Insights into the gut microbiome of vitiligo patients from India.

BACKGROUND: Vitiligo is an autoimmune disease characterized by loss of pigmentation in the skin. It affects 0.4 to 2% of the global population, but the factors that trigger autoimmunity remain elusive. Previous work on several immune-mediated dermatological disorders has illuminated the substantial roles of the gut microbiome in disease pathogenesis. Here, we examined the gut microbiome composition in a cohort of vitiligo patients and healthy controls from India, including patients with a family history of the disease. RESULTS: Our results show significant alterations in the gut microbiome of vitiligo patients compared to healthy controls, affecting taxonomic and functional profiles as well as community structure. We observed a reduction in the abundance of several bacterial taxa commonly associated with a healthy gut microbiome and noted a decrease in the abundance of SCFA (Short Chain Fatty Acids) producing taxa in the vitiligo group. Observation of a higher abundance of genes linked to bacteria-mediated degradation of intestinal mucus suggested a potential compromise of the gut mucus barrier in vitiligo. Functional analysis also revealed a higher abundance of fatty acid and lipid metabolism-related genes in the vitiligo group. Combined analysis with data from a French cohort of vitiligo also led to the identification of common genera differentiating healthy and gut microbiome across populations. CONCLUSION: Our observations, together with available data, strengthen the role of gut microbiome dysbiosis in symptom exacerbation and possibly pathogenesis in vitiligo. The reported microbiome changes also showed similarities with other autoimmune disorders, suggesting common gut microbiome-mediated mechanisms in autoimmune diseases. Further investigation can lead to the exploration of dietary interventions and probiotics for the management of these conditions.

Exploring variation in the fecal microbial communities of Kasaragod Dwarf and Holstein crossbred cattle.

The gut microbiota and its impact on health and nutrition in animals, including cattle has been of intense interest in recent times. Cattle, in particular indigenous varieties like Kasaragod Dwarf cow, have not received the due consideration given to other non-native cattle breeds, and the composition of their fecal microbiome is yet to be established. This study applied 16S rRNA high-throughput sequencing of fecal samples and compared the Kasaragod Dwarf with the highly prevalent Holstein crossbred cattle. Variation in their microbial composition was confirmed by marker gene-based taxonomic analysis. Principle Coordinate Analysis (PCoA) showed the distinct microbial architecture of the two cattle types. While the two cattle types possess unique signature taxa, in Kasaragod Dwarf cattle, many of the identified genera, including Anaerovibrio, Succinivibrio, Roseburia, Coprococcus, Paludibacter, Sutterella, Coprobacillus, and Ruminobacter, have previously been shown to be present in higher abundance in animals with higher feed efficiency. This is the first report of Kasaragod Dwarf cattle fecal microbiome profiling. Our findings highlight the predominance of specific taxa potentially associated with different fermentation products and feed efficiency phenotypes in Kasaragod Dwarf cattle compared to Holstein crossbred cattle.

MP4: a machine learning based classification tool for prediction and functional annotation of pathogenic proteins from metagenomic and genomic datasets.

Bacteria can exceptionally evolve and develop pathogenic features making it crucial to determine novel pathogenic proteins for specific therapeutic interventions. Therefore, we have developed a machine-learning tool that predicts and functionally classifies pathogenic proteins into their respective pathogenic classes. Through construction of pathogenic proteins database and optimization of ML algorithms, Support Vector Machine was selected for the model construction. The developed SVM classifier yielded an accuracy of 81.72% on the blind-dataset and classified the proteins into three classes: Non-pathogenic proteins (Class-1), Antibiotic Resistance Proteins and Toxins (Class-2), and Secretory System Associated and capsular proteins (Class-3). The classifier provided an accuracy of 79% on real dataset-1, and 72% on real dataset-2. Based on the probability of prediction, users can estimate the pathogenicity and annotation of proteins under scrutiny. Tool will provide accurate prediction of pathogenic proteins in genomic and metagenomic datasets providing leads for experimental validations. Tool is available at: http://metagenomics.iiserb.ac.in/mp4 .

Molib: A machine learning based classification tool for the prediction of biofilm inhibitory molecules.

Identification of biofilm inhibitory small molecules appears promising for therapeutic intervention against biofilm-forming bacteria. However, the experimental identification of such molecules is a time-consuming task, and thus, the computational approaches emerge as promising alternatives. We developed the 'Molib' tool to predict the biofilm inhibitory activity of small molecules. We curated a training dataset of biofilm inhibitory molecules, and the structural and chemical features were used for feature selection, followed by algorithms optimization and building of machine learning-based classification models. On five-fold cross validation, Random Forest-based descriptor, fingerprint and hybrid classification models showed accuracies of 0.93, 0.88 and 0.90, respectively. The performances of all models were evaluated on two different validation datasets including biofilm inhibitory and non-inhibitory molecules, attesting to its accuracy (≥ 0.90). The Molib web server would serve as a highly useful and reliable tool for the prediction of biofilm inhibitory activity of small molecules.

Mechanistic elucidation of amphetamine metabolism by tyramine oxidase from human gut microbiota using molecular dynamics simulations.

The human gut harbors diverse bacterial species in the gut, which play an important role in the metabolism of food and host health. Recent studies have also revealed their role in altering the pharmacological properties and efficacy of oral drugs through promiscuous metabolism. However, the atomistic details of the enzyme-drug interactions of gut bacterial enzymes which can potentially carry out the metabolism of drug molecules are still scarce. A well-known example is the FDA drug amphetamine (a central nervous system stimulant), which has been predicted to undergo promiscuous metabolism by gut bacteria. Therefore, to understand the atomistic details and energy landscape of the gut microbial enzyme-mediated metabolism of this drug, molecular dynamics studies were performed. It was observed that amphetamine binds to tyramine oxidase from the Escherichia coli strain present in the human gut microbiota at the binding site harboring polar and nonpolar amino acids. The stability analysis of amphetamine at the binding site showed that the binding is stable and the free energy for the binding of amphetamine was found to be ~ -51.71 kJ/mol. The insights provided by this study on promiscuous metabolism of amphetamine by a gut enzyme will be very useful to improve the efficacy of the drug.

Mechanistic and structural insight into promiscuity based metabolism of cardiac drug digoxin by gut microbial enzyme.

The recent advances in microbiome studies have revealed the role of gut microbiota in altering the pharmacological properties of oral drugs, which contributes to patient-response variation and undesired effect of the drug molecule. These studies are essential to guide us for achieving the desired efficacy and pharmacological activity of the existing drug molecule or for discovering novel and more effective therapeutics. However, one of the main limitations is the lack of atomistic details on the binding and metabolism of these drug molecules by gut-microbial enzymes. Therefore, in this study, for a well-known and important FDA-approved cardiac glycoside drug, digoxin, we report the atomistic details and energy economics for its binding and metabolism by the Cgr2 protein of Eggerthella lenta DSM 2243. It was observed that the binding pocket of digoxin to Cgr2 primarily involved the negatively charged polar amino acids and a few non-polar hydrophobic residues. The drug digoxin was found to bind Cgr2 at the same binding site as that of fumarate, which is the proposed natural substrate. However, digoxin showed a much lower binding energy (17.75 ± 2 Kcal mol-1 ) than the binding energy (42.17 ± 2 Kcal mol-1 ) of fumarate. This study provides mechanistic insights into the structural and promiscuity-based metabolism of widely used cardiac drug digoxin and presents a methodology, which could be useful to confirm the promiscuity-based metabolism of other orally administrated drugs by gut microbial enzymes and also help in designing strategies for improving the efficacy of the drugs.

Gut microbiome contributes to impairment of immunity in pulmonary tuberculosis patients by alteration of butyrate and propionate producers.

Tuberculosis (TB) is primarily associated with decline in immune health status. As gut microbiome (GM) is implicated in the regulation of host immunity and metabolism, here we investigate GM alteration in TB patients by 16S rRNA gene and whole-genome shotgun sequencing. The study group constituted of patients with pulmonary TB and their healthy household contacts as controls (HCs). Significant alteration of microbial taxonomic and functional capacity was observed in patients with active TB as compared to the HCs. We observed that Prevotella and Bifidobacterium abundance were associated with HCs, whereas butyrate and propionate-producing bacteria like Faecalibacterium, Roseburia, Eubacterium and Phascolarctobacterium were significantly enriched in TB patients. Functional analysis showed reduced biosynthesis of vitamins and amino acids in favour of enriched metabolism of butyrate and propionate in TB subjects. The TB subjects were also investigated during the course of treatment, to analyse the variation of GM. Although perturbation in microbial composition was still evident after a month's administration of anti-TB drugs, significant changes were observed in metagenome gene pool that pointed towards recovery in functional capacity. Therefore, the findings from this pilot study suggest that microbial dysbiosis may contribute to pathophysiology of TB by enhancing the anti-inflammatory milieu in the host.

Gut Microbial Dysbiosis in Indian Children with Autism Spectrum Disorders.

Autism spectrum disorder (ASD) is a term associated with a group of neurodevelopmental disorders. The etiology of ASD is not yet completely understood; however, a disorder in the gut-brain axis is emerging as a prominent factor leading to autism. To identify the taxonomic composition and markers associated with ASD, we compared the fecal microbiota of 30 ASD children diagnosed using Childhood Autism Rating Scale (CARS) score, DSM-5 approved AIIMS-modified INCLEN Diagnostic Tool for Autism Spectrum Disorder (INDT-ASD), and Indian Scale for Assessment of Autism (ISAA) tool, with family-matched 24 healthy children from Indian population using next-generation sequencing (NGS) of 16S rRNA gene amplicon. Our study showed prominent dysbiosis in the gut microbiome of ASD children, with higher relative abundances of families Lactobacillaceae, Bifidobacteraceae, and Veillonellaceae, whereas the gut microbiome of healthy children was dominated by the family Prevotellaceae. Comparative meta-analysis with a publicly available dataset from the US population consisting of 20 ASD and 20 healthy control samples from children of similar age, revealed a significantly high abundance of genus Lactobacillus in ASD children from both the populations. The results reveal the microbial dysbiosis and an association of selected Lactobacillus species with the gut microbiome of ASD children.

Prediction of anti-inflammatory proteins/peptides: an insilico approach.

BACKGROUND: The current therapy for inflammatory and autoimmune disorders involves the use of nonspecific anti-inflammatory drugs and other immunosuppressant, which are often accompanied with potential side effects. As an alternative therapy, anti-inflammatory peptides are recently being exploited as anti-inflammatory agents for treatment of various inflammatory diseases such as Alzheimer's disease and rheumatoid arthritis. Thus, understanding the correlation between amino acid sequence and its potential anti-inflammatory property is of great importance for the discovery of novel and efficient anti-inflammatory peptide-based therapeutics. METHODS: In this study, we have developed a prediction tool for the classification of peptides as anti-inflammatory epitopes or non anti-inflammatory epitopes. The training was performed using experimentally validated epitopes obtained from Immune epitope database and analysis resource database. Different sequence-based features and their hybrids with motif information were employed for development of support vector machine-based machine learning models. Similarly, machine learning models were also constructed using random forest. RESULTS: The composition and terminal residue conservation analysis of peptides revealed the dominance of leucine, serine, tyrosine and arginine residues in anti-inflammatory epitopes as compared to non anti-inflammatory epitopes. Similarly, the anti-inflammatory epitopes specific motifs were found to be rich in hydrophobic and polar residues. The hybrid of tripeptide composition-based support vector machine model and motif yielded the best performance on 10-fold cross validation with an accuracy of 78.1% and MCC of 0.58. The same displayed an accuracy of 72% and MCC of 0.45 on validation dataset, rejecting any possibility of over-fitting. The tripeptide composition-based random forest model displayed an accuracy of 0.8 and MCC of 0.59 on 10-fold cross validation, however, the accuracy (0.68) and MCC (0.31) was lower as compared to support vector machine model on validation dataset. Thus, the support vector machine model is implemented as the default model and an additional option of using the random forest model is provided. CONCLUSION: The prediction models along with tools for epitope mapping and similarity search have been provided as a web server which is freely accessible at http://metagenomics.iiserb.ac.in/antiinflam/ .

Prediction of peptidoglycan hydrolases- a new class of antibacterial proteins.

BACKGROUND: The efficacy of antibiotics against bacterial infections is decreasing due to the development of resistance in bacteria, and thus, there is a need to search for potential alternatives to antibiotics. In this scenario, peptidoglycan hydrolases can be used as alternate antibacterial agents due to their unique property of cleaving peptidoglycan cell wall present in both gram-positive and gram-negative bacteria. Along with a role in maintaining overall peptidoglycan turnover in a cell and in daughter cell separation, peptidoglycan hydrolases also play crucial role in bacterial pathophysiology requiring development of a computational tool for the identification and classification of novel peptidoglycan hydrolases from genomic and metagenomic data. RESULTS: In this study, the known peptidoglycan hydrolases were divided into multiple classes based on their site of action and were used for the development of a computational tool 'HyPe' for identification and classification of novel peptidoglycan hydrolases from genomic and metagenomic data. Various classification models were developed using amino acid and dipeptide composition features by training and optimization of Random Forest and Support Vector Machines. Random Forest multiclass model was selected for the development of HyPe tool as it showed up to 71.12 % sensitivity, 99.98 % specificity, 99.55 % accuracy and 0.80 MCC in four different classes of peptidoglycan hydrolases. The tool was validated on 24 independent genomic datasets and showed up to 100 % sensitivity and 0.94 MCC. The ability of HyPe to identify novel peptidoglycan hydrolases was also demonstrated on 24 metagenomic datasets. CONCLUSIONS: The present tool helps in the identification and classification of novel peptidoglycan hydrolases from complete genomic or metagenomic ORFs. To our knowledge, this is the only tool available for the prediction of peptidoglycan hydrolases from genomic and metagenomic data. AVAILABILITY: http://metagenomics.iiserb.ac.in/hype/ and http://metabiosys.iiserb.ac.in/hype/ .

ProInflam: a webserver for the prediction of proinflammatory antigenicity of peptides and proteins.

BACKGROUND: Proinflammatory immune response involves a complex series of molecular events leading to inflammatory reaction at a site, which enables host to combat plurality of infectious agents. It can be initiated by specific stimuli such as viral, bacterial, parasitic or allergenic antigens, or by non-specific stimuli such as LPS. On counter with such antigens, the complex interaction of antigen presenting cells, T cells and inflammatory mediators like IL1α, IL1ß, TNFα, IL12, IL18 and IL23 lead to proinflammatory immune response and further clearance of infection. In this study, we have tried to establish a relation between amino acid sequence of antigen and induction of proinflammatory response. RESULTS: A total of 729 experimentally-validated proinflammatory and 171 non-proinflammatory epitopes were obtained from IEDB database. The A, F, I, L and V amino acids and AF, FA, FF, PF, IV, IN dipeptides were observed as preferred residues in proinflammatory epitopes. Using the compositional and motif-based features of proinflammatory and non-proinflammatory epitopes, we have developed machine learning-based models for prediction of proinflammatory response of peptides. The hybrid of motifs and dipeptide-based features displayed best performance with MCC = 0.58 and an accuracy of 87.6 %. CONCLUSION: The amino acid sequence-based features of peptides were used to develop a machine learning-based prediction tool for the prediction of proinflammatory epitopes. This is a unique tool for the computational identification of proinflammatory peptide antigen/candidates and provides leads for experimental validations. The prediction model and tools for epitope mapping and similarity search are provided as a comprehensive web server which is freely available at http://metagenomics.iiserb.ac.in/proinflam/ and http://metabiosys.iiserb.ac.in/proinflam/ .

Woods: A fast and accurate functional annotator and classifier of genomic and metagenomic sequences.

Functional annotation of the gigantic metagenomic data is one of the major time-consuming and computationally demanding tasks, which is currently a bottleneck for the efficient analysis. The commonly used homology-based methods to functionally annotate and classify proteins are extremely slow. Therefore, to achieve faster and accurate functional annotation, we have developed an orthology-based functional classifier 'Woods' by using a combination of machine learning and similarity-based approaches. Woods displayed a precision of 98.79% on independent genomic dataset, 96.66% on simulated metagenomic dataset and >97% on two real metagenomic datasets. In addition, it performed >87 times faster than BLAST on the two real metagenomic datasets. Woods can be used as a highly efficient and accurate classifier with high-throughput capability which facilitates its usability on large metagenomic datasets.

Using the taxon-specific genes for the taxonomic classification of bacterial genomes.

BACKGROUND: The correct taxonomic assignment of bacterial genomes is a primary and challenging task. With the availability of whole genome sequences, the gene content based approaches appear promising in inferring the bacterial taxonomy. The complete genome sequencing of a bacterial genome often reveals a substantial number of unique genes present only in that genome which can be used for its taxonomic classification. RESULTS: In this study, we have proposed a comprehensive method which uses the taxon-specific genes for the correct taxonomic assignment of existing and new bacterial genomes. The taxon-specific genes identified at each taxonomic rank have been successfully used for the taxonomic classification of 2,342 genomes present in the NCBI genomes, 36 newly sequenced genomes, and 17 genomes for which the complete taxonomy is not yet known. This approach has been implemented for the development of a tool 'Microtaxi' which can be used for the taxonomic assignment of complete bacterial genomes. CONCLUSION: The taxon-specific gene based approach provides an alternate valuable methodology to carry out the taxonomic classification of newly sequenced or existing bacterial genomes.

Genome sequencing and functional analysis of a multipurpose medicinal herb Tinospora cordifolia (Giloy).

Tinospora cordifolia (Willd.) Hook.f. & Thomson, also known as Giloy, is among the most important medicinal plants that have numerous therapeutic applications in human health due to the production of a diverse array of secondary metabolites. To gain genomic insights into the medicinal properties of T. cordifolia, the genome sequencing was carried out using 10× Genomics linked read and Nanopore long-read technologies. The draft genome assembly of T. cordifolia was comprised of 1.01 Gbp, which is the genome sequenced from the plant family Menispermaceae. We also performed the genome size estimation for T. cordifolia, which was found to be 1.13 Gbp. The deep sequencing of transcriptome from the leaf tissue was also performed. The genome and transcriptome assemblies were used to construct the gene set, resulting in 17,245 coding gene sequences. Further, the phylogenetic position of T. cordifolia was also positioned as basal eudicot by constructing a genome-wide phylogenetic tree using multiple species. Further, a comprehensive comparative evolutionary analysis of gene families contraction/expansion and multiple signatures of adaptive evolution was performed. The genes involved in benzyl iso-quinoline alkaloid, terpenoid, lignin and flavonoid biosynthesis pathways were found with signatures of adaptive evolution. These evolutionary adaptations in genes provide genomic insights into the presence of diverse medicinal properties of this plant. The genes involved in the common symbiosis signalling pathway associated with endosymbiosis (Arbuscular Mycorrhiza) were found to be adaptively evolved. The genes involved in adventitious root formation, peroxisome biogenesis, biosynthesis of phytohormones, and tolerance against abiotic and biotic stresses were also found to be adaptively evolved in T. cordifolia.

Genome of the most noxious weed water hyacinth (Eichhornia crassipes) provides insights into plant invasiveness and its translational potential.

The invasive character of Eichhornia crassipes (water hyacinth) is a major threat to global biodiversity and ecosystems. To investigate the genomic basis of invasiveness, we performed the genome and transcriptome sequencing of E. crassipes and reported the genome of 1.11 Gbp size with 63,299 coding genes and N50 of 1.98 Mb. We confirmed a recent whole genome duplication event in E. crassipes that resulted in high intraspecific collinearity and significant expansion in gene families. Further, the orthologs gene clustering analysis and comparative evolutionary analysis with 14 other aquatic invasive and non-invasive angiosperm species revealed adaptive evolution in genes associated with plant-pathogen interaction, hormone signaling, abiotic stress tolerance, heavy metals sequestration, photosynthesis, and cell wall biosynthesis with highly expanded gene families, which contributes toward invasive characteristics of the water hyacinth. However, these characteristics also make water hyacinth an excellent candidate for biofuel production, phytoremediation, and other translational applications.

Metagenomic exploration of Andaman region of the Indian Ocean.

Ocean microbiome is crucial for global biogeochemical cycles and primary productivity. Despite numerous studies investigating the global ocean microbiomes, the microbiome composition of the Andaman region of the Indian Ocean remains largely unexplored. While this region harbors pristine biological diversity, the escalating anthropogenic activities along coastal habitats exert an influence on the microbial ecology and impact the aquatic ecosystems. We investigated the microbiome composition in the coastal waters of the Andaman Islands by 16S rRNA gene amplicon and metagenomic shotgun sequencing approaches and compared it with the Tara Oceans Consortium. In the coastal waters of the Andaman Islands, a significantly higher abundance and diversity of Synechococcus species was observed with a higher abundance of photosynthesis pigment-related genes to adapt to variable light conditions and nutrition. In contrast, Prochlorococcus species showed higher abundance in open ocean water samples of the Indian Ocean region, with a relatively limited functional diversity. A higher abundance of antibiotic-resistance genes was also noted in the coastal waters region. We also updated the ocean microbiome gene catalog with 93,172 unique genes from the Andaman coastal water microbiome. This study provides valuable insights into the Indian Ocean microbiome and supplements the global marine microbial ecosystem studies.

Dissipation of residues of mancozeb and metalaxyl in tomato (Solanum lycopersicum L.).

Dissipation of mancozeb and metalaxyl in tomato was estimated following four applications of a combination formulation Ridomil MZ (mancozeb 64% + metalaxyl 8%) at 0.25 and 0.50% at 10 days interval by carbon disulphide evolution method and gas liquid chromatography with nitrogen phosphorous detector, respectively. Half-life periods for mancozeb were 3.76 and 4.14 days, whereas for metalaxyl these values were 1.29 and 0.41 days at single and double the application rates, respectively. Residues of mancozeb dissipated below limit of quantification (LOQ) of 0.25 mg kg(-1) after 10 and 15 days at single and double the application dosage, respectively. Similarly, residues of metalaxyl took 3 and 5 days to reach LOQ of 0.02 mg kg(-1), at single and double dosages, respectively.

Application of artificial intelligence approaches to predict the metabolism of xenobiotic molecules by human gut microbiome.

A highly complex, diverse, and dense community of more than 1,000 different gut bacterial species constitutes the human gut microbiome that harbours vast metabolic capabilities encoded by more than 300,000 bacterial enzymes to metabolise complex polysaccharides, orally administered drugs/xenobiotics, nutraceuticals, or prebiotics. One of the implications of gut microbiome mediated biotransformation is the metabolism of xenobiotics such as medicinal drugs, which lead to alteration in their pharmacological properties, loss of drug efficacy, bioavailability, may generate toxic byproducts and sometimes also help in conversion of a prodrug into its active metabolite. Given the diversity of gut microbiome and the complex interplay of the metabolic enzymes and their diverse substrates, the traditional experimental methods have limited ability to identify the gut bacterial species involved in such biotransformation, and to study the bacterial species-metabolite interactions in gut. In this scenario, computational approaches such as machine learning-based tools presents unprecedented opportunities and ability to predict the gut bacteria and enzymes that can potentially metabolise a candidate drug. Here, we have reviewed the need to identify the gut microbiome-based metabolism of xenobiotics and have provided comprehensive information on the available methods, tools, and databases to address it along with their scope and limitations.

High-quality genome assemblies provide clues on the evolutionary advantage of blue peafowl over green peafowl.

An intriguing example of differential adaptability is the case of two Asian peafowl species, Pavo cristatus (blue peafowl) and Pavo muticus (green peafowl), where the former has a "Least Concern" conservation status and the latter is an "Endangered" species. To understand the genetic basis of this differential adaptability of the two peafowl species, a comparative analysis of these species is much needed to gain the genomic and evolutionary insights. Thus, we constructed a high-quality genome assembly of blue peafowl with an N50 value of 84.81 Mb (pseudochromosome-level assembly), and a high-confidence coding gene set to perform the genomic and evolutionary analyses of blue and green peafowls with 49 other avian species. The analyses revealed adaptive evolution of genes related to neuronal development, immunity, and skeletal muscle development in these peafowl species. Major genes related to axon guidance such as NEO1 and UNC5, semaphorin (SEMA), and ephrin receptor showed adaptive evolution in peafowl species. However, blue peafowl showed the presence of 42% more coding genes compared to the green peafowl along with a higher number of species-specific gene clusters, segmental duplicated genes and expanded gene families, and comparatively higher evolution in neuronal and developmental pathways. Blue peafowl also showed longer branch length compared to green peafowl in the species phylogenetic tree. These genomic insights obtained from the high-quality genome assembly of P. cristatus constructed in this study provide new clues on the superior adaptability of the blue peafowl over green peafowl despite having a recent species divergence time.

GutBug: A Tool for Prediction of Human Gut Bacteria Mediated Biotransformation of Biotic and Xenobiotic Molecules Using Machine Learning.

Dietary components and bioactive molecules present in functional foods and nutraceuticals provide various beneficial effects including modulation of host gut microbiome. These metabolites along with orally administered drugs can be potentially bio-transformed by gut microbiome, which can alter their bioavailability and intended biological or pharmacological activity resulting in individual or population-specific variation in drug and dietary responses. Experimental determination of microbiome-mediated metabolism of orally ingested molecules is difficult due to the enormous diversity and complexity of the gut microbiome. To address this problem, we developed "GutBug", a web-based resource that predicts all possible bacterial metabolic enzymes that can potentially biotransform xenobiotics and biotic molecules using a combination of machine learning, neural networks and chemoinformatic methods. Using 3,457 enzyme substrates for training and a curated database of 363,872 enzymes from ∼700 gut bacterial strains, GutBug can predict complete EC number of the bacterial enzymes involved in a biotransformation reaction of the given molecule along with the reaction centres with accuracies between 0.78 and 0.97 across different reaction classes. Validation of GutBug's performance using 27 molecules known to be biotransformed by human gut bacteria, including complex polysaccharides, flavonoids, and oral drugs further attests to GutBug's accuracy and utility. Thus, GutBug enhances our understanding of various metabolite-gut bacterial interactions and their resultant effects on the human host health across populations, which will find enormous applications in diet design and intervention, identification and administration of new prebiotics, development of nutraceutical products, and improvements in drug designing. GutBug is available at https://metabiosys.iiserb.ac.in/gutbug.