Convolutional Neural Network Can Recognize Drug Resistance of Single Cancer Cells.

It is known that single or isolated tumor cells enter cancer patients' circulatory systems. These circulating tumor cells (CTCs) are thought to be an effective tool for diagnosing cancer malignancy. However, handling CTC samples and evaluating CTC sequence analysis results are challenging. Recently, the convolutional neural network (CNN) model, a type of deep learning model, has been increasingly adopted for medical image analyses. However, it is controversial whether cell characteristics can be identified at the single-cell level by using machine learning methods. This study intends to verify whether an AI system could classify the sensitivity of anticancer drugs, based on cell morphology during culture. We constructed a CNN based on the VGG16 model that could predict the efficiency of antitumor drugs at the single-cell level. The machine learning revealed that our model could identify the effects of antitumor drugs with ~0.80 accuracies. Our results show that, in the future, realizing precision medicine to identify effective antitumor drugs for individual patients may be possible by extracting CTCs from blood and performing classification by using an AI system.

A mesoporous gold biosensor to investigate immune checkpoint protein heterogeneity in single lung cancer cells.

Immune checkpoint proteins (ICPs) play a major role in a patient's immune response against cancer. Tumour cells usually express those proteins to communicate with immune cells as a process of escaping the anti-cancer immune response. Detecting the major functional immune checkpoint proteins present on cancer cells (such as circulating tumor cells or CTCs) and examining the heterogeneity in their expression at the single-cell level could play a crucial role in both cancer diagnosis and the monitoring of therapy. In this study, we develop a mesoporous gold biosensor to precisely assess ICP heterogeneity in individual cancer cells within a lung cancer model. The platform utilizes a nanostructured mesoporous gold surface to capture CTCs and a Surface Enhanced Raman Scattering (SERS) readout to identify and monitor the expression of key ICP proteins (PD-L1, B7H4, CD276, CD80) in lung cancer cells. The homogeneous and abundant pores in mesoporous 3D gold nanostructures enable increased antibody loading on-chip and an enhanced SERS signal, which are key to our single cell capture, and accurate analysis of ICPs in cancer cells with high sensitivity. Our lung cancer cell line model data showed that our method can detect single cells and analyse the expression of four lung cancer associated ICPs on individual cell surfaces during treatment. To show the potential of our mesoporous gold biosensor in analysing clinical samples, we tested 9 longitudinal Peripheral Blood Mononuclear Cells (PBMC) samples from lung cancer patient before and after therapy. Our mesoporous biosensor successfully captured single CTCs and found that the expression of ICPs in CTCs is highly heterogeneous in both pre-treatment and treated PBMC samples isolated from lung cancer patient blood. We suggest that our findings will help clinicians in selecting the most appropriate therapy for patients.

An Editorial View on the Special Issue "Colorectal Cancers: From Present Problems to Future Solutions".

Colorectal cancer (CRC) represents one of the most frequent human cancer entities and is still amongst the "top killers" in human cancer, although fundamental progress has been made in recent years in CRC prevention, early diagnosis, basic and translational research, and (targeted) therapy [...].