Conditional Generative Models for Synthetic Tabular Data: Applications for Precision Medicine and Diverse Representations.

Tabular medical datasets, like electronic health records (EHRs), biobanks, and structured clinical trial data, are rich sources of information with the potential to advance precision medicine and optimize patient care. However, real-world medical datasets have limited patient diversity and cannot simulate hypothetical outcomes, both of which are necessary for equitable and effective medical research. Fueled by recent advancements in machine learning, generative models offer a promising solution to these data limitations by generating enhanced synthetic data.

A deoxyfluoroalkylation-aromatization strategy to access fluoroalkyl arenes.

Fluoroalkyl arenes (Ar-R) are valuable substructures present in several FDA-approved drugs, patents, agrochemicals, and materials, and complementary strategies that enable access to a broad spectrum of Ar-R compounds benefit these applied fields. Herein, we report a deoxyfluoroalkylation-aromatization strategy to convert cyclohexanones into broad-spectrum Ar-R containing compounds. Generally, the fluoroalkyl sources were activated to participate in a 1,2-addition reaction followed by aromatization in a sequence that contrasts more common preparations of these Ar-R compounds, such as (i) transition-metal catalyzed cross-coupling reactions of aryl electrophiles and nucleophiles, and (ii) radical fluoroalkylation reactions of C-H bonds of arenes.

Heat-Induced Phosphatidylserine Changes Drive HSPA1A's Plasma Membrane Localization.

Heat shock protein A1A (HSPA1A) is a molecular chaperone crucial in cell survival. In addition to its cytosolic functions, HSPA1A translocates to heat-shocked and cancer cells' plasma membrane (PM). In cancer, PM-localized HSPA1A (mHSPA1A) is associated with increased tumor aggressiveness and therapeutic resistance, suggesting that preventing its membrane localization could have therapeutic value.

Identifying DNA methylation sites affecting drug response using electronic health record-derived GWAS summary statistics.

Adverse drug responses (ADRs) result in over 7,000 deaths annually. Pharmacogenomic studies have shown that many ADRs are partially attributable to genetics. However, emerging data suggest that epigenetic mechanisms, such as DNA methylation (DNAm) also contribute to this variance.

Detecting clinician implicit biases in diagnoses using proximal causal inference.

Clinical decisions to treat and diagnose patients are affected by implicit biases formed by racism, ableism, sexism, and other stereotypes. These biases reflect broader systemic discrimination in healthcare and risk marginalizing already disadvantaged groups. Existing methods for measuring implicit biases require controlled randomized testing and only capture individual attitudes rather than outcomes.