Interpretable Deep-Learning p Prediction for Small Molecule Drugs via Atomic Sensitivity Analysis.

Machine learning (ML) models now play a crucial role in predicting properties essential to drug development, such as a drug's logscale acid-dissociation constant (p). Despite recent architectural advances, these models often generalize poorly to novel compounds due to a scarcity of ground-truth data. Further, these models lack interpretability.

A Retrospective Analysis of 190 Patients With Scoliosis Referred to a Private Australian Clinical Advisory Service Between 2017 and 2020.

Objective: The aim of this study was to describe the demographic and clinical characteristics of patients with scoliosis from Australian primary care practices.

Methods: A retrospective review of 190 patient records from August 2017 to April 2020 from a private Australian clinical advisory service database was performed. Deidentified demographic and clinical data were collated and analyzed, along with information regarding the referring practitioners and any accompanying clinical or paraclinical information.

Bispecific antibody targeting of lipid nanoparticles.

Lipid nanoparticles (LNP) are the most clinically advanced non-viral gene delivery system. While progress has been made for enhancing delivery, cell specific targeting remains a challenge. Targeting moieties such as antibodies can be chemically-conjugated to LNPs however, this approach is complex and has challenges for scaling up.

Dendritic cells type 1 control the formation, maintenance, and function of tertiary lymphoid structures in cancer.

Tertiary lymphoid structures (TLS) are organized immune cell aggregates that arise in chronic inflammatory conditions. In cancer, TLS are associated with better prognosis and enhanced response to immunotherapy, making these structures attractive therapeutic targets. However, the mechanisms regulating TLS formation and maintenance in cancer are incompletely understood.