Predicting phenotypes from genetic, environment, management, and historical data using CNNs.

KEY MESSAGE: Convolutional Neural Networks (CNNs) can perform similarly or better than standard genomic prediction methods when sufficient genetic, environmental, and management data are provided. Predicting phenotypes from genetic (G), environmental (E), and management (M) conditions is a long-standing challenge with implications to agriculture, medicine, and conservation. Most methods reduce the factors in a dataset (feature engineering) in a subjective and potentially oversimplified manner. Deep neural networks such as Multilayer Perceptrons (MPL) and Convolutional Neural Networks (CNN) can overcome this by allowing the data itself to determine which factors are most important. CNN models were developed for predicting agronomic yield from a combination of replicated trials and historical yield survey data. The results were more accurate than standard methods when tested on held-out G, E, and M data (r = 0.50 vs. r = 0.43), and performed slightly worse than standard methods when only G was held out (r = 0.74 vs. r = 0.80). Pre-training on historical data increased accuracy compared to trial data alone. Saliency map analysis indicated the CNN has "learned" to prioritize many factors of known agricultural importance.

The role of cognitive functions in the diagnosis of bipolar disorder: A machine learning model.

BACKGROUND: Considering the clinical heterogeneity of the bipolar disorder, difficulties are encountered in making the correct diagnosis. Although a number of common findings have been found in studies on the neurocognitive profile of bipolar disorder, the search for a neurocognitive endophenotype has failed. The aim of this study is to separate bipolar disorder patients from healthy controls with higher accuracy by using a broader neurocognitive evaluation and a novel machine-learning algorithm. METHODS: Individuals who presented to the Bipolar Outpatient Clinic of the Medical Faculty of Eskisehir Osmangazi University and met the inclusion criteria of the research are included in the study. Six neurocognitive tests from the CANTAB test battery were used for neurocognitive evaluation, Polyhedral Conic Functions algorithm was used to classify the participants. RESULTS: Bipolar disorder patients differentiated from healthy controls with an accuracy of 78 %. DISCUSSION: Our study presents a prediction algorithm that separates bipolar disorder from healthy controls with high accuracy by using CANTAB neurocognitive battery.

Building a tRNA thermometer to estimate microbial adaptation to temperature.

Because ambient temperature affects biochemical reactions, organisms living in extreme temperature conditions adapt protein composition and structure to maintain biochemical functions. While it is not feasible to experimentally determine optimal growth temperature (OGT) for every known microbial species, organisms adapted to different temperatures have measurable differences in DNA, RNA and protein composition that allow OGT prediction from genome sequence alone. In this study, we built a 'tRNA thermometer' model using tRNA sequence to predict OGT. We used sequences from 100 archaea and 683 bacteria species as input to train two Convolutional Neural Network models. The first pairs individual tRNA sequences from different species to predict which comes from a more thermophilic organism, with accuracy ranging from 0.538 to 0.992. The second uses the complete set of tRNAs in a species to predict optimal growth temperature, achieving a maximum ${r^2}$ of 0.86; comparable with other prediction accuracies in the literature despite a significant reduction in the quantity of input data. This model improves on previous OGT prediction models by providing a model with minimum input data requirements, removing laborious feature extraction and data preprocessing steps and widening the scope of valid downstream analyses.

Deep learning for plant genomics and crop improvement.

Our era has witnessed tremendous advances in plant genomics, characterized by an explosion of high-throughput techniques to identify multi-dimensional genome-wide molecular phenotypes at low costs. More importantly, genomics is not merely acquiring molecular phenotypes, but also leveraging powerful data mining tools to predict and explain them. In recent years, deep learning has been found extremely effective in these tasks. This review highlights two prominent questions at the intersection of genomics and deep learning: 1) how can the flow of information from genomic DNA sequences to molecular phenotypes be modeled; 2) how can we identify functional variants in natural populations using deep learning models? Additionally, we discuss the possibility of unleashing the power of deep learning in synthetic biology to create novel genomic elements with desirable functions. Taken together, we propose a central role of deep learning in future plant genomics research and crop genetic improvement.

Oncologists awareness about bisphosphonate related osteonecrosis of the jaws.

OBJECTIVE: To evaluate the oncologists thoughts about the positive and adverse effects of bisphosphonates, drug holiday and the awareness about BRONJ. METHODS: A written questionnaire was sent to 7 hospitals, which have oncology facilities in Ankara, Turkey. Results were evaluated as percentages. Chi Square and Kruskal Wallis H test was used to analyze the data. RESULTS: A total of 53 oncologists replied to the questionnaire. BRONJ is the most seen complication (66%) due to bisphosphonates usage. Temporary suspension of the drug (52.8%) is the best treatment choice for this complication. Oncologists usually prefered dentist consultatation (39.6%). CONCLUSIONS: A good cooperation of oncologists and dentists is very important to prevent BRONJ.

Comparison of Different Fixation Types Used in Unilateral Mandibular Condylar Fractures: An In Vivo Study With New Biomechanical Model.

INTRODUCTION: The aim of this in vivo study is to compare the single-titanium, double-titanium mini plate, and single resorbable plate systems used in internal rigid fixation of the unilateral mandibular condylar fractures on new design biomechanical model. METHODS: Thirty synthetic polyurethane models were used for biomechanical testing. Fracture lines were created for each model. Fragments were fixed with single-titanium plates in Group A (n = 10), double-titanium plates in Group B (n = 10), and single biodegradable plate (PPLA) in Group C (n = 10). Masticatory forces were applied to the models and the biomechanical properties of the titanium plate and screws, resorbable plate, and screws were evaluated. RESULTS: The average failure force for Group A, Group B, and Group C is 199, 324, 177N and the average bone displacement for Group A, Group B, Group C is 1.9, 0.3, 2.1 mm, respectively. DISCUSSION: Double titanium plates showed the most acceptable results in the fixation of unilateral subcondylar fractures where the single titanium and biodegradable plate systems failed to provide enough stability in unilateral subcondylar fracture fixation. Biodegradable plate systems are still not an alternative in fixation of unilateral condylar fractures.

Combined surgical-orthodontic rehabilitation of cleidocranial dysplasia: 5 years follow-up.

Cleidocranial dysplasia (CD) is an autosomal dominant syndrome which is characterized by several skeletal malformations such as non-closed fontanelles, skeletal abnormalities of the maxilla and mandible and absence of clavicles. Mid-facial hypoplasia and mandibular prognathism are mostly seen jaw abnormalities in CD. In this study, the combined orthodontic-surgical treatment of a patient with CD with class III malocclusion and multiple unerupted primary and deciduous teeth is presented.

Adenomatoid hyperplasia of the minor salivary glands on the buccal mucosa: A rare case report.

INTRODUCTION: Adenomatoid hyperplasia of the minor salivary glands is a hyperplastic oral lesion which may be seen on minor salivary gland bearing areas on all oral mucosa, especially on soft and hard palate. This study reports a rare case of buccal adenomatoid hyperplasia of the minor salivary glands and discusses the clinical significance. PRESENTATION OF CASE: 48 year old male patient presented with a complaint of a swelling on his left cheek. Clinical examination revealed a bluish mass on the buccal mucosa. A provisional diagnosis of salivary gland neoplasm was made and the lesion was excised under local anesthesia. The histological diagnosis was adenomatoid hyperplasia of the minor salivary glands. DISCUSSION: Buccal localization of the adenomatoid hyperplasia of the minor salivary glands is quite uncommon in the literature. There are two cases in the English literature for our knowledge. In the clinical examination, the nodular and protuberated appearance of the lesion resembles buccal minor salivary gland tumors and vascular lesions. Histological analysis is fundamental to achieve correct diagnosis. CONCLUSION: The differential diagnosis of buccal nodular, exophytic and colored mucosal lesions should include adenomatoid hyperplasia of the minor salivary glands.

Micronucleus assay assessment of possible genotoxic effects in patients treated with titanium alloy endosseous implants or miniplates.

The use of titanium and its alloys (Ti-6Al-4V) for oral surgery has increased dramatically in recent years. Ti is a stable biocompatible metal suitable for oral applications and it has been used for endosseous subperiosteal implants and miniplate fixation for more than 25 years. Dental implants are typically made of Ti or Ti alloys. The alloys are potentially toxic due to release of vanadium and aluminum. We tested the possible genotoxicity of Ti alloy endosseous implants and miniplates on the oral mucosal tissues of two groups of patients: 17 patients receiving Ti miniplate and screw fixation, and 37 endosseous dental implant placement patients. Preoperative and postoperative mucogingival cell samples were collected. Genotoxicity was assessed by the micronucleus assay (MN). There were slight but not statistically significant increases in the frequencies of MN (p=0.087 and p=0.047) post-operation in both groups. In summary, neither of the applications showed genotoxicity in the oral epithelial cells of patients.

Postoperative analgesia in orthognathic surgery patients: diclofenac sodium or paracetamol?

Our aim was to compare the analgesic affects of paracetamol and the non-steroidal anti-inflammatory drug (NSAID) diclofenac sodium for the relief of postoperative pain in patients having bimaxillary osteotomy. Thirty patients were randomly allocated into two groups (n = 15 in each) using sealed envelopes. The first group was given paracetamol 1g intravenously and the second diclofenac sodium 75 mg intramuscularly. The analgesics were given during the last 15 min of the operation while the mucosa was being sutured. The number of requests for further analgesia, and the amount of analgesia given postoperatively (as diclofenac sodium) were recorded. The intensity of postoperative pain was recorded on a visual analogue scale (VAS), and postoperative requests for analgesia, haemodynamic variables (systolic blood pressure and heart rate), and complications were compared. The groups were comparable. A single dose of diclofenac or paracetamol effectively decreases the intensity of postoperative pain after bimaxillary osteotomy.