ADMET evaluation in drug discovery: 21. Application and industrial validation of machine learning algorithms for Caco-2 permeability prediction.

The Caco-2 cell model has been widely used to assess the intestinal permeability of drug candidates in vitro, owing to its morphological and functional similarity to human enterocytes. While Caco-2 cell assay is considered safe and cost-effective, it is also characterized by being time-consuming. Therefore, computational models that achieve high accuracies in predicting Caco-2 permeability are crucial for enhancing the efficiency of oral drug development.

Staging of prostate Cancer with ultra-fast PSMA-PET scans enhanced by AI.

Purpose: PSMA-PET is a reference standard examination for patients with prostate cancer, but even using recently introduced digital PET detectors image acquisition with standard field-of-view scanners is still in the range of 20 min. This may cause limited access to examination slots because of the growing demand for PSMA-PET. Ultra-fast PSMA-PET may enhance throughput but comes at the cost of poor image quality.

JOSD2 promotes breast cancer metastasis by deubiquitinating and stabilizing SMAD4.

Breast cancer is one of the most common malignant tumors among women worldwide, and its high degree of metastasis significantly impacts treatment effectiveness leading to poor prognosis. The potential molecular mechanisms underlying breast cancer metastasis remain to be further elucidated. In this study, via database analysis, we revealed that the deubiquitinase josephin domain containing 2 (JOSD2) was abnormally amplified in patients with metastatic breast cancer, and was significantly negatively correlated with patient prognosis.

A Transformer-Based Pipeline for German Clinical Document De-Identification.

Objective:  Commercially available large language models such as Chat Generative Pre-Trained Transformer (ChatGPT) cannot be applied to real patient data for data protection reasons. At the same time, de-identification of clinical unstructured data is a tedious and time-consuming task when done manually. Since transformer models can efficiently process and analyze large amounts of text data, our study aims to explore the impact of a large training dataset on the performance of this task.

Multi-channel learning for integrating structural hierarchies into context-dependent molecular representation.

Reliable molecular property prediction is essential for various scientific endeavors and industrial applications, such as drug discovery. However, the data scarcity, combined with the highly non-linear causal relationships between physicochemical and biological properties and conventional molecular featurization schemes, complicates the development of robust molecular machine learning models. Self-supervised learning (SSL) has emerged as a popular solution, utilizing large-scale, unannotated molecular data to learn a foundational representation of chemical space that might be advantageous for downstream tasks.

PPI-CoAttNet: A Web Server for Protein-Protein Interaction Tasks Using a Coattention Model.

Predicting protein-protein interactions (PPIs) is crucial for advancing drug discovery. Despite the proposal of numerous advanced computational methods, these approaches often suffer from poor usability for biologists and lack generalization. In this study, we designed a deep learning model based on a coattention mechanism that was capable of both PPI and site prediction and used this model as the foundation for PPI-CoAttNet, a user-friendly, multifunctional web server for PPI prediction.

Development of a two-component recombinant vaccine for COVID-19.

Introduction: Though COVID-19 as a public health emergency of international concern (PHEIC) was declared to be ended by the WHO, it continues to pose a significant threat to human society. Vaccination remains one of the most effective methods for preventing COVID-19. While most of the antigenic regions are found in the receptor binding domain (RBD), the N-terminal domain (NTD) of the S protein is another crucial region for inducing neutralizing antibodies (nAbs) against COVID-19.

Analyzing the TotalSegmentator for facial feature removal in head CT scans.

Background: Facial recognition technology in medical imaging, particularly with head scans, poses privacy risks due to identifiable facial features. This study evaluates the use of facial recognition software in identifying facial features from head CT scans and explores a defacing pipeline using TotalSegmentator to reduce re-identification risks while preserving data integrity for research.

Methods: 1404 high-quality renderings from the UCLH EIT Stroke dataset, both with and without defacing were analysed.

Auto-RapTAC: A Versatile and Sustainable Platform for the Automated Rapid Synthesis and Evaluation of PROTAC.

The tedious synthesis and limited throughput biological evaluation remain a great challenge for discovering new proteolysis targeting chimera (PROTAC). To rapidly identify potential PROTAC lead compounds, we report a platform named Auto-RapTAC. Based on the modular characteristic of the PROTAC molecule, a streamlined workflow that integrates lab automation with "click chemistry" joint building-block libraries was constructed.

- a large-scale dataset of 3D medical shapes for computer vision.

Objectives: The shape is commonly used to describe the objects. State-of-the-art algorithms in medical imaging are predominantly diverging from computer vision, where voxel grids, meshes, point clouds, and implicit surface models are used. This is seen from the growing popularity of ShapeNet (51,300 models) and Princeton ModelNet (127,915 models).

Mechanisms of low MHC I expression and strategies for targeting MHC I with small molecules in cancer immunotherapy.

Major histocompatibility complex (MHC) class I load antigens and present them on the cell surface, which transduces the tumor-associated antigens to CD8 T cells, activating the acquired immune system. However, many tumors downregulate MHC I expression to evade immune surveillance. The low expression of MHC I not only reduce recognition by- and cytotoxicity of CD8 T cells, but also seriously weakens the anti-tumor effect of immunotherapy by restoring CD8 T cells, such as immune checkpoint inhibitors (ICIs).

Artificial intelligence-enabled discovery of a RIPK3 inhibitor with neuroprotective effects in an acute glaucoma mouse model.

Background: Retinal ganglion cell (RGC) death caused by acute ocular hypertension is an important characteristic of acute glaucoma. Receptor-interacting protein kinase 3 (RIPK3) that mediates necroptosis is a potential therapeutic target for RGC death. However, the current understanding of the targeting agents and mechanisms of RIPK3 in the treatment of glaucoma remains limited.

Multi-Modal CLIP-Informed Protein Editing.

Proteins govern most biological functions essential for life, and achieving controllable protein editing has made great advances in probing natural systems, creating therapeutic conjugates, and generating novel protein constructs. Recently, machine learning-assisted protein editing (MLPE) has shown promise in accelerating optimization cycles and reducing experimental workloads. However, current methods struggle with the vast combinatorial space of potential protein edits and cannot explicitly conduct protein editing using biotext instructions, limiting their interactivity with human feedback.

Durian: A Comprehensive Benchmark for Structure-Based 3D Molecular Generation.

Three-dimensional (3D) molecular generation models employ deep neural networks to simultaneously generate both topological representation and molecular conformations. Due to their advantages in utilizing the structural and interaction information on targets, as well as their reduced reliance on existing bioactivity data, these models have attracted widespread attention. However, limited training and testing data sets and the unexpected biases inherent in single evaluation metrics pose a significant challenge in comparing these models in practical settings.

Activation of HSPA5 contributes to pazopanib-induced hepatotoxicity through l-ornithine metabolism pathway and endoplasmic reticulum stress.

Objectives: The clinical application of Pazopanib (Paz) is often accompanied by hepatotoxicity. However, the mechanisms of hepatic toxicity induced by pazopanib are not entirely clarified.

Methods: Male C57BL/6J mice were treated with pazopanib every day for 2, 4, or 8 weeks.

Descriptor-Free Collective Variables from Geometric Graph Neural Networks.

Enhanced sampling simulations make the computational study of rare events feasible. A large family of such methods crucially depends on the definition of some collective variables (CVs) that could provide a low-dimensional representation of the relevant physics of the process. Recently, many methods have been proposed to semiautomatize the CV design by using machine learning tools to learn the variables directly from the simulation data.

Fully automatic quantification of pulmonary fat attenuation volume by CT: an exploratory pilot study.

Background: Non-malignant chronic diseases remain a major public health concern. Given the alterations in lipid metabolism and deposition in the lung and its association with fibrotic interstitial lung disease (fILD) and chronic obstructive pulmonary disease (COPD), this study aimed to detect those alterations using computed tomography (CT)-based analysis of pulmonary fat attenuation volume (CTpfav).

Methods: This observational retrospective single-center study involved 716 chest CT scans from three subcohorts: control (n = 279), COPD (n = 283), and fILD (n = 154).

Ivacaftor, a CFTR potentiator, synergizes with osimertinib against acquired resistance to osimertinib in NSCLC by regulating CFTR-PTEN-AKT axis.

Osimertinib, a third-generation epidermal growth factor receptor tyrosine kinase inhibitor (EGFR-TKI), has demonstrated significant clinical benefits in the treatment of EGFR-mutated non-small cell lung cancer (NSCLC). However, inevitable acquired resistance to osimertinib limits its clinical utility, and there is a lack of effective countermeasures. Here, we established osimertinib-resistant cell lines and performed drug library screening.

Impact of immunological aging on T cell-mediated therapies in older adults with multiple myeloma and lymphoma.

The treatment landscape for lymphoma and multiple myeloma, which disproportionally affect older adults, has been transformed by the advent of T cell-mediated immunotherapies, including immune checkpoint inhibition, T cell-engaging bispecific antibodies, and chimeric antigen receptor (CAR) T cell therapy, during the last decade. These treatment modalities re-enable the patient's own immune system to combat malignant cells and offer the potential for sustained remissions and cure for various diseases.Age profoundly affects the physiological function of the immune system.

Identification and validation of WDR5 WIN-site ligands via DNA-encoded chemical library screening.

WD repeat-containing protein 5 (WDR5) is a scaffolding protein involved in critical protein-protein interactions and a promising target for therapeutic development. Novel small-molecule ligands targeting WDR5 were identified using the DELopen platform, a free-access DNA-encoded chemical library (DEL) for academic research. Through off-DNA structure-activity relationship studies and photoaffinity labeling, two promising initial leads, DBL-6-13 and DBL-6-33, were identified as new binders of WDR5.

The crucial involvement of gamma-Mangostin and CYP1B1 in the mechanism underlying the toxicity caused by cigarette smoke extract: In silico and in vitro insights.

Cigarette smoke extracts (CSE) contain harmful substances that significantly contribute to respiratory conditions. Previous studies have primarily focused on the presence of carcinogens in CSE. However, it should be noted that other compounds may also synergistically contribute to a greater impact.