Gene-specific artificial intelligence-based variant classification engine: results of a time-capsule experiment

2019 ◽  
Author(s):  
Yaron Einhorn ◽  
Moshe Einhorn ◽  
Adaia Kamshov ◽  
Oron Lev ◽  
Amir Trabelsi ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Clinical Information ◽  
Cost Effective ◽  
Training Data ◽  
Variant Classification ◽  
Full Dataset ◽  
Blinded Study ◽  
Novel Variants ◽  
Uncertain Significance ◽  
Specific Rule

Abstract Background: Interpretation of genetic variation remains an impediment to cost-effective application of genomics to medicine. An advanced artificial intelligence (AI)-based Variant Classification Engine (aiVCE), rooted in ACMG/AMP guidelines, employs data-driven methods to expedite gene-specific classification (franklin.genoox.com). In this blinded study, the aiVCE’s overall and rule-level performances were evaluated using ClinVar (v. 2018-10) variants with creation dates after 5/01/2017. By removing any prior knowledge of these variants from the aiVCE training data, they were treated as novel variants. Using a ‘Full’ dataset (75,801 variants with ≥1 star) and an ‘Increased-Certainty’ dataset (3,993 variants with ≥2 stars), the aiVCE classified variants as pathogenic (P), likely-pathogenic (LP), uncertain significance (VUS), likely-benign (LB), or benign (B). VUS with sufficient supporting data were subclassified as VUS-leaning benign or VUS-leaning pathogenic. aiVCE results were evaluated to determine concordance with final ClinVar classification and rule-level determinations. Results: The aiVCE demonstrated >97% concordance among Increased-Certainty variants. Concordance was >95% across variant effects (e.g., missense, null, splice region), and was >93.5% for the Full dataset. When assessing the aiVCE’s application of specific ACMG rules, significant differences were observed between ClinVar P/LP and B/LB variants rule-met proportions (all P<0.00001), thus supporting gene-specific rule selections. Evaluation of discordance between the aiVCE and ClinVar uncovered evidences that might have been unavailable to submitting laboratories, highlighting AI utility in variant classification. Conclusions: The aiVCE exhibited robust performance, despite lacking past evidence, in determining whether variants would be categorized as P/LP. Applying latest computational advances to existing guidelines may assist scientists and clinicians interpret variants with limited clinical information and greatly reduce analytical bottlenecks.

scholarly journals A Collaborative Effort to Define Classification Criteria for ATM Variants in Hereditary Cancer Patients

2020 ◽  
Author(s):  
Lidia Feliubadaló ◽  
Alejandro Moles-Fernández ◽  
Marta Santamariña-Pena ◽  
Alysson T Sánchez ◽  
Anael López-Novo ◽  
...  
Keyword(s):  
Hereditary Cancer ◽  
Diagnostic Yield ◽  
Clinical Information ◽  
Variant Classification ◽  
Collaborative Effort ◽  
Variants Of Uncertain Significance ◽  
Large Gene ◽  
Gene Panel Testing ◽  
Uncertain Significance ◽  
Risk Of Cancer

Abstract Background Gene panel testing by massive parallel sequencing has increased the diagnostic yield but also the number of variants of uncertain significance. Clinical interpretation of genomic data requires expertise for each gene and disease. Heterozygous ATM pathogenic variants increase the risk of cancer, particularly breast cancer. For this reason, ATM is included in most hereditary cancer panels. It is a large gene, showing a high number of variants, most of them of uncertain significance. Hence, we initiated a collaborative effort to improve and standardize variant classification for the ATM gene. Methods Six independent laboratories collected information from 766 ATM variant carriers harboring 283 different variants. Data were submitted in a consensus template form, variant nomenclature and clinical information were curated, and monthly team conferences were established to review and adapt American College of Medical Genetics and Genomics/Association for Molecular Pathology (ACMG/AMP) criteria to ATM, which were used to classify 50 representative variants. Results Amid 283 different variants, 99 appeared more than once, 35 had differences in classification among laboratories. Refinement of ACMG/AMP criteria to ATM involved specification for twenty-one criteria and adjustment of strength for fourteen others. Afterwards, 50 variants carried by 254 index cases were classified with the established framework resulting in a consensus classification for all of them and a reduction in the number of variants of uncertain significance from 58% to 42%. Conclusions Our results highlight the relevance of data sharing and data curation by multidisciplinary experts to achieve improved variant classification that will eventually improve clinical management.

Press “A” for Artificial Intelligence in Agriculture: A Review

2020 ◽  
Vol 4 (3) ◽  
Author(s):  
Yogesh Awasthi
Keyword(s):  
Artificial Intelligence ◽  
Image Analysis ◽  
Significant Role ◽  
Pattern Analysis ◽  
Cost Effective ◽  
Predictive Analysis ◽  
Accurate Information ◽  
Digital Era ◽  
Learning Techniques ◽  
Crucial Information

Agriculture is the backbone of the developing country. In old era agriculture was based on the experience which was shared by people to people but in this digital era technology play a very important and significant role in agriculture. Now agriculture become a business hub therefore farmers are focusing on precision farming. They introduced the technology in agriculture to define the accurate information about seed, soil, weather, disease and all factors which affecting the farming. Artificial Intelligence uses predictive analysis, image analysis, learning techniques and Pattern analysis to declare the best cost effective and maximum gain for the agriculturist. The aim of this paper is to provide the crucial information with the help of technology which a farmers can use to harvest the variety of crops as per the demand in world so that they can get maximum benefits.

scholarly journals Improving Semi-Supervised Learning for Audio Classification with FixMatch

Electronics ◽  
2021 ◽  
Vol 10 (15) ◽  
pp. 1807
Author(s):  
Sascha Grollmisch ◽  
Estefanía Cano
Keyword(s):  
Neural Networks ◽  
Supervised Learning ◽  
Transfer Learning ◽  
Data Transfer ◽  
State Of The Art ◽  
Training Data ◽  
Audio Classification ◽  
Image Domain ◽  
Full Dataset ◽  
Audio Data

Including unlabeled data in the training process of neural networks using Semi-Supervised Learning (SSL) has shown impressive results in the image domain, where state-of-the-art results were obtained with only a fraction of the labeled data. The commonality between recent SSL methods is that they strongly rely on the augmentation of unannotated data. This is vastly unexplored for audio data. In this work, SSL using the state-of-the-art FixMatch approach is evaluated on three audio classification tasks, including music, industrial sounds, and acoustic scenes. The performance of FixMatch is compared to Convolutional Neural Networks (CNN) trained from scratch, Transfer Learning, and SSL using the Mean Teacher approach. Additionally, a simple yet effective approach for selecting suitable augmentation methods for FixMatch is introduced. FixMatch with the proposed modifications always outperformed Mean Teacher and the CNNs trained from scratch. For the industrial sounds and music datasets, the CNN baseline performance using the full dataset was reached with less than 5% of the initial training data, demonstrating the potential of recent SSL methods for audio data. Transfer Learning outperformed FixMatch only for the most challenging dataset from acoustic scene classification, showing that there is still room for improvement.

scholarly journals Deep Learning-Based Differentiation between Mucinous Cystic Neoplasm and Serous Cystic Neoplasm in the Pancreas Using Endoscopic Ultrasonography

Diagnostics ◽  
2021 ◽  
Vol 11 (6) ◽  
pp. 1052
Author(s):  
Leang Sim Nguon ◽  
Kangwon Seo ◽  
Jung-Hyun Lim ◽  
Tae-Jun Song ◽  
Sung-Hyun Cho ◽  
...  
Keyword(s):  
Decision Making ◽  
Deep Learning ◽  
Network Model ◽  
Endoscopic Ultrasonography ◽  
Data Augmentation ◽  
Clinical Information ◽  
Training Data ◽  
Fine Tuning ◽  
Cystic Neoplasm ◽  
Cystic Neoplasms

Mucinous cystic neoplasms (MCN) and serous cystic neoplasms (SCN) account for a large portion of solitary pancreatic cystic neoplasms (PCN). In this study we implemented a convolutional neural network (CNN) model using ResNet50 to differentiate between MCN and SCN. The training data were collected retrospectively from 59 MCN and 49 SCN patients from two different hospitals. Data augmentation was used to enhance the size and quality of training datasets. Fine-tuning training approaches were utilized by adopting the pre-trained model from transfer learning while training selected layers. Testing of the network was conducted by varying the endoscopic ultrasonography (EUS) image sizes and positions to evaluate the network performance for differentiation. The proposed network model achieved up to 82.75% accuracy and a 0.88 (95% CI: 0.817–0.930) area under curve (AUC) score. The performance of the implemented deep learning networks in decision-making using only EUS images is comparable to that of traditional manual decision-making using EUS images along with supporting clinical information. Gradient-weighted class activation mapping (Grad-CAM) confirmed that the network model learned the features from the cyst region accurately. This study proves the feasibility of diagnosing MCN and SCN using a deep learning network model. Further improvement using more datasets is needed.

scholarly journals Janus-faced EPHB4-associated disorders: novel pathogenic variants and unreported intrafamilial overlapping phenotypes

2021 ◽  
Author(s):  
Silvia Martin-Almedina ◽  
Kazim Ogmen ◽  
Ege Sackey ◽  
Dionysios Grigoriadis ◽  
Christina Karapouliou ◽  
...  
Keyword(s):  
Subcellular Localization ◽  
Fetal Hydrops ◽  
Clinical Phenotypes ◽  
Functional Studies ◽  
Pathogenic Variants ◽  
Disease Mechanisms ◽  
Novel Variants ◽  
Uncertain Significance ◽  
Clinical Phenotyping

Abstract Purpose Several clinical phenotypes including fetal hydrops, central conducting lymphatic anomaly or capillary malformations with arteriovenous malformations 2 (CM-AVM2) have been associated with EPHB4 (Ephrin type B receptor 4) variants, demanding new approaches for deciphering pathogenesis of novel variants of uncertain significance (VUS) identified in EPHB4, and for the identification of differentiated disease mechanisms at the molecular level. Methods Ten index cases with various phenotypes, either fetal hydrops, CM-AVM2, or peripheral lower limb lymphedema, whose distinct clinical phenotypes are described in detail in this study, presented with a variant in EPHB4. In vitro functional studies were performed to confirm pathogenicity. Results Pathogenicity was demonstrated for six of the seven novel EPHB4 VUS investigated. A heterogeneity of molecular disease mechanisms was identified, from loss of protein production or aberrant subcellular localization to total reduction of the phosphorylation capability of the receptor. There was some phenotype–genotype correlation; however, previously unreported intrafamilial overlapping phenotypes such as lymphatic-related fetal hydrops (LRFH) and CM-AVM2 in the same family were observed. Conclusion This study highlights the usefulness of protein expression and subcellular localization studies to predict EPHB4 variant pathogenesis. Our accurate clinical phenotyping expands our interpretation of the Janus-faced spectrum of EPHB4-related disorders, introducing the discovery of cases with overlapping phenotypes.

scholarly journals Cyber-Physical Systems Improving Building Energy Management: Digital Twin and Artificial Intelligence

Energies ◽  
2021 ◽  
Vol 14 (8) ◽  
pp. 2338
Author(s):  
Sofia Agostinelli ◽  
Fabrizio Cumo ◽  
Giambattista Guidi ◽  
Claudio Tomazzoli
Keyword(s):  
Artificial Intelligence ◽  
Renewable Energy ◽  
Energy Management ◽  
Three Dimensional ◽  
Cost Effective ◽  
Automation System ◽  
Climate Conditions ◽  
Digital Twin ◽  
Building Energy Management ◽  
Computing Paradigm

The research explores the potential of digital-twin-based methods and approaches aimed at achieving an intelligent optimization and automation system for energy management of a residential district through the use of three-dimensional data model integrated with Internet of Things, artificial intelligence and machine learning. The case study is focused on Rinascimento III in Rome, an area consisting of 16 eight-floor buildings with 216 apartment units powered by 70% of self-renewable energy. The combined use of integrated dynamic analysis algorithms has allowed the evaluation of different scenarios of energy efficiency intervention aimed at achieving a virtuous energy management of the complex, keeping the actual internal comfort and climate conditions. Meanwhile, the objective is also to plan and deploy a cost-effective IT (information technology) infrastructure able to provide reliable data using edge-computing paradigm. Therefore, the developed methodology led to the evaluation of the effectiveness and efficiency of integrative systems for renewable energy production from solar energy necessary to raise the threshold of self-produced energy, meeting the nZEB (near zero energy buildings) requirements.

scholarly journals Artificial Intelligence, 3D Documentation, and Rock Art—Approaching and Reflecting on the Automation of Identification and Classification of Rock Art Images

2021 ◽  
Author(s):  
Christian Horn ◽  
Oscar Ivarsson ◽  
Cecilia Lindhé ◽  
Rich Potter ◽  
Ashely Green ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Bronze Age ◽  
Data Augmentation ◽  
Rock Art ◽  
Training Data ◽  
Future Research ◽  
Rock Surface ◽  
Southern Scandinavia ◽  
Bounding Boxes

AbstractRock art carvings, which are best described as petroglyphs, were produced by removing parts of the rock surface to create a negative relief. This tradition was particularly strong during the Nordic Bronze Age (1700–550 BC) in southern Scandinavia with over 20,000 boats and thousands of humans, animals, wagons, etc. This vivid and highly engaging material provides quantitative data of high potential to understand Bronze Age social structures and ideologies. The ability to provide the technically best possible documentation and to automate identification and classification of images would help to take full advantage of the research potential of petroglyphs in southern Scandinavia and elsewhere. We, therefore, attempted to train a model that locates and classifies image objects using faster region-based convolutional neural network (Faster-RCNN) based on data produced by a novel method to improve visualizing the content of 3D documentations. A newly created layer of 3D rock art documentation provides the best data currently available and has reduced inscribed bias compared to older methods. Several models were trained based on input images annotated with bounding boxes produced with different parameters to find the best solution. The data included 4305 individual images in 408 scans of rock art sites. To enhance the models and enrich the training data, we used data augmentation and transfer learning. The successful models perform exceptionally well on boats and circles, as well as with human figures and wheels. This work was an interdisciplinary undertaking which led to important reflections about archaeology, digital humanities, and artificial intelligence. The reflections and the success represented by the trained models open novel avenues for future research on rock art.

scholarly journals An Artificial-Intelligence-Discovered Functional Ingredient, NRT_N0G5IJ, Derived from Pisum sativum, Decreases HbA1c in a Prediabetic Population

Nutrients ◽  
2021 ◽  
Vol 13 (5) ◽  
pp. 1635
Author(s):  
Sweeny Chauhan ◽  
Alish Kerr ◽  
Brian Keogh ◽  
Stephanie Nolan ◽  
Rory Casey ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Pisum Sativum ◽  
Cost Effective ◽  
Glycated Haemoglobin ◽  
Glucose Regulation ◽  
Functional Ingredient ◽  
Effective Manner ◽  
Human Skeletal Muscle Cells ◽  
Increased Risk

The prevalence of prediabetes is rapidly increasing, and this can lead to an increased risk for individuals to develop type 2 diabetes and associated diseases. Therefore, it is necessary to develop nutritional strategies to maintain healthy glucose levels and prevent glucose metabolism dysregulation in the general population. Functional ingredients offer great potential for the prevention of various health conditions, including blood glucose regulation, in a cost-effective manner. Using an artificial intelligence (AI) approach, a functional ingredient, NRT_N0G5IJ, was predicted and produced from Pisum sativum (pea) protein by hydrolysis and then validated. Treatment of human skeletal muscle cells with NRT_N0G5IJ significantly increased glucose uptake, indicating efficacy of this ingredient in vitro. When db/db diabetic mice were treated with NRT_N0G5IJ, we observed a significant reduction in glycated haemoglobin (HbA1c) levels and a concomitant benefit on fasting glucose. A pilot double-blinded, placebo controlled human trial in a population of healthy individuals with elevated HbA1c (5.6% to 6.4%) showed that HbA1c percentage was significantly reduced when NRT_N0G5IJ was supplemented in the diet over a 12-week period. Here, we provide evidence of an AI approach to discovery and demonstrate that a functional ingredient identified using this technology could be used as a supplement to maintain healthy glucose regulation.

Prediction Models for Truck Accidents at Freeway Ramps in Washington State Using Regression and Artificial Intelligence Techniques

1998 ◽  
Vol 1635 (1) ◽  
pp. 30-36 ◽  
Author(s):  
Wael H. Awad ◽  
Bruce N. Janson
Keyword(s):  
Artificial Intelligence ◽  
Neural Networks ◽  
Linear Regression ◽  
Prediction Models ◽  
Washington State ◽  
Training Data ◽  
Coefficient Of Determination ◽  
Training Process ◽  
Truck Accidents ◽  
High Level

Three different modeling approaches were applied to explain truck accidents at interchanges in Washington State during a 27-month period. Three models were developed for each ramp type including linear regression, neural networks, and a hybrid system using fuzzy logic and neural networks. The study showed that linear regression was able to predict accident frequencies that fell within one standard deviation from the overall mean of the dependent variable. However, the coefficient of determination was very low in all cases. The other two artificial intelligence (AI) approaches showed a high level of performance in identifying different patterns of accidents in the training data and presented a better fit when compared to the regression model. However, the ability of these AI models to predict test data that were not included in the training process showed unsatisfactory results.

Sign in / Sign up

Export Citation Format

Share Document