Genes selection using deep learning and explainable artificial intelligence for chronic lymphocytic leukemia predicting the need and time to therapy

Frontiers in Oncology

Oncology

Fortunato Morabito¹  Graziella D’Arrigo²  Giovanni Tripepi²  Yissel Rodriguez-Aldana³  Gianluigi Greco³  Carlo Adornetto³  Claudia Vener⁴  Massimo Gentile⁵  Teresa Rossi⁶  Federica Torricelli⁶  Monica Colombo⁷  Giovanna Cutrona⁷  Paola Monti⁸  Antonino Neri⁹  Francesco Reggiani^1,10  Adriana Amaro^1,10  Manlio Ferrarini^1,11 

[1] Biotechnology Research Unit, ‘A. Sforza’ Foundation, Cosenza, Italy;Consiglio Nazionale delle Ricerche, Istituto di Fisiologia Clinica del Consiglio Nazionale delle Ricerche (CNR), Reggio Calabria, Italy;Department of Mathematics and Computer Science, University of Calabria, Cosenza, Italy;Department of Oncology and Hemato-Oncology, University of Milan, Milan, Italy;Hematology Unit, Department of Onco-Hematology, Azienda Ospedaliera (A.O.) of Cosenza, Cosenza, Italy;Department of Pharmacy and Health and Nutritional Sciences, University of Calabria, Cosenza, Italy;Laboratory of Translational Research, Azienda Unità Sanitaria Locale - Istituto di Ricovero e Cura a Crabtree Scientifico (USL-IRCCS) of Reggio Emilia, Reggio Emilia, Italy;Molecular Pathology Unit, Istituto di Ricovero e Cura a Carattere Scientifico (IRCCS) Ospedale Policlinico San Martino, Genoa, Italy;Mutagenesis and Cancer Prevention Unit, Istituto di Ricovero e Cura a Carattere Scientifico (IRCCS) Ospedale Policlinico San Martino, Genoa, Italy;Scientific Directorate, Azienda Unità Sanitaria Locale - Istituto di Ricovero e Cura a Carattere Scientifico (USL-IRCCS) of Reggio Emilia, Reggio Emilia, Italy;Tumor Epigenetics Unit, Istituto di Ricovero e Cura a Carattere Scientifico (IRCCS) Ospedale Policlinico San Martino, Genoa, Italy;Unità Operariva (UO) Molecular Pathology, Ospedale Policlinico San Martino Istituto di Ricovero e Cura a Carattere Scientifico (IRCCS), Genoa, Italy;

关键词: chronic lymphocytic leukemia;    gene expression profile;    deep learning;    explainable artificial intelligence;    feature selection;   

DOI  :  10.3389/fonc.2023.1198992

 received in 2023-04-02, accepted in 2023-07-31,  发布年份 2023

来源: Frontiers

【 摘 要 】

Analyzing gene expression profiles (GEP) through artificial intelligence provides meaningful insight into cancer disease. This study introduces DeepSHAP Autoencoder Filter for Genes Selection (DSAF-GS), a novel deep learning and explainable artificial intelligence-based approach for feature selection in genomics-scale data. DSAF-GS exploits the autoencoder’s reconstruction capabilities without changing the original feature space, enhancing the interpretation of the results. Explainable artificial intelligence is then used to select the informative genes for chronic lymphocytic leukemia prognosis of 217 cases from a GEP database comprising roughly 20,000 genes. The model for prognosis prediction achieved an accuracy of 86.4%, a sensitivity of 85.0%, and a specificity of 87.5%. According to the proposed approach, predictions were strongly influenced by CEACAM19 and PIGP, moderately influenced by MKL1 and GNE, and poorly influenced by other genes. The 10 most influential genes were selected for further analysis. Among them, FADD, FIBP, FIBP, GNE, IGF1R, MKL1, PIGP, and SLC39A6 were identified in the Reactome pathway database as involved in signal transduction, transcription, protein metabolism, immune system, cell cycle, and apoptosis. Moreover, according to the network model of the 3D protein-protein interaction (PPI) explored using the NetworkAnalyst tool, FADD, FIBP, IGF1R, QTRT1, GNE, SLC39A6, and MKL1 appear coupled into a complex network. Finally, all 10 selected genes showed a predictive power on time to first treatment (TTFT) in univariate analyses on a basic prognostic model including IGHV mutational status, del(11q) and del(17p), NOTCH1 mutations, β2-microglobulin, Rai stage, and B-lymphocytosis known to predict TTFT in CLL. However, only IGF1R [hazard ratio (HR) 1.41, 95% CI 1.08-1.84, P=0.013), COL28A1 (HR 0.32, 95% CI 0.10-0.97, P=0.045), and QTRT1 (HR 7.73, 95% CI 2.48-24.04, P<0.001) genes were significantly associated with TTFT in multivariable analyses when combined with the prognostic factors of the basic model, ultimately increasing the Harrell’s c-index and the explained variation to 78.6% (versus 76.5% of the basic prognostic model) and 52.6% (versus 42.2% of the basic prognostic model), respectively. Also, the goodness of model fit was enhanced (χ2 = 20.1, P=0.002), indicating its improved performance above the basic prognostic model. In conclusion, DSAF-GS identified a group of significant genes for CLL prognosis, suggesting future directions for bio-molecular research.

【 授权许可】

Unknown   
Copyright © 2023 Morabito, Adornetto, Monti, Amaro, Reggiani, Colombo, Rodriguez-Aldana, Tripepi, D’Arrigo, Vener, Torricelli, Rossi, Neri, Ferrarini, Cutrona, Gentile and Greco