Robust and accurate quantification of biomarkers of immune cells in lung cancer micro-environment using deep convolutional neural networks.

Recent years have seen a growing awareness of the role the immune system plays in successful cancer treatment, especially in novel therapies like immunotherapy. The characterization of the immunological composition of tumors and their micro-environment is thus becoming a necessity. In this paper we introduce a deep learning-based immune cell detection and quantification method, which is based on supervised learning, i.e., the input data for training comprises labeled images. Our approach objectively deals with staining variation and staining artifacts in immunohistochemically stained lung cancer tissue and is as precise as humans. This is evidenced by the low cell count difference to humans of 0.033 cells on average. This method, which is based on convolutional neural networks, has the potential to provide a new quantitative basis for research on immunotherapy.

Structures of plasmepsin II from Plasmodium falciparum in complex with two hydroxyethylamine-based inhibitors.

Plasmepsin II (PMII) is one of the ten plasmepsins (PMs) identified in the genome of Plasmodium falciparum, the causative agent of the most severe and deadliest form of malaria. Owing to the emergence of P. falciparum strains that are resistant to current antimalarial agents such as chloroquine and sulfadoxine/pyrimethamine, there is a constant pressure to find new and lasting chemotherapeutic drug therapies. Previously, the crystal structure of PMII in complex with NU655, a potent antimalarial hydroxyethylamine-based inhibitor, and the design of new compounds based on it have been reported. In the current study, two of these newly designed hydroxyethylamine-based inhibitors, PG418 and PG394, were cocrystallized with PMII and their structures were solved, analyzed and compared with that of the PMII-NU655 complex. Structural analysis of the PMII-PG418 complex revealed that the flap loop can adopt a fully closed conformation, stabilized by interactions with the inhibitor, and a fully open conformation, causing an overall expansion in the active-site cavity, which in turn causes unstable binding of the inhibitor. PG418 also stabilizes the flexible loop Gln275-Met286 of another monomer in the asymmetric unit of PMII, which is disordered in the PMII-NU655 complex structure. The crystal structure of PMII in complex with the inhibitor PG418 demonstrates the conformational flexibility of the active-site cavity of the plasmepsins. The interactions of the different moieties in the P1' position of PG418 and PG394 with Thr217 have to be taken into account in the design of new potent plasmepsin inhibitors.