Human-in-the-loop active learning for goal-oriented molecule generation.

Machine learning (ML) systems have enabled the modelling of quantitative structure-property relationships (QSPR) and structure-activity relationships (QSAR) using existing experimental data to predict target properties for new molecules. These property predictors hold significant potential in accelerating drug discovery by guiding generative artificial intelligence (AI) agents to explore desired chemical spaces. However, they often struggle to generalize due to the limited scope of the training data.

Tools, techniques, and challenges in preparing cytology specimens for ancillary studies: results of the ASC Optimizing Cytology and Small Biopsy Specimen Processing for Ancillary Studies task force survey.

Introduction: Ancillary testing on cytopathology and other small biopsy specimens is crucial for diagnosis and provides critical information to clinicians. Testing is dependent on preanalytic factors and would benefit from standardization of specimen collection protocols across laboratories. To assess institutional practices and areas of need for evidence-based standards, we surveyed current practices across cytopathology laboratories.

The Histopathologic Features of Early COVID Pneumonia in a Pediatric Patient: New Insight into the Role of Macrophages.

A life-threatening complication of severe acute respiratory syndrome coronavirus-2 (SARS-CoV-2) infection is acute respiratory distress syndrome. Our understanding of the pathologic changes in coronavirus disease 2019 (COVID-19) is based almost exclusively on post-mortem analyses of adults. These studies established several hallmarks of SARS-CoV-2 lung infection, including diffuse alveolar damage, microvascular thrombi, and acute bronchopneumonia.

Text classification models for assessing the completeness of randomized controlled trial publications based on CONSORT reporting guidelines.

Complete and transparent reporting of randomized controlled trial publications (RCTs) is essential for assessing their credibility. We aimed to develop text classification models for determining whether RCT publications report CONSORT checklist items. Using a corpus annotated with 37 fine-grained CONSORT items, we trained sentence classification models (PubMedBERT fine-tuning, BioGPT fine-tuning, and in-context learning with GPT-4) and compared their performance.