Herpin, L. | bioRxiv Science

bioRxiv2022

Deep Learning Allows Assessment of Risk of Metastatic Relapse from Invasive Breast Cancer Histological Slides

BackgroundCorrectly classifying early estrogen receptor-positive and HER2-negative (ER+/HER2) breast cancer (EBC) cases allows to propose an adapted adjuvant systemic treatment strategy. We developed a new AI-based tool to assess the risk of distant relapse at 5 years for ER+/HER2-EBC patients from pathological slides. Patients and MethodsThe discovery dataset (GrandTMA) included 1429 ER+/HER2-EBC patients, with long-term follow-up and an available hematoxylin-eosin and saffron (HES) whole slide image (WSI). A Deep Learning (DL) network was trained to predict metastasis free survival (MFS) at five years, based on the HES WSI only (termed RlapsRisk). A combined score was then built using RlapsRisk and well established prognostic factors. A threshold corresponding to a probability of MFS event of 5% at 5 years was applied to dichotomize patients into low or high-risk groups. The external validation, as well as assessment of the additional prognosis value of the DL model beyond standard clinico-pathologic factors were carried out on an independent, prospective cohort (CANTO, NCT01993498) including 889 HES WSI of ER+/HER2-EBC patients. ResultsRlapsRisk was an independent prognostic factor of MFS in multivariable analysis adjusted for established clinico-pathological factors (p<0.005 in GrandTMA and CANTO). Combining RlapsRisk score and the clinico-pathological factors improved the prognostic discrimination as compared to the clinico-pathological factors alone (increment of c-index in the validation set 0.80 versus 0.76, +0.04, p-value < 0.005). After dichotomization, the Combined Model showed a higher cumulative sensitivity on the entire population (0.76 vs 0.61) for an equal dynamic specificity (0.76) in comparison with the clinical score alone. ConclusionsOur deep learning model developed on digitized HES slides provided additional prognostic information as compared to current clinico-pathological factors and has the potential of valuably informing the decision making process in the adjuvant setting when combined with current clinico-pathological factors.

pathology↗

bioRxiv2022

Generation and characterization of conditional yeast mutants affecting each of the two essential functions of the scaffolding proteins Boi1/2 and Bem1

Boi1 and Boi2 are closely related yeast scaffolding proteins, either of which can perform an essential function. Previous studies have suggested a role in cell polarity, interacting with lipids, components of the late secretory pathway, and actin nucleators. We report detailed studies of their localization, dynamics, and the generation and characterization of conditional mutants. Boi1/2 are present on the plasma membrane in dynamic patches, then at the bud neck during cytokinesis. These distributions are unaffected by perturbation of the actin cytoskeleton or the secretory pathway. We identify two critical aromatic residues, present in both Boi1 and Boi2, in the essential C-terminal PH domain, that cause temperature sensitive growth resulting in defects in polarized growth leading to cell lysis. The scaffolding protein, Bem1, colocalizes with Boi1 in patches at the growing bud, and at the bud neck, the latter requiring the N-terminal SH3 domain of Boi1p. Loss of function of Boi1-SH3 domain renders Bem1 essential which can be fully replaced by a fusion of the SH3b and PB1 domains of Bem1. Thus, the two essential functions of the Boi1/2/Bem1 proteins can be satisfied by Bem1-SH3b-PB1 and Boi1-PH. Generation and characterization of conditional mutations in the essential function of Bem1 reveal a slow onset of defects in polarized growth, which is difficult to define a specific initial defect. This study provides more details into the functions of Boi1/2 and their relationship with Bem1, and presents the generation of conditional mutants that will be useful for future genetic analysis.

cell biology↗