Bon-EV: an improved multiple testing procedure for controlling false discovery rates

Prediction of aptamer affinity using an artificial intelligence approach

Aptamers are oligonucleotide sequences that can connect to particular target molecules, similar to monoclonal antibodies. They can be chosen by systematic evolution of ligands by exponential enrichment (SELEX), and are modifiable and can be synthesized. Even if the SELEX approach has been improved a lot, it is frequently challenging and time-consuming to identify aptamers experimentally. In particular, structure-based methods are the most used in computer-aided design and development of aptamers. For this purpose, numerous web-based platforms have been suggested for the purpose of forecasting the secondary structure and 3D configurations of RNAs and DNAs. Also, molecular docking and molecular dynamics (MD), which are commonly utilized in protein compound selection by structural information, are suitable for aptamer selection. On the other hand, from a large number of sequences, artificial intelligence (AI) may be able to quickly discover the possible aptamer candidates. Conversely, sophisticated machine and deep-learning (DL) models have demonstrated efficacy in forecasting the binding properties between ligands and targets during drug discovery; as such, they may provide a reliable and precise method for forecasting the binding of aptamers to targets. This research looks at advancements in AI pipelines and strategies for aptamer binding ability prediction, such as machine and deep learning, as well as structure-based approaches, molecular dynamics and molecular docking simulation methods.

A joint entity Relation Extraction method for document level Traditional Chinese Medicine texts

Chinese medicine is a unique and complex medical system with complete and rich scientific theories. The textual data of Traditional Chinese Medicine (TCM) contains a large amount of relevant knowledge in the field of TCM, which can serve as guidance for accurate disease diagnosis as well as efficient disease prevention and treatment. Existing TCM texts are disorganized and lack a uniform standard. For this reason, this paper proposes a joint extraction framework by using graph convolutional networks to extract joint entity relations on document-level TCM texts to achieve TCM entity relation mining. More specifically, we first finetune the pre-trained language model by using the TCM domain knowledge to obtain the task-specific model. Taking the integrity of TCM into account, we extract the complete entities as well as the relations corresponding to diagnosis and treatment from the document-level medical cases by using multiple features such as word fusion coding, TCM lexicon information, and multi-relational graph convolutional networks. The experimental results show that the proposed method outperforms the state-of-the-art methods. It has an F1-score of 90.7% for Name Entity Recognization and 76.14% for Relation Extraction on the TCM dataset, which significantly improves the ability to extract entity relations from TCM texts. Code is available at https://github.com/xxxxwx/TCMERE.

Unraveling the complexities of drought stress in cotton: a multifaceted analysis of selection criteria and breeding approaches

Abiotic stress tolerance breeding programs present a spectrum of perspectives, yet definitive solutions remain elusive, with each approach carrying its own set of advantages and disadvantages. This study systematically evaluates extant methodologies, comparing plant performance across varied genotypes and selection traits under optimal and stress conditions. The objective is to elucidate prevailing ambiguities. Ten homozygous lines (F8 generation) were assessed using a randomized block design alongside five control varieties, with four replicates cultivated under well-watered and deficit water conditions. It is noteworthy that six of the ten homozygous lines were cultivated exclusively under well-watered conditions (F3 to F7), while four lines experienced deficit water conditions (F3 to F7). All five control varieties underwent cultivation under both conditions. These findings underscore the necessity for tailored breeding programs attuned to specific environmental exigencies, recognizing that individual traits manifest divergent responses to varying conditions. It is evident that certain traits exhibit marked disparities under well-watered conditions, while others evince heightened differentiation under water deficit conditions. Significantly, our analysis reveals a pronounced interaction between irrigation regimes and selection traits, which serves to underscore the nuanced interplay between genotype and environmental stress.

Learning peptide properties with positive examples only

Deep learning can create accurate predictive models by exploiting existing large-scale experimental data, and guide the design of molecules. However, a major barrier is the requirement of both positive and negative examples in the classical supervised learning frameworks. Notably, most peptide databases come with missing information and low number of observations on negative examples, as such sequences are hard to obtain using high-throughput screening methods. To address this challenge, we solely exploit the limited known positive examples in a semi-supervised setting, and discover peptide sequences that are likely to map to certain antimicrobial properties via positive-unlabeled learning (PU). In particular, we use the two learning strategies of adapting base classifier and reliable negative identification to build deep learning models for inferring solubility, hemolysis, binding against SHP-2, and non-fouling activity of peptides, given their sequence. We evaluate the predictive performance of our PU learning method and show that by only using the positive data, it can achieve competitive performance when compared with the classical positive-negative (PN) classification approach, where there is access to both positive and negative examples.

Energy optimization for wireless sensor network using minimum redundancy maximum relevance feature selection and classification techniques

In wireless sensor networks (WSN), conserving energy is usually a basic issue, and several approaches are applied to optimize energy consumption. In this article, we adopt feature selection approaches by using minimum redundancy maximum relevance (MRMR) as a feature selection technique to minimize the number of sensors thereby conserving energy. MRMR ranks the sensors according to their significance. The selected features are then classified by different types of classifiers; SVM with linear kernel classifier, naïve Bayes classifier, and k-nearest neighbors classifier (KNN) to compare accuracy values. The simulation results illustrated an improvement in the lifetime extension factor of sensors and showed that the KNN classifier gives better results than the naïve Bayes and SVM classifier.

Assessment of Genomic and Metabolic Characteristics of Cholesterol-Reducing and GABA Producer Limosilactobacillus fermentum AGA52 Isolated from Lactic Acid Fermented Shalgam Based on "In Silico" and "In Vitro" Approaches

This study aimed to characterize the genomic and metabolic properties of a novel Lb. fermentum strain AGA52 which was isolated from a lactic acid fermented beverage called "shalgam." The genome size of AGA52 was 2,001,184 bp, which is predicted to carry 2024 genes, including 50 tRNAs, 3 rRNAs, 3 ncRNAs, 15 CRISPR repeats, 14 CRISPR spacers, and 1 CRISPR array. The genome has a GC content of 51.82% including 95 predicted pseudogenes, 56 complete or partial transposases, and 2 intact prophages. The similarity of the clusters of orthologous groups (COG) was analyzed by comparison with the other Lb. fermentum strains. The detected resistome on the genome of AGA52 was found to be intrinsic originated. Besides, it has been determined that AGA52 has an obligate heterofermentative carbohydrate metabolism due to the absence of the 1-phosphofructokinase (pfK) enzyme. Furthermore, the strain is found to have a better antioxidant capacity and to be tolerant to gastrointestinal simulated conditions. It was also observed that the AGA52 has antimicrobial activity against Yersinia enterocolitica ATCC9610, Bacillus cereus ATCC33019, Salmonella enterica sv. Typhimurium, Escherichia coli O157:h7 ATCC43897, Listeria monocytogenes ATCC7644, Klebsiella pneumoniae ATCC13883, and Proteus vulgaris ATCC8427. Additionally, AGA52 exhibited 42.74 ± 4.82% adherence to HT29 cells. Cholesterol assimilation (33.9 ± 0.005%) and GABA production capacities were also confirmed by "in silico" and "in vitro." Overall, the investigation of genomic and metabolic features of the AGA52 revealed that is a potential psychobiotic and probiotic dietary supplement candidate and can bring functional benefits to the host.

Surveying biomedical relation extraction: a critical examination of current datasets and the proposal of a new resource

Natural language processing (NLP) has become an essential technique in various fields, offering a wide range of possibilities for analyzing data and developing diverse NLP tasks. In the biomedical domain, understanding the complex relationships between compounds and proteins is critical, especially in the context of signal transduction and biochemical pathways. Among these relationships, protein-protein interactions (PPIs) are of particular interest, given their potential to trigger a variety of biological reactions. To improve the ability to predict PPI events, we propose the protein event detection dataset (PEDD), which comprises 6823 abstracts, 39 488 sentences and 182 937 gene pairs. Our PEDD dataset has been utilized in the AI CUP Biomedical Paper Analysis competition, where systems are challenged to predict 12 different relation types. In this paper, we review the state-of-the-art relation extraction research and provide an overview of the PEDD's compilation process. Furthermore, we present the results of the PPI extraction competition and evaluate several language models' performances on the PEDD. This paper's outcomes will provide a valuable roadmap for future studies on protein event detection in NLP. By addressing this critical challenge, we hope to enable breakthroughs in drug discovery and enhance our understanding of the molecular mechanisms underlying various diseases.

Extracting adverse drug events from clinical Notes: A systematic review of approaches used

BACKGROUND

An adverse drug event (ADE) is any unfavorable effect that occurs due to the use of a drug. Extracting ADEs from unstructured clinical notes is essential to biomedical text extraction research because it helps with pharmacovigilance and patient medication studies.

OBJECTIVE

From the considerable amount of clinical narrative text, natural language processing (NLP) researchers have developed methods for extracting ADEs and their related attributes. This work presents a systematic review of current methods.

METHODOLOGY

Two biomedical databases have been searched from June 2022 until December 2023 for relevant publications regarding this review, namely the databases PubMed and Medline. Similarly, we searched the multi-disciplinary databases IEEE Xplore, Scopus, ScienceDirect, and the ACL Anthology. We adopted the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) 2020 statement guidelines and recommendations for reporting systematic reviews in conducting this review. Initially, we obtained 5,537 articles from the search results from the various databases between 2015 and 2023. Based on predefined inclusion and exclusion criteria for article selection, 100 publications have undergone full-text review, of which we consider 82 for our analysis.

RESULTS

We determined the general pattern for extracting ADEs from clinical notes, with named entity recognition (NER) and relation extraction (RE) being the dual tasks considered. Researchers that tackled both NER and RE simultaneously have approached ADE extraction as a "pipeline extraction" problem (n = 22), as a "joint task extraction" problem (n = 7), and as a "multi-task learning" problem (n = 6), while others have tackled only NER (n = 27) or RE (n = 20). We further grouped the reviews based on the approaches for data extraction, namely rule-based (n = 8), machine learning (n = 11), deep learning (n = 32), comparison of two or more approaches (n = 11), hybrid (n = 12) and large language models (n = 8). The most used datasets are MADE 1.0, TAC 2017 and n2c2 2018.

CONCLUSION

Extracting ADEs is crucial, especially for pharmacovigilance studies and patient medications. This survey showcases advances in ADE extraction research, approaches, datasets, and state-of-the-art performance in them. Challenges and future research directions are highlighted. We hope this review will guide researchers in gaining background knowledge and developing more innovative ways to address the challenges.

Protein embedding based alignment

PURPOSE

Despite the many progresses with alignment algorithms, aligning divergent protein sequences with less than 20-35% pairwise identity (so called "twilight zone") remains a difficult problem. Many alignment algorithms have been using substitution matrices since their creation in the 1970's to generate alignments, however, these matrices do not work well to score alignments within the twilight zone. We developed Protein Embedding based Alignments, or PEbA, to better align sequences with low pairwise identity. Similar to the traditional Smith-Waterman algorithm, PEbA uses a dynamic programming algorithm but the matching score of amino acids is based on the similarity of their embeddings from a protein language model.

METHODS

We tested PEbA on over twelve thousand benchmark pairwise alignments from BAliBASE, each one extracted from one of their multiple sequence alignments. Five different BAliBASE references were used, each with different sequence identities, motifs, and lengths, allowing PEbA to showcase how well it aligns under different circumstances.

RESULTS

PEbA greatly outperformed BLOSUM substitution matrix-based pairwise alignments, achieving different levels of improvements of the alignment quality for pairs of sequences with different levels of similarity (over four times as well for pairs of sequences with <10% identity). We also compared PEbA with embeddings generated by different protein language models (ProtT5 and ESM-2) and found that ProtT5-XL-U50 produced the most useful embeddings for aligning protein sequences. PEbA also outperformed DEDAL and vcMSA, two recently developed protein language model embedding-based alignment methods.

CONCLUSION

Our results suggested that general purpose protein language models provide useful contextual information for generating more accurate protein alignments than typically used methods.

Cracking the black box of deep sequence-based protein-protein interaction prediction

Identifying protein-protein interactions (PPIs) is crucial for deciphering biological pathways. Numerous prediction methods have been developed as cheap alternatives to biological experiments, reporting surprisingly high accuracy estimates. We systematically investigated how much reproducible deep learning models depend on data leakage, sequence similarities and node degree information, and compared them with basic machine learning models. We found that overlaps between training and test sets resulting from random splitting lead to strongly overestimated performances. In this setting, models learn solely from sequence similarities and node degrees. When data leakage is avoided by minimizing sequence similarities between training and test set, performances become random. Moreover, baseline models directly leveraging sequence similarity and network topology show good performances at a fraction of the computational cost. Thus, we advocate that any improvements should be reported relative to baseline methods in the future. Our findings suggest that predicting PPIs remains an unsolved task for proteins showing little sequence similarity to previously studied proteins, highlighting that further experimental research into the 'dark' protein interactome and better computational methods are needed.

BioEGRE: a linguistic topology enhanced method for biomedical relation extraction based on BioELECTRA and graph pointer neural network

BACKGROUND

Automatic and accurate extraction of diverse biomedical relations from literature is a crucial component of bio-medical text mining. Currently, stacking various classification networks on pre-trained language models to perform fine-tuning is a common framework to end-to-end solve the biomedical relation extraction (BioRE) problem. However, the sequence-based pre-trained language models underutilize the graphical topology of language to some extent. In addition, sequence-oriented deep neural networks have limitations in processing graphical features.

RESULTS

In this paper, we propose a novel method for sentence-level BioRE task, BioEGRE (BioELECTRA and Graph pointer neural net-work for Relation Extraction), aimed at leveraging the linguistic topological features. First, the biomedical literature is preprocessed to retain sentences involving pre-defined entity pairs. Secondly, SciSpaCy is employed to conduct dependency parsing; sentences are modeled as graphs based on the parsing results; BioELECTRA is utilized to generate token-level representations, which are modeled as attributes of nodes in the sentence graphs; a graph pointer neural network layer is employed to select the most relevant multi-hop neighbors to optimize representations; a fully-connected neural network layer is employed to generate the sentence-level representation. Finally, the Softmax function is employed to calculate the probabilities. Our proposed method is evaluated on three BioRE tasks: a multi-class (CHEMPROT) and two binary tasks (GAD and EU-ADR). The results show that our method achieves F1-scores of 79.97% (CHEMPROT), 83.31% (GAD), and 83.51% (EU-ADR), surpassing the performance of existing state-of-the-art models.

CONCLUSION

The experimental results on 3 biomedical benchmark datasets demonstrate the effectiveness and generalization of BioEGRE, which indicates that linguistic topology and a graph pointer neural network layer explicitly improve performance for BioRE tasks.

Effects of nanoscale zinc oxide treatment on growth, rhizosphere microbiota, and metabolism of Aconitum carmichaelii

Trace elements play a crucial role in the growth and bioactive substance content of medicinal plants, but their utilization efficiency in soil is often low. In this study, soil and Aconitum carmichaelii samples were collected and measured from 22 different locations, followed by an analysis of the relationship between trace elements and the yield and alkaloid content of the plants. The results indicated a significant positive correlation between zinc, trace elements in the soil, and the yield and alkaloid content of A. carmichaelii. Subsequent treatment of A. carmichaelii with both bulk zinc oxide (ZnO) and zinc oxide nanoparticles (ZnO NPs) demonstrated that the use of ZnO NPs significantly enhanced plant growth and monoester-type alkaloid content. To elucidate the underlying mechanisms responsible for these effects, metabolomic analysis was performed, resulting in the identification of 38 differentially expressed metabolites in eight metabolic pathways between the two treatments. Additionally, significant differences were observed in the rhizosphere bacterial communities, with Bacteroidota and Actinobacteriota identified as valuable biomarkers for ZnO NP treatment. Covariation analysis further revealed significant correlations between specific microbial communities and metabolite expression levels. These findings provide compelling evidence that nanoscale zinc exhibits much higher utilization efficiency compared to traditional zinc fertilizer.

Microglial Nogo delays recovery following traumatic brain injury in mice

Nogo-A, B, and C are well described members of the reticulon family of proteins, most well known for their negative regulatory effects on central nervous system (CNS) neurite outgrowth and repair following injury. Recent research indicates a relationship between Nogo-proteins and inflammation. Microglia, the brain's immune cells and inflammation-competent compartment, express Nogo protein, although specific roles of the Nogo in these cells is understudied. To examine inflammation-related effects of Nogo, we generated a microglial-specific inducible Nogo KO (MinoKO) mouse and challenged the mouse with a controlled cortical impact (CCI) traumatic brain injury (TBI). Histological analysis shows no difference in brain lesion sizes between MinoKO-CCI and Control-CCI mice, although MinoKO-CCI mice do not exhibit the levels of ipsilateral lateral ventricle enlargement as injury matched controls. Microglial Nogo-KO results in decreased lateral ventricle enlargement, microglial and astrocyte immunoreactivity, and increased microglial morphological complexity compared to injury matched controls, suggesting decreased tissue inflammation. Behaviorally, healthy MinoKO mice do not differ from control mice, but automated tracking of movement around the home cage and stereotypic behavior, such as grooming and eating (termed cage "activation"), following CCI is significantly elevated. Asymmetrical motor function, a deficit typical of unilaterally brain lesioned rodents, was not detected in CCI injured MinoKO mice, while the phenomenon was present in CCI injured controls 1-week post-injury. Overall, our studies show microglial Nogo as a negative regulator of recovery following brain injury. To date, this is the first evaluation of the roles microglial specific Nogo in a rodent injury model.

On the challenges of predicting treatment response in Hodgkin's Lymphoma using transcriptomic data

BACKGROUND

Despite the advancements in multiagent chemotherapy in the past years, up to 10% of Hodgkin's Lymphoma (HL) cases are refractory to treatment and, after remission, patients experience an elevated risk of death from all causes. These complications are dependent on the treatment and therefore an increase in the prognostic accuracy of HL can help improve these outcomes and control treatment-related toxicity. Due to the low incidence of this cancer, there is a lack of works comprehensively assessing the predictability of treatment response, especially by resorting to machine learning (ML) advances and high-throughput technologies.

METHODS

We present a methodology for predicting treatment response after two courses of Adriamycin, Bleomycin, Vinblastine and Dacarbazine (ABVD) chemotherapy, through the analysis of gene expression profiles using state-of-the-art ML algorithms. We work with expression levels of tumor samples of Classical Hodgkin's Lymphoma patients, obtained through the NanoString's nCounter platform. The presented approach combines dimensionality reduction procedures and hyperparameter optimization of various elected classifiers to retrieve reference predictability levels of refractory response to ABVD treatment using the regulatory profile of diagnostic tumor samples. In addition, we propose a data transformation procedure to map the original data space into a more discriminative one using biclustering, where features correspond to discriminative putative regulatory modules.

RESULTS

Through an ensemble of feature selection procedures, we identify a set of 14 genes highly representative of the result of an fuorodeoxyglucose Positron Emission Tomography (FDG-PET) after two courses of ABVD chemotherapy. The proposed methodology further presents an increased performance against reference levels, with the proposed space transformation yielding improvements in the majority of the tested predictive models (e.g. Decision Trees show an improvement of 20pp in both precision and recall).

CONCLUSIONS

Taken together, the results reveal improvements for predicting treatment response in HL disease by resorting to sophisticated statistical and ML principles. This work further consolidates the current hypothesis on the structural difficulty of this prognostic task, showing that there is still a considerable gap to be bridged for these technologies to reach the necessary maturity for clinical practice.

Rapid estimation of cortical neuron activation thresholds by transcranial magnetic stimulation using convolutional neural networks

BACKGROUND

Transcranial magnetic stimulation (TMS) can modulate neural activity by evoking action potentials in cortical neurons. TMS neural activation can be predicted by coupling subject-specific head models of the TMS-induced electric field (E-field) to populations of biophysically realistic neuron models; however, the significant computational cost associated with these models limits their utility and eventual translation to clinically relevant applications.

OBJECTIVE

To develop computationally efficient estimators of the activation thresholds of multi-compartmental cortical neuron models in response to TMS-induced E-field distributions.

METHODS

Multi-scale models combining anatomically accurate finite element method (FEM) simulations of the TMS E-field with layer-specific representations of cortical neurons were used to generate a large dataset of activation thresholds. 3D convolutional neural networks (CNNs) were trained on these data to predict thresholds of model neurons given their local E-field distribution. The CNN estimator was compared to an approach using the uniform E-field approximation to estimate thresholds in the non-uniform TMS-induced E-field.

RESULTS

The 3D CNNs estimated thresholds with mean absolute percent error (MAPE) on the test dataset below 2.5% and strong correlation between the CNN predicted and actual thresholds for all cell types (R2 > 0.96). The CNNs estimated thresholds with a 2-4 orders of magnitude reduction in the computational cost of the multi-compartmental neuron models. The CNNs were also trained to predict the median threshold of populations of neurons, speeding up computation further.

CONCLUSION

3D CNNs can estimate rapidly and accurately the TMS activation thresholds of biophysically realistic neuron models using sparse samples of the local E-field, enabling simulating responses of large neuron populations or parameter space exploration on a personal computer.

Effect of miR-4270 Suppression on Migration in Hepatocellular Carcinoma Cell Line (HepG2)

Background

Liver transplantation and surgical resection are two major strategies for treatment of hepatocellular carcinoma (HCC) patients. One approach to treating HCC is the suppression of metastasis to other tissues. Herein, we aimed to study the effect of miR-4270 inhibitor on migration of HepG2 cells as well as activity of matrix metalloproteinase (MMP) these cells in order to find a strategy to suppress metastasis in future.

Methods

HepG2 cells were treated with 0, 10, 20, 30, 40, 50, 60, 70, 80, and 90 nM of miR-4270 inhibitor, and then the cell viability was measured by trypan blue staining. Afterwards, cell migration and MMP activity of HepG2 cells were assessed by wound healing assay and zymography, respectively. The MMP gene expression was determined by real-time reverse transcription polymerase chain reaction.

Results

Results showed that miR-4270 inhibitor decreased the cell viability of HepG2 cells in a concentration-dependent manner. Also, inhibition of the miR-4270 reduced invasion, MMP activity, and expression of MMP genes in HepG2 cells, respectively.

Conclusion

Our findings suggest that miR-4270 inhibitor decreases in vitro migration, which could help find a new approach for HCC therapy patients.

MM-StackEns: A new deep multimodal stacked generalization approach for protein-protein interaction prediction

Accurate in-silico identification of protein-protein interactions (PPIs) is a long-standing problem in biology, with important implications in protein function prediction and drug design. Current computational approaches predominantly use a single data modality for describing protein pairs, which may not fully capture the characteristics relevant for identifying PPIs. Another limitation of existing methods is their poor generalization to proteins outside the training graph. In this paper, we aim to address these shortcomings by proposing a new ensemble approach for PPI prediction, which learns information from two modalities, corresponding to pairs of sequences and to the graph formed by the training proteins and their interactions. Our approach uses a siamese neural network to process sequence information, while graph attention networks are employed for the network view. For capturing the relationships between the proteins in a pair, we design a new feature fusion module, based on computing the distance between the distributions corresponding to the two proteins. The prediction is made using a stacked generalization procedure, in which the final classifier is represented by a Logistic Regression model trained on the scores predicted by the sequence and graph models. Additionally, we show that protein sequence embeddings obtained using pretrained language models can significantly improve the generalization of PPI methods. The experimental results demonstrate the good performance of our approach, which surpasses all the related work on two Yeast data sets, while outperforming the majority of literature approaches on two Human data sets and on independent multi-species data sets.

ChestX-Ray6: Prediction of multiple diseases including COVID-19 from chest X-ray images using convolutional neural network

In the last few decades, several epidemic diseases have been introduced. In some cases, doctors and medical physicians are facing difficulties in identifying these diseases correctly. A machine can perform some of these identification tasks more accurately than a human if it is trained correctly. With time, the number of medical data is increasing. A machine can analyze this medical data and extract knowledge from this data, which can help doctors and medical physicians. This study proposed a lightweight convolutional neural network (CNN) named ChestX-ray6 that automatically detects pneumonia, COVID19, cardiomegaly, lung opacity, and pleural from digital chest x-ray images. Here multiple databases have been combined, containing 9,514 chest x-ray images of normal and other five diseases. The lightweight ChestX-ray6 model achieved an accuracy of 80% for the detection of six diseases. The ChestX-ray6 model has been saved and used for binary classification of normal and pneumonia patients to reveal the model's generalization power. The pre-trained ChestX-ray6 model has achieved an accuracy and recall of 97.94% and 98% for binary classification, which outweighs the state-of-the-art (SOTA) models.

Tool and techniques study to plant microbiome current understanding and future needs: an overview

Microorganisms are present in the universe and they play role in beneficial and harmful to human life, society, and environments. Plant microbiome is a broad term in which microbes are present in the rhizo, phyllo, or endophytic region and play several beneficial and harmful roles with the plant. To know of these microorganisms, it is essential to be able to isolate purification and identify them quickly under laboratory conditions. So, to improve the microbial study, several tools and techniques such as microscopy, rRNA, or rDNA sequencing, fingerprinting, probing, clone libraries, chips, and metagenomics have been developed. The major benefits of these techniques are the identification of microbial community through direct analysis as well as it can apply in situ. Without tools and techniques, we cannot understand the roles of microbiomes. This review explains the tools and their roles in the understanding of microbiomes and their ecological diversity in environments.

Deep learning joint models for extracting entities and relations in biomedical: a survey and comparison

The rapid development of biomedicine has produced a large number of biomedical written materials. These unstructured text data create serious challenges for biomedical researchers to find information. Biomedical named entity recognition (BioNER) and biomedical relation extraction (BioRE) are the two most fundamental tasks of biomedical text mining. Accurately and efficiently identifying entities and extracting relations have become very important. Methods that perform two tasks separately are called pipeline models, and they have shortcomings such as insufficient interaction, low extraction quality and easy redundancy. To overcome the above shortcomings, many deep learning-based joint name entity recognition and relation extraction models have been proposed, and they have achieved advanced performance. This paper comprehensively summarize deep learning models for joint name entity recognition and relation extraction for biomedicine. The joint BioNER and BioRE models are discussed in the light of the challenges existing in the BioNER and BioRE tasks. Five joint BioNER and BioRE models and one pipeline model are selected for comparative experiments on four biomedical public datasets, and the experimental results are analyzed. Finally, we discuss the opportunities for future development of deep learning-based joint BioNER and BioRE models.

Systems biology approach reveals a common molecular basis for COVID-19 and non-alcoholic fatty liver disease (NAFLD)

Background

Patients with non-alcoholic fatty liver disease (NAFLD) may be more susceptible to coronavirus disease 2019 (COVID-19) and even more likely to suffer from severe COVID-19. Whether there is a common molecular pathological basis for COVID-19 and NAFLD remains to be identified. The present study aimed to elucidate the transcriptional alterations shared by COVID-19 and NAFLD and to identify potential compounds targeting both diseases.

Methods

Differentially expressed genes (DEGs) for COVID-19 and NAFLD were extracted from the GSE147507 and GSE89632 datasets, and common DEGs were identified using the Venn diagram. Subsequently, we constructed a protein–protein interaction (PPI) network based on the common DEGs and extracted hub genes. Then, we performed gene ontology (GO) and pathway analysis of common DEGs. In addition, transcription factors (TFs) and miRNAs regulatory networks were constructed, and drug candidates were identified.

Results

We identified a total of 62 common DEGs for COVID-19 and NAFLD. The 10 hub genes extracted based on the PPI network were IL6, IL1B, PTGS2, JUN, FOS, ATF3, SOCS3, CSF3, NFKB2, and HBEGF. In addition, we also constructed TFs–DEGs, miRNAs–DEGs, and protein–drug interaction networks, demonstrating the complex regulatory relationships of common DEGs.

Conclusion

We successfully extracted 10 hub genes that could be used as novel therapeutic targets for COVID-19 and NAFLD. In addition, based on common DEGs, we propose some potential drugs that may benefit patients with COVID-19 and NAFLD.

ParticleChromo3D: a Particle Swarm Optimization algorithm for chromosome 3D structure prediction from Hi-C data

Background

The three-dimensional (3D) structure of chromatin has a massive effect on its function. Because of this, it is desirable to have an understanding of the 3D structural organization of chromatin. To gain greater insight into the spatial organization of chromosomes and genomes and the functions they perform, chromosome conformation capture (3C) techniques, particularly Hi-C, have been developed. The Hi-C technology is widely used and well-known because of its ability to profile interactions for all read pairs in an entire genome. The advent of Hi-C has greatly expanded our understanding of the 3D genome, genome folding, gene regulation and has enabled the development of many 3D chromosome structure reconstruction methods.

Results

Here, we propose a novel approach for 3D chromosome and genome structure reconstruction from Hi-C data using Particle Swarm Optimization (PSO) approach called ParticleChromo3D. This algorithm begins with a grouping of candidate solution locations for each chromosome bin, according to the particle swarm algorithm, and then iterates its position towards a global best candidate solution. While moving towards the optimal global solution, each candidate solution or particle uses its own local best information and a randomizer to choose its path. Using several metrics to validate our results, we show that ParticleChromo3D produces a robust and rigorous representation of the 3D structure for input Hi-C data. We evaluated our algorithm on simulated and real Hi-C data in this work. Our results show that ParticleChromo3D is more accurate than most of the existing algorithms for 3D structure reconstruction.

Conclusions

Our results also show that constructed ParticleChromo3D structures are very consistent, hence indicating that it will always arrive at the global solution at every iteration. The source code for ParticleChromo3D, the simulated and real Hi-C datasets, and the models generated for these datasets are available here: https://github.com/OluwadareLab/ParticleChromo3D

Synthetic PPAR Agonist DTMB Alleviates Alzheimer's Disease Pathology by Inhibition of Chronic Microglial Inflammation in 5xFAD Mice

Abnormal productions of amyloid beta (Aβ) plaque and chronic neuroinflammation are commonly observed in the brain of patients with Alzheimer's disease, and both of which induce neuronal cell death, loss of memory, and cognitive dysfunction. However, many of the drugs targeting the production of Aβ peptides have been unsuccessful in treating Alzheimer's disease. In this study, we identified synthetic novel peroxisome proliferator-activating receptor (PPAR) agonist, DTMB, which can ameliorate the chronic inflammation and Aβ pathological progression of Alzheimer's disease. We discovered that DTMB attenuated the proinflammatory cytokine production of microglia by reducing the protein level of NF-κB. DTMB also improved the learning and memory defects and reduced the amount of Aβ plaque in the brain of 5xFAD mice. This reduction in Aβ pathology was attributed to the changes in gliosis and chronic inflammation level. Additionally, bulk RNA-sequencing showed that genes related to inflammation and cognitive function were changed in the hippocampus and cortex of DTMB-treated mice. Our findings demonstrate that DTMB has the potential to be a novel therapeutic agent for Alzheimer's disease.

Volumetric macromolecule identification in cryo-electron tomograms using capsule networks

Background

Despite recent advances in cellular cryo-electron tomography (CET), developing automated tools for macromolecule identification in submolecular resolution remains challenging due to the lack of annotated data and high structural complexities. To date, the extent of the deep learning methods constructed for this problem is limited to conventional Convolutional Neural Networks (CNNs). Identifying macromolecules of different types and sizes is a tedious and time-consuming task. In this paper, we employ a capsule-based architecture to automate the task of macromolecule identification, that we refer to as 3D-UCaps. In particular, the architecture is composed of three components: feature extractor, capsule encoder, and CNN decoder. The feature extractor converts voxel intensities of input sub-tomograms to activities of local features. The encoder is a 3D Capsule Network (CapsNet) that takes local features to generate a low-dimensional representation of the input. Then, a 3D CNN decoder reconstructs the sub-tomograms from the given representation by upsampling.

Results

We performed binary and multi-class localization and identification tasks on synthetic and experimental data. We observed that the 3D-UNet and the 3D-UCaps had an \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$F_1-$$\end{document}F1-score mostly above 60% and 70%, respectively, on the test data. In both network architectures, we observed degradation of at least 40% in the \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$F_1$$\end{document}F1-score when identifying very small particles (PDB entry 3GL1) compared to a large particle (PDB entry 4D8Q). In the multi-class identification task of experimental data, 3D-UCaps had an \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$F_1$$\end{document}F1-score of 91% on the test data in contrast to 64% of the 3D-UNet. The better \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$F_1$$\end{document}F1-score of 3D-UCaps compared to 3D-UNet is obtained by a higher precision score. We speculate this to be due to the capsule network employed in the encoder. To study the effect of the CapsNet-based encoder architecture further, we performed an ablation study and perceived that the \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$F_1$$\end{document}F1-score is boosted as network depth is increased which is in contrast to the previously reported results for the 3D-UNet. To present a reproducible work, source code, trained models, data as well as visualization results are made publicly available.

Conclusion

Quantitative and qualitative results show that 3D-UCaps successfully perform various downstream tasks including identification and localization of macromolecules and can at least compete with CNN architectures for this task. Given that the capsule layers extract both the existence probability and the orientation of the molecules, this architecture has the potential to lead to representations of the data that are better interpretable than those of 3D-UNet.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12859-022-04901-w.

aRNAque: an evolutionary algorithm for inverse pseudoknotted RNA folding inspired by Lévy flights

BACKGROUND

We study in this work the inverse folding problem for RNA, which is the discovery of sequences that fold into given target secondary structures.

RESULTS

We implement a Lévy mutation scheme in an updated version of aRNAque an evolutionary inverse folding algorithm and apply it to the design of RNAs with and without pseudoknots. We find that the Lévy mutation scheme increases the diversity of designed RNA sequences and reduces the average number of evaluations of the evolutionary algorithm. Compared to antaRNA, aRNAque CPU time is higher but more successful in finding designed sequences that fold correctly into the target structures.

CONCLUSION

We propose that a Lévy flight offers a better standard mutation scheme for optimizing RNA design. Our new version of aRNAque is available on GitHub as a python script and the benchmark results show improved performance on both Pseudobase++ and the Eterna100 datasets, compared to existing inverse folding tools.

Modulation of osteogenic differentiation by Escherichia coli-derived recombinant bone morphogenetic protein-2

Recombinant human bone morphogenetic protein-2 (rhBMP-2), a key regulator of osteogenesis, induces the differentiation of mesenchymal cells into cartilage or bone tissues. Early orthopedic and dental studies often used mammalian cell-derived rhBMP-2, especially Chinese hamster ovary (CHO) cells. However, CHO cell-derived rhBMP-2 (C-rhBMP-2) presents disadvantages such as high cost and low production yield. To overcome these problems, Escherichia coli-derived BMP-2 (E-rhBMP-2) was developed; however, the E-rhBMP-2-induced signaling pathways and gene expression profiles during osteogenesis remain unclear. Here, we investigated the E-rhBMP-2-induced osteogenic differentiation pattern in C2C12 cells and elucidated the difference in biological characteristics between E-rhBMP-2 and C-rhBMP-2 via surface plasmon resonance, western blotting, qRT-PCR, RNA-seq, and alkaline phosphatase assays. The binding affinities of E-rhBMP-2 and C-rhBMP-2 towards BMP receptors were similar, both being confirmed at the nanomolecular level. However, the phosphorylation of Smad1/5/9 at 3 h after treatment with E-rhBMP-2 was significantly lower than that on treatment with C-rhBMP-2. The expression profiles of osteogenic marker genes were similar in both the E-rhBMP-2 and C-rhBMP-2 groups, but the gene expression level in the E-rhBMP-2 group was lower than that in the C-rhBMP-2 group at each time point. Taken together, our results suggest that the osteogenic signaling pathways induced by E-rhBMP-2 and C-rhBMP-2 both follow the general Smad-signaling pathway, but the difference in intracellular phosphorylation intensity results in distinguishable transcription profiles on osteogenic marker genes and biological activities of each rhBMP-2. These findings provide an extensive understanding of the biological properties of E-rhBMP-2 and the signaling pathways during osteogenic differentiation.

Transcriptome analysis revealed gene expression feminization of testis after exogenous tetrodotoxin administration in pufferfish Takifugu flavidus

Tetrodotoxin (TTX) is a deadly neurotoxin and usually accumulates in large amounts in the ovaries but is non-toxic or low toxic in the testis of pufferfish. The molecular mechanism underlying sexual dimorphism accumulation of TTX in ovary and testis, and the relationship between TTX accumulation with sex related genes expression remain largely unknown. The present study investigated the effects of exogenous TTX treatment on Takifugu flavidus. The results demonstrated that exogenous TTX administration significantly incresed level of TTX concentration in kidney, cholecyst, skin, liver, heart, muscle, ovary and testis of the treatment group (TG) than that of the control group (CG). Transcriptome sequencing and analysis were performed to study differential expression profiles of mRNA and piRNA after TTX administration of the ovary and testis. The results showed that compared with female control group (FCG) and male control group (MCG), TTX administration resulted in 80 and 23 piRNAs, 126 and 223 genes up and down regulated expression in female TTX-treated group (FTG), meanwhile, 286 and 223 piRNAs, 2 and 443 genes up and down regulated expression in male TTX-treated group (MTG). The female dominant genes cyp19a1, gdf9 and foxl2 were found to be up-regulated in MTG. The cyp19a1, whose corresponding target piRNA uniq_554482 was identified as down-regulated in the MTG, indicating the gene expression feminization in testis after exogenous TTX administration. The KEGG enrichment analysis revealed that differentially expressed genes (DEGs) and piRNAs (DEpiRNAs) in MTG vs MCG group were more enriched in metabolism pathways, indicating that the testis produced more metabolic pathways in response to exogenous TTX, which might be a reason for the sexual dimorphism of TTX distribution in gonads. In addition, TdT-mediated dUTP-biotin nick end labeling staining showed that significant apoptosis was detected in the MTG testis, and the role of the cell apoptotic pathways was further confirmed. Overall, our research revealed that the response of the ovary and testis to TTX administration was largely different, the ovary is more tolerant whereas the testis is more sensitive to TTX. These data will deepen our understanding on the accumulation of TTX sexual dimorphism in Takifugu.

Reciprocal perspective as a super learner improves drug-target interaction prediction (MUSDTI)

The identification of novel drug-target interactions (DTI) is critical to drug discovery and drug repurposing to address contemporary medical and public health challenges presented by emergent diseases. Historically, computational methods have framed DTI prediction as a binary classification problem (indicating whether or not a drug physically interacts with a given protein target); however, framing the problem instead as a regression-based prediction of the physiochemical binding affinity is more meaningful. With growing databases of experimentally derived drug-target interactions (e.g. Davis, Binding-DB, and Kiba), deep learning-based DTI predictors can be effectively leveraged to achieve state-of-the-art (SOTA) performance. In this work, we formulated a DTI competition as part of the coursework for a senior undergraduate machine learning course and challenged students to generate component DTI models that might surpass SOTA models and effectively combine these component models as part of a meta-model using the Reciprocal Perspective (RP) multi-view learning framework. Following 6 weeks of concerted effort, 28 student-produced component deep-learning DTI models were leveraged in this work to produce a new SOTA RP-DTI model, denoted the Meta Undergraduate Student DTI (MUSDTI) model. Through a series of experiments we demonstrate that (1) RP can considerably improve SOTA DTI prediction, (2) our new double-cold experimental design is more appropriate for emergent DTI challenges, (3) that our novel MUSDTI meta-model outperforms SOTA models, (4) that RP can improve upon individual models as an ensembling method, and finally, (5) RP can be utilized for low computation transfer learning. This work introduces a number of important revelations for the field of DTI prediction and sequence-based, pairwise prediction in general.

Distinct modulation of IFNγ-induced transcription by BET bromodomain and catalytic P300/CBP inhibition in breast cancer

Background

Interferon gamma (IFNγ) is a pro-inflammatory cytokine that directly activates the JAK/STAT pathway. However, the temporal dynamics of chromatin remodeling and transcriptional activation initiated by IFNγ have not been systematically profiled in an unbiased manner. Herein, we integrated transcriptomic and epigenomic profiling to characterize the acute epigenetic changes induced by IFNγ stimulation in a murine breast cancer model.

Results

We identified de novo activation of cis-regulatory elements bound by Irf1 that were characterized by increased chromatin accessibility, differential usage of pro-inflammatory enhancers, and downstream recruitment of BET proteins and RNA polymerase II. To functionally validate this hierarchical model of IFNγ-driven transcription, we applied selective antagonists of histone acetyltransferases P300/CBP or acetyl-lysine readers of the BET family. This highlighted that histone acetylation is an antecedent event in IFNγ-driven transcription, whereby targeting of P300/CBP acetyltransferase activity but not BET inhibition could curtail the epigenetic remodeling induced by IFNγ through suppression of Irf1 transactivation.

Conclusions

These data highlight the ability for epigenetic therapies to reprogram pro-inflammatory gene expression, which may have therapeutic implications for anti-tumor immunity and inflammatory diseases.

Graphical Abstract

Supplementary Information

The online version contains supplementary material available at 10.1186/s13148-022-01316-5.

Overdominant expression of related genes of ion homeostasis improves K+ content advantage in hybrid tobacco leaves

BACKGROUND

Potassium(K+) plays a vital role in improving the quality of tobacco leaves. However, how to improve the potassium content of tobacco leaves has always been a difficult problem in tobacco planting. K+ content in tobacco hybrid is characterized by heterosis, which can improve the quality of tobacco leaves, but its underlying molecular genetic mechanisms remain unclear.

RESULTS

Through a two-year field experiment, G70×GDH11 with strong heterosis and K326×GDH11 with weak heterosis were screened out. Transcriptome analyses revealed that 80.89% and 57.28% of the differentially expressed genes (DEGs) in the strong and weak heterosis combinations exhibited an overdominant expression pattern, respectively. The genes that up-regulated the overdominant expression in the strong heterosis hybrids were significantly enriched in the ion homeostasis. Genes involved in K+ transport (KAT1/2, GORK, AKT2, and KEA3), activity regulation complex (CBL-CIPK5/6), and vacuole (TPKs) genes were overdominant expressed in strong heterosis hybrids, which contributed to K+ homeostasis and heterosis in tobacco leaves.

CONCLUSIONS

K+ homeostasis and accumulation in tobacco hybrids were collectively improved. The overdominant expression of K+ transport and homeostasis-related genes conducted a crucial role in the heterosis of K+ content in tobacco leaves.

A Survey on Deep Networks Approaches in Prediction of Sequence-Based Protein–Protein Interactions

The prominence of protein–protein interactions (PPIs) in system biology with diverse biological procedures has become the topic to discuss because it acts as a fundamental part in predicting the protein function of the target protein and drug ability of molecules. Numerous researches have been published to predict PPIs computationally because they provide an alternative solution to laboratory trials and a cost-effective way of predicting the most likely set of interactions at the entire proteome scale. In recent computational methods, deep learning has become a buzzword with numerous scientific researches. This paper presents, for the first time, a comprehensive survey of sequence-based PPI prediction by three popular deep learning architectures i.e. deep neural networks, convolutional neural networks and recurrent neural networks and its variants. The thorough survey discussed herein carefully mined every possible information, can help the researchers to further explore the success in this area.

Comparative metabolome analysis unravels a close association between dormancy release and metabolic alteration induced by low temperature in lily bulbs

The correlation between dormancy release and metabolic metabolic changes in lily bulbs during low temperature storage was investigated. Low temperature is a major environmental factor required for dormancy release in lily bulbs. Although great advances in plant metabolomics have been achieved, knowledge about the molecular basis of lily bulb metabolomes at different developmental stages in response to low temperature is still limited. In this work, the dormancy release, vegetative growth, flowering, metabolic profile and gene expression in the less dormant cultivar Lilium longiforum × Oriental hybrid 'Triumphator' (T) and the more dormant cultivar Lilium Asiatic hybrid 'Honesty' (H) were compared. Exposure to low temperature (LT) successfully promoted stem elongation, floral transition and flowering of both T and H bulbs. However, exposure to room temperature (RT) restricted stalk elongation of both T and H bulbs, and prohibited floral transition and flowering of H bulbs. Correspondingly, higher antioxidant enzyme activity and total primary metabolite contents were observed in the apical bud of T bulbs. Gene expression analysis revealed that expressions of LiFT, LiFLK, LiSOC1 and LiCBF were decreased, whereas the expression of LiSVP and LiFLC were increased, in the apical bud of H bulbs under RT storage condition. Our findings reveal that the growth and dormancy breaking of lily bulbs are closely associated with the metabolic changes in the apical buds during postharvest storage.

Multi-view heterogeneous molecular network representation learning for protein-protein interaction prediction

BACKGROUND

Protein-protein interaction (PPI) plays an important role in regulating cells and signals. Despite the ongoing efforts of the bioassay group, continued incomplete data limits our ability to understand the molecular roots of human disease. Therefore, it is urgent to develop a computational method to predict PPIs from the perspective of molecular system.

METHODS

In this paper, a highly efficient computational model, MTV-PPI, is proposed for PPI prediction based on a heterogeneous molecular network by learning inter-view protein sequences and intra-view interactions between molecules simultaneously. On the one hand, the inter-view feature is extracted from the protein sequence by k-mer method. On the other hand, we use a popular embedding method LINE to encode the heterogeneous molecular network to obtain the intra-view feature. Thus, the protein representation used in MTV-PPI is constructed by the aggregation of its inter-view feature and intra-view feature. Finally, random forest is integrated to predict potential PPIs.

RESULTS

To prove the effectiveness of MTV-PPI, we conduct extensive experiments on a collected heterogeneous molecular network with the accuracy of 86.55%, sensitivity of 82.49%, precision of 89.79%, AUC of 0.9301 and AUPR of 0.9308. Further comparison experiments are performed with various protein representations and classifiers to indicate the effectiveness of MTV-PPI in predicting PPIs based on a complex network.

CONCLUSION

The achieved experimental results illustrate that MTV-PPI is a promising tool for PPI prediction, which may provide a new perspective for the future interactions prediction researches based on heterogeneous molecular network.

PEPPI: Whole-proteome Protein-protein Interaction Prediction through Structure and Sequence Similarity, Functional Association, and Machine Learning

Proteome-wide identification of protein-protein interactions is a formidable task which has yet to be sufficiently addressed by experimental methodologies. Many computational methods have been developed to predict proteome-wide interaction networks, but few leverage both the sensitivity of structural information and the wide availability of sequence data. We present PEPPI, a pipeline which integrates structural similarity, sequence similarity, functional association data, and machine learning-based classification through a naïve Bayesian classifier model to accurately predict protein-protein interactions at a proteomic scale. Through benchmarking against a set of 798 ground truth interactions and an equal number of non-interactions, we have found that PEPPI attains 4.5% higher AUROC than the best of other state-of-the-art methods. As a proteomic-scale application, PEPPI was applied to model the interactions which occur between SARS-CoV-2 and human host cells during coronavirus infection, where 403 high-confidence interactions were identified with predictions covering 73% of a gold standard dataset from PSICQUIC and demonstrating significant complementarity with the most recent high-throughput experiments. PEPPI is available both as a webserver and in a standalone version and should be a powerful and generally applicable tool for computational screening of protein-protein interactions.

Multi-type feature fusion based on graph neural network for drug-drug interaction prediction

Background

Drug-Drug interactions (DDIs) are a challenging problem in drug research. Drug combination therapy is an effective solution to treat diseases, but it can also cause serious side effects. Therefore, DDIs prediction is critical in pharmacology. Recently, researchers have been using deep learning techniques to predict DDIs. However, these methods only consider single information of the drug and have shortcomings in robustness and scalability.

Results

In this paper, we propose a multi-type feature fusion based on graph neural network model (MFFGNN) for DDI prediction, which can effectively fuse the topological information in molecular graphs, the interaction information between drugs and the local chemical context in SMILES sequences. In MFFGNN, to fully learn the topological information of drugs, we propose a novel feature extraction module to capture the global features for the molecular graph and the local features for each atom of the molecular graph. In addition, in the multi-type feature fusion module, we use the gating mechanism in each graph convolution layer to solve the over-smoothing problem during information delivery. We perform extensive experiments on multiple real datasets. The results show that MFFGNN outperforms some state-of-the-art models for DDI prediction. Moreover, the cross-dataset experiment results further show that MFFGNN has good generalization performance.

Conclusions

Our proposed model can efficiently integrate the information from SMILES sequences, molecular graphs and drug-drug interaction networks. We find that a multi-type feature fusion model can accurately predict DDIs. It may contribute to discovering novel DDIs.

Global leaf and root transcriptome in response to cadmium reveals tolerance mechanisms in Arundo donax L

The expected increase of sustainable energy demand has shifted the attention towards bioenergy crops. Due to their know tolerance against abiotic stress and relatively low nutritional requirements, they have been proposed as election crops to be cultivated in marginal lands without disturbing the part of lands employed for agricultural purposes. Arundo donax L. is a promising bioenergy crop whose behaviour under water and salt stress has been recently studied at transcriptomic levels. As the anthropogenic activities produced in the last years a worrying increase of cadmium contamination worldwide, the aim of our work was to decipher the global transcriptomic response of A. donax leaf and root in the perspective of its cultivation in contaminated soil. In our study, RNA-seq libraries yielded a total of 416 million clean reads and 10.4 Gb per sample. De novo assembly of clean reads resulted in 378,521 transcripts and 126,668 unigenes with N50 length of 1812 bp and 1555 bp, respectively. Differential gene expression analysis revealed 5,303 deregulated transcripts (3,206 up- and 2,097 down regulated) specifically observed in the Cd-treated roots compared to Cd-treated leaves. Among them, we identified genes related to “Protein biosynthesis”, “Phytohormone action”, “Nutrient uptake”, “Cell wall organisation”, “Polyamine metabolism”, “Reactive oxygen species metabolism” and “Ion membrane transport”. Globally, our results indicate that ethylene biosynthesis and the downstream signal cascade are strongly induced by cadmium stress. In accordance to ethylene role in the interaction with the ROS generation and scavenging machinery, the transcription of several genes (NADPH oxidase 1, superoxide dismutase, ascorbate peroxidase, different glutathione S-transferases and catalase) devoted to cope the oxidative stress is strongly activated. Several small signal peptides belonging to ROTUNDIFOLIA, CLAVATA3, and C-TERMINALLY ENCODED PEPTIDE 1 (CEP) are also among the up-regulated genes in Cd-treated roots functioning as messenger molecules from root to shoot in order to communicate the stressful status to the upper part of the plants. Finally, the main finding of our work is that genes involved in cell wall remodelling and lignification are decisively up-regulated in giant reed roots. This probably represents a mechanism to avoid cadmium uptake which strongly supports the possibility to cultivate giant cane in contaminated soils in the perspective to reserve agricultural soil for food and feed crops.

Clair W, Clair DS. The RelB-BLNK Axis Determines Cellular Response to a Novel Redox-Active Agent Betamethasone during Radiation Therapy in Prostate Cancer

Aberrant levels of reactive oxygen species (ROS) are potential mechanisms that contribute to both cancer therapy efficacy and the side effects of cancer treatment. Upregulation of the non-canonical redox-sensitive NF-kB family member, RelB, confers radioresistance in prostate cancer (PCa). We screened FDA-approved compounds and identified betamethasone (BET) as a drug that increases hydrogen peroxide levels in vitro and protects non-PCa tissues/cells while also enhancing radiation killing of PCa tissues/cells, both in vitro and in vivo. Significantly, BET increases ROS levels and exerts different effects on RelB expression in normal cells and PCa cells. BET induces protein expression of RelB and RelB target genes, including the primary antioxidant enzyme, manganese superoxide dismutase (MnSOD), in normal cells, while it suppresses protein expression of RelB and MnSOD in LNCaP cells and PC3 cells. RNA sequencing analysis identifies B-cell linker protein (BLNK) as a novel RelB complementary partner that BET differentially regulates in normal cells and PCa cells. RelB and BLNK are upregulated and correlate with the aggressiveness of PCa in human samples. The RelB-BLNK axis translocates to the nuclear compartment to activate MnSOD protein expression. BET promotes the RelB-BLNK axis in normal cells but suppresses the RelB-BLNK axis in PCa cells. Targeted disruptions of RelB-BLNK expressions mitigate the radioprotective effect of BET on normal cells and the radiosensitizing effect of BET on PCa cells. Our study identified a novel RelB complementary partner and reveals a complex redox-mediated mechanism showing that the RelB-BLNK axis, at least in part, triggers differential responses to the redox-active agent BET by stimulating adaptive responses in normal cells but pushing PCa cells into oxidative stress overload.

In silico and in vitro study of Mycobacterium tuberculosis H37Rv uncharacterized protein (RipD): an insight on tuberculosis therapeutics

Tuberculosis caused by Mycobacterium tuberculosis (Mtb) is responsible for the highest global health problem, with the deaths of millions of people. With prevalence of multiple drug resistance (MDR) strains and extended therapeutic times, it is important to discover small molecule inhibitors against novel hypothetical proteins of the pathogen. In this study, a virtual screening protocol was carried out against MtbH37Rv hypothetical protein RipD (Rv1566c) for the identification of potential small molecule inhibitors. The 3D model of the protein structure binding site was used for virtual screening (VS) of inhibitors from the Pathogen Box, followed by its validation through a molecular docking study. The stability of the protein-ligand complex was assessed using a 150 ns molecular dynamics simulation. MM-PBSA and MM-GBSA are the two approaches that were used to perform the trajectory analysis and determine the binding free energies, respectively. The ligand binding was observed to be stable across the entire time frame with an approximate binding free energy of -22.9916 kcal/mol. The drug-likeness of the inhibitors along with a potential anti-tuberculosis compound was validated by ADMET prediction software. Furthermore, a CFU inhibition assay was used to validate the best hit compound's in vitro inhibitory efficacy against a non-pathogenic Mycobacterium smegmatis MC2155 under low nutrient culture conditions. The study reported that the compound proposed in our study (Pathogen Box ID: MMV687700) will be useful for the identification of potential inhibitors against Mtb in future.

Human emotion recognition from EEG-based brain–computer interface using machine learning: a comprehensive review

Affective computing, a subcategory of artificial intelligence, detects, processes, interprets, and mimics human emotions. Thanks to the continued advancement of portable non-invasive human sensor technologies, like brain–computer interfaces (BCI), emotion recognition has piqued the interest of academics from a variety of domains. Facial expressions, speech, behavior (gesture/posture), and physiological signals can all be used to identify human emotions. However, the first three may be ineffectual because people may hide their true emotions consciously or unconsciously (so-called social masking). Physiological signals can provide more accurate and objective emotion recognition. Electroencephalogram (EEG) signals respond in real time and are more sensitive to changes in affective states than peripheral neurophysiological signals. Thus, EEG signals can reveal important features of emotional states. Recently, several EEG-based BCI emotion recognition techniques have been developed. In addition, rapid advances in machine and deep learning have enabled machines or computers to understand, recognize, and analyze emotions. This study reviews emotion recognition methods that rely on multi-channel EEG signal-based BCIs and provides an overview of what has been accomplished in this area. It also provides an overview of the datasets and methods used to elicit emotional states. According to the usual emotional recognition pathway, we review various EEG feature extraction, feature selection/reduction, machine learning methods (e.g., k-nearest neighbor), support vector machine, decision tree, artificial neural network, random forest, and naive Bayes) and deep learning methods (e.g., convolutional and recurrent neural networks with long short term memory). In addition, EEG rhythms that are strongly linked to emotions as well as the relationship between distinct brain areas and emotions are discussed. We also discuss several human emotion recognition studies, published between 2015 and 2021, that use EEG data and compare different machine and deep learning algorithms. Finally, this review suggests several challenges and future research directions in the recognition and classification of human emotional states using EEG.

Performance Analysis of Conventional Machine Learning Algorithms for Diabetic Sensorimotor Polyneuropathy Severity Classification Using Nerve Conduction Studies

Background

Diabetic sensorimotor polyneuropathy (DSPN) is a major form of complication that arises in long-term diabetic patients. Even though the application of machine learning (ML) in disease diagnosis is very common and well-established in the field of research, its application in DSPN diagnosis using nerve conduction studies (NCS), is very limited in the existing literature.

Method

In this study, the NCS data were collected from the Diabetes Control and Complications Trial (DCCT) and its follow-up Epidemiology of Diabetes Interventions and Complications (EDIC) clinical trials. The NCS variables are median motor velocity (m/sec), median motor amplitude (mV), median motor F-wave (msec), median sensory velocity (m/sec), median sensory amplitude (μV), Peroneal Motor Velocity (m/sec), peroneal motor amplitude (mv), peroneal motor F-wave (msec), sural sensory velocity (m/sec), and sural sensory amplitude (μV). Three different feature ranking techniques were used to analyze the performance of eight different conventional classifiers.

Results

The ensemble classifier outperformed other classifiers for the NCS data ranked when all the NCS features were used and provided an accuracy of 93.40%, sensitivity of 91.77%, and specificity of 98.44%. The random forest model exhibited the second-best performance using all the ten features with an accuracy of 93.26%, sensitivity of 91.95%, and specificity of 98.95%. Both ensemble and random forest showed the kappa value 0.82, which indicates that the models are in good agreement with the data and the variables used and are accurate to identify DSPN using these ML models.

Conclusion

This study suggests that the ensemble classifier using all the ten NCS variables can predict the DSPN severity which can enhance the management of DSPN patients.

Machine Learning-Based Diabetic Neuropathy and Previous Foot Ulceration Patients Detection Using Electromyography and Ground Reaction Forces during Gait

Diabetic neuropathy (DN) is one of the prevalent forms of neuropathy that involves alterations in biomechanical changes in the human gait. Diabetic foot ulceration (DFU) is one of the pervasive types of complications that arise due to DN. In the literature, for the last 50 years, researchers have been trying to observe the biomechanical changes due to DN and DFU by studying muscle electromyography (EMG) and ground reaction forces (GRF). However, the literature is contradictory. In such a scenario, we propose using Machine learning techniques to identify DN and DFU patients by using EMG and GRF data. We collected a dataset from the literature which involves three patient groups: Control (n = 6), DN (n = 6), and previous history of DFU (n = 9) and collected three lower limb muscles EMG (tibialis anterior (TA), vastus lateralis (VL), gastrocnemius lateralis (GL)), and three GRF components (GRFx, GRFy, and GRFz). Raw EMG and GRF signals were preprocessed, and different feature extraction techniques were applied to extract the best features from the signals. The extracted feature list was ranked using four different feature ranking techniques, and highly correlated features were removed. In this study, we considered different combinations of muscles and GRF components to find the best performing feature list for the identification of DN and DFU. We trained eight different conventional ML models: Discriminant analysis classifier (DAC), Ensemble classification model (ECM), Kernel classification model (KCM), k-nearest neighbor model (KNN), Linear classification model (LCM), Naive Bayes classifier (NBC), Support vector machine classifier (SVM), and Binary decision classification tree (BDC), to find the best-performing algorithm and optimized that model. We trained the optimized the ML algorithm for different combinations of muscles and GRF component features, and the performance matrix was evaluated. Our study found the KNN algorithm performed well in identifying DN and DFU, and we optimized it before training. We found the best accuracy of 96.18% for EMG analysis using the top 22 features from the chi-square feature ranking technique for features from GL and VL muscles combined. In the GRF analysis, the model showed 98.68% accuracy using the top 7 features from the Feature selection using neighborhood component analysis for the feature combinations from the GRFx-GRFz signal. In conclusion, our study has shown a potential solution for ML application in DN and DFU patient identification using EMG and GRF parameters. With careful signal preprocessing with strategic feature extraction from the biomechanical parameters, optimization of the ML model can provide a potential solution in the diagnosis and stratification of DN and DFU patients from the EMG and GRF signals.

Predicting residues involved in anti-DNA autoantibodies with limited neural networks

Abstract

Computer-aided rational vaccine design (RVD) and synthetic pharmacology are rapidly developing fields that leverage existing datasets for developing compounds of interest. Computational proteomics utilizes algorithms and models to probe proteins for functional prediction. A potentially strong target for computational approach is autoimmune antibodies, which are the result of broken tolerance in the immune system where it cannot distinguish “self” from “non-self” resulting in attack of its own structures (proteins and DNA, mainly). The information on structure, function, and pathogenicity of autoantibodies may assist in engineering RVD against autoimmune diseases. Current computational approaches exploit large datasets curated with extensive domain knowledge, most of which include the need for many resources and have been applied indirectly to problems of interest for DNA, RNA, and monomer protein binding. We present a novel method for discovering potential binding sites. We employed long short-term memory (LSTM) models trained on FASTA primary sequences to predict protein binding in DNA-binding hydrolytic antibodies (abzymes). We also employed CNN models applied to the same dataset for comparison with LSTM. While the CNN model outperformed the LSTM on the primary task of binding prediction, analysis of internal model representations of both models showed that the LSTM models recovered sub-sequences that were strongly correlated with sites known to be involved in binding. These results demonstrate that analysis of internal processes of LSTM models may serve as a powerful tool for primary sequence analysis.

Graphical abstract

IFNL4 genotype influences the rate of HIV-1 seroconversion in men who have sex with men

Individuals lacking interferon lambda 4 (IFNL4) protein due to a common null mutation (rs368234815) in the IFNL4 gene display higher resistance against several infections. The influence of IFNL4 on HIV-1 infection is still under discussion and conflicting results have been reported. This study intended to corroborate or refute the association of the null allele of IFNL4 and HIV-1 predisposition in a cohort of men who have sex with men (MSM). IFNL4 null genotype was assessed on 619 HIV-1-seronegative MSM who were followed for 36 months during a trial of a prophylactic vaccine against HIV-1. Of those, 257 individuals seroconverted during this period. A logistic regression model was constructed including demographic and IFNL4 genotype. In addition, a meta-analysis using data from the current study and other European populations was conducted. The null IFNL4 genotypes were correlated with lower HIV-1 seroconversion (Adjusted OR = 0.4 [95%CI: 0.2–0.8], P = 0.008) and longer time to seroconversion (889 vs. 938 days, P= 0.01). These results were validated by a meta-analysis incorporating data from other European populations and the result yielded a significant association of the IFNL4 null genotype under a dominant model with a lower probability of HIV-1 infection (OR=0.4 [95% CI: 0.3-0.6]; P= 1.3 x 10E-5).

Gene expression profiles provide insights into the survival strategies in deep-sea mussel (Bathymodiolus platifrons) of different developmental stages

Background

Deep-sea mussels living in the cold seeps with enormous biomass act as the primary consumers. They are well adapted to the extreme environment where light is absent, and hydrogen sulfide, methane, and other hydrocarbon-rich fluid seepage occur. Despite previous studies on diversity, role, evolution, and symbiosis, the changing adaptation patterns during different developmental stages of the deep-sea mussels remain largely unknown.

Results

The deep-sea mussels (Bathymodiolus platifrons) of two developmental stages were collected from the cold seep during the ocean voyage. The gills, mantles, and adductor muscles of these mussels were used for the Illumina sequencing. A total of 135 Gb data were obtained, and subsequently, 46,376 unigenes were generated using de-novo assembly strategy. According to the gene expression analysis, amounts of genes were most actively expressed in the gills, especially genes involved in environmental information processing. Genes encoding Toll-like receptors and sulfate transporters were up-regulated in gills, indicating that the gill acts as both intermedium and protective screen in the deep-sea mussel. Lysosomal enzymes and solute carrier responsible for nutrients absorption were up-regulated in the older mussel, while genes related to toxin resistance and autophagy were up-regulated in the younger one, suggesting that the older mussel might be in a vigorous stage while the younger mussel was still paying efforts in survival and adaptation.

Conclusions

In general, our study suggested that the adaptation capacity might be formed gradually during the development of deep-sea mussels, in which the gill and the symbionts play essential roles.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12864-022-08505-9.

Bioinformatics analysis for identifying micro-RNAs, long noncoding RNAs, transcription factors, and immune genes regulatory networks in diabetic cardiomyopathy using an integrated bioinformatics analysis

OBJECTIVES

We identified functional genes and studied the underlying molecular mechanisms of diabetic cardiomyopathy (DCM) using bioinformatics tools.

METHODS

Original gene expression profiles were obtained from the GSE21610 and GSE112556 data sets. We used GEO2R to screen the differentially expressed genes (DEGs). Gene Ontology and Kyoto Encyclopedia of Genes and Genomes pathway enrichment analyses were performed on DEGs. Protein-protein interaction (PPI) networks of DEGs were constructed using STRING and hub genes of signaling pathways were identified using Cytoscape. Aberrant hub gene expression was verified using The Cancer Genome Atlas data set.

RESULTS

The DEGs in DCM were mainly enriched in the nuclei and cytoplasm and involved in DCM and chemokine-related signaling pathways. In the PPI network, 32 nodes were chosen as hub nodes and an RNA interaction network was constructed with 517 interactions. The expression of key genes (JPIK3R1, CCR9, XIST, WDFY3.AS2, hsa-miR-144-5p, and hsa-miR-146b-5p) was significantly different between DCM and normal tissues.

CONCLUSIONS

The identified hub genes could be associated with DCM pathogenesis and could be used for treating DCM.

Characterization of differential gene expression of broiler chicken to thermal stress in discrete developmental stages

Prolonged exposure to high temperatures is linked to a range of physiological responses in broiler chickens including reduced disease resistance, low growth rate, and high mortality rate. In this study, we investigated the effect of heat stress on gene expression levels in 4-week-old and 6-week-old chickens each exposed to environments conditioned at thermoneutral (21 °C) and high (32 °C) temperatures. The analysis of differentially expressed genes (DEGs) using microarray revealed that genes underlying reactive oxygen species (ROS) production, cell nutrient intake, glucose metabolism, and circadian rhythm were differentially regulated in association with heat stress. We also found that the deviation in expression levels across the transcriptome in response to heat stress was significantly stronger (P< 2.2×10-16) in 6-week-olds compared to younger chickens. We finally observed a significant trend (r = 0.78, P< 2.2×10-16) that genes with a higher estimate of expression in the microarray were more likely to have a higher expression level in RNA-sequencing. Together, our findings provide comprehensive insights into the physiology involved in stress responses at varying developmental stages, which may facilitate chicken breeding to maximize their productivity under adverse conditions.