Discriminate the response of Acute Myeloid Leukemia patients to treatment by using proteomics data and Answer Set Programming

Abstract

BackgroundDuring the last years, several approaches were applied on biomedical data to detect disease specific proteins and genes in order to better target drugs. It was shown that statistical and machine learning based methods use mainly clinical data and improve later their results by adding omics data. This work proposes a new method to discriminate the response of Acute Myeloid Leukemia (AML) patients to treatment. The proposed approach uses proteomics data and prior regulatory knowledge in the form of networks to predict cancer treatment outcomes by finding out the different Boolean networks specific to each type of response to drugs. To show its effectiveness we evaluate our method on a dataset from the DREAM 9 challenge.ResultsThe results are encouraging and demonstrate the benefit of our approach to distinguish patient groups with different response to treatment. In particular each treatment response group is characterized by a predictive model in the form of a signaling Boolean network. This model describes regulatory mechanisms which are specific to each response group. The proteins in this model were selected from the complete dataset by imposing optimization constraints that maximize the difference in the logical response of the Boolean network associated to each group of patients given the omic dataset. This mechanistic and predictive model also allow us to classify new patients data into the two different patient response groups.ConclusionsWe propose a new method to detect the most relevant proteins for understanding different patient responses upon treatments in order to better target drugs using a Prior Knowledge Network and proteomics data. The results are interesting and show the effectiveness of our method.Electronic supplementary materialThe online version of this article (10.1186/s12859-018-2034-4) contains supplementary material, which is available to authorized users.

Data mining for mutation-specific targets in acute myeloid leukemia

“…Chebouba et al used Boolean networks to predict treatment outcomes -responsive or resistant -using proteomics data from 191 AML patients. 46 Although the number of proteins and the number of patients in the final learning phase was modest (33 proteins and 26 patients), the network could predict clinical remission from proteomics data with an accuracy of 64.7%. The strength of this approach is that signaling pathways can be directly inferred from the network, resulting in new protein pathway associations.…”

Boolean Network Models of Human Preimplantation Development

“…In this note, we provide a step-by-step explanation of the ASP program devised to identify pseudoperturbations. Our program, based on the method proposed in Chebouba et al (2018), differs primarily in the rule governing the generation of distinct Boolean pseudo-perturbation vectors. Our logic program is tailored specifically to handle scRNAseq data, which often exhibits redundancy due to cells within the same developmental stage sharing identical gene expressions.…”

Inferring Boolean Networks from Single-Cell Human Embryo Datasets

“…We tested our algorithm on 4 toy datasets (see specifications in Table 1, datasets A − D). We also applied our program on 2 entire datasets: phosphoproteomics data, measuring averaged cell population protein expression (dataset P ) from [2] and scRNAseq data (dataset SC) from [9]. Our results are shown in Table 1.…”