Cell-free DNA in maternal blood and artificial intelligence: accurate prenatal detection of fetal congenital heart defects.

BACKGROUND: DNA cytosine nucleotide methylation (epigenomics and epigenetics) is an important mechanism for controlling gene expression in cardiac development. Combined artificial intelligence and whole-genome epigenomic analysis of circulating cell-free DNA in maternal blood has the potential for the detection of fetal congenital heart defects. OBJECTIVE: This study aimed to use genome-wide DNA cytosine methylation and artificial intelligence analyses of circulating cell-free DNA for the minimally invasive detection of fetal congenital heart defects. STUDY DESIGN: In this prospective study, whole-genome cytosine nucleotide methylation analysis was performed on circulating cell-free DNA using the Illumina Infinium MethylationEPIC BeadChip array. Multiple artificial intelligence approaches were evaluated for the detection of congenital hearts. The Ingenuity Pathway Analysis program was used to identify gene pathways that were epigenetically altered and important in congenital heart defect pathogenesis to further elucidate the pathogenesis of isolated congenital heart defects. RESULTS: There were 12 cases of isolated nonsyndromic congenital heart defects and 26 matched controls. A total of 5918 cytosine nucleotides involving 4976 genes had significantly altered methylation, that is, a P value of <.05 along with ≥5% whole-genome cytosine nucleotide methylation difference, in congenital heart defect cases vs controls. Artificial intelligence analysis of the methylation data achieved excellent congenital heart defect predictive accuracy (areas under the receiver operating characteristic curve, ≥0.92). For example, an artificial intelligence model using a combination of 5 whole-genome cytosine nucleotide markers achieved an area under the receiver operating characteristic curve of 0.97 (95% confidence interval, 0.87-1.0) with 98% sensitivity and 94% specificity. We found epigenetic changes in genes and gene pathways involved in the following important cardiac developmental processes: "cardiovascular system development and function," "cardiac hypertrophy," "congenital heart anomaly," and "cardiovascular disease." This lends biologic plausibility to our findings. CONCLUSION: This study reported the feasibility of minimally invasive detection of fetal congenital heart defect using artificial intelligence and DNA methylation analysis of circulating cell-free DNA for the prediction of fetal congenital heart defect. Furthermore, the findings supported an important role of epigenetic changes in congenital heart defect development.

Maternal opioid use disorder: Placental transcriptome analysis for neonatal opioid withdrawal syndrome.

Excessive prenatal opioid exposure may lead to the development of Neonatal Opioid Withdrawal Syndrome (NOWS). RNA-seq was done on 64 formalin-fixed paraffin-embedded placental tissue samples from 32 mothers with opioid use disorder, with newborns with NOWS that required treatment, and 32 prenatally unexposed controls. We identified 93 differentially expressed genes in the placentas of infants with NOWS compared to unexposed controls. There were 4 up- and 89 downregulated genes. Among these, 7 genes CYP1A1, APOB, RPH3A, NRXN1, LINC01206, AL157396.1, UNC80 achieved an FDR p-value of <0.01. The remaining 87 genes were significant with FDR p-value <0.05. The 4 upregulated, CYP1A1, FP671120.3, RAD1, RN7SL856P, and the 10 most significantly downregulated genes were RNA5SP364, GRIN2A, UNC5D, DMBT1P1, MIR3976HG, LINC02199, LINC02822, PANTR1, AC012178.1, CTNNA2. Ingenuity Pathway Analysis identified the 7 most likely to play an important role in the etiology of NOWS. Our study expands insights into the genetic mechanisms of NOWS development.

Placental DNA methylation profiles in opioid-exposed pregnancies and associations with the neonatal opioid withdrawal syndrome.

Opioid abuse during pregnancy can result in Neonatal Opioid Withdrawal Syndrome (NOWS). We investigated genome-wide methylation analyses of 96 placental tissue samples, including 32 prenatally opioid-exposed infants with NOWS who needed therapy (+Opioids/+NOWS), 32 prenatally opioid-exposed infants with NOWS who did not require treatment (+Opioids/-NOWS), and 32 prenatally unexposed controls (-Opioids/-NOWS, control). Statistics, bioinformatics, Artificial Intelligence (AI), including Deep Learning (DL), and Ingenuity Pathway Analyses (IPA) were performed. We identified 17 dysregulated pathways thought to be important in the pathophysiology of NOWS and reported accurate AI prediction of NOWS diagnoses. The DL had an AUC (95% CI) =0.98 (0.95-1.0) with a sensitivity and specificity of 100% for distinguishing NOWS from the +Opioids/-NOWS group and AUCs (95% CI) =1.00 (1.0-1.0) with a sensitivity and specificity of 100% for distinguishing NOWS versus control and + Opioids/-NOWS group versus controls. This study provides strong evidence of methylation dysregulation of placental tissue in NOWS development.

Red panda: a novel method for detecting variants in single-cell RNA sequencing.

BACKGROUND: Single-cell sequencing enables us to better understand genetic diseases, such as cancer or autoimmune disorders, which are often affected by changes in rare cells. Currently, no existing software is aimed at identifying single nucleotide variations or micro (1-50 bp) insertions and deletions in single-cell RNA sequencing (scRNA-seq) data. Generating high-quality variant data is vital to the study of the aforementioned diseases, among others. RESULTS: In this study, we report the design and implementation of Red Panda, a novel method to accurately identify variants in scRNA-seq data. Variants were called on scRNA-seq data from human articular chondrocytes, mouse embryonic fibroblasts (MEFs), and simulated data stemming from the MEF alignments. Red Panda had the highest Positive Predictive Value at 45.0%, while other tools-FreeBayes, GATK HaplotypeCaller, GATK UnifiedGenotyper, Monovar, and Platypus-ranged from 5.8-41.53%. From the simulated data, Red Panda had the highest sensitivity at 72.44%. CONCLUSIONS: We show that our method provides a novel and improved mechanism to identify variants in scRNA-seq as compared to currently existing software. However, methods for identification of genomic variants using scRNA-seq data can be still improved.

Sex-Specific Whole-Transcriptome Analysis in the Cerebral Cortex of FAE Offspring.

Fetal alcohol spectrum disorders (FASDs) are associated with systemic inflammation and neurodevelopmental abnormalities. Several candidate genes were found to be associated with fetal alcohol exposure (FAE)-associated behaviors, but a sex-specific complete transcriptomic analysis was not performed at the adult stage. Recent studies have shown that they are regulated at the developmental stage. However, the sex-specific role of RNA in FAE offspring brain development and function has not been studied yet. Here, we carried out the first systematic RNA profiling by utilizing a high-throughput transcriptomic (RNA-seq) approach in response to FAE in the brain cortex of male and female offspring at adulthood (P60). Our RNA-seq data analysis suggests that the changes in RNA expression in response to FAE are marked sex-specific. We show that the genes Muc3a, Pttg1, Rec8, Clcnka, Capn11, and pnp2 exhibit significantly higher expression in the male offspring than in the female offspring at P60. FAE female mouse brain sequencing data also show an increased expression of Eno1, Tpm3, and Pcdhb2 compared to male offspring. We performed a pathway analysis using a commercial software package (Ingenuity Pathway Analysis). We found that the sex-specific top regulator genes (Rictor, Gaba, Fmri, Mlxipl) are highly associated with eIF2 (translation initiation), synaptogenesis (the formation of synapses between neurons in the nervous system), sirtuin (metabolic regulation), and estrogen receptor (involved in obesity, aging, and cancer) signaling. Taken together, our transcriptomic results demonstrate that FAE differentially alters RNA expression in the adult brain in a sex-specific manner.

A Review of Radiation-Induced Alterations of Multi-Omic Profiles, Radiation Injury Biomarkers, and Countermeasures.

Increasing utilization of nuclear power enhances the risks associated with industrial accidents, occupational hazards, and the threat of nuclear terrorism. Exposure to ionizing radiation interferes with genomic stability and gene expression resulting in the disruption of normal metabolic processes in cells and organs by inducing complex biological responses. Exposure to high-dose radiation causes acute radiation syndrome, which leads to hematopoietic, gastrointestinal, cerebrovascular, and many other organ-specific injuries. Altered genomic variations, gene expression, metabolite concentrations, and microbiota profiles in blood plasma or tissue samples reflect the whole-body radiation injuries. Hence, multi-omic profiles obtained from high-resolution omics platforms offer a holistic approach for identifying reliable biomarkers to predict the radiation injury of organs and tissues resulting from radiation exposures. In this review, we performed a literature search to systematically catalog the radiation-induced alterations from multi-omic studies and radiation countermeasures. We covered radiation-induced changes in the genomic, transcriptomic, proteomic, metabolomic, lipidomic, and microbiome profiles. Furthermore, we have covered promising multi-omic biomarkers, FDA-approved countermeasure drugs, and other radiation countermeasures that include radioprotectors and radiomitigators. This review presents an overview of radiation-induced alterations of multi-omics profiles and biomarkers, and associated radiation countermeasures.

Precision cardiovascular medicine: artificial intelligence and epigenetics for the pathogenesis and prediction of coarctation in neonates.

BACKGROUND: Advances in omics and computational Artificial Intelligence (AI) have been said to be key to meeting the objectives of precision cardiovascular medicine. The focus of precision medicine includes a better assessment of disease risk and understanding of disease mechanisms. Our objective was to determine whether significant epigenetic changes occur in isolated, non-syndromic CoA. Further, we evaluated the AI analysis of DNA methylation for the prediction of CoA. METHODS: Genome-wide DNA methylation analysis of newborn blood DNA was performed in 24 isolated, non-syndromic CoA cases and 16 controls using the Illumina HumanMethylation450 BeadChip arrays. Cytosine nucleotide (CpG) methylation changes in CoA in each of 450,000 CpG loci were determined. Ingenuity pathway analysis (IPA) was performed to identify molecular and disease pathways that were epigenetically dysregulated. Using methylation data, six artificial intelligence (AI) platforms including deep learning (DL) was used for CoA detection. RESULTS: We identified significant (FDR p-value ≤ .05) methylation changes in 65 different CpG sites located in 75 genes in CoA subjects. DL achieved an AUC (95% CI) = 0.97 (0.80-1) with 95% sensitivity and 98% specificity. Gene ontology (GO) analysis yielded epigenetic alterations in important cardiovascular developmental genes and biological processes: abnormal morphology of cardiovascular system, left ventricular dysfunction, heart conduction disorder, thrombus formation, and coronary artery disease. CONCLUSION: In an exploratory study we report the use of AI and epigenomics to achieve important objectives of precision cardiovascular medicine. Accurate prediction of CoA was achieved using a newborn blood spot. Further, we provided evidence of a significant epigenetic etiology in isolated CoA development.

New-onset postpartum preeclampsia: epigenetic mechanism and prediction.

OBJECTIVE: Placental cytosine (CpG) methylation was measured to predict new-onset postpartum preeclampsia (NOPP) and interrogate its molecular pathogenesis. METHODS: NOPP was defined as patients with a new diagnosis of postpartum preeclampsia developing ≥48 h to ≤6 weeks after delivery with no prior hypertensive disorders. Placental tissue was obtained from 12 NOPP cases and 12 normotensive controls. Genome-wide individual cytosine (CpG) methylation level was measured with the Infinium MethylationEPIC BeadChip array. Significant differential methylation (NOPP vs. controls) for individual CpG loci was defined as false discovery rate (FDR) p value <.05. Gene functional enrichment using Qiagen's ingenuity pathway analysis (IPA) was performed to help elucidate the molecular pathogenesis of NOPP. A logistic regression model for NOPP prediction based on the methylation level in a combination of CpG loci was generated. The area under the receiver operating characteristic curves (AUC [95% CI]) sensitivity, and specificity for NOPP prediction based on the CpG methylation level was calculated for each locus. RESULTS: There were 537 (in 540 separate genes) significantly (FDR p<.05 with a ≥ 2.0-fold methylation difference) differentially methylated CpG loci between the groups. A total of 143 individual CpG markers had excellent individual predictive accuracy for NOPP prediction (AUC ≥0.80), of which 14 markers had outstanding accuracy (AUC ≥0.90). A logistic regression model based on five CpG markers yielded an AUC (95% CI)=0.99 (0.95-0.99) with sensitivity 95% and specificity 93% for NOPP prediction. IPA revealed dysregulation of critical pathways (e.g., angiogenesis, chronic inflammation, and epithelial-mesenchymal transition) known to be linked to classic preeclampsia, in addition to other previously undescribed genes/pathways. CONCLUSIONS: There was significant placental epigenetic dysregulation in NOPP. NOPP shared both common and unique molecular pathways with classic preeclampsia. Finally, we have identified novel potential biomarkers for the early post-partum prediction of NOPP.

A novel dual epigenetic approach targeting BET proteins and HDACs in Group 3 (MYC-driven) Medulloblastoma.

BACKGROUND: Medulloblastoma (MB) patients with MYC oncogene amplification or overexpression exhibit extremely poor clinical outcomes and respond poorly to current therapies. Epigenetic deregulation is very common in MYC-driven MB. The bromodomain extra-terminal (BET) proteins and histone deacetylases (HDACs) are epigenetic regulators of MYC transcription and its associated tumorigenic programs. This study aimed to investigate the therapeutic potential of inhibiting the BET proteins and HDACs together in MB. METHODS: Using clinically relevant BET inhibitors (JQ1 or OTX015) and a pan-HDAC inhibitor (panobinostat), we evaluated the effects of combined inhibition on cell growth/survival in MYC-amplified MB cell lines and xenografts and examined underlying molecular mechanism(s). RESULTS: Co-treatment of JQ1 or OTX015 with panobinostat synergistically suppressed growth/survival of MYC-amplified MB cells by inducing G2 cell cycle arrest and apoptosis. Mechanistic investigation using RNA-seq revealed that co-treatment of JQ1 with panobinostat synergistically modulated global gene expression including MYC/HDAC targets. SYK and MSI1 oncogenes were among the top 50 genes synergistically downregulated by JQ1 and panobinostat. RT-PCR and western blot analyses confirmed that JQ1 and panobinostat synergistically inhibited the mRNA and protein expression of MSI1/SYK along with MYC expression. Reduced SYK/MSI expression after BET (specifically, BRD4) gene-knockdown further confirmed the epigenetic regulation of SYK and MSI1 genes. In addition, the combination of OTX015 and panobinostat significantly inhibited tumor growth in MYC-amplified MB xenografted mice by downregulating expression of MYC, compared to single-agent therapy. CONCLUSIONS: Together, our findings demonstrated that dual-inhibition of BET and HDAC proteins of the epigenetic pathway can be a novel therapeutic approach against MYC-driven MB.

The Mammalian Ecdysoneless Protein Interacts with RNA Helicase DDX39A To Regulate Nuclear mRNA Export.

The mammalian orthologue of ecdysoneless (ECD) protein is required for embryogenesis, cell cycle progression, and mitigation of endoplasmic reticulum stress. Here, we identified key components of the mRNA export complexes as binding partners of ECD and characterized the functional interaction of ECD with key mRNA export-related DEAD BOX protein helicase DDX39A. We find that ECD is involved in RNA export through its interaction with DDX39A. ECD knockdown (KD) blocks mRNA export from the nucleus to the cytoplasm, which is rescued by expression of full-length ECD but not an ECD mutant that is defective in interaction with DDX39A. We have previously shown that ECD protein is overexpressed in ErbB2+ breast cancers (BC). In this study, we extended the analyses to two publicly available BC mRNA The Cancer Genome Atlas (TCGA) and Molecular Taxonomy of Breast Cancer International Consortium (METABRIC) data sets. In both data sets, ECD mRNA overexpression correlated with short patient survival, specifically ErbB2+ BC. In the METABRIC data set, ECD overexpression also correlated with poor patient survival in triple-negative breast cancer (TNBC). Furthermore, ECD KD in ErbB2+ BC cells led to a decrease in ErbB2 mRNA level due to a block in its nuclear export and was associated with impairment of oncogenic traits. These findings provide novel mechanistic insight into the physiological and pathological functions of ECD.

Prediction of FAD interacting residues in a protein from its primary sequence using evolutionary information.

BACKGROUND: Flavin binding proteins (FBP) plays a critical role in several biological functions such as electron transport system (ETS). These flavoproteins contain very tightly bound, sometimes covalently, flavin adenine dinucleotide (FAD) or flavin mono nucleotide (FMN). The interaction between flavin nucleotide and amino acids of flavoprotein is essential for their functionality. Thus identification of FAD interacting residues in a FBP is an important step for understanding their function and mechanism. RESULTS: In this study, we describe models developed for predicting FAD interacting residues using 15, 17 and 19 window pattern. Support vector machine (SVM) based models have been developed using binary pattern of amino acid sequence of protein and achieved maximum accuracy 69.65% with Mathew's Correlation Coefficient (MCC) 0.39 and Area Under Curve (AUC) 0.773. The performance of these models have been improved significantly from 69.65% to 82.86% with MCC 0.66 and AUC 0.904, when evolutionary information is used as input in SVM. The evolutionary information was generated in form of position specific score matrix (PSSM) profile by using PSI-BLAST at e-value 0.001. All models were developed on 198 non-redundant FAD binding protein chains containing 5172 FAD interacting residues and evaluated using fivefold cross-validation technique. CONCLUSION: This study suggests that evolutionary information of 17 amino acid patterns perform best for FAD interacting residues prediction. We also developed a web server which predicts FAD interacting residues in a protein which is freely available for academics.

Prediction of GTP interacting residues, dipeptides and tripeptides in a protein from its evolutionary information.

BACKGROUND: Guanosine triphosphate (GTP)-binding proteins play an important role in regulation of G-protein. Thus prediction of GTP interacting residues in a protein is one of the major challenges in the field of the computational biology. In this study, an attempt has been made to develop a computational method for predicting GTP interacting residues in a protein with high accuracy (Acc), precision (Prec) and recall (Rc). RESULT: All the models developed in this study have been trained and tested on a non-redundant (40% similarity) dataset using five-fold cross-validation. Firstly, we have developed neural network based models using single sequence and PSSM profile and achieved maximum Matthews Correlation Coefficient (MCC) 0.24 (Acc 61.30%) and 0.39 (Acc 68.88%) respectively. Secondly, we have developed a support vector machine (SVM) based models using single sequence and PSSM profile and achieved maximum MCC 0.37 (Prec 0.73, Rc 0.57, Acc 67.98%) and 0.55 (Prec 0.80, Rc 0.73, Acc 77.17%) respectively. In this work, we have introduced a new concept of predicting GTP interacting dipeptide (two consecutive GTP interacting residues) and tripeptide (three consecutive GTP interacting residues) for the first time. We have developed SVM based model for predicting GTP interacting dipeptides using PSSM profile and achieved MCC 0.64 with precision 0.87, recall 0.74 and accuracy 81.37%. Similarly, SVM based model have been developed for predicting GTP interacting tripeptides using PSSM profile and achieved MCC 0.70 with precision 0.93, recall 0.73 and accuracy 83.98%. CONCLUSION: These results show that PSSM based method performs better than single sequence based method. The prediction models based on dipeptides or tripeptides are more accurate than the traditional model based on single residue. A web server "GTPBinder" http://www.imtech.res.in/raghava/gtpbinder/ based on above models has been developed for predicting GTP interacting residues in a protein.

AntiBP2: improved version of antibacterial peptide prediction.

BACKGROUND: Antibacterial peptides are one of the effecter molecules of innate immune system. Over the last few decades several antibacterial peptides have successfully approved as drug by FDA, which has prompted an interest in these antibacterial peptides. In our recent study we analyzed 999 antibacterial peptides, which were collected from Antibacterial Peptide Database (APD). We have also developed methods to predict and classify these antibacterial peptides using Support Vector Machine (SVM). RESULTS: During analysis we observed that certain residues are preferred over other in antibacterial peptide, particularly at the N and C terminus. These observation and increased data of antibacterial peptide in APD encouraged us to again develop a new and more robust method for predicting antibacterial peptides in protein from their amino acid sequence or given peptide have antibacterial properties or not. First, the binary patterns of the 15 N terminus residues were used for predicting antibacterial peptide using SVM and achieved accuracy of 85.46% with 0.705 Mathew's Correlation Coefficient (MCC). Then we used the binary pattern of 15 C terminus residues and achieved accuracy of 85.05% with 0.701 MCC, latter on we developed prediction method by combining N & C terminus and achieved an accuracy of 91.64% with 0.831 MCC. Finally we developed SVM based model using amino acid composition of whole peptide and achieved 92.14% accuracy with MCC 0.843. In this study we used five-fold cross validation technique to develop all these models and tested the performance of these models on an independent dataset. We further classify antibacterial peptides according to their sources and achieved an overall accuracy of 98.95%. We further classify antibacterial peptides in their respective family and got a satisfactory result. CONCLUSION: Among antibacterial peptides, there is preference for certain residues at N and C terminus, which helps to discriminate them from non-antibacterial peptides. Amino acid composition of antibacterial peptides helps to demarcate them from non-antibacterial peptide and their further classification in source and family. Antibp2 will be helpful in discovering efficacious antibacterial peptide, which we hope will be helpful against antibiotics resistant bacteria. We also developed user friendly web server for the biological community.

Prediction of cytochrome P450 isoform responsible for metabolizing a drug molecule.

BACKGROUND: Different isoforms of Cytochrome P450 (CYP) metabolized different types of substrates (or drugs molecule) and make them soluble during biotransformation. Therefore, fate of any drug molecule depends on how they are treated or metabolized by CYP isoform. There is a need to develop models for predicting substrate specificity of major isoforms of P450, in order to understand whether a given drug will be metabolized or not. This paper describes an in-silico method for predicting the metabolizing capability of major isoforms (e.g. CYP 3A4, 2D6, 1A2, 2C9 and 2C19). RESULTS: All models were trained and tested on 226 approved drug molecules. Firstly, 2392 molecular descriptors for each drug molecule were calculated using various softwares. Secondly, best 41 descriptors were selected using general and genetic algorithm. Thirdly, Support Vector Machine (SVM) based QSAR models were developed using 41 best descriptors and achieved an average accuracy of 86.02%, evaluated using fivefold cross-validation. We have also evaluated the performance of our model on an independent dataset of 146 drug molecules and achieved average accuracy 70.55%. In addition, SVM based models were developed using 26 Chemistry Development Kit (CDK) molecular descriptors and achieved an average accuracy of 86.60%. CONCLUSIONS: This study demonstrates that SVM based QSAR model can predict substrate specificity of major CYP isoforms with high accuracy. These models can be used to predict isoform responsible for metabolizing a drug molecule. Thus these models can used to understand whether a molecule will be metabolized or not. This is possible to develop highly accurate models for predicting substrate specificity of major isoforms using CDK descriptors. A web server MetaPred has been developed for predicting metabolizing isoform of a drug molecule http://crdd.osdd.net/raghava/metapred/.

Pan-Cancer Analysis Reveals the Diverse Landscape of Novel Sense and Antisense Fusion Transcripts.

Gene fusions that contribute to oncogenicity can be explored for identifying cancer biomarkers and potential drug targets. To investigate the nature and distribution of fusion transcripts in cancer, we examined the transcriptome data of about 9,000 primary tumors from 33 different cancers in TCGA (The Cancer Genome Atlas) along with cell line data from CCLE (Cancer Cell Line Encyclopedia) using ChimeRScope, a novel fusion detection algorithm. We identified several fusions with sense (canonical, 39%) or antisense (non-canonical, 61%) transcripts recurrent across cancers. The majority of the recurrent non-canonical fusions found in our study are novel, unexplored, and exhibited highly variable profiles across cancers, with breast cancer and glioblastoma having the highest and lowest rates, respectively. Overall, 4,344 recurrent fusions were identified from TCGA in this study, of which 70% were novel. Additional analysis of 802 tumor-derived cell line transcriptome data across 20 cancers revealed significant variability in recurrent fusion profiles between primary tumors and corresponding cell lines. A subset of canonical and non-canonical fusions was validated by examining the structural variation evidence in whole-genome sequencing (WGS) data or by Sanger sequencing of fusion junctions. Several recurrent fusion genes identified in our study show promise for drug repurposing in basket trials and present opportunities for mechanistic studies.

Identification of ATP binding residues of a protein from its primary sequence.

BACKGROUND: One of the major challenges in post-genomic era is to provide functional annotations for large number of proteins arising from genome sequencing projects. The function of many proteins depends on their interaction with small molecules or ligands. ATP is one such important ligand that plays critical role as a coenzyme in the functionality of many proteins. There is a need to develop method for identifying ATP interacting residues in a ATP binding proteins (ABPs), in order to understand mechanism of protein-ligands interaction. RESULTS: We have compared the amino acid composition of ATP interacting and non-interacting regions of proteins and observed that certain residues are preferred for interaction with ATP. This study describes few models that have been developed for identifying ATP interacting residues in a protein. All these models were trained and tested on 168 non-redundant ABPs chains. First we have developed a Support Vector Machine (SVM) based model using primary sequence of proteins and obtained maximum MCC 0.33 with accuracy of 66.25%. Secondly, another SVM based model was developed using position specific scoring matrix (PSSM) generated by PSI-BLAST. The performance of this model was improved significantly (MCC 0.5) from the previous one, where only the primary sequence of the proteins were used. CONCLUSION: This study demonstrates that it is possible to predict 'ATP interacting residues' in a protein with moderate accuracy using its sequence. The evolutionary information is important for the identification of 'ATP interacting residues', as it provides more information compared to the primary sequence. This method will be useful for researchers studying ATP-binding proteins. Based on this study, a web server has been developed for predicting 'ATP interacting residues' in a protein http://www.imtech.res.in/raghava/atpint/.

Artificial intelligence analysis of newborn leucocyte epigenomic markers for the prediction of autism.

A great diversity of factors contribute to the pathogenesis of autism and autism spectrum disorder (ASD). Early detection is known to correlate with improved long term outcomes. There is therefore intense scientific interest in the pathogenesis of and early prediction of autism. Recent reports suggest that epigenetic alterations may play a vital role in disease pathophysiology. We conducted an epigenome-wide analysis of newborn leucocyte (blood spot) DNA in autism as defined at the time of sample collection. Our goal was to investigate the epigenetic basis of autism and identification of early biomarkers for disease prediction. Infinium HumanMethylation450 BeadChip assay was performed to measure DNA methylation level in 14 autism cases and 10 controls. The accuracy of cytosine methylation for autism detection using six different Machine Learning/Artificial Intelligence (AI) approaches including Deep-Learning (DL) was determined. Ingenuity Pathway Analysis (IPA) was further used to interrogate autism pathogenesis by identifying over-represented biological pathways. We found highly significant dysregulation of CpG methylation in 230 loci (249 genes). DL yielded an AUC (95% CI) = 1.00 (0.80-1.00) with 97.5% sensitivity and 100.0% specificity for autism detection. Epigenetic dysregulation was identified in several important candidate genes including some previously linked to autism development e.g.: EIF4E, FYN, SHANK1, VIM, LMX1B, GABRB1, SDHAP3 and PACS2. We observed significant enrichment of molecular pathways involved in neuroinflammation signaling, synaptic long term potentiation, serotonin degradation, mTOR signaling and signaling by Rho-Family GTPases. Our findings suggest significant epigenetic role in autism development and epigenetic markers appeared highly accurate for newborn prediction.

Epigenetically dysregulated genes and pathways implicated in the pathogenesis of non-syndromic high myopia.

Myopia, commonly referred to as nearsightedness, is one of the most common causes of visual disability throughout the world. It affects more people worldwide than any other chronic visual impairment condition. Although the prevalence varies among various ethnic groups, the incidence of myopia is increasing in all populations across globe. Thus, it is considered a pressing public health problem. Both genetics and environment play a role in development of myopia. To elucidate the epigenetic mechanism(s) underlying the pathophysiology of high-myopia, we conducted methylation profiling in 18 cases and 18 matched controls (aged 4-12 years), using Illumina MethylationEPIC BeadChips array. The degree of myopia was variable among subjects, ranging from -6 to -15D. We identified 1541 hypermethylated CpGs, representing 1745 genes (2.0-fold or higher) (false discovery rate (FDR) p ≤ 0.05), multiple CpGs were p < 5 × 10-8 with a receiver operating characteristic area under the curve (ROC-AUC) ≥ 0.75 in high-myopia subjects compared to controls. Among these, 48 CpGs had excellent correlation (AUC ≥ 0.90). Herein, we present the first genome-wide DNA methylation analysis in a unique high-myopia cohort, showing extensive and discrete methylation changes relative to controls. The genes we identified hold significant potential as targets for novel therapeutic intervention either alone, or in combination.

Placental epigenetics for evaluation of fetal congenital heart defects: Ventricular Septal Defect (VSD).

Ventricular Septal Defect (VSD), the most common congenital heart defect, is characterized by a hole in the septum between the right and left ventricles. The pathogenesis of VSD is unknown in most clinical cases. There is a paucity of data relevant to epigenetic changes in VSD. The placenta is a fetal tissue crucial in cardiac development and a potentially useful surrogate for evaluating the development of heart tissue. To understand epigenetic mechanisms that may play a role in the development of VSD, genome-wide DNA methylation assay on placentas of 8 term subjects with isolated VSD and no known or suspected genetic syndromes and 10 unaffected controls was performed using the Illumina HumanMethylation450 BeadChip assay. We identified a total of 80 highly accurate potential CpGs in 80 genes for detection of VSD; area under the receiver operating characteristic curve (AUC ROC) 1.0 with significant 95% CI (FDR) p-values < 0.05 for each individual locus. The biological processes and functions for many of these differentially methylated genes are previously known to be associated with heart development or disease, including cardiac ventricle development (HEY2, ISL1), heart looping (SRF), cardiac muscle cell differentiation (ACTC1, HEY2), cardiac septum development (ISL1), heart morphogenesis (SRF, HEY2, ISL1, HEYL), Notch signaling pathway (HEY2, HEYL), cardiac chamber development (ISL1), and cardiac muscle tissue development (ACTC1, ISL1). In addition, we identified 8 microRNAs that have the potential to be biomarkers for the detection of VSD including: miR-191, miR-548F1, miR-148A, miR-423, miR-92B, miR-611, miR-2110, and miR-548H4. To our knowledge this is the first report in which placental analysis has been used for determining the pathogenesis of and predicting VSD.

Newborn blood DNA epigenetic variations and signaling pathway genes associated with Tetralogy of Fallot (TOF).

Tetralogy of Fallot (TOF) is the most common Critical Congenital Heart Defect (CCHD). The etiology of TOF is unknown in most cases. Preliminary data from our group and others suggest that epigenetic changes may play an important role in CHD. Epidemiologically, a significant percentage of CHD including TOF fail to be diagnosed in the prenatal and early newborn period which can negatively affect health outcomes. We performed genome-wide methylation assay in newborn blood in 24 non-syndromic TOF cases and 24 unaffected matched controls using Illumina Infinium HumanMethylation450 BeadChips. We identified 64 significantly differentially methylated CpG sites in TOF cases, of which 25 CpG sites had high predictive accuracy for TOF, based on the area under the receiver operating characteristics curve (AUC ROC) ≥ 0.90). The CpG methylation difference between TOF and controls was ≥10% in 51 CpG targets suggesting biological significance. Gene ontology analysis identified significant biological processes and functions related to these differentially methylated genes, including: CHD development, cardiomyopathy, diabetes, immunological, inflammation and other plausible pathways in CHD development. Multiple genes known or plausibly linked to heart development and post-natal heart disease were found to be differentially methylated in the blood DNA of newborns with TOF including: ABCB1, PPP2R5C, TLR1, SELL, SCN3A, CREM, RUNX and LHX9. We generated novel and highly accurate putative molecular markers for TOF detection using leucocyte DNA and thus provided information on pathogenesis of TOF.