Sara Szincsak

Machine learning (ML) algorithms hold the potential to outperform the selection of patients for immunotherapy (ICIs) compared to previous biomarker studies. We analyzed the predictive performance of ML models and compared them to traditional clinical biomarkers (TCBs) in the field of gastrointestinal (GI) cancers. The study has been registered in PROSPERO (number: CRD42023465917). A systematic search of PubMed was conducted to identify studies applying different ML algorithms to GI cancer patients treated with ICIs using tumor RNA gene expression profiles. The outcomes included were response to immunotherapy (ITR) or survival. Additionally, we compared the ML methodology details and predictive power inherent in the published gene sets using 5-fold cross-validation and logistic regression (LR), on an available well-defined ICI-treated metastatic gastric cancer (GC) cohort (n = 45). A set of standard clinical ICI biomarkers (MLH, MSH, and CD8 genes, plus PMS2 and PD-L1)) and de-novo calculated principal components (PCs) of the original datasets were also included as additional points of comparison. Nine articles were identified as eligible to meet the inclusion criteria. Three were pan-cancer studies, five assessed GC, and one studied colorectal cancer (CRC). Classification and regression models were used to predict ICI efficacy. Next, using LR, we validated the predictive power of applied ML algorithms on RNA signatures, using their reported receiver operating characteristics (ROC) analysis area under the curve (AUC) values on a well-defined ICI-treated gastric cancer (GC) dataset (n = 45). In two cases our method has outperformed the published results (reported/LR comparison: 0.74/0.831, 0.67/0.735). Besides the published studies, we have included two benchmarks: a set of TCBs and using principal components based on the whole dataset (PCA, 99% explained variance, 40 components). Interestingly, a study using a selected gene set (immuno-oncology panel) with AUC = 0.83 was the only one that outperformed the TCB (AUC = 0.8) and the PCA (AUC =0.81) results. Cross-validation of the predictive performance of these genes on the same GC dataset and an investigation of their prognostic role on a collated multi-cohort GC dataset of n = 375 resected, or chemotherapy-treated patients revealed that genes mannose-6-phosphate receptor (M6PR), Indoleamine 2,3-Dioxygenase 1 (IDO1), Neuropilin-1 (NRP1), and MAGEA3 performed similarly, or better than established biomarkers like PD-L1 and MSI. We found an immuno-oncology panel with an AUC = 0.83 that outperformed the clinical benchmark or the PC results. We recommend further investigation and experimental validation in the case of M6PR, IDO1, NRP1, and MAGEA3 expressions based on their strong predictive power in GC ITR. Well-designed studies with larger sample sizes and nonlinear ML models might help improve biomarker selections.

The compound eye of the fruit fly Drosophila melanogaster is one of the most intensively studied and best understood model organs in the field of developmental genetics. Herein we demonstrate that autophagy, an evolutionarily conserved selfdegradation process of eukaryotic cells, is essential for eye development in this organism. Autophagic structures accumulate in a specific pattern in the developing eye disc, predominantly in the morphogenetic furrow (MF) and differentiation zone. Silencing of several autophagy genes (Atg) in the eye primordium severely affects the morphology of the adult eye through triggering ectopic cell death. In Atg mutant genetic backgrounds however genetic compensatory mechanisms largely rescue autophagic activity in, and thereby normal morphogenesis of, this organ. We also show that in the eye disc the expression of a key autophagy gene, Atg8a, is controlled in a complex manner by the anterior Hox paralog Lab (Labial), a master regulator of early development. Atg8a transcription is repressed in front of, while activated along, the MF by Lab. The amount of autophagic structures then remains elevated behind the moving MF. These results indicate that eye development in Drosophila depends on the cell death-suppressing and differentiating effects of the autophagic process. This novel, developmentally regulated function of autophagy in the morphogenesis of the compound eye may shed light on a more fundamental role for cellular self-digestion in differentiation and organ formation than previously thought. Abbreviations: αTub84B, α-Tubulin at 84B; Act5C, Actin5C; AO, acridine orange; Atg, autophagy-related; Ato, Atonal; CASP3, caspase 3; Dcr-2; Dicer-2; Dfd, Deformed; DZ, differentiation zone; eGFP, enhanced green fluorescent protein; EM, electron microscopy; exd, extradenticle; ey, eyeless; FLP, flippase recombinase; FRT, FLP recognition target; Gal4, gene encoding the yeast transcription activator protein GAL4; GFP, green fluorescent protein; GMR, Glass multimer reporter; Hox, homeobox; hth, homothorax; lab, labial; L3F, L3 feeding larval stage; L3W, L3 wandering larval stage; lf, loss-of-function; MAP1LC3, microtubule-associated protein 1 light chain 3; MF, morphogenetic furrow; PE, phosphatidylethanolamine; PBS, phosphate-buffered saline; PI3K/PtdIns3K, class III phosphatidylinositol 3-kinase; PZ, proliferation zone; Ref(2)P, refractory to sigma P, RFP, red fluorescent protein; RNAi, RNA interference; RpL32, Ribosomal protein L32; RT-PCR, reverse transcription-coupled polymerase chain reaction; S.D., standard deviation; SQSTM1, Sequestosome-1, Tor, Target of rapamycin; TUNEL, terminal deoxynucleotidyl transferase mediated dUTP nick end labeling assay; UAS, upstream activation sequence; qPCR, quantitative real-time polymerase chain reaction; w, white