Drug target prediction through deep learning functional representation of gene signatures

Many machine learning applications in bioinformatics currently rely on matching gene identities when analyzing input gene signatures and fail to take advantage of preexisting knowledge about gene functions. To further enable comparative analysis of OMICS datasets, including target deconvolution and mechanism of action studies, we develop an approach that represents gene signatures projected onto their biological functions, instead of their identities, similar to how the word2vec technique works in natural language processing. We develop the Functional Representation of Gene Signatures (FRoGS) approach by training a deep learning model and demonstrate that its application to the Broad Institute's L1000 datasets results in more effective compound-target predictions than models based on gene identities alone. By integrating additional pharmacological activity data sources, FRoGS significantly increases the number of high-quality compound-target predictions relative to existing approaches, many of which are supported by in silico and/or experimental evidence. These results underscore the general utility of FRoGS in machine learning-based bioinformatics applications. Prediction networks pre-equipped with the knowledge of gene functions may help uncover new relationships among gene signatures acquired by large-scale OMICs studies on compounds, cell types, disease models, and patient cohorts.

Structure-activity relationship of dihydropyridines for rhabdomyosarcoma

Childhood muscle-related cancer rhabdomyosarcoma is a rare disease with a 50-year unmet clinical need for the patients presented with advanced disease. The rarity of ∼350 cases per year in North America generally diminishes the viability of large-scale, pharmaceutical industry driven drug development efforts for rhabdomyosarcoma. In this study, we performed a large-scale screen of 640,000 compounds to identify the dihydropyridine (DHP) class of anti-hypertensives as a priority compound hit. A structure-activity relationship was uncovered with increasing cell growth inhibition as side chain length increases at the ortho and para positions of the parent DHP molecule. Growth inhibition was consistent across n = 21 rhabdomyosarcoma cell line models. Anti-tumor activity in vitro was paralleled by studies in vivo. The unexpected finding was that the action of DHPs appears to be other than on the DHP receptor (i.e., L-type voltage-gated calcium channel). These findings provide the basis of a medicinal chemistry program to develop dihydropyridine derivatives that retain anti-rhabdomyosarcoma activity without anti-hypertensive effects.

Evolution of Novartis' Small Molecule Screening Deck Design

This article summarizes the evolution of the screening deck at the Novartis Institutes for BioMedical Research (NIBR). Historically, the screening deck was an assembly of all available compounds. In 2015, we designed a first deck to facilitate access to diverse subsets with optimized properties. We allocated the compounds as plated subsets on a 2D grid with property based ranking in one dimension and increasing structural redundancy in the other. The learnings from the 2015 screening deck were applied to the design of a next generation in 2019. We found that using traditional leadlikeness criteria (mainly MW, clogP) reduces the hit rates of attractive chemical starting points in subset screening. Consequently, the 2019 deck relies on solubility and permeability to select preferred compounds. The 2019 design also uses NIBR's experimental assay data and inferred biological activity profiles in addition to structural diversity to define redundancy across the compound sets.

A Fully Automated High-Throughput Flow Cytometry Screening System Enabling Phenotypic Drug Discovery

The goal of high-throughput screening is to enable screening of compound libraries in an automated manner to identify quality starting points for optimization. This often involves screening a large diversity of compounds in an assay that preserves a connection to the disease pathology. Phenotypic screening is a powerful tool for drug identification, in that assays can be run without prior understanding of the target and with primary cells that closely mimic the therapeutic setting. Advanced automation and high-content imaging have enabled many complex assays, but these are still relatively slow and low throughput. To address this limitation, we have developed an automated workflow that is dedicated to processing complex phenotypic assays for flow cytometry. The system can achieve a throughput of 50,000 wells per day, resulting in a fully automated platform that enables robust phenotypic drug discovery. Over the past 5 years, this screening system has been used for a variety of drug discovery programs, across many disease areas, with many molecules advancing quickly into preclinical development and into the clinic. This report will highlight a diversity of approaches that automated flow cytometry has enabled for phenotypic drug discovery.

NSAID and other analgesic use by endurance runners during training, competition and recovery

Background. An increasing popularity of ultra-endurance events coupled with excessive or inappropriate non-steroidal anti-inflammatory drug (NSAID) use during such events could pose considerable potential risks to runners’ health.Objective. To evaluate the incidence of NSAID and other analgesic use in distance runners during training, competition and recovery.Methods. We performed an observational cross-sectional study at the Desert Race Across the Sand race (Colorado to Utah, USA) in June 2011 and the Empire State Marathon half-marathon, and relay races in Syracuse, NY, October 2011. A total of 27 ultramarathon runners and 46 marathon, half-marathon and marathon relay runners participated in the study. Surveys were distributed to runners during race registration. Self-reported use of common analgesic medications during training, racing and recovery was assessed.Results. Among all runners at all stages, NSAIDs were the most commonly used analgesic medication. NSAID use by ultramarathon runners compared with all other runners was similar during training (59% and 63%, respectively; χ2=0.008; p=0.93) and recovery (59% and 61%, respectively; χ2=0.007; p=0.93). However, ultramarathon runners were more likely than all other runners to use NSAIDs during the race (70% and 26%, respectively; χ2=11.76; p=0.0006).Conclusion. Despite undesirable side-effects associated with the use of NSAIDs, there was a high prevalence of use in all runners, particularly during training and recovery. NSAID use during the race was significantly greater in ultramarathon runners. Medical staff at endurance events need to be aware of, and prepared for potential complications related to the high use of NSAIDs in runners. Future efforts should focus on teaching runners about the undesirable effects of medication and emphasising alternatives to pain medication.

NSAID and other analgesic use by endurance runners during training, competition and recovery

Background. An increasing popularity of ultra-endurance events coupled with excessive or inappropriate non-steroidal anti-inflammatory drug (NSAID) use during such events could pose considerable potential risks to runners’ health.Objective. To evaluate the incidence of NSAID and other analgesic use in distance runners during training, competition and recovery.Methods. We performed an observational cross-sectional study at the Desert Race Across the Sand race (Colorado to Utah, USA) in June 2011 and the Empire State Marathon half-marathon, and relay races in Syracuse, NY, October 2011. A total of 27 ultramarathon runners and 46 marathon, half-marathon and marathon relay runners participated in the study. Surveys were distributed to runners during race registration. Self-reported use of common analgesic medications during training, racing and recovery was assessed.Results. Among all runners at all stages, NSAIDs were the most commonly used analgesic medication. NSAID use by ultramarathon runners compared with all other runners was similar during training (59% and 63%, respectively; χ2=0.008; p=0.93) and recovery (59% and 61%, respectively; χ2=0.007; p=0.93). However, ultramarathon runners were more likely than all other runners to use NSAIDs during the race (70% and 26%, respectively; χ2=11.76; p=0.0006).Conclusion. Despite undesirable side-effects associated with the use of NSAIDs, there was a high prevalence of use in all runners, particularly during training and recovery. NSAID use during the race was significantly greater in ultramarathon runners. Medical staff at endurance events need to be aware of, and prepared for potential complications related to the high use of NSAIDs in runners. Future efforts should focus on teaching runners about the undesirable effects of medication and emphasising alternatives to pain medication.

The legend of plantar neuropraxia in long-distance athletes

Background. Legend has it that endurance athletes who develop plantar foot pain during long-distance running frequently experience an eventual relief of pain due to a transient neuropraxia brought on by continued activity.Objective. To evaluate the nature of this legend, we assessed long-distance runners for the presence of sensory deficits before and after completion of an ultramarathon, expecting to find an induced neuropraxia  and abnormal sensory results.Methods. Twenty-five adult participants of an ultramarathon were evaluated prior to their 50/100 km run and again upon completion of the race. Neurosensory testing was performed using a 10 g monofilament at 4 locations on each foot and a 128 Hz tuning fork at one location on each foot. The same techniques were used prior to, and at conclusion of the race.Results. We detected no neuropraxia or sensory deficits in any participant, despite reports by the same subjects that they had experienced the phenomenon during the race. While runners commonly report losing sensation in their feet during long runs, we were unable to demonstrate any sensory deficit with simple field-based testing.Conclusion. We believe that there is room for additional research to be performed using more sensitive means of neurosensory evaluation.

The legend of plantar neuropraxia in long-distance athletes

Background. Legend has it that endurance athletes who develop plantar foot pain during long-distance running frequently experience an eventual relief of pain due to a transient neuropraxia brought on by continued activity.Objective. To evaluate the nature of this legend, we assessed long-distance runners for the presence of sensory deficits before and after completion of an ultramarathon, expecting to find an induced neuropraxia  and abnormal sensory results.Methods. Twenty-five adult participants of an ultramarathon were evaluated prior to their 50/100 km run and again upon completion of the race. Neurosensory testing was performed using a 10 g monofilament at 4 locations on each foot and a 128 Hz tuning fork at one location on each foot. The same techniques were used prior to, and at conclusion of the race.Results. We detected no neuropraxia or sensory deficits in any participant, despite reports by the same subjects that they had experienced the phenomenon during the race. While runners commonly report losing sensation in their feet during long runs, we were unable to demonstrate any sensory deficit with simple field-based testing.Conclusion. We believe that there is room for additional research to be performed using more sensitive means of neurosensory evaluation.

Transcript map and comparative analysis of the 1.5-Mb commonly deleted segment of human 5q31 in malignant myeloid diseases with a del(5q)

Loss of a whole chromosome 5, or a del(5q), are recurring abnormalities in malignant myeloid diseases. In previous studies, we defined a commonly deleted segment (CDS) of 1.5 Mb between D5S479 and D5S500 in patients with a del(5q), and we established a P1 artificial chromosome-based contig encompassing this interval. To identify candidate tumor suppressor genes (TSGs), we developed a transcript map of the CDS. The map contains 18 genes and 12 expressed sequence tags/UniGenes. Among the 18 genes are 10 genes that were previously cloned and 8 novel genes. The newly identified genes include CDC23, which encodes a component of the anaphase-promoting complex; RAB6KIFL, which encodes a kinesin-like protein involved in organelle transport; and KLHL3, which encodes a human homologue of the Drosophila ring canal protein, kelch. We determined the intron/exon organization of 14 genes and eliminated each gene as a classical TSG by mutation analysis. In addition, we established a single-nucleotide polymorphism map as well as a map of the mouse genome that is syntenic to the CDS of human 5q31. The development of a transcription map will facilitate the molecular cloning of a myeloid leukemia suppressor gene on 5q.