are not depicted. The drugs may activate some pathways such as some of the stress responses, directly or indirectly. Thus, the interactions of these drugs and their combinatory effects are difficult to predict.

Concentrations of the drugs used in the three and four drug treatments.

A | Drug Name | Drug Concentration |
---|---|---|

AG490 | 0, 0.3, 1, 3, 10, 30, 100, 300 (uM) | |

U0126 | 0, 0.1, 0.3, 1, 3, 10, 30, 100 (uM) | |

Indirubin-3'-monoxime | 0, 0.3, 1, 3, 10, 30, 100, 300 (uM) | |

| | |

AG490 | 0, 1, 3, 10, 30, 100, 300 (uM) | |

U0126 | 0, 0.1, 0.3, 1, 3, 10, 30 (uM) | |

Indirubin-3'-monoxime | 0, 1, 3, 10, 30, 100, 300 (uM) | |

GF109203X | 0, 0.3, 1, 3, 10, 30, 100 (uM) |

The ATP level in response to all of the 512 drug combinations was experimentally measured in lung cancer A549 cells and in primary lung fibroblast AG02603 cells. The fibroblast cells were derived from normal healthy tissue and are not cancer cells. There are several mathematical methods that can be used to generate models of input-output data. Here we provide a comparison of some of these methods in view of the function approximation problem considered. The methods include two neural network structures and two linear regression models. The neural network structures are a single layer multi-layer perceptron (MLP) and a cascaded neural network [18, 19]. We have examined different numbers of neurons per layer for each of these neural network structures. The results below show that a four-neuron single-layer MLP is sufficient for the purposes of this work. For the cascaded network, two layers with a single neuron per layer were sufficient. Networks with more neurons per layer also produced satisfactory results. The two linear regression models involve different nonlinear regressors. The first one uses interaction terms that are pairwise and k-wise products of all the concentrations of the drugs. The second is a quadratic response surface that uses only pairwise products and quadratic terms of the concentrations (See the Methods Sections).

Correlation coefficients between the 432 points not used for training and the corresponding experimentally measured values.

Cell Type | QRF | LR | Cascaded NNet | MLP |
---|---|---|---|---|

AG02603 | R = 0.96 | R = 0.95 | R = 0.95 | R = 0.96 |

A549 | R = 0.96 | R = 0.92 | R = 0.97 | R = 0.98 |

However, no significant improvement in the errors are observed for models with more than 80 points. Using a small number of points results in poor prediction with the linear regression models, the interaction model and the quadratic models. In the absence of post-processing of the data by passing through a saturation function, the mean square error of prediction of the linear regression models become significantly worse. Between the two linear regression models, the quadratic model performs better than the interaction model, potentially due to the added quadratic terms, suggesting the nonlinearity of the response of these cells to the drug combinations used. These models also have higher mean square errors than the neural network models. The differences between the mean square error of these models tend to diminish as the number of points used increases. The two neural network models were comparable overall.

The number of data points required to generate a valid model relies on factors including intrinsic signal-response relationships for individual cell cultures and the experimental measurement error. In addition, the smoothness of many signal-response relationships enables the modeling to rely on less dense mapping over small ranges of signal concentrations. Our results suggest that with a proper mathematical modeling method, the effect of signal combinations can be systematically described through randomly testing a relatively small percentage of signal combinations within specified concentration ranges.

### Characterization of Signal-Cellular Response Relationships in Systems of Higher Complexity

We have also investigated the ability of these models to predict the experimental data obtained in the three drug combinations experiment. These combinations correspond to four-drug combinations where the concentration of the fourth drug is set to zero.

Correlation coefficients between the 512 data points and their predicted values were 0.86 for A549 cells and 0.88 for AG02603. These correlation coefficients are quite reasonable given that the two experiments were conducted several months apart and the model was trained on a separate and independent data set. This provides evidence of the ability of our models to predict cellular responses despite the relatively small number of data points used to generate these models.

### Effects of Single Signal Versus Multiple Signals

Although all four drugs inhibit cellular functions common in both cell types, combinations of these drugs may result in a significant difference in cellular ATP-levels between A549 and AG02603. Inhibition of A549 cells and preservation of AG02603 cells using the same drug combination constitute two conflicting objectives. Our goal of identifying the drug combinations that effectively satisfy the above objectives can be realized by utilizing a multi-objective search or optimization technique. A performance function combining the relative importance of each of the two conflicting objectives is introduced (Materials and Methods). The drug combinations resulting in the highest performance are considered the best drug combinations of a given set of drugs with corresponding concentrations.

Identification of the best performing subset is achievable through various methods. Enumeration and sorting of all possible combinations and their corresponding performances is one method. Alternatively, we can use a clustering algorithm such as a k-means clustering algorithm to group combinations with similar performances [20, 21].

Shown are the concentrations used for for generating the drug response curves.

Drug Name | Low | Medium | Maximum | Selected |
---|---|---|---|---|

AG490 | 0 | 10 | 300 | 30 |

U0126 | 0 | 1 | 30 | 0.3 |

Indirubin-3'-monoxime | 0 | 10 | 300 | 10 |

GF109203X | 0 | 3 | 100 | 0.3 |

### Examining the Efficacy of Mixtures of Two, Three, and Four drugs

However, this improvement becomes less as four drugs are used instead of three. The results also show that the improvement is more significant for certain mixtures of drugs, e.g., the performance of the mixture of AG490 and I-3-M is better than the performance of AG490 and U0126. A similar observation can be made about three-drug mixtures where the mixture of AG490, I-3-M and GF109203X performs better than the three other three-drug mixtures. This information is not known a priori and without this approach, determining the best mixtures requires testing of each mixture independently. This can be a lengthy and costly process. Moreover, if one elects to randomly select combinations for the mixtures then there is no guarantee that the combination or mixture can have a good performance. In fact the random combination and mixture can perform quite poorly (Figure 10A). Hence, an effective approach for identifying mixtures of drugs and effective combinations can be very useful in this regard.

The potency of our approach can be illustrated by examining the performance of this approach versus more simple approaches. An example of such approaches is combining the drugs at the best single-drug concentrations. The best concentrations for each single drug were 30uM, 30uM, 30uM, and 100uM for AG490, U0126, I-3-M, and GF109203X respectively. Combining the drugs at the best single-drug concentrations results in a poor performance of 44.48 corresponding to zero normalized ATP levels of A549 and AG02603. One can argue that this combination can be very toxic because of the combined high concentration of each of the drugs. However, there is no simpler way to reduce the concentration of some or all drugs to achieve a better performance. Additionally, an argument can be made for the selection of the mixture of two drugs by picking the two best single drugs. In our case, this would correspond to mixing U0126 and I-3-M. This mixture does not perform as well as the mixture of AG490 and I-3-M (Figure 10). Again, there is no simpler approach for the selection of such mixtures. The approach we introduced attempts to answer to this need and provides a systematic approach that can be used to identify the best combinations for mixtures of two, three, and four drugs. In a more general setting, the approach enables identification of efficient combinations and mixtures for any number of *n*-drugs.

Validation of selected top performing combinations (30 uM of AG490, 0.3 uM of U0126, 10 uM of I-3-M, and 0.3 uM of GF109203X), (30 uM of AG490, 0.3 uM of U0126, 30 uM of I-3-M, and 1 uM of GF109203X), and (30 uM of AG490, 1 uM of U0126, 10 uM of I-3-M, and 0.3 uM of GF109203X) showed that the experimental ATP levels of A549 and AG02603 were 0.2 and 0.65, 0.13 and 0.51, and 0.13 and 0.5 respectively. This is in agreement with the predicted values for A549 and AG02603 of 0.21 and 0.59, 0.08 and 0.51, and 0.2 and 0.58 respectively.

### Drug-Drug Interactions Affect the Observed System Responses

Modeling of multi-signal induced cellular responses can also be used to study key system-level signaling interactions between the applied signals and their effects on the system outputs. To that end, consider the linear regression model with interaction terms. This model uses a total of 15 regressors that are the concentrations of the drugs, six pairwise interaction terms, four three-drug interaction terms, and one four-drug interaction term. This is a large number of regressors and, potentially, only a portion of these regressors are necessary to describe the variation in the data. Reduction of the regressors matrix *X* can be achieved using principal components analysis. Partial least squares can also be used and in this case the reduction in the regressors matrix takes into account variation in the output. However, the components obtained with principal component analysis or partial least squares models would be hard to interpret given the large number of regressors. Instead, we pursue a subset selection algorithm based on all the possible subset regressions [22]. The algorithm provides the best models of 1, 2, 3, . . ., 15 regressors. In total, the algorithm provides the best 15 models out of 2^{15} - 1 possible models.

## Discussion and Conclusions

We demonstrated the integration of an efficient mathematical approach for a systematic quantitative characterization of the effect of multi-signal combinations in two different cell types. Our method enables the establishment of accurate models to directly connect multi-signal combinations and their effects through a learning process. Only a small percentage of total data points are required to be experimentally tested to establish a predictive model that is capable of simulating the effect of all possible signal combinations.

The resulting predictive model is also able to systematically reveal the inter-drug interactions which are often non-linear relationships. Such a model is necessary for multi-drug combination optimization as the optimal combination, upon the addition of a new drug, cannot be achieved simply by testing various amounts of the new drug added to the previously optimized combination. Moreover, the approach allows for examining all lower order mixtures of the drugs and for evaluating the effectiveness without added experimental overhead. This enables efficient selection of drug combinations of different drugs particularly as the interactions between the different drugs vary. The approach enables systematic selection of input signals (drug combinations) that can achieve desired therapeutic goals. Experimental validation of selected top performing combinations presents additional evidence of the validity and utility of the approach introduced.

Our approach requires a relatively small number of experimental measurements. With the development of large scale-high throughput measurement systems, our approach will be necessary and more efficient, e.g., when the number of inputs increases. Additionally, it will allow for integration into automated machines for testing and analysis of various biological systems. The addition of other cellular outputs can be another factor in favor of using this approach.

### Mathematical Modeling Methods

We demonstrated the utility of various mathematical modeling approaches for the purposes of modeling and predicting multi-signal induced cellular responses. Linear regression with models including interaction and quadratic terms were capable of producing powerful predictive models. The usefulness of linear regression methods and subset selection algorithms was also demonstrated as they enabled determination of key system-level signal interactions that result in the observed cellular responses. Alternately, neural network models performed generally better for fitting the data particularly when fewer data points were available to fit the models. Additionally, different structures of neural networks were almost equally powerful in producing the models. This present ample opportunity to exploit different structure of networks to mimic more realistic interactions within the cell given such a priori data. The choice of the best method for fitting the model is dependent on many factors. While in some cases simple linear regression can be used, in other cases nonlinear regression methods are necessary to get satisfactory models. Neural networks represent powerful computational models with great flexibility. Different types and configuration renders them useful for a wide range of problems including dynamic prediction using, e.g., recurrent neural networks. This presents an additional use for neural network to build on a wide range of applications in biological and medical research [23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34].

It is important to note here that the novelty in this work is not this particular use of artificial neural networks. Rather, it is the use of a system-level model-based approach to study the effects of a large number of signals on various cellular processes and to use that as a basis for selection of the retrospective optimal input signals. Our method resembles a general systems biology approach that can be utilized to address a broad range of biological questions. The method enables comparison of multiple system performances through modeling of their responses. The advantage of our method becomes critical when input signal combinations are characterized for the development of effective *in vivo* therapies, in which case the limited experimental scale imposes restrictions on the number of possible drug combinations to test. By largely reducing the number of tests required, our approach can greatly facilitate the development of clinically applicable treatments.

For the drugs and cell types chosen, our results showed that four drugs did not provide a significant improvement over three drugs. However, this is not a general result and the causes of this observation are not well known and pose an interesting problem to be examined in a separate study. A potential cause is that the signaling pathways affected by some of the drugs are saturated potentially due to sharing of a common target between two of the drugs. In other studies we are working on with different drugs and cells, four drugs result in an improvement over three drugs and five drugs also improve on four drugs.

### Mechanistic Reasoning

Our modeling approach enabled identification of key system-level signaling interactions that contribute to the observed responses. These interactions highlighted potential differences in the signaling networks of different cell types as demonstrated. While some signaling interactions were common to the two cell types studied, there were other interactions that were specific to each cell type. Many of these interactions were known a priori. For example, the interactions between U0126 and GF109203X, I-3-M and GF109203X, AG490 and I-3-M, as well as AG490 and U0126 and GF109203X. There are other interactions that were not known a priori such as the interaction between U0126 and I-3-M. Thus the prediction of such interactions can guide experimental identification of the molecules mediating the interactions.

In the work presented, we used mathematical tools to construct a predictive model of cellular outcomes. The method was developed in experimental systems that only involved single output measurements. However, the method is a general method that can be used to construct models of the effects of multiple signals on various cellular outcomes, including signaling intermediates. Molecules from various cellular pathways, "intermediates", can serve as candidates for measurement and quantification [1, 35, 36]. Moreover, measuring these cellular outcomes and intermediates at various time points enables the construction of predictive dynamic models. The incorporation of time provides the model with predictive capability similar to those of ordinary differential equation models, though without a priori assumptions or knowledge about the molecular interactions. The introduction of more cellular outcomes presents the opportunity to utilize additional tools that can infer sets of rules which can provide, at least in part, descriptive reasoning of some of the internal interactions within the cell [37, 38, 39].

### Implications on the Design of Combination Therapies

Combinational therapies have attracted significant research efforts. Combination therapy for cancer is one example. The challenges associated with cancer treatment range from a lack of understanding of fundamental pathogenic mechanisms to practical experimentation limitations. Cancer is usually caused by multiple mutations and alterations of multiple signaling pathways which pose an extra challenge when defining the mechanisms underlining cancer development [40]. In addition, there is extensive heterogeneity of tumors among individual patients. Thus there are multiple potential targets for cancer therapy, resulting in an increasing need for distinct therapeutic agents and their combinations. Furthermore, drug resistance, arising from a subpopulation of original tumor cells or from subsequent mutations under the selection pressure of drug treatment, has been a major hurdle in cancer treatment. Drug combination therapy is emerging as a potentially effective approach to prevent drug resistance, as well as achieve higher efficacy and lower toxicity [41, 42, 43].

However, the design of combination therapies based on studies of the response to individual drugs might not lead to the desired outcomes as interactions between the various drugs can lead to unknown outcomes. The emerging toxicities can be a major hurdle to the development of combination therapies. Therefore, it is important to consider system level signals or outputs that are representative of the state of the cell in addition to cellular intermediates targeted by the drugs. As such, it is important to investigate whether and how a combination of drugs can lead to a better system response compared to any of the individual single-drug responses.

Development of drug combination therapies for cancer can lead to more effective therapies to overcome drug resistance and achieve maximal drug efficacy. The demanding task is to find a combination that is maximally effective on cancer cells with minimal effect on non-cancer cells. The method introduced in this work provides the ability to study the system-level effects of combinations of drugs and use the data to select combinations that can lead to desired outcomes by comparing the mathematical models of multiple cellular types. Furthermore, the method is capable of studying and characterizing experimental problems of higher complexity such as the order and timing of administration of multiple inputs into the system, which may help further reduce cytotoxicity and enhance efficacy with the same drugs utilized in clinical treatment of diseases. Moreover, employing our method with emerging technologies such as micro-fluidic devices or "lab-on-chip" will enable high-throughput investigation of multi-drug combinations, and become a promising platform for developing personalized medicine.

## Methods

### Cell Culture and Experimental Measurements

A549 cells were cultured in RPMI1640 medium (CellGro) supplemented with 10% heat-inactivated FBS, 100U/ml penicillin and 100g/ml streptomycin (CellGro). AG02603 cells were in MEM (Gibco) supplemented with non-essential amino acid (Gibco), 15%heat-inactivated FBS, 100U/ml penicillin, and 100g/ml streptomycin. Cells were seeded one day before drug treatment at a density of 1000cells/well for A549, and 8000cells/well for AG02603, in 96 well plates. ATP assays were conducted with the ATPlite 1step assay system (PerkinElmer) following the manufacturer's instructions and the luminescence signal was measured by Lmax microplate luminometer (Molecular Devices).

### Neural Networks Models

We used two types of neural networks to fit the data. The first is a single layer four-neuron multilayer perceptron and the other is a two-layer cascaded neural network with a single neuron per layer. The networks were constructed and trained using the neural network toolbox of MATLAB [44]. The training was done using Bayesian Regularization.

### Linear Regression Models

### Performance Function

*x*

_{nc}be the ATP-level of AG02603 and

*x*

_{cc}be the ATP-level of A549 cells. Then, the performance function used is given by Perf(

*x*

_{nc},

*x*

_{cc})

*μ* is the column vector Open image in new window . The performance function range is adjusted to be within the interval [0,100] using the relation Perf = (Perf - 0.25)/0.14 * 100. This function can be easily generalized to accommodate more decision criteria.

## Notes

### Acknowledgements

We thank Shiva Portonovo and Drs. Christopher Denny, Desmond Smith, Helen Brown, Elliot Landaw, and Henry Huang for critical reading of the manuscript; all Sun lab members for helpful discussions. This study is supported by NIH (CA091791 and CA127042), the Stop Cancer Foundation, Burroughs Wellcome Fund, NSF grant (ECS-0501394) and NIH Roadmap for Medical Research (PN2 EY018228).

## Supplementary material

## References

- 1.Janes KA, Albeck JG, Gaudet S, Sorger PK, Lauffenburger DA, Yaffe MB: A systems model of signaling identifies a molecular basis set for cytokine-induced apoptosis. Science. 2005, 310 (5754): 1646-1653. 10.1126/science.1116598CrossRefPubMedGoogle Scholar
- 2.Janes KA, Yaffe MB: Data-driven modelling of signal-transduction networks. Nat Rev Mol Cell Biol. 2006, 7 (11): 820-828. 10.1038/nrm2041CrossRefPubMedGoogle Scholar
- 3.Irish JM, Kotecha N, Nolan GP: Mapping normal and cancer cell signalling networks: towards single-cell proteomics. Nat Rev Cancer. 2006, 6 (2): 146-155. 10.1038/nrc1804CrossRefPubMedGoogle Scholar
- 4.Natarajan M, Lin KM, Hsueh RC, Sternweis PC, Ranganathan R: A global analysis of cross-talk in a mammalian cellular signalling network. Nat Cell Biol. 2006, 8 (6): 571-580. 10.1038/ncb1418CrossRefPubMedGoogle Scholar
- 5.Berenbaum M: Direct search methods in the optimisation of cancer chemotherapy regimens. Br J Cancer. 1990, 61: 101-109. 10.1038/bjc.1990.22PubMedCentralCrossRefPubMedGoogle Scholar
- 6.Curatolo M, Sveticic G: Drug combinations in pain treatment: a review of the published evidence and a method for finding the optimal combination. Best Practice & Research Clinical Anaesthesiology. 2002, 16 (4): 507-519. 10.1053/bean.2002.0254CrossRefGoogle Scholar
- 7.Wong PK, Yu F, Shahangian A, Cheng G, Sun R, Ho CM: Closed-loop control of cellular functions using combinatory drugs guided by a stochastic search algorithm. Proc Natl Acad Sci USA. 2008, 105 (13): 5105-10. 10.1073/pnas.0800823105PubMedCentralCrossRefPubMedGoogle Scholar
- 8.Sun CP, Usui T, Yu F, Al-Shyoukh I, Shamma J, Sun R, Ho CM: Integrative systems control approach for reactivating Kaposi's sarcoma-associated herpesvirus (KSHV) with combinatory drugs. Integrative Biology. 2009, 1: 123-130. 10.1039/b815225jPubMedCentralCrossRefPubMedGoogle Scholar
- 9.Calzolari D, Bruschi S, Coquin L, Schofield J, Feala J, Reed J, McCulloch A, Paternostro G: Search Algorithms as a Framework for the Optimization of Drug Combinations. PLOS Computational Biology. 2008, 4 (12): e1000249- 10.1371/journal.pcbi.1000249PubMedCentralCrossRefPubMedGoogle Scholar
- 10.Iadevaia S, Lu Y, Morales FC, Mills GB, Ram PT: Identification of Optimal Drug Combinations Targeting Cellular Networks: Integrating Phospho-Proteomics and Computational Network Analysis. Cancer Research. 2010, 70 (17): 6704-6714. 10.1158/0008-5472.CAN-10-0460PubMedCentralCrossRefPubMedGoogle Scholar
- 11.Feala J, Cortes J, Duxbury P, Piermarocchi C, McCulloch A, Paternostro G: Systems approaches and algorithms for discovery of combinatorial therapies. WIREs Syst Biol Med. 2010, 2 (2): 181-193.CrossRefGoogle Scholar
- 12.Mellor D, Prieto E, Mathieson L, Moscato P: A Kernelisation Approach for Multiple
*d*-Hitting Set and Its Application in Optimal Multi-Drug Therapeutic Combinations. PLoS ONE. 2010, 5 (10): e13055- 10.1371/journal.pone.0013055PubMedCentralCrossRefPubMedGoogle Scholar - 13.Zinner RG, Barrett BL, Popova E, Damien P, Volgin AY, Gelovani JG, Lotan R, Tran HT, Pisano C, Mills GB, Mao L, Hong WK, Lippman SM, Miller JH: Algorithmic guided screening of drug combinations of arbitrary size for activity against cancer cells. Molecular Cancer Therapeutics. 2009, 8 (3): 521-532. 10.1158/1535-7163.MCT-08-0937CrossRefPubMedGoogle Scholar
- 14.Mukherjee JS, Rich ML, Socci AR, Joseph JK, Virú FA, Shin SS, Furin JJ, Becerra MC, Barry DJ, Kim JY, Bayona J, Farmer P, Fawzi MCS, Seung KJ: Programmes and principles in treatment of multidrug-resistant tuberculosis. Lancet. 2004, 363 (9407): 474-481. 10.1016/S0140-6736(04)15496-2CrossRefPubMedGoogle Scholar
- 15.Richman DD: HIV chemotherapy. Nature. 2001, 410 (6831): 995-1001. 10.1038/35073673CrossRefPubMedGoogle Scholar
- 16.Evan GI, Vousden KH: Proliferation, cell cycle and apoptosis in cancer. Nature. 2001, 411 (6835): 342-348. 10.1038/35077213CrossRefPubMedGoogle Scholar
- 17.Bellamy WT: Prediction of response to drug therapy of cancer. A review of in vitro assays. Drugs. 1992, 44 (5): 690-708. 10.2165/00003495-199244050-00002CrossRefPubMedGoogle Scholar
- 18.Jain AK, Mao J, Mohiuddin KM: Artificial Neural Networks: A Tutorial. IEEE Computer. 1996, 29 (3): 31-44.CrossRefGoogle Scholar
- 19.Gupta MM, Homma N, Jin L: Static and Dynamic Neural Networks: From Fundamentals to Advanced Theory. 2003, New York, NY, USA: John Wiley & Sons, IncCrossRefGoogle Scholar
- 20.Hartigan J: Clustering Algorithms. 1975, NY. WileyGoogle Scholar
- 21.Afifi A, Clark VA, May S: Computer-Aided Multivariate Analysis. 2003, Chapman & Hall/CRC, fourthGoogle Scholar
- 22.Hofmann M, Gatu C, Kontoghiorghes E: Efficient algorithms for computing the best subset regression models for large-scale... Computational Statistics and Data Analysis. 2007, http://linkinghub.elsevier.com/retrieve/pii/S0167947307001168Google Scholar
- 23.Agatonovic-Kustrin S, Beresford R: Basic concepts of artificial neural network (ANN) modeling and its application in pharmaceutical research. J Pharm Biomed Anal. 2000, 22 (5): 717-27. 10.1016/S0731-7085(99)00272-1CrossRefPubMedGoogle Scholar
- 24.Bourquin J, Schmidli H, van Hoogevest P, Leuenberger H: Application of artificial neural networks (ANN) in the development of solid dosage forms. Pharm Dev Technol. 1997, 2 (2): 111-21. 10.3109/10837459709022616CrossRefPubMedGoogle Scholar
- 25.Bourquin J, Schmidli H, van Hoogevest P, Leuenberger H: Basic concepts of artificial neural networks (ANN) modeling in the application to pharmaceutical development. Pharm Dev Technol. 1997, 2 (2): 95-109. 10.3109/10837459709022615CrossRefPubMedGoogle Scholar
- 26.Chen HY, Chen TC, Min DI, Fischer GW, Wu YM: Prediction of tacrolimus blood levels by using the neural network with genetic algorithm in liver transplantation patients. Ther Drug Monit. 1999, 21: 50-6. 10.1097/00007691-199902000-00008CrossRefPubMedGoogle Scholar
- 27.de Matas M, Shao Q, Richardson CH, Chrystyn H: Evaluation of in vitro in vivo correlations for dry powder inhaler delivery using artificial neural networks. Eur J Pharm Sci. 2008, 33: 80-90.CrossRefPubMedGoogle Scholar
- 28.Lin CC, Wang YC, Chen JY, Liou YJ, Bai YM, Lai IC, Chen TT, Chiu HW, Li YC: Artificial neural network prediction of clozapine response with combined pharmacogenetic and clinical data. Comput Methods Programs Biomed. 2008, 91 (2): 91-9. 10.1016/j.cmpb.2008.02.004CrossRefPubMedGoogle Scholar
- 29.Papadourakis GM, Gaga E, Vareltzis G, Bebis G: Use of artificial neural networks for clinical decision-making (Maldescensus testis). Neural Networks, 1992. IJCNN. International Joint Conference on. 1992, 3: 159-164.CrossRefGoogle Scholar
- 30.Payne SJ, Arrol HP, Hunt SV, Young SP: Automated classification and analysis of the calcium response of single T lymphocytes using a neural network approach. IEEE Trans Neural Netw. 2005, 16 (4): 949-58. 10.1109/TNN.2005.849820CrossRefPubMedGoogle Scholar
- 31.Penny W, Frost D: Neural networks in clinical medicine. Med Decis Making. 1996, 16 (4): 386-98. 10.1177/0272989X9601600409CrossRefPubMedGoogle Scholar
- 32.Sun Y, Peng Y, Chen Y, Shukla AJ: Application of artificial neural networks in the design of controlled release drug delivery systems. Adv Drug Deliv Rev. 2003, 55 (9): 1201-15. 10.1016/S0169-409X(03)00119-4CrossRefPubMedGoogle Scholar
- 33.Xie H, Gan Y, Ma S, Gan L, Chen Q: Optimization and evaluation of time-dependent tablets comprising an immediate and sustained release profile using artificial neural network. Drug Dev Ind Pharm. 2008, 34 (4): 363-72. 10.1080/03639040701657701CrossRefPubMedGoogle Scholar
- 34.Yamamura S, Kawada K, Takehira R, Nishizawa K, Katayama S, Hirano M, Momose Y: Prediction of aminoglycoside response against methicillin-resistant Staphylococcus aureus infection in burn patients by artificial neural network modeling. Biomed Pharmacother. 2008, 62: 53-8. 10.1016/j.biopha.2007.11.004CrossRefPubMedGoogle Scholar
- 35.Miller-Jensen K, Janes KA, Brugge JS, Lauffenburger DA: Common effector processing mediates cell-specific responses to stimuli. Nature. 2007, 448 (7153): 604-608. 10.1038/nature06001CrossRefPubMedGoogle Scholar
- 36.Irish JM, Hovland R, Krutzik PO, Perez OD, Bruserud Φystein, Gjertsen BT, Nolan" GP: Single cell profiling of potentiated phospho-protein networks in cancer cells. Cell. 2004, 118 (2): 217-228. 10.1016/j.cell.2004.06.028CrossRefPubMedGoogle Scholar
- 37.Andrews R, Diederich J, Tickle AB: Survey and critique of techniques for extracting rules from trained neural networks. Knowledge-based Systems. 1996, 8: 373-389.CrossRefGoogle Scholar
- 38.Jacobsson H: Rule extraction from recurrent neural networks: A taxonomy and review. Neural Computation. 2005, 17: 1223-1263. 10.1162/0899766053630350.CrossRefGoogle Scholar
- 39.Kahramanli H, Allahverdi N: Rule extraction from trained adaptive neural networks using artificial immune systems. Expert Systems with Applications. 2009, 36: 1513-1522. 10.1016/j.eswa.2007.11.024.CrossRefGoogle Scholar
- 40.Sjoblom T, Jones S, Wood LD, Parsons DW, Lin J, Barber TD, Mandelker D, Leary RJ, Ptak J, Silliman N, Szabo S, Buckhaults P, Farrell C, Meeh P, Markowitz SD, Willis J, Dawson D, Willson JKV, Gazdar AF, Hartigan J, Wu L, Liu C, Parmigiani G, Park BH, Bachman KE, Papadopoulos N, Vogelstein B, Kinzler KW, Velculescu VE: The Consensus Coding Sequences of Human Breast and Colorectal Cancers. Science. 2006, 314 (5797): 268-274. 10.1126/science.1133427CrossRefPubMedGoogle Scholar
- 41.Vogelstein B, Kinzler KW: Cancer genes and the pathways they control. Nat Med. 2004, 10 (8): 789-799. 10.1038/nm1087CrossRefPubMedGoogle Scholar
- 42.Sawyers CL: Cancer: Mixing cocktails. Nature. 2007, 449 (7165): 993-996. 10.1038/449993aCrossRefPubMedGoogle Scholar
- 43.Ramaswamy S: Rational design of cancer-drug combinations. N Engl J Med. 2007, 357 (3): 299-300. 10.1056/NEJMcibr072593CrossRefPubMedGoogle Scholar
- 44.Demuth H, Beale M, Hagan M: Neural Network Toolbox 6 User's Guide. The Mathworks inc. 2010Google Scholar

## Copyright information

This article is published under license to BioMed Central Ltd. This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/2.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.