AFITbin: a metagenomic contig binning method using aggregate l-mer frequency based on initial and terminal nucleotides.

BACKGROUND: Using next-generation sequencing technologies, scientists can sequence complex microbial communities directly from the environment. Significant insights into the structure, diversity, and ecology of microbial communities have resulted from the study of metagenomics. The assembly of reads into longer contigs, which are then binned into groups of contigs that correspond to different species in the metagenomic sample, is a crucial step in the analysis of metagenomics. It is necessary to organize these contigs into operational taxonomic units (OTUs) for further taxonomic profiling and functional analysis. For binning, which is synonymous with the clustering of OTUs, the tetra-nucleotide frequency (TNF) is typically utilized as a compositional feature for each OTU. RESULTS: In this paper, we present AFIT, a new l-mer statistic vector for each contig, and AFITBin, a novel method for metagenomic binning based on AFIT and a matrix factorization method. To evaluate the performance of the AFIT vector, the t-SNE algorithm is used to compare species clustering based on AFIT and TNF information. In addition, the efficacy of AFITBin is demonstrated on both simulated and real datasets in comparison to state-of-the-art binning methods such as MetaBAT 2, MaxBin 2.0, CONCOT, MetaCon, SolidBin, BusyBee Web, and MetaBinner. To further analyze the performance of the purposed AFIT vector, we compare the barcodes of the AFIT vector and the TNF vector. CONCLUSION: The results demonstrate that AFITBin shows superior performance in taxonomic identification compared to existing methods, leveraging the AFIT vector for improved results in metagenomic binning. This approach holds promise for advancing the analysis of metagenomic data, providing more reliable insights into microbial community composition and function. AVAILABILITY: A python package is available at: https://github.com/SayehSobhani/AFITBin .

MiRAGE: mining relationships for advanced generative evaluation in drug repositioning.

MOTIVATION: Drug repositioning, the identification of new therapeutic uses for existing drugs, is crucial for accelerating drug discovery and reducing development costs. Some methods rely on heterogeneous networks, which may not fully capture the complex relationships between drugs and diseases. However, integrating diverse biological data sources offers promise for discovering new drug-disease associations (DDAs). Previous evidence indicates that the combination of information would be conducive to the discovery of new DDAs. However, the challenge lies in effectively integrating different biological data sources to identify the most effective drugs for a certain disease based on drug-disease coupled mechanisms. RESULTS: In response to this challenge, we present MiRAGE, a novel computational method for drug repositioning. MiRAGE leverages a three-step framework, comprising negative sampling using hard negative mining, classification employing random forest models, and feature selection based on feature importance. We evaluate MiRAGE on multiple benchmark datasets, demonstrating its superiority over state-of-the-art algorithms across various metrics. Notably, MiRAGE consistently outperforms other methods in uncovering novel DDAs. Case studies focusing on Parkinson's disease and schizophrenia showcase MiRAGE's ability to identify top candidate drugs supported by previous studies. Overall, our study underscores MiRAGE's efficacy and versatility as a computational tool for drug repositioning, offering valuable insights for therapeutic discoveries and addressing unmet medical needs.

DPSP: a multimodal deep learning framework for polypharmacy side effects prediction.

Motivation: Because unanticipated drug-drug interactions (DDIs) can result in severe bodily harm, identifying the adverse effects of polypharmacy is one of the most important tasks in human health. Over the past few decades, computational methods for predicting the adverse effects of polypharmacy have been developed. Results: This article presents DPSP, a framework for predicting polypharmacy side effects based on the construction of novel drug features and the application of a deep neural network to predict DDIs. In the first step, a variety of drug information is evaluated, and a feature extraction method and the Jaccard similarity are used to determine similarities between two drugs. By combining these similarities, a novel feature vector is generated for each drug. In the second step, the method predicts DDIs for specific DDI events using a multimodal framework and drug feature vectors. On three benchmark datasets, the performance of DPSP is measured by comparing its results to those of several well-known methods, such as GNN-DDI, MSTE, MDF-SA-DDI, NNPS, DDIMDL, DNN, DeepDDI, KNN, LR, and RF. DPSP outperforms these classification methods based on a variety of classification metrics. The results indicate that the use of diverse drug information is effective and efficient for identifying DDI adverse effects. Availability and implementation: The source code and datasets are available at https://github.com/raziyehmasumshah/DPSP.

NN-RNALoc: Neural network-based model for prediction of mRNA sub-cellular localization using distance-based sub-sequence profiles.

The localization of messenger RNAs (mRNAs) is a frequently observed phenomenon and a crucial aspect of gene expression regulation. It is also a mechanism for targeting proteins to a specific cellular region. Moreover, prior research and studies have shown the significance of intracellular RNA positioning during embryonic and neural dendrite formation. Incorrect RNA localization, which can be caused by a variety of factors, such as mutations in trans-regulatory elements, has been linked to the development of certain neuromuscular diseases and cancer. In this study, we introduced NN-RNALoc, a neural network-based method for predicting the cellular location of mRNA using novel features extracted from mRNA sequence data and protein interaction patterns. In fact, we developed a distance-based subsequence profile for RNA sequence representation that is more memory and time-efficient than well-known k-mer sequence representation. Combining protein-protein interaction data, which is essential for numerous biological processes, with our novel distance-based subsequence profiles of mRNA sequences produces more accurate features. On two benchmark datasets, CeFra-Seq and RNALocate, the performance of NN-RNALoc is compared to powerful predictive models proposed in previous works (mRNALoc, RNATracker, mLoc-mRNA, DM3Loc, iLoc-mRNA, and EL-RMLocNet), and a ground neural (DNN5-mer) network. Compared to the previous methods, NN-RNALoc significantly reduces computation time and also outperforms them in terms of accuracy. This study's source code and datasets are freely accessible at https://github.com/NeginBabaiha/NN-RNALoc.

Removing the association of random gene sets and survival time in cancers with positive random bias using fixed-point gene set.

Cancer research aims to identify genes that cause or control disease progression. Although a wide range of gene sets have been published, they are usually in poor agreement with one another. Furthermore, recent findings from a gene-expression cohort of different cancer types, known as positive random bias, showed that sets of genes chosen randomly are significantly associated with survival time much higher than expected. In this study, we propose a method based on Brouwer's fixed-point theorem that employs significantly survival-associated random gene sets and reveals a small fixed-point gene set for cancers with a positive random bias property. These sets significantly correspond to cancer-related pathways with biological relevance for the progression and metastasis of the cancer types they represent. Our findings show that our proposed significant gene sets are biologically related to each cancer type available in the cancer genome atlas with the positive random bias property, and by using these sets, positive random bias is significantly more reduced in comparison with state-of-the-art methods in this field. The random bias property is removed in 8 of these 17 cancer types, and the number of random sets of genes associated with survival time is significantly reduced in the remaining 9 cancers.

Identification of repurposed drugs targeting significant long non-coding RNAs in the cross-talk between diabetes mellitus and Alzheimer's disease.

The relationship between diabetes mellitus (DM) and Alzheimer's disease (AD) is so strong that scientists called it "brain diabetes". According to several studies, the critical factor in this relationship is brain insulin resistance. Due to the rapid global spread of both diseases, overcoming this cross-talk has a significant impact on societies. Long non-coding RNAs (lncRNAs), on the other hand, have a substantial impact on complex diseases due to their ability to influence gene expression via a variety of mechanisms. Consequently, the regulation of lncRNA expression in chronic diseases permits the development of innovative therapeutic techniques. However, developing a new drug requires considerable time and money. Recently repurposing existing drugs has gained popularity due to the use of low-risk compounds, which may result in cost and time savings. in this study, we identified drug repurposing candidates capable of controlling the expression of common lncRNAs in the cross-talk between DM and AD. We also utilized drugs that interfered with this cross-talk. To do this, high degree common lncRNAs were extracted from microRNA-lncRNA bipartite network. The drugs that interact with the specified lncRNAs were then collected from multiple data sources. These drugs, referred to as set D, were classified in to positive (D+) and negative (D-) groups based on their effects on the expression of the interacting lncRNAs. A feature selection algorithm was used to select six important features for D. Using a random forest classifier, these features were capable of classifying D+ and D- with an accuracy of 82.5%. Finally, the same six features were extracted for the most recently Food and Drug Administration (FDA) approved drugs in order to identify those with the highest likelihood of belonging to D+ or D-. The most significant FDA-approved positive drugs, chromium nicotinate and tapentadol, were presented as repurposing candidates, while cefepime and dihydro-alpha-ergocryptine were recommended as significant adverse drugs. Moreover, two natural compounds, curcumin and quercetin, were recommended to prevent this cross-talk. According to the previous studies, less attention has been paid to the role of lncRNAs in this cross-talk. Our research not only did identify important lncRNAs, but it also suggested potential repurposed drugs to control them.

Exploring the role of non-coding RNAs as potential candidate biomarkers in the cross-talk between diabetes mellitus and Alzheimer's disease.

Background: Recent research has investigated the connection between Diabetes Mellitus (DM) and Alzheimer's Disease (AD). Insulin resistance plays a crucial role in this interaction. Studies have focused on dysregulated proteins to disrupt this connection. Non-coding RNAs (ncRNAs), on the other hand, play an important role in the development of many diseases. They encode the majority of the human genome and regulate gene expression through a variety of mechanisms. Consequently, identifying significant ncRNAs and utilizing them as biomarkers could facilitate the early detection of this cross-talk. On the other hand, computational-based methods may help to understand the possible relationships between different molecules and conduct future wet laboratory experiments. Materials and methods: In this study, we retrieved Genome-Wide Association Study (GWAS, 2008) results from the United Kingdom Biobank database using the keywords "Alzheimer's" and "Diabetes Mellitus." After excluding low confidence variants, statistical analysis was performed, and adjusted p-values were determined. Using the Linkage Disequilibrium method, 127 significant shared Single Nucleotide Polymorphism (SNP) were chosen and the SNP-SNP interaction network was built. From this network, dense subgraphs were extracted as signatures. By mapping each signature to the reference genome, genes associated with the selected SNPs were retrieved. Then, protein-microRNA (miRNA) and miRNA-long non-coding RNA (lncRNA) bipartite networks were built and significant ncRNAs were extracted. After the validation process, by applying the scoring function, the final protein-miRNA-lncRNA tripartite network was constructed, and significant miRNAs and lncRNAs were identified. Results: Hsa-miR-199a-5p, hsa-miR-199b-5p, hsa-miR-423-5p, and hsa-miR-3184-5p, the four most significant miRNAs, as well as NEAT1, XIST, and KCNQ1OT1, the three most important lncRNAs, and their interacting proteins in the final tripartite network, have been proposed as new candidate biomarkers in the cross-talk between DM and AD. The literature review also validates the obtained ncRNAs. In addition, miRNA/lncRNA pairs; hsa-miR-124-3p/KCNQ1OT1, hsa-miR-124-3p/NEAT1, and hsa-miR-124-3p/XIST, all expressed in the brain, and their interacting proteins in our final network are suggested for future research investigation. Conclusion: This study identified 127 shared SNPs, 7 proteins, 15 miRNAs, and 11 lncRNAs involved in the cross-talk between DM and AD. Different network analysis and scoring function suggested the most significant miRNAs and lncRNAs as potential candidate biomarkers for wet laboratory experiments. Considering these candidate biomarkers may help in the early detection of DM and AD co-occurrence.

Assignment of structural domains in proteins using diffusion kernels on graphs.

Though proposing algorithmic approaches for protein domain decomposition has been of high interest, the inherent ambiguity to the problem makes it still an active area of research. Besides, accurate automated methods are in high demand as the number of solved structures for complex proteins is on the rise. While majority of the previous efforts for decomposition of 3D structures are centered on the developing clustering algorithms, employing enhanced measures of proximity between the amino acids has remained rather uncharted. If there exists a kernel function that in its reproducing kernel Hilbert space, structural domains of proteins become well separated, then protein structures can be parsed into domains without the need to use a complex clustering algorithm. Inspired by this idea, we developed a protein domain decomposition method based on diffusion kernels on protein graphs. We examined all combinations of four graph node kernels and two clustering algorithms to investigate their capability to decompose protein structures. The proposed method is tested on five of the most commonly used benchmark datasets for protein domain assignment plus a comprehensive non-redundant dataset. The results show a competitive performance of the method utilizing one of the diffusion kernels compared to four of the best automatic methods. Our method is also able to offer alternative partitionings for the same structure which is in line with the subjective definition of protein domain. With a competitive accuracy and balanced performance for the simple and complex structures despite relying on a relatively naive criterion to choose optimal decomposition, the proposed method revealed that diffusion kernels on graphs in particular, and kernel functions in general are promising measures to facilitate parsing proteins into domains and performing different structural analysis on proteins. The size and interconnectedness of the protein graphs make them promising targets for diffusion kernels as measures of affinity between amino acids. The versatility of our method allows the implementation of future kernels with higher performance. The source code of the proposed method is accessible at https://github.com/taherimo/kludo . Also, the proposed method is available as a web application from https://cbph.ir/tools/kludo .

Detection of structural and conformational changes in ALS-causing mutant profilin-1 with hydrogen/deuterium exchange mass spectrometry and bioinformatics techniques.

The hydrogen/deuterium exchange (HDX) is a reliable method to survey the dynamic behavior of proteins and epitope mapping. Matrix-Assisted Laser Desorption Ionization-Time of Flight Mass Spectrometry (MALDI-TOF MS) is a quantifying tool to assay for HDX in the protein of interest. We combined HDX-MALDI-TOF MS and molecular docking/MD simulation to identify accessible amino acids and analyze their contribution into the structural changes of profilin-1 (PFN-1). The molecular docking/MD simulations are computational tools for enabling the analysis of the type of amino acids that may be involved via HDX identified under the lowest binding energy condition. Glycine to valine amino acid (G117V) substitution mutation is linked to amyotrophic lateral sclerosis (ALS). This mutation is found to be in the actin-binding site of PFN-1 and prevents the dimerization/polymerization of actin and invokes a pathologic toxicity that leads to ALS. In this study, we sought to understand the PFN-1 protein dynamic behavior using purified wild type and mutant PFN-1 proteins. The data obtained from HDX-MALDI-TOF MS for PFN-1WT and PFN-1G117V at various time intervals, from seconds to hours, revealed multiple peaks corresponding to molecular weights from monomers to multimers. PFN-1/Benzaldehyde complexes identified 20 accessible amino acids to HDX that participate in the docking simulation in the surface of WT and mutant PFN-1. Consistent results from HDX-MALDI-TOF MS and docking simulation predict candidate amino acid(s) involved in the dimerization/polymerization of PFNG117V. This information may shed critical light on the structural and conformational changes with details of amino acid epitopes for mutant PFN-1s' dimerization, oligomerization, and aggregation.

Clinical drug response prediction from preclinical cancer cell lines by logistic matrix factorization approach.

Predicting tumor drug response using cancer cell line drug response values for a large number of anti-cancer drugs is a significant challenge in personalized medicine. Predicting patient response to drugs from data obtained from preclinical models is made easier by the availability of different knowledge on cell lines and drugs. This paper proposes the TCLMF method, a predictive model for predicting drug response in tumor samples that was trained on preclinical samples and is based on the logistic matrix factorization approach. The TCLMF model is designed based on gene expression profiles, tissue type information, the chemical structure of drugs and drug sensitivity (IC 50) data from cancer cell lines. We use preclinical data from the Genomics of Drug Sensitivity in Cancer dataset (GDSC) to train the proposed drug response model, which we then use to predict drug sensitivity of samples from the Cancer Genome Atlas (TCGA) dataset. The TCLMF approach focuses on identifying successful features of cell lines and drugs in order to calculate the probability of the tumor samples being sensitive to drugs. The closest cell line neighbours for each tumor sample are calculated using a description of similarity between tumor samples and cell lines in this study. The drug response for a new tumor is then calculated by averaging the low-rank features obtained from its neighboring cell lines. We compare the results of the TCLMF model with the results of the previously proposed methods using two databases and two approaches to test the model's performance. In the first approach, 12 drugs with enough known clinical drug response, considered in previous methods, are studied. For 7 drugs out of 12, the TCLMF can significantly distinguish between patients that are resistance to these drugs and the patients that are sensitive to them. These approaches are converted to classification models using a threshold in the second approach, and the results are compared. The results demonstrate that the TCLMF method provides accurate predictions across the results of the other algorithms. Finally, we accurately classify tumor tissue type using the latent vectors obtained from TCLMF's logistic matrix factorization process. These findings demonstrate that the TCLMF approach produces effective latent vectors for tumor samples. The source code of the TCLMF method is available in https://github.com/emdadi/TCLMF.

A neural network-based method for polypharmacy side effects prediction.

BACKGROUND: Polypharmacy is a type of treatment that involves the concurrent use of multiple medications. Drugs may interact when they are used simultaneously. So, understanding and mitigating polypharmacy side effects are critical for patient safety and health. Since the known polypharmacy side effects are rare and they are not detected in clinical trials, computational methods are developed to model polypharmacy side effects. RESULTS: We propose a neural network-based method for polypharmacy side effects prediction (NNPS) by using novel feature vectors based on mono side effects, and drug-protein interaction information. The proposed method is fast and efficient which allows the investigation of large numbers of polypharmacy side effects. Our novelty is defining new feature vectors for drugs and combining them with a neural network architecture to apply for the context of polypharmacy side effects prediction. We compare NNPS on a benchmark dataset to predict 964 polypharmacy side effects against 5 well-established methods and show that NNPS achieves better results than the results of all 5 methods in terms of accuracy, complexity, and running time speed. NNPS outperforms about 9.2% in Area Under the Receiver-Operating Characteristic, 12.8% in Area Under the Precision-Recall Curve, 8.6% in F-score, 10.3% in Accuracy, and 18.7% in Matthews Correlation Coefficient with 5-fold cross-validation against the best algorithm among other well-established methods (Decagon method). Also, the running time of the Decagon method which is 15 days for one fold of cross-validation is reduced to 8 h by the NNPS method. CONCLUSIONS: The performance of NNPS is benchmarked against 5 well-known methods, Decagon, Concatenated drug features, Deep Walk, DEDICOM, and RESCAL, for 964 polypharmacy side effects. We adopt the 5-fold cross-validation for 50 iterations and use the average of the results to assess the performance of the NNPS method. The evaluation of the NNPS against five well-known methods, in terms of accuracy, complexity, and running time speed shows the performance of the presented method for an essential and challenging problem in pharmacology. Datasets and code for NNPS algorithm are freely accessible at https://github.com/raziyehmasumshah/NNPS .

Predicting anti-cancer drug response by finding optimal subset of drugs.

MOTIVATION: One of the most difficult challenges in precision medicine is determining the best treatment strategy for each patient based on personal information. Since drug response prediction in vitro is extremely expensive, time-consuming and virtually impossible, and because there are so many cell lines and drug data, computational methods are needed. RESULTS: MinDrug is a method for predicting anti-cancer drug response which try to identify the best subset of drugs that are the most similar to other drugs. MinDrug predicts the anti-cancer drug response on a new cell line using information from drugs in this subset and their connections to other drugs. MinDrug employs a heuristic star algorithm to identify an optimal subset of drugs and a regression technique known as Elastic-Net approaches to predict anti-cancer drug response in a new cell line. To test MinDrug, we use both statistical and biological methods to assess the selected drugs. MinDrug is also compared to four state-of-the-art approaches using various k-fold cross-validations on two large public datasets: GDSC and CCLE. MinDrug outperforms the other approaches in terms of precision, robustness and speed. Furthermore, we compare the evaluation results of all the approaches with an external dataset with a statistical distribution that is not exactly the same as the training data. The results show that MinDrug continues to outperform the other approaches. AVAILABILITY AND IMPLEMENTATION: MinDrug's source code can be found at https://github.com/yassaee/MinDrug. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

A computational method for drug sensitivity prediction of cancer cell lines based on various molecular information.

Determining sensitive drugs for a patient is one of the most critical problems in precision medicine. Using genomic profiles of the tumor and drug information can help in tailoring the most efficient treatment for a patient. In this paper, we proposed a classification machine learning approach that predicts the sensitive/resistant drugs for a cell line. It can be performed by using both drug and cell line similarities, one of the cell line or drug similarities, or even not using any similarity information. This paper investigates the influence of using previously defined as well as two newly introduced similarities on predicting anti-cancer drug sensitivity. The proposed method uses max concentration thresholds for assigning drug responses to class labels. Its performance was evaluated using stratified five-fold cross-validation on cell line-drug pairs in two datasets. Assessing the predictive powers of the proposed model and three sets of methods, including state-of-the-art classification methods, state-of-the-art regression methods, and off-the-shelf classification machine learning approaches shows that the proposed method outperforms other methods. Moreover, The efficiency of the model is evaluated in tissue-specific conditions. Besides, the novel sensitive associations predicted by this model were verified by several supportive evidence in the literature and reliable database. Therefore, the proposed model can efficiently be used in predicting anti-cancer drug sensitivity. Material and implementation are available at https://github.com/fahmadimoughari/CDSML.

An order independent algorithm for inferring gene regulatory network using quantile value for conditional independence tests.

In recent years, due to the difficulty and inefficiency of experimental methods, numerous computational methods have been introduced for inferring the structure of Gene Regulatory Networks (GRNs). The Path Consistency (PC) algorithm is one of the popular methods to infer the structure of GRNs. However, this group of methods still has limitations and there is a potential for improvements in this field. For example, the PC-based algorithms are still sensitive to the ordering of nodes i.e. different node orders results in different network structures. The second is that the networks inferred by these methods are highly dependent on the threshold used for independence testing. Also, it is still a challenge to select the set of conditional genes in an optimal way, which affects the performance and computation complexity of the PC-based algorithm. We introduce a novel algorithm, namely Order Independent PC-based algorithm using Quantile value (OIPCQ), which improves the accuracy of the learning process of GRNs and solves the order dependency issue. The quantile-based thresholds are considered for different orders of CMI tests. For conditional gene selection, we consider the paths between genes with length equal or greater than 2 while other well-known PC-based methods only consider the paths of length 2. We applied OIPCQ on the various networks of the DREAM3 and DREAM4 in silico challenges. As a real-world case study, we used OIPCQ to reconstruct SOS DNA network obtained from Escherichia coli and GRN for acute myeloid leukemia based on the RNA sequencing data from The Cancer Genome Atlas. The results show that OIPCQ produces the same network structure for all the permutations of the genes and improves the resulted GRN through accurately quantifying the causal regulation strength in comparison with other well-known PC-based methods. According to the GRN constructed by OIPCQ, for acute myeloid leukemia, two regulators BCLAF1 and NRSF reported previously are significantly important. However, the highest degree nodes in this GRN are ZBTB7A and PU1 which play a significant role in cancer, especially in leukemia. OIPCQ is freely accessible at https://github.com/haammim/OIPCQ-and-OIPCQ2 .

In silico studies reveal structural deviations of mutant profilin-1 and interaction with riluzole and edaravone in amyotrophic lateral sclerosis.

This study aimed to investigate four of the eight PFN-1 mutations that are located near the actin-binding domain and determine the structural changes due to each mutant and unravel how these mutations alter protein structural behavior. Swapaa's command in UCSF chimera for generating mutations, FTMAP were employed and the data was analyzed by RMSD, RMSF graphs, Rg, hydrogen bonding analysis, and RRdisMaps utilizing Autodock4 and GROMACS. The functional changes and virtual screening, structural dynamics, and chemical bonding behavior changes, molecular docking simulation with two current FDA-approved drugs for ALS were investigated. The highest reduction and increase in Rg were found to exist in the G117V and M113T mutants, respectively. The RMSF data consistently shows changes nearby to this site. The in silico data described indicate that each of the mutations is capable of altering the structure of PFN-1 in vivo. The potential effect of riluzole and edaravone two FDA approved drugs for ALS, impacting the structural deviations and stabilization of the mutant PFN-1 is evaluated using in silico tools. Overall, the analysis of data collected reveals structural changes of mutant PFN-1 protein that may explain the neurotoxicity and the reason(s) for possible loss and gain of function of PFN-1 in the neurotoxic model of ALS.

DisCoVering potential candidates of RNAi-based therapy for COVID-19 using computational methods.

The ongoing pandemic of a novel coronavirus (SARS-CoV-2) leads to international concern; thus, emergency interventions need to be taken. Due to the time-consuming experimental methods for proposing useful treatments, computational approaches facilitate investigating thousands of alternatives simultaneously and narrow down the cases for experimental validation. Herein, we conducted four independent analyses for RNA interference (RNAi)-based therapy with computational and bioinformatic methods. The aim is to target the evolutionarily conserved regions in the SARS-CoV-2 genome in order to down-regulate or silence its RNA. miRNAs are denoted to play an important role in the resistance of some species to viral infections. A comprehensive analysis of the miRNAs available in the body of humans, as well as the miRNAs in bats and many other species, were done to find efficient candidates with low side effects in the human body. Moreover, the evolutionarily conserved regions in the SARS-CoV-2 genome were considered for designing novel significant siRNA that are target-specific. A small set of miRNAs and five siRNAs were suggested as the possible efficient candidates with a high affinity to the SARS-CoV-2 genome and low side effects. The suggested candidates are promising therapeutics for the experimental evaluations and may speed up the procedure of treatment design. Materials and implementations are available at: https://github.com/nrohani/SARS-CoV-2.

Auto-HMM-LMF: feature selection based method for prediction of drug response via autoencoder and hidden Markov model.

BACKGROUND: Predicting the response of cancer cell lines to specific drugs is an essential problem in personalized medicine. Since drug response is closely associated with genomic information in cancer cells, some large panels of several hundred human cancer cell lines are organized with genomic and pharmacogenomic data. Although several methods have been developed to predict the drug response, there are many challenges in achieving accurate predictions. This study proposes a novel feature selection-based method, named Auto-HMM-LMF, to predict cell line-drug associations accurately. Because of the vast dimensions of the feature space for predicting the drug response, Auto-HMM-LMF focuses on the feature selection issue for exploiting a subset of inputs with a significant contribution. RESULTS: This research introduces a novel method for feature selection of mutation data based on signature assignments and hidden Markov models. Also, we use the autoencoder models for feature selection of gene expression and copy number variation data. After selecting features, the logistic matrix factorization model is applied to predict drug response values. Besides, by comparing to one of the most powerful feature selection methods, the ensemble feature selection method (EFS), we showed that the performance of the predictive model based on selected features introduced in this paper is much better for drug response prediction. Two datasets, the Genomics of Drug Sensitivity in Cancer (GDSC) and Cancer Cell Line Encyclopedia (CCLE) are used to indicate the efficiency of the proposed method across unseen patient cell-line. Evaluation of the proposed model showed that Auto-HMM-LMF could improve the accuracy of the results of the state-of-the-art algorithms, and it can find useful features for the logistic matrix factorization method. CONCLUSIONS: We depicted an application of Auto-HMM-LMF in exploring the new candidate drugs for head and neck cancer that showed the proposed method is useful in drug repositioning and personalized medicine. The source code of Auto-HMM-LMF method is available in https://github.com/emdadi/Auto-HMM-LMF .

Classifying Breast Cancer Molecular Subtypes by Using Deep Clustering Approach.

Cancer is a complex disease with a high rate of mortality. The characteristics of tumor masses are very heterogeneous; thus, the appropriate classification of tumors is a critical point in the effective treatment. A high level of heterogeneity has also been observed in breast cancer. Therefore, detecting the molecular subtypes of this disease is an essential issue for medicine that could be facilitated using bioinformatics. This study aims to discover the molecular subtypes of breast cancer using somatic mutation profiles of tumors. Nonetheless, the somatic mutation profiles are very sparse. Therefore, a network propagation method is used in the gene interaction network to make the mutation profiles dense. Afterward, the deep embedded clustering (DEC) method is used to classify the breast tumors into four subtypes. In the next step, gene signature of each subtype is obtained using Fisher's exact test. Besides the enrichment of gene signatures in numerous biological databases, clinical and molecular analyses verify that the proposed method using mutation profiles can efficiently detect the molecular subtypes of breast cancer. Finally, a supervised classifier is trained based on the discovered subtypes to predict the molecular subtype of a new patient. The code and material of the method are available at: https://github.com/nrohani/MolecularSubtypes.

ADRML: anticancer drug response prediction using manifold learning.

One of the prominent challenges in precision medicine is to select the most appropriate treatment strategy for each patient based on the personalized information. The availability of massive data about drugs and cell lines facilitates the possibility of proposing efficient computational models for predicting anticancer drug response. In this study, we propose ADRML, a model for Anticancer Drug Response Prediction using Manifold Learning to systematically integrate the cell line information with the drug information to make accurate predictions about drug therapeutic. The proposed model maps the drug response matrix into the lower-rank spaces that lead to obtaining new perspectives about cell lines and drugs. The drug response for a new cell line-drug pair is computed using the low-rank features. The evaluation of ADRML performance on various types of cell lines and drug information, in addition to the comparisons with previously proposed methods, shows that ADRML provides accurate and robust predictions. Further investigations about the association between drug response and pathway activity scores reveal that the predicted drug responses can shed light on the underlying drug mechanism. Also, the case studies suggest that the predictions of ADRML about novel cell line-drug pairs are validated by reliable pieces of evidence from the literature. Consequently, the evaluations verify that ADRML can be used in accurately predicting and imputing the anticancer drug response.