Molecular Sets (MOSES): A Benchmarking Platform for Molecular Generation Models.

Generative models are becoming a tool of choice for exploring the molecular space. These models learn on a large training dataset and produce novel molecular structures with similar properties. Generated structures can be utilized for virtual screening or training semi-supervized predictive models in the downstream tasks. While there are plenty of generative models, it is unclear how to compare and rank them. In this work, we introduce a benchmarking platform called Molecular Sets (MOSES) to standardize training and comparison of molecular generative models. MOSES provides training and testing datasets, and a set of metrics to evaluate the quality and diversity of generated structures. We have implemented and compared several molecular generation models and suggest to use our results as reference points for further advancements in generative chemistry research. The platform and source code are available at https://github.com/molecularsets/moses.

Effects of the August 2003 blackout on the New York City healthcare delivery system: a lesson for disaster preparedness.

BACKGROUND: On August 14, 2003, the United States and Canada suffered the largest power failure in history. We report the effects of this blackout on New York City's healthcare system by examining the following: 1) citywide 911 emergency medical service (EMS) calls and ambulance responses; and 2) emergency department (ED) visits and hospital admissions to one of New York City's largest hospitals. METHODS: Citywide EMS calls and ambulance responses were categorized by 911 call type. Montefiore Medical Center (MMC) ED visits and hospital admissions were categorized by diagnosis and physician-reviewed for relationship to the blackout. Comparisons were made to the week pre- and postblackout. RESULTS: Citywide EMS calls numbered 5,299 on August 14, 2003, and 5,021 on August 15, 2003, a 58% increase (p < .001). During the blackout, there were increases in "respiratory" (189%; p < .001), "cardiac" (68%; p = .016), and "other" (40%; p < .001) EMS call categories, but when expressed as a percent of daily totals, "cardiac" was no longer significant. The MMC-ED reflected this surge with only "respiratory" visits significantly increased (expressed as percent of daily total visits; p < .001). Respiratory device failure (mechanical ventilators, positive pressure breathing assist devices, nebulizers, and oxygen compressors) was responsible for the greatest burden (65 MMC-ED visits, with 37 admissions) as compared with 0 pre- and postblackout. CONCLUSIONS: The blackout dramatically increased EMS and hospital activity, with unexpected increases resulting from respiratory device failures in community-based patients. Our findings suggest that current capacity to respond to public health emergencies could be easily overwhelmed by widespread/prolonged power failure(s). Disaster preparedness planning would be greatly enhanced if fully operational, backup power systems were mandated, not only for acute care facilities, but also for community-based patients dependent on electrically powered lifesaving devices.

Unexplained metabolic acidosis in critically ill patients: the role of pyroglutamic acid.

OBJECTIVE: To determine the role of pyroglutamic acid (PGA) in the pathogenesis of unexplained metabolic acidosis in critically ill patients. DESIGN AND SETTING: Case series in the medical ICU of an urban hospital. PATIENTS: 23 patients admitted to the medical ICU with acidemia (pH <7.35 or HC0(3) < or = 16 mEq/l) not explained by the presence of ketoacidosis, lactic acidosis, renal failure or ingestion of drugs or toxins and who had an increase in the strong ion gap (SIG) greater than 5. MEASUREMENTS AND RESULTS: Plasma levels of sodium, potassium, chloride, bicarbonate, calcium (ionized), magnesium, lactate, phosphate, albumin, blood urea nitrogen, and creatinine were measured. Arterial blood gases and urine dipstick for ketones were also analyzed. Plasma was assayed for PGA using gas chromatography. The patient's history and Kardex were reviewed for evidence of acetaminophen administration. The plasma PGA level was found to be very low in all patients studied. The correlation between SIG and PGA (r) was -0.01 (95% CI: -0.42 to 0.40). PGA therefore did not account for the observed increase in the SIG. There appeared to be no obvious influence of acetaminophen intake on levels of PGA in the plasma. CONCLUSIONS: We were unable to confirm the importance of PGA as a cause of unexplained metabolic acidosis and increased SIG in our critically ill patients.