Comparing gene regulatory inferring algorithms with different perspective

Abstract

More than hundred algorithms were developed to infer Gene Regulatory Networks (GRN) describing relations between genes. GRN construction has been a field of interest to researchers since the beginning of the current century. Many competitions were held to encourage the development of GRN inference algorithms, such competitions offer synthetic data to enable the validation of proposed algorithms. A GRN is constructed from an adjacency matrix which contains relations between genes. The developers of many of the GRN inference algorithms set a threshold on the adjacency matrix to construct GRN based on high gene-gene relation weights. This threshold strategy was followed in previous studies to increase the accuracy of any algorithm but yet based on no well-known rule. A different perspective here is to compare different GRN inference algorithms without setting any threshold. Comparison in this work is among different GRN inference algorithms by implementing all algorithms with no threshold on values of adjacency matrices: Differential Equation methods (TSNI), Granger Causality, GP4GRN, GENIE3, NIMEFI (SVR), and PLSNET. Another comparison between different distance metric equations to create adjacency matrix is also studied in an attempt to construct GRN. GP4GRN and GENIE3 participate in producing best results for dream4 InSilico_Size10 while GENIE3 produce best results for all networks of dream4 InSilico_Size100. 654 I2M. Volume 17-n° 4/2018 Mé thodes d'é quation diffé rentielle (TSNI), causalité de Granger, GP4GRN, GENIE3, NIMEFI (SVR) et PLSNET. Une autre comparaison entre diffé rentes é quations mé triques de distance pour cré er une matrice d'adjacence est é galement é tudié e dans le but de construire un GRN. GP4GRN et GENIE3 contribuent à produire les meilleurs ré sultats pour dream4 InSilico_Size10, tandis que GENIE3 fournit les meilleurs ré sultats pour tous les ré seaux de dream4 InSilico_Size100.

ANOVAG3: A Hybrid Algorithm for Inferring Gene Regulatory Network Using Time Series Gene Expression Data

“…ADANET algorithm converts problem of GRN inference to set of independent tasks and solves them with AdaBoost ensemble classifier and uses structure of models to discover relation between transcription factors and regulatory genes [23]. Some of previous algorithm collected and implemented in comparison study with DREAM4 data (10 genes and 100 genes) [24].…”