ProBioPred uses available genetic information and advanced machine learning models for the prediction of a potential probiotic candidate. In brief, ProBioPred uses curated reference sequences for genes imparting Probiotic Properties, Virulence Factors, and Antibiotic Resistance Genes to predict a potential probiotic candidate. These models can be used for the analysis of genome sequences using ProBioPred either online or as a stand-alone tool. It is built entirely using open source software and tools.

The ProBioPred designed and developed by Dr. Dhiraj Dhotre, Dr. Shrikant Pawar, Dr. Yogesh Shouche, Mr. Nitin Narwade, Mr. Datta Mongad and Mr. Vikas Ghattargi at National Centre for Microbial Resource, National Centre for Cell Science, India.

The National Centrefor Cell Science (NCCS) is a National Level, Biotechnology, Tissue Engineering and Tissue Banking research center located at Savitribai Phule Pune University campus in Pune, city of western Indian state of Maharashtra. The institute is one of the premier research centers in India, which works on cell-culture, cell-repository, immunology, chromatin-remodeling.

The NCCS’s - NationalCentre for Microbial Resource (NCMR) is one of the largest culture collection in the world. It has an excellent infrastructure and expertise in microbial taxonomy and long term preservation. It started offering in 2013 various services involving microorganisms. It is also an InternationalDepository Authority (IDA) for the deposit of microorganisms for the purposes of patent procedures under the Budapest Treaty by the World Intellectual Property Organization, Geneva.

NCMR plays a crucial role as custodian of microbial diversity of India and an attempt is primarily focused on understanding the diversity of the microbes present and their functional role in sustaining the ecosystem. The research here is on pressing issues in microbial taxonomy, diversity, and ecology. Also, using extensive –omics approaches, we strive to highlight and understand the role of microbes in our research themes. The work culture and facilities attract students from diverse backgrounds, both nationally and internationally, and work with the right scientific spirit towards enhancing knowledge of the microbial realm.

ProBioPred an online server for prediction of potential probiotic candidate from the genome using marker genes that are specifically responsible for imparting probiotic properties and differentiate the genomes into probiotic and non-probiotic. These marker genes have been identified by dedicated mutant analyses and thus have confirmed some postulated roles involved in probiotic action. Mutant studies are of the utmost importance in the unraveling of modes of action of bacteria as they can often directly relate genotype to phenotype. Therefore, these molecular techniques can be considered as complementary to the in-vivo studies done earlier. Genome sequence allows quick detection and elimination of strains that pose a potential risk, through the presence of antibiotic resistance or virulence genes. Also, genomic data can be exploited to identify genes that impart beneficial properties and can be very effective for follow-up analysis of in vitro and/or in vivo screening. Thus, computational genome analysis can be a cost-effective solution for the primary screening of potential probiotics.

ProBioPred accepts complete as well as draft whole genome sequences and also metagenomic assembled genomes. However, whole genome analysis is still preferred to reduce false predictions. We suggest minimizing the number of contigs before performing analysis. Contigs will be taken in the order given by the user. Please note that for better results genomes with more than 70% completeness are recommended. Uploaded genomes and predictions will not be visible to other users of ProBioPred and results will be stored for 15 days. Currently this server can be used for nine bacterial genera containing species commonly used as probiotics for human consumption. ProBioPred currently supports prediction from genera Lactobacillus, Lactococcus, Bifidobacterium, Leuconostoc, Bacillus, Enterococcus, Streptococcus, Clostridium and Pediocoocus. List of genes associated with probiotic properties, antibiotic resistance and virulence factors are screened in all the input genome and the prediction of probiotic potential is carried out.

ProBioPred is developed at National Centre for Microbial Resource (NCMR) of National Centre for Cell Science (NCCS), Pune, India. We foresee that ProBioPred with further refinements will help in identifying potential probiotic candidate from the genomes generated from single-cell genomes and population genomes recovered from metagenomic data.