Search

Despite impressive improvement in the next-generation sequencing technology, reliable detection of indels is still a difficult endeavour. Recognition of true indels is of prime importance in many applications, such as personalized health care, disease genomics and population genetics. Recently, advanced machine learning techniques have been successfully applied to classification problems with large-scale data. In this paper, we present SICaRiO, a gradient boosting classifier for the reliable detection of true indels, trained with the gold-standard dataset from 'Genome in a Bottle' (GIAB) consortium. Our filtering scheme significantly improves the performance of each variant calling pipeline used in GIAB and beyond. SICaRiO uses genomic features that can be computed from publicly available resources, i.e. it does not require sequencing pipeline-specific information (e.g. read depth). This study also sheds lights on prior genomic contexts responsible for the erroneous calling of indels made by sequencing pipelines. We have compared prediction difficulty for three categories of indels over different sequencing pipelines. We have also ranked genomic features according to their predictivity in determining false positives., (© The Author(s) 2020. Published by Oxford University Press. All rights reserved. For Permissions, please email: journals.permissions@oup.com.)

Background: The latest works on CRISPR genome editing tools mainly employs deep learning techniques. However, deep learning models lack explainability and they are harder to reproduce. We were motivated to build an accurate genome editing tool using sequence-based features and traditional machine learning that can compete with deep learning models., Results: In this paper, we present CRISPRpred(SEQ), a method for sgRNA on-target activity prediction that leverages only traditional machine learning techniques and hand-crafted features extracted from sgRNA sequences. We compare the results of CRISPRpred(SEQ) with that of DeepCRISPR, the current state-of-the-art, which uses a deep learning pipeline. Despite using only traditional machine learning methods, we have been able to beat DeepCRISPR for the three out of four cell lines in the benchmark dataset convincingly (2.174%, 6.905% and 8.119% improvement for the three cell lines)., Conclusion: CRISPRpred(SEQ) has been able to convincingly beat DeepCRISPR in 3 out of 4 cell lines. We believe that by exploring further, one can design better features only using the sgRNA sequences and can come up with a better method leveraging only traditional machine learning algorithms that can fully beat the deep learning models.

Raman spectroscopy provides a vibrational profile of the molecules and thus can be used to uniquely identify different kinds of materials. This sort of molecule fingerprinting has thus led to the widespread application of Raman spectrum in various fields like medical diagnosis, forensics, mineralogy, bacteriology, virology, etc. Despite the recent rise in Raman spectra data volume, there has not been any significant effort in developing generalized machine learning methods targeted toward Raman spectra analysis. We examine, experiment, and evaluate existing methods and conjecture that neither current sequential models nor traditional machine learning models are satisfactorily sufficient to analyze Raman spectra. Both have their perks and pitfalls; therefore, we attempt to mix the best of both worlds and propose a novel network architecture RamanNet. RamanNet is immune to the invariance property in convolutional neural networks (CNNs) and at the same time better than traditional machine learning models for the inclusion of sparse connectivity. This has been achieved by incorporating shifted multi-layer perceptrons (MLP) at the earlier levels of the network to extract significant features across the entire spectrum, which are further refined by the inclusion of triplet loss in the hidden layers. Our experiments on 4 public datasets demonstrate superior performance over the much more complex state-of-the-art methods, and thus, RamanNet has the potential to become the de facto standard in Raman spectra data analysis. [ABSTRACT FROM AUTHOR]

Customer churn is one of the most critical issues faced by the telecommunication industry (TCI). Researchers and analysts leverage customer relationship management (CRM) data through the use of various machine learning models and data transformation methods to identify the customers who are likely to churn. While several studies have been conducted in the customer churn prediction (CCP) context in TCI, a review of performance of the various models stemming from these studies show a clear room for improvement. Therefore, to improve the accuracy of customer churn prediction in the telecommunication industry, we have investigated several machine learning models, as well as, data transformation methods. To optimize the prediction models, feature selection has been performed using univariate technique and the best hyperparameters have been selected using the grid search method. Subsequently, experiments have been conducted on several publicly available TCI datasets to assess the performance of our models in terms of the widely used evaluation metrics, such as AUC, precision, recall, and F-measure. Through a rigorous experimental study, we have demonstrated the benefit of applying data transformation methods as well as feature selection while training an optimized CCP model. Our proposed technique improved the prediction performance by up to 26.2% and 17% in terms of AUC and F-measure, respectively. [ABSTRACT FROM AUTHOR]

Machine learning models have gained popularity nowadays for their potential to solve real-life issues when trained on pertinent data. In many cases, the real-life data are class imbalanced and hence the corresponding machine learning models trained on the data tend to perform poorly on metrics like precision, recall, AUC, F1, and G-mean score. Since class imbalance issue poses serious challenges to the performance of trained models, a multitude of research works have addressed this issue. Two common data-based sampling techniques have mostly been proposed-undersampling the data of the majority class and oversampling the data of the minority class. In this article, we focus on the former approach. We propose two novel algorithms that employ neural network-based approaches to remove majority samples that are found to reside in the vicinity of the minority samples, thereby undersampling the former to remove (or alleviate) the imbalance issue. We delineate the proposed algorithms and then test the proposed algorithms on some publicly available imbalanced datasets. We then compare the performance of our proposed algorithms to other popular undersampling algorithms. Finally, we conclude that our proposed algorithms outperform most of the existing undersampling approaches on most performance metrics. [ABSTRACT FROM AUTHOR]

Interpretation of the colossal number of genetic variants identified from sequencing applications is one of the major bottlenecks in clinical genetics, with the inference of the effect of amino acidsubstituting missense variations on protein structure and function being especially challenging. Here we characterize the threedimensional (3D) amino acid positions affected in pathogenic and population variants from 1,330 disease-associated genes using over 14,000 experimentally solved human protein structures. By measuring the statistical burden of variations (i.e., point mutations) from all genes on 40 3D protein features, accounting for the structural, chemical, and functional context of the variations' positions, we identify features that are generally associated with pathogenic and population missense variants. We then perform the same amino acid-level analysis individually for 24 protein functional classes, which reveals unique characteristics of the positions of the altered amino acids: We observe up to 46% divergence of the class-specific features from the general characteristics obtained by the analysis on all genes, which is consistent with the structural diversity of essential regions across different protein classes. We demonstrate that the function-specific 3D features of the variants match the readouts of mutagenesis experiments for BRCA1 and PTEN, and positively correlate with an independent set of clinically interpreted pathogenic and benign missense variants. Finally, we make our results available through a web server to foster accessibility and downstream research. Our findings represent a crucial step toward translational genetics, from highlighting the impact of mutations on protein structure to rationalizing the variants' pathogenicity in terms of the perturbed molecular mechanisms. [ABSTRACT FROM AUTHOR]

Highlights • We present an elegant feature engineering scheme by exploiting the characteristics of a ventricular fibrillation class ECG signal. • Subsequently, we apply machine learning techniques and develop and robust predictor called VFPred. • VFPred thus is a fusion of both signal processing and machine learning techniques. • We have conducted extensive experiments and according to the experimental results, VFPred outperforms the state of the art. Abstract Ventricular Fibrillation (VF), one of the most dangerous arrhythmias, is responsible for sudden cardiac arrests. Thus, various algorithms have been developed to predict VF from electrocardiogram (ECG), which is a binary classification problem. In the literature, we find a number of algorithms based on signal processing, where, after some robust mathematical operations the decision is given based on a predefined threshold over a single value. On the other hand, some machine learning based algorithms are also reported in the literature; however, these algorithms merely combine some parameters and make a prediction using those as features. Both the approaches have their perks and pitfalls; thus our motivation was to coalesce them to get the best out of the both worlds. Hence we have developed, VFPred that, in addition to employing a signal processing pipeline, namely, Empirical Mode Decomposition and Discrete Fourier Transform for useful feature extraction, uses a Support Vector Machine for efficient classification. VFPred turns out to be a robust algorithm as it is able to successfully segregate the two classes with equal confidence (sensitivity = 99.99%, specificity = 98.40%) even from a short signal of 5 s long, whereas existing works though requires longer signals, flourishes in one but fails in the other. [ABSTRACT FROM AUTHOR]

The CRISPR/Cas9-sgRNA system has recently become a popular tool for genome editing and a very hot topic in the field of medical research. In this system, Cas9 protein is directed to a desired location for gene engineering and cleaves target DNA sequence which is complementary to a 20-nucleotide guide sequence found within the sgRNA. A lot of experimental efforts, ranging from in vivo selection to in silico modeling, have been made for efficient designing of sgRNAs in CRISPR/Cas9 system. In this article, we present a novel tool, called CRISPRpred, for efficient in silico prediction of sgRNAs on-target activity which is based on the applications of Support Vector Machine (SVM) model. To conduct experiments, we have used a benchmark dataset of 17 genes and 5310 guide sequences where there are only 20% true values. CRISPRpred achieves Area Under Receiver Operating Characteristics Curve (AUROC-Curve), Area Under Precision Recall Curve (AUPR-Curve) and maximum Matthews Correlation Coefficient (MCC) as 0.85, 0.56 and 0.48, respectively. Our tool shows approximately 5% improvement in AUPR-Curve and after analyzing all evaluation metrics, we find that CRISPRpred is better than the current state-of-the-art. CRISPRpred is enough flexible to extract relevant features and use them in a learning algorithm. The source code of our entire software with relevant dataset can be found in the following link: . [ABSTRACT FROM AUTHOR]

• Proposed dataset is one of the largest in blood cell segmentation domain. • Learning based algorithm outperforms non-learning based methods in both qualitative and quantitative aspect. • Although Otsu's method demonstrated competitive results in blood segmentation, but it failed to segment low contrast images. With the recent developments in deep learning, automatic cell segmentation from images of microscopic examination slides seems to be a solved problem as recent methods have achieved comparable results on existing benchmark datasets. However, most of the existing cell segmentation benchmark datasets either contain a single cell type, few instances of the cells, not publicly available. Therefore, it is unclear whether the performance improvements can generalize on more diverse datasets. In this paper, we present a large and diverse cell segmentation dataset BBBC041Seg 1 1 https://github.com/Deponker/Blood-cell-segmentation-dataset , which consists both of uninfected cells (i.e., red blood cells/RBCs, leukocytes) and infected cells (i.e., gametocytes, rings, trophozoites, and schizonts). Additionally, all cell types do not have equal instances, which encourages researchers to develop algorithms for learning from imbalanced classes in a few shot learning paradigm. Furthermore, we conduct a comparative study using both classical rule-based and recent deep learning state-of-the-art (SOTA) methods for automatic cell segmentation and provide them as strong baselines. We believe the introduction of BBBC041Seg will promote future research towards clinically applicable cell segmentation methods from microscopic examinations, which can be later used for downstream tasks such as detecting hematological diseases (i.e., malaria). [ABSTRACT FROM AUTHOR]

Obesity is an emerging public health problem in the Western world as well as in the Gulf region. Qatar, a tiny wealthy county, is among the top-ranked obese countries with a high obesity rate among its population. Compared to Qatar's severity of this health crisis, only a limited number of studies focused on the systematic identification of potential risk factors using multimodal datasets. This study aims to develop machine learning (ML) models to distinguish healthy from obese individuals and reveal potential risk factors associated with obesity in Qatar. We designed a case-control study focused on 500 Qatari subjects, comprising 250 obese and 250 healthy individuals- the later forming the control group. We obtained the most extensive collection of clinical measurements for the Qatari population from the Qatar Biobank (QBB) repertoire, including (i) Physio-clinical Biomarkers, (ii) Spirometry, (iii) VICORDER, (iv) DXA scan composition, and (v) DXA scan densitometry readings. We developed several machine learning (ML) models to distinguish healthy from obese individuals and applied multiple feature selection techniques to identify potential risk factors associated with obesity. The proposed ML model achieved over 90% accuracy, thereby outperforming the existing state of the art models. The outcome from the ablation study on multimodal clinical datasets revealed physio-clinical measurements as the most influential risk factors in distinguishing healthy versus obese subjects. Furthermore, multiple feature ranking techniques confirmed known obesity risk factors (c-peptide, insulin, albumin, uric acid) and identified potential risk factors linked to obesity-related comorbidities such as diabetes (e.g., HbA1c, glucose), liver function (e.g., alkaline phosphatase, gamma-glutamyl transferase), lipid profile (e.g., triglyceride, low density lipoprotein cholesterol, high density lipoprotein cholesterol), etc. Most of the DXA measurements (e.g., bone area, bone mineral composition, bone mineral density, etc.) were significantly (p-value < 0.05) higher in the obese group. Overall, the net effect of hypothesized protective factors of obesity on bone mass seems to have surpassed the hypothesized harmful factors. All the identified factors warrant further investigation in a clinical setup to understand their role in obesity. [ABSTRACT FROM AUTHOR]

At present, cryptocurrencies have become a global phenomenon in financial sectors, as it is one of the most traded financial instruments worldwide. Cryptocurrency is not only one of the most complicated and abstruse fields among financial instruments but also deemed as a perplexing problem in finance due to its high volatility. This work makes an attempt to apply machine learning techniques on the index and constituents of cryptocurrency with a goal to predict and forecast prices thereof. In particular, the purpose of this article is to predict and forecast the close (closing) price of the cryptocurrency index 30 and nine constituents of cryptocurrencies using machine learning algorithms and models so that it becomes easier for people to trade these currencies. We have used several machine learning techniques and algorithms and compared the models with each other to get the best output. We believe that our work will help reduce the challenges and difficulties faced by people who invest in cryptocurrencies. Moreover, the obtained results can play a major role in cryptocurrency portfolio management and in observing the fluctuations in the prices of constituents of cryptocurrency market. We have also compared our approach with similar state of the art works from the literature, where machine learning approaches have been considered for predicting and forecasting the prices of these currencies. In the sequel, we have found that our best approach presents better and competitive results (especially by using ensemble learning method) than the best works from the literature thereby advancing the state of the art. Using such prediction and forecasting methods, people can easily understand the trend and it would be even easier for them to trade in a difficult and challenging financial instrument like cryptocurrency. [ABSTRACT FROM AUTHOR]

• Understanding the characteristics of spatiotemporal clustering of the COVID-19 epidemic and R0 is critical in effectively preventing and controlling the pandemic. • Temperature profile played a significant role in the spatiotemporal clustering of the COVID-19 epidemic in China • The increase in temperature increases the R0 value • Temperatures had more contribution towards the transmission of COVID-19 than population age in China. The COVID-19 epidemic spread rapidly through China and subsequently proliferated globally leading to a pandemic situation around the globe. Human-to-human transmission, as well as asymptomatic transmission of the infection, have been confirmed. As of April 03, 2020, public health crisis in China due to COVID-19 was potentially under control. We compiled a daily dataset of case counts, mortality, recovery, temperature, population density, and demographic information for each prefecture during the period of January 11 to April 07, 2020. Understanding the characteristics of spatial clustering of the COVID-19 epidemic and R 0 is critical in effectively preventing and controlling the ongoing global pandemic. Considering this, the prefectures were grouped based on several relevant features using unsupervised machine learning techniques. Subsequently, we performed a computational analysis utilizing the reported cases in China to estimate the revised R 0 among different regions. Finally, our overall research indicates that the impact of temperature and demographic factors on virus transmission may be characterized using a stochastic transmission model. Such predictions will help in prevention planning in an ongoing global pandemic, prioritizing segments of a given community/region for action and providing a visual aid in designing prevention strategies for a specific geographic region. Furthermore, revised estimation and our methodology will aid in improving the human health consequences of COVID-19 elsewhere. [ABSTRACT FROM AUTHOR]