Abstract

The last two decades have witnessed unprecedented advancements in computational techniques and artificial intelligence. These new developments will greatly impact biological data analyses for the health care system. The availability of large scale, high-throughput, biomedical data sets offers fertile ground for the application of AI-based techniques to extract valuable information that can be harnessed in the diagnosis and treatment of disease. This chapter provides a comprehensive review of the computational tools and online resources for the high-throughput analysis of biomedical data. It focuses on single-cell RNA sequencing data, multi-omics data integration, AI drug design, medical imaging data analysis, and the IoT. After providing a brief overview of fundamental biological terms, we describe a variety of research problems in the health care system and how high-throughput data can help. Next, we provide an in depth overview of machine learning techniques in computing and learning methods that can be used in sequencing data analyses (including profiles of traditional mass sequencing, single-cell data, interaction data, line-cell drugs, and medical imaging data). Finally, applications of IoT methods are discussed for biomedical research in detail. In conclusion, the review delineates the overall scope of AI-based computational techniques in biomedical research.

Abstract

A total of 2835 overseas patients from 55 countries received cancer treatment in two hospitals in Delhi, India between November 2013 and April 2019. Of these, 937 patients participated in a 30-point questionnaire on patient reported outcomes. The questionnaire included clinical information, difficulties, expenditure, financial toxicity (FT), education, profession/earning, family/emotional issues, and the reason for the choice of Delhi.

Abstract

RNAs are the major regulators of gene expression, and their secondary structures play crucial roles at different levels. RiboSNitches are disease-associated SNPs that cause changes in the pre-mRNA secondary structural ensemble. Several riboSNitches have been detected in the 5′ and 3′ untranslated regions and lncRNA. Although cases of secondary structural elements playing a regulatory role in alternative splicing are known, regions specific to splicing events, such as splice junctions have not received much attention. We tested splice-site mutations for their efficiency in disrupting the secondary structure and hypothesized that these could play a crucial role in alternative splicing. Multiple riboSNitch prediction methods were applied to obtain overlapping results that are potentially more reliable. Putative riboSNitches were identified from aberrant 5′ and 3′ splice site mutations, cancer-causing somatic mutations, and genes that harbor the regulatory RNA secondary structural elements. Our workflow for predicting riboSNitches associated with alternative splicing is novel and paves the way for subsequent experimental validation.

Abstract

Nucleocytoplasmic shuttling of viral elements, supported by several host factors, is essential for the replication of the human immunodeficiency virus (HIV). HIV-1 uses a nuclear RNA export pathway mediated by viral protein Rev to transport its Rev response element (RRE)-containing partially spliced and unspliced transcripts aided by the host nuclear RNA export protein CRM1. The factor(s) interacting with the CRM1-Rev complex are potential antiretroviral target(s) and could serve as a retroviral model system to study nuclear export machinery adapted by these viruses. We earlier reported that cellular Staufen-2 interacts with Rev, facilitating viral-RNA export. Here, we identified the formation of a complex between Staufen-2, CRM1 and Rev. Molecular docking and simulations mapped the interacting residues in the RNA-binding Domain 4 of Staufen-2 as R336 and R337, which were experimentally verified to be critical for interactions among Staufen-2, CRM1 and Rev by mutational analysis. Staufen-2 mutants defective in interaction with CRM1 or Rev failed to supplement the Rev-RNA export activity and viral production, demonstrating the importance of these interactions. Rev-dependent reporter assays and proviral DNA-construct transfection-based studies in Staufen-2 knockout cells in the presence of leptomycin-B (LMB) revealed a significant reduction in CRM1-mediated Rev-dependent RNA export with decreased virus production as compared to Staufen-2 knockout background or LMB treatment alone, suggesting the relevance of these interactions in augmenting RNA export activity of Rev. Our observations provide further insights into the mechanistic intricacies of unspliced viral-RNA export to the cytoplasm and support the notion that abrogating such interactions can reduce HIV-1 proliferation.

Abstract

The present report compares the antibacterial properties of unique (sphere+rod)-shaped gold nanostar with its structural components, i.e., gold nanorods and nanosphere. Gold nanostars, nanorods, and nanospheres have been synthesized using literature reported protocols. Clinical isolates of gram-negative E. coli and gram-positive S. aureus bacteria have been used as model pathogens for the antibacterial studies. The antibacterial activities of the nanoparticles have been assessed using various techniques. To compare the antimicrobial activity of the nanoparticles, we have investigated the effects of varying gold concentrations of different nanoparticles on bacterial growth kinetics. The impacts of the leached/residual gold ions and the surface capping agent and charge of the particles on the antibacterial activity have also been assessed. Studies of the nanoparticle’s dose and exposure time show the highest antibacterial activity for nanostars and lowest for nanospheres for a given quantity of gold. Bradford’s Reagent Assay and confocal fluorescent microscopy studies confirm the trend of the particle-specific antibacterial activities. SEM/TEM and DNA extraction studies show that the bactericidal activities involve a combination of effects like the destruction of cell membrane, fragmentation of bacterial DNA, internalization of particles, etc. To assess the antibacterial impacts of the amount of leached/residual gold ions, their concentrations have been determined by inductively coupled plasma - optical emission (ICP-OES) and mass (ICP-MS) spectroscopic studies as well as the effects of the added gold ions have been studied. No discernible effects have been observed due to the variation in the leached/residual gold ions amount. The DCHF-DA fluorescence assay has been employed to determine the levels of reactive oxygen species (ROS) produced by different nanoparticle systems, which corresponds to the trend in antibacterial activities observed. The nature and magnitude of the surface charge have been determined by zeta potential measurements. Analyses of the impacts of various parameters/factors like gold ions, capping agents, surface charges, ROS levels, etc., show that the antibacterial activities of the gold nanoparticles of different morphology arise from both morphology-specific physical and chemical effects of the gold nanoparticles.

Abstract

With the increase in user-generated content on social media networks, hate speech and offensive language content are also increasing. From the perspective of computer science, automatic detection of such hate speech and offensive language content is an interesting problem to solve. The natural language community has taken a step to identify such content via automated hate speech and offensive content detection. The hate speech content is generated mostly on social media, and automatic hate speech and offensive language detection face many challenges due to non-standard spelling and grammar variations. Specifically, in a multilingual community, the hate content would be in code-mixed form, making the task further challenging. In this article, we propose a model for code-mixed hate speech detection. This model embeds the knowledge from both user-trained and multilingual pre-trained models. The proposed method also calculates the profanity word list and augments it. Experimental results on code-mixed hate speech and offensive language detection benchmarks show that our method outperforms the existing baselines.

Abstract

Conventional Automatic Speech Recognition (ASR) systems are susceptible to dialect variations within a language, thereby adversely affecting the ASR. Therefore, the current practice is to use dialect-specific ASRs. However, dialectspecific information or data is hard to obtain making it difficult to build dialect-specific ASRs. Furthermore, it is cumbersome to maintain multiple dialect-specific ASR systems for each language. We build a unified multi-dialect End-to-End ASR that removes the need for a dialect recognition block and the need to maintain multiple dialect-specific ASRs for three Telugu regional dialects: Telangana, Coastal Andhra, and Rayalaseema. We find that pooling the data and training a multi-dialect ASR benefits the low-resource dialect the most – an improvement of over 9.71% in relative Word Error Rate (WER). Subsequently, we experiment with multi-task ASRs where the primary task is to transcribe the audio and the secondary task is to predict the dialect. We do this by adding a Dialect ID to the output targets. Such a model outperforms naive multi-dialect ASRs by up to 8.24% in relative WER. Additionally, we test this model on a dialect recognition task and find that it outperforms strong baselines by 6.14% in accuracy. Index Terms: multi-dialect, speech recognition, sequence-tosequence, dialect recognition

Abstract

Parkinson’s disease (PD) is a speech disorder caused by the effect of neurological damage on motor control activity of speech production. Due to the noninvasive nature, detection of PD from the speech is remarkable. This study proposes the use of Long-Term Average Spectral (LTAS) feature to detect PD from speech using different filterbank techniques and classifiers on the PC-GITA dataset. The fact that PD can be perceived from long-temporal information has motivated us to explore the LTAS features for PD detection. Performance of LTAS features is compared to baseline features, namely statistical and openSMILE features (ComParE, GeMAPS, and eGeMAPS). The performance of these features is validated using five different classifiers. The LTAS features, which are obtained with auditory filterbanks (Constant Q Transform and Gammatone), showed better performance as compared to the statistical features (MFCC_Stat and LPCC_Stat) and openSMILE features (ComParE, GeMAPS, and eGeMAPS). The combination of the Gammatone-based LTAS feature with eGeMAPS further improved the detection accuracy of the PD detection system on the PC-GITA database.

Abstract

Coherence is an important aspect of text quality and is crucial for ensuring its readability. It is essential for outputs from text generation systems like summarization, question answering, machine translation, question generation, table-to-text, etc. An automated coherence scoring model is also helpful in essay scoring or providing writing feedback. A large body of previous work has leveraged entity-based methods, syntactic patterns, discourse relations, and traditional deep learning architectures for text coherence assessment. However, these approaches do not consider factual information present in the documents. The transitions of facts associated with entities across sentences could help capture the essence of textual coherence better. We hypothesize that coherence assessment is a cognitively complex task that requires deeper fact-aware models and can benefit from other related tasks. In this work, we propose a novel deep learning model that fuses document-level information with factual information to improve coherence modeling. We further enhance the model efficacy by training it simultaneously with Natural Language Inference task in multi-task learning setting, taking advantage of inductive transfer between the two tasks. Our experiments with popular benchmark datasets across multiple domains demonstrate that the proposed model achieves state-of-the-art results on a synthetic coherence evaluation task and two real-world tasks involving prediction of varying degrees of coherence.

Abstract

Body shaming, a criticism based on the body’s shape, size, or appearance, has become a dangerous act on social media. With a rise in the reporting of body shaming experiences on the web, automated monitoring of body shaming posts will help rescue individuals, especially adolescents, from the emotional anguish they experience. To the best of our knowledge, this is the first work on body shaming detection, and we contribute the dataset in which the posts are tagged as body shaming or non-body shaming. We use transformer-based language models to detect body shaming posts. Further, we leverage unlabeled data in a semi-supervised manner using the GAN-BERT model, as it was developed for tasks where labeled data is scarce and unlabeled data is abundant. The findings of the experiments reveal that the algorithm learns valuable knowledge from the unlabeled dataset and outperforms many deep learning and conventional machine learning baselines.