Search

Protein language models learn from diverse sequences spanning the evolutionary tree and have proven to be powerful tools for sequence design, variant effect prediction and structure prediction. What are the foundations of protein language models, and how are they applied in protein engineering? [ABSTRACT FROM AUTHOR]

Deep-learning language models have shown promise in various biotechnological applications, including protein design and engineering. Here we describe ProGen, a language model that can generate protein sequences with a predictable function across large protein families, akin to generating grammatically and semantically correct natural language sentences on diverse topics. The model was trained on 280 million protein sequences from >19,000 families and is augmented with control tags specifying protein properties. ProGen can be further fine-tuned to curated sequences and tags to improve controllable generation performance of proteins from families with sufficient homologous samples. Artificial proteins fine-tuned to five distinct lysozyme families showed similar catalytic efficiencies as natural lysozymes, with sequence identity to natural proteins as low as 31.4%. ProGen is readily adapted to diverse protein families, as we demonstrate with chorismate mutase and malate dehydrogenase. A generative deep-learning model designs artificial proteins with desired enzymatic activities. [ABSTRACT FROM AUTHOR]

A decade of unprecedented progress in artificial intelligence (AI) has demonstrated the potential for many fields—including medicine—to benefit from the insights that AI techniques can extract from data. Here we survey recent progress in the development of modern computer vision techniques—powered by deep learning—for medical applications, focusing on medical imaging, medical video, and clinical deployment. We start by briefly summarizing a decade of progress in convolutional neural networks, including the vision tasks they enable, in the context of healthcare. Next, we discuss several example medical imaging applications that stand to benefit—including cardiology, pathology, dermatology, ophthalmology–and propose new avenues for continued work. We then expand into general medical video, highlighting ways in which clinical workflows can integrate computer vision to enhance care. Finally, we discuss the challenges and hurdles required for real-world clinical deployment of these technologies. [ABSTRACT FROM AUTHOR]

Protein structure prediction with a language model improves accuracy for orphan and designed proteins. [ABSTRACT FROM AUTHOR]

A low cost recipe for thin film deposition of Potassium Sodium Niobate, (Na,K)NbO (KNN) is pursued. The use of expensive noble metals as electrodes was avoided and instead highly doped silicon was used for both the structural layer and the bottom electrode. Nickel was used for the top electrode. In order to evaluate the outcome, the films were studied in terms of stoichiometry, crystal structure and leakage current density. RF sputtering of thin films of KNN at room temperature was successfully done. Proper crystal structure (Perovskite structure) was achieved after post deposition annealing. Though the leakage current density exhibited high dependency on the polarity of the applied voltage, a leakage current density of 1 × 10 A/cm at 100 kV/ cm was measured. A stoichiometry study revealed that the relative ratio of the volatile elements (Na and K) in the samples was within the acceptable range, however, a total loss of about 25-33 % was observed. [ABSTRACT FROM AUTHOR]

Wild blueberry ( Vaccinium angustifolium Ait.) fields in the north east Canada are naturally grown in a course textured thin layer of soil and below this layer is a soilless layer of gravel. The root zone depth of this crop varies from 10 to 15 cm. Investigating the depth to the gravel layer below the course textured soil is advantageous, as it affects the water holding capacity of the root zone. Water and nutrient management are the two primary determinants of crop yield and the amount of leaching. The objective of this study was to estimate the depth to the gravel layer using DualEM-2 instrument. A C++ program written in Visual Studio 2010 was used to develop mathematical models for estimating the depth to the gravel layer from the outputs of DualEM-2 sensor. Two wild blueberry fields were selected in central Nova Scotia, Canada to evaluate the performance of DualEM-2 instrument in estimating the rootzone depth above the gravel layer. The mid points of squares created by grid lines were used as the sampling points at each experimental site. The actual depth to the interface was measured manually at selected grid points ( n = 50). The apparent ground conductivity (EC) values of DualEM-2 were recorded and the depth to the interface was estimated for the same sampling points within the selected fields. The fruit yield samples were also collected from the same grid points to identify the impact of the depth to the gravel layer on crop yield. After calibrations, comprehensive surveys were conducted and the actual and estimated depths to the interface were established. The interpolated maps of fruit yield, and the actual (z) and estimated ( $$ {\text{z}}_{\text{in}}^{*} $$ ) depths to the interface were created in ArcGIS 10 software. Results indicated that the z was significantly correlated with $$ {\text{z}}_{\text{in}}^{*} $$ for the North River ( R = 0.73; RMSE = 0.27 m) and the Carmel ( R = 0.45; RMSE = 0.20 m) sites. Results revealed that the areas with shallow depth to the gravel layer were low yielding, indicating that the variation in the depth to the gravel layer can have an impact on crop productivity. Non-destructive estimations of the depth to the gravel layer can be used to develop erosion control strategies, which will result in an increased crop production. [ABSTRACT FROM AUTHOR]

Objectives: To evaluate the potential relationship between scrotal ultrasound findings and abnormal semen analysis. Methods: Eighty-seven patients with varicoceles underwent semen analysis and scrotal sonography. On ultrasound, estimated testes volume and the largest pampiniform vein diameters on the affected side at rest and with Valsalva manoeuvre in both the supine and upright positions were examined. In addition, the differences between the largest venous diameters at rest and during the Valsalva manoeuvre in each position (supine and upright) and also the differences between the largest venous diameter in the supine position and the upright position in each condition (at rest and during the Valsalva manoeuvre) were calculated. The relationship between various ultrasound parameters and impaired semen analysis was evaluated using receiver operating characteristic curves. Results: Seventy-one patients had spermatogenesis impairment, and the remaining 16 had normal semen analysis. The difference in the mean spermatic vein diameter at rest between the supine and upright positions (cut-off point, 0.25 mm) had the highest diagnostic accuracy in differentiating the patients with abnormal sperm analysis from those with normal spermatogenesis with an area under the curve of 0.86. Conclusions: Real-time scrotal ultrasound can be helpful in predicting abnormal sperm analysis in patients with varicoceles. Key Points: • Scrotal ultrasound is a non-invasive method to evaluate spermatic veins in varicoceles. • Ultrasound can evaluate venous dimension change at rest after upright position (ΔD ). • ΔD > 2.5 mm distinguishes patients with abnormal semen analysis. • ΔD has the most accuracy in predicting abnormal spermatogenesis. • Ultrasound findings improve differentiation between patients with abnormal and normal spermatogeneses. [ABSTRACT FROM AUTHOR]

Government priorities on provincial Nutrient Management Planning (NMP) programs include improving the program effectiveness for environmental quality protection, and promoting more widespread adoption. Understanding the effect of NMP on both crop yield and key water-quality parameters in agricultural watersheds requires a comprehensive evaluation that takes into consideration important NMP attributes and location-specific farming conditions. This study applied the Soil and Water Assessment Tool (SWAT) to investigate the effects of crop and rotation sequence, tillage type, and nutrient N application rate on crop yield and the associated groundwater $${\text{NO}_{3}}^{ - } {\text{-N }}$$ leaching and sediment loss. The SWAT model was applied to the Thomas Brook Watershed, located in the most intensively managed agricultural region of Nova Scotia, Canada. Cropping systems evaluated included seven fertilizer application rates and two tillage systems (i.e., conventional tillage and no-till). The analysis reflected cropping systems commonly managed by farmers in the Annapolis Valley region, including grain corn-based and potato-based cropping systems, and a vegetable-horticulture system. ANOVA models were developed and used to assess the effects of crop management choices on crop yield and two water-quality parameters (i.e., $${\text{NO}_{3}}^{ - } {\text{-N }}$$ leaching and sediment loading). Results suggest that existing recommended N-fertilizer rate can be reduced by 10-25 %, for grain crop production, to significantly lower $${\text{NO}_{3}}^{ - } {\text{-N }}$$ leaching ( P > 0.05) while optimizing the crop yield. The analysis identified the nutrient N rates in combination with specific crops and rotation systems that can be used to manage $${\text{NO}_{3}}^{ - } {\text{-N }}$$ leaching while balancing impacts on crop yields within the watershed. [ABSTRACT FROM AUTHOR]

Purpose: Benign prostatic hyperplasia (BPH) is the main cause of lower urinary tract symptoms (LUTS) in elderly men. Some patients respond poorly to routine medical therapy and are not well suited for surgery, too. This study was planned to evaluate the effect of Botulinum-A on BPH refractory to current medical therapy in poor surgical candidates. Methods: In this clinical trial, 10 patients with LUTS suggestive of BPH who had responded poorly to medical therapy for at least 6 months and were poor surgical candidates, were received different doses of transurethral Botulinum-A injection based on their prostate volume. The prostate volume, PSA, Qmax, IPSS, PVR and frequency of nocturia were evaluated and compared before and after treatment. Results: The mean IPSS was 24.50 ± 3.8 and 13.40 ± 2.67 before and after the treatment, respectively ( P < 0.001). The mean prostate volume was decreased from 41.50 ± 10.85 mL to 30.40 ± 8.05 mL ( P < 0.001). The Qmax was increased from 7.87 ± 2.01 mL/s to 16.19 ± 1.76 mL/s ( P < 0.001). The mean PSA was 3.12 ± 0.49 ng/mL and 1.71 ± 0.39 ng/mL before and after treatment, respectively ( P < 0.001). The mean PVR was 75.6 ± 51.63 mL and 63.50 ± 36.59 mL before and after treatment, respectively ( P = 0.096). The mean number of nocturia was decreased from 4.1 ± 0.87 to 2.4 ± 0.84 ( P < 0.001). The mean IPSS, Prostate volume, PSA and frequency of nocturia were decreased significantly. Although mean PVR was decreased but it wasn't statistically significant. The mean Qmax was increased significantly. Conclusion: Intraprostatic injection of Botulinum-A may be an effective and safe treatment for symptomatic BPH in selected patients whose medical treatment has faced failure and are poor surgical candidates. Transurethral method could be selected as a preferable technique of injection. [ABSTRACT FROM AUTHOR]

Purpose: Erectile dysfunction (ED) is a common male sexual dysfunction and affects the individual's physical and psychological well-being. It has been classified as organic and psychogenic. Men with low testosterone levels have an increased risk of ED. On the other hand, direct detrimental effect of metabolic syndrome on the endothelium, smooth muscle and nerves of the vascular system of the penis is what causes ED to develop in men with metabolic syndrome. Therefore, it is supposed that a large number of men with erectile dysfunction are patients who have ED, metabolic syndrome and testosterone deficiency as a triad. The aim of this study is determining relative frequencies of metabolic syndrome and testosterone deficiency in a group of men with ED. Methods: Men suffering from ED who were referred to a certain private urology clinic between 22.11.2009 and 22.9.2010 were evaluated for metabolic syndrome criteria; their morning free testosterone levels were measured, and then the related questionnaires were filled out. Results: Of 241 men with ED, the relative frequency of metabolic syndrome was 41.5%, of testosterone deficiency was 36.5% and of metabolic syndrome in combination with testosterone deficiency was 19.5%. Conclusion: The relative frequencies of metabolic syndrome and testosterone deficiency in men with ED seem to be significant, and it is the time that we should evaluate ED not as a disease but as a presentation of multiple underlying pathologies which needs medical attention to general health. [ABSTRACT FROM AUTHOR]

Enzymes belonging to the glutathione-S-transferase (GST) and cytochrome P450 (CYP) families are involved in a 2-stage detoxification process of a wide range of environmental toxins and carcinogens. In order to investigate whether there is a genetic association of the biotransformation enzymes and idiopathic male fertility, we studied GSTT1, GSTM1, and CYP1A1*2A polymorphisms in 150 infertile men and 200 healthy men as controls from Northern Iran. Genotyping of the GSTT1 and GSTM1 genes were performed using the multiplex polymerase chain reaction (PCR). However, the CYP1A1 polymorphism was determined using PCR-restriction fragment length polymorphism (RFLP). The GSTM1 and GSTT1 null genotypes were present at frequencies of 0.61 and 0.34 in infertile cases, whereas in controls the frequencies were 0.33 and 0.17, respectively. Double-null genotype was found to be elevated among infertile men (odds ratio [OR] = 3.75, 95% confidence interval [CI] = 2.42-6.45; P < .0001). The frequency of TT, TC, and CC genotypes of CYP1A1 polymorphism in the controls were 42.5%, 45.5%, and 12%, respectively, while those in the infertile men were 38.7%, 48%, and 13.3%. The CYP1A1*2A did not display any association with male infertility. We observed an association between male infertility and the GSTM1 and GSTT1 null deletion, but not with the CYP1A1 polymorphism in North Iranian men with idiopathic infertility. [ABSTRACT FROM PUBLISHER]

It has been suggested that nitrates are potent smooth muscle relaxants that may reduce pain and facilitate ureteral stone passage; therefore it may be an option for medical expulsive therapy in ureteral stones. In a prospective randomized controlled clinical trial, we evaluated the efficacy of medical expulsive therapy with isosorbide-SR 40 mg in patients with ureteral stones (≤10 mm). The patients with ureteral stones in KUB or urinary tract ultrasonography were randomized to receive methylprednisolone plus celecoxib without (control group), and with isosorbide-SR 40 mg (treatment group) for 21 days. 66 patients [33(50%) in control, 33(50%) in treatment group] were entered randomly to our study. The stone expulsion rate was not significantly different between two groups (54.5 vs. 45.5%) ( P = 0.497). The need for surgical procedures were more common in control group within 21 days (9.4 vs. 6.1%) and more common in treatment group after 21 days (33.3 vs. 21.9%) ( P = 0.756).Patients in the treatment group experienced more intractable pain (27.3 vs. 6.1%), intractable vomiting (3 vs. 0%) ( P = 0.046) and hospitalization (3 vs. 0%) ( P = 0.314). Drug side effects including headache and dizziness were more common in treatment group (39.4 vs. 9.1%) ( P = 0.004). In our study, the use of isosorbide-SR in treatment group did not improve the stone expulsion rate in patients with ureteral stones (≤10 mm) but developed more side effects. Then it may not an appropriate alternative for medical expulsive therapy. Of course, further trials are recommended. [ABSTRACT FROM AUTHOR]

Constructed wetlands are cost effective wastewater treatment systems being increasingly used in agriculture. Efficient phosphorus (P) treatment by wetlands can however, be a challenge due to slow removal mechanisms. As a result, extended contact times are often required to achieve desired treatment. There are also concerns related to the long-term sustainability of P treatment. Therefore, a five year dataset from a surface flow constructed wetland located in Bible Hill Nova Scotia, Canada was examined to: 1) determine the effects of continued loading on P treatment and 2) evaluate hydrological impacts on P treatment. The wetland was intensively monitored year-round from November, 2000 through April, 2005 for total P (TP) and soluble reactive P (SRP). Dairy wastewater (milkhouse wash water and liquid manure) was loaded at 1.5 ± 1.0 kg ha-1 d-1 for TP and 1.0 ± 0.9 kg ha-1 d-1 for SRP. Mass reductions for the entire monitoring period were 53.7% and 52.7% for TP and SRP, respectively. Soils in this wetland appeared to have a sustained P adsorption capacity, with treatment being largely influenced by hydrology and fluctuations in wastewater loading rates. Linear regression of monthly TP and SRP mass reductions, with monthly outflow volumes resulted in decreased mass reductions with increased outflow. Monthly mass reductions were > 50% when corresponding outflows were < 100 mm. When monthly outflow exceeded 100 mm, however, mass reductions became highly variable. To maintain effective P management by constructed wetlands, the use of approaches that prevent high external hydrological loadings are recommended. [ABSTRACT FROM AUTHOR]

Constructed wetlands are used throughout North America to treat various types of wastewater in warm climates; however, little has been documented about their treatment processes and efficiencies during winter periods in Atlantic Canada. Two small-scale constructed wetlands (100 m²) of differing operational depth (wetland 1: 0.15 m shallow zone depth and wetland 2: managed water level) were designed to treat agricultural wastewater at the Bio-Environmental Engineering Center of the Nova Scotia Agricultural College. Both wetlands were monitored from November 2000 through March 2002 to evaluate treatment efficiencies and mass reductions of five-day biological oxygen demand (BOD5), total suspended solids (TSS), total phosphorus (TP), and ammonia-nitrogen (NH3-N). An average loading rate of 44.7 kg BOD ha-1 d-1 was loaded into each wetland, even during winter months. Percent removal and mass reductions for BOD5, TSS, TP, and NH3-N in both wetlands, irrespective of water levels, ranged from 62 to 99%. The treatment of TP was not found to be as effective as the other parameters, especially during high loading periods. Results show promise for the operation of constructed wetlands on a year-round basis in Atlantic Canada. [ABSTRACT FROM AUTHOR]

The MTCP1 gene is involved in the t(X;14)(q28;q11) translocation associated with T-cell prolymphocytic leukemia and related conditions. This gene is unusual in that it codes for two distinct proteins: a small mitochondrial protein, p8MTCP1, and a putative oncogenic protein, p13MTCP1. Scarcity of material from t(X;14)-associated proliferations and very low levels of mRNA expression have so far prevented a thorough description of p13MTCP1-encoding transcripts. Here, we characterize two additional t(X;14) bearing leukemias allowing this analysis. In one case, with a breakpoint located 5′ to the MTCP1 gene, the level of transcription of previously described p13MTCP1-encoding transcripts is enhanced. In the second case, with a breakpoint within the MTCP1 intron I, an alternative transcription initiation site is demonstrated in the tumor cells at 229 bp upstream to exon II. The identification of this internal promoter, together with the similarity between TCL1 and MTCP1 genomic structures, allow us to propose a model in which the duplication of an ancestral gene was followed by the insertion of one copy within the intron of a p8-encoding gene, accounting for the unusual feature of the MTCP1 gene. [ABSTRACT FROM AUTHOR]

For newly diagnosed breast cancer, estrogen receptor status (ERS) is a key molecular marker used for prognosis and treatment decisions. During clinical management, ERS is determined by pathologists from immunohistochemistry (IHC) staining of biopsied tissue for the targeted receptor, which highlights the presence of cellular surface antigens. This is an expensive, time-consuming process which introduces discordance in results due to variability in IHC preparation and pathologist subjectivity. In contrast, hematoxylin and eosin (H&E) staining—which highlights cellular morphology—is quick, less expensive, and less variable in preparation. Here we show that machine learning can determine molecular marker status, as assessed by hormone receptors, directly from cellular morphology. We develop a multiple instance learning-based deep neural network that determines ERS from H&E-stained whole slide images (WSI). Our algorithm—trained strictly with WSI-level annotations—is accurate on a varied, multi-country dataset of 3,474 patients, achieving an area under the curve (AUC) of 0.92 for sensitivity and specificity. Our approach has the potential to augment clinicians' capabilities in cancer prognosis and theragnosis by harnessing biological signals imperceptible to the human eye. Determination of estrogen receptor status (ERS) in breast cancer tissue requires immunohistochemistry, which is sensitive to the vagaries of sample processing and the subjectivity of pathologists. Here the authors present a deep learning model that determines ERS from H&E stained tissue, which could improve oncology decisions in under-resourced settings. [ABSTRACT FROM AUTHOR]

Diagnosis of endoleak following endovascular aortic repair (EVAR) relies on manual review of multi-slice CT angiography (CTA) by physicians which is a tedious and time-consuming process that is susceptible to error. We evaluate the use of a deep neural network for the detection of endoleak on CTA for post-EVAR patients using a novel data efficient training approach. 50 CTAs and 20 CTAs with and without endoleak respectively were identified based on gold standard interpretation by a cardiovascular subspecialty radiologist. The Endoleak Augmentor, a custom designed augmentation method, provided robust training for the machine learning (ML) model. Predicted segmentation maps underwent post-processing to determine the presence of endoleak. The model was tested against 3 blinded general radiologists and 1 blinded subspecialist using a held-out subset (10 positive endoleak CTAs, 10 control CTAs). Model accuracy, precision and recall for endoleak diagnosis were 95%, 90% and 100% relative to reference subspecialist interpretation (AUC = 0.99). Accuracy, precision and recall was 70/70/70% for generalist1, 50/50/90% for generalist2, and 90/83/100% for generalist3. The blinded subspecialist had concordant interpretations for all test cases compared with the reference. In conclusion, our ML-based approach has similar performance for endoleak diagnosis relative to subspecialists and superior performance compared with generalists. [ABSTRACT FROM AUTHOR]