AntiCP 2.0: an updated model for predicting anticancer peptides.

Increasing use of therapeutic peptides for treating cancer has received considerable attention of the scientific community in the recent years. The present study describes the in silico model developed for predicting and designing anticancer peptides (ACPs). ACPs residue composition analysis show the preference of A, F, K, L and W. Positional preference analysis revealed that residues A, F and K are favored at N-terminus and residues L and K are preferred at C-terminus. Motif analysis revealed the presence of motifs like LAKLA, AKLAK, FAKL and LAKL in ACPs. Machine learning models were developed using various input features and implementing different machine learning classifiers on two datasets main and alternate dataset. In the case of main dataset, dipeptide composition based ETree classifier model achieved maximum Matthews correlation coefficient (MCC) of 0.51 and 0.83 area under receiver operating characteristics (AUROC) on the training dataset. In the case of alternate dataset, amino acid composition based ETree classifier performed best and achieved the highest MCC of 0.80 and AUROC of 0.97 on the training dataset. Five-fold cross-validation technique was implemented for model training and testing, and their performance was also evaluated on the validation dataset. Best models were implemented in the webserver AntiCP 2.0, which is freely available at https://webs.iiitd.edu.in/raghava/anticp2/. The webserver is compatible with multiple screens such as iPhone, iPad, laptop and android phones. The standalone version of the software is available at GitHub; docker-based container also developed.

Benchmarking of different molecular docking methods for protein-peptide docking.

BACKGROUND: Molecular docking studies on protein-peptide interactions are a challenging and time-consuming task because peptides are generally more flexible than proteins and tend to adopt numerous conformations. There are several benchmarking studies on protein-protein, protein-ligand and nucleic acid-ligand docking interactions. However, a series of docking methods is not rigorously validated for protein-peptide complexes in the literature. Considering the importance and wide application of peptide docking, we describe benchmarking of 6 docking methods on 133 protein-peptide complexes having peptide length between 9 to 15 residues. The performance of docking methods was evaluated using CAPRI parameters like FNAT, I-RMSD, L-RMSD. RESULT: Firstly, we performed blind docking and evaluate the performance of the top docking pose of each method. It was observed that FRODOCK performed better than other methods with average L-RMSD of 12.46 Å. The performance of all methods improved significantly for their best docking pose and achieved highest average L-RMSD of 3.72 Å in case of FRODOCK. Similarly, we performed re-docking and evaluated the performance of the top and best docking pose of each method. We achieved the best performance in case of ZDOCK with average L-RMSD 8.60 Å and 2.88 Å for the top and best docking pose respectively. Methods were also evaluated on 40 protein-peptide complexes used in the previous benchmarking study, where peptide have length up to 5 residues. In case of best docking pose, we achieved the highest average L-RMSD of 4.45 Å and 2.09 Å for the blind docking using FRODOCK and re-docking using AutoDock Vina respectively. CONCLUSION: The study shows that FRODOCK performed best in case of blind docking and ZDOCK in case of re-docking. There is a need to improve the ranking of docking pose generated by different methods, as the present ranking scheme is not satisfactory. To facilitate the scientific community for calculating CAPRI parameters between native and docked complexes, we developed a web-based service named PPDbench ( http://webs.iiitd.edu.in/raghava/ppdbench/ ).

HumCFS: a database of fragile sites in human chromosomes.

BACKGROUND: Fragile sites are the chromosomal regions that are susceptible to breakage, and their frequency varies among the human population. Based on the frequency of fragile site induction, they are categorized as common and rare fragile sites. Common fragile sites are sensitive to replication stress and often rearranged in cancer. Rare fragile sites are the archetypal trinucleotide repeats. Fragile sites are known to be involved in chromosomal rearrangements in tumors. Human miRNA genes are also present at fragile sites. A better understanding of genes and miRNAs lying in the fragile site regions and their association with disease progression is required. RESULT: HumCFS is a manually curated database of human chromosomal fragile sites. HumCFS provides useful information on fragile sites such as coordinates on the chromosome, cytoband, their chemical inducers and frequency of fragile site (rare or common), genes and miRNAs lying in fragile sites. Protein coding genes in the fragile sites were identified by mapping the coordinates of fragile sites with human genome Ensembl (GRCh38/hg38). Genes present in fragile sites were further mapped to DisGenNET database, to understand their possible link with human diseases. Human miRNAs from miRBase was also mapped on fragile site coordinates. In brief, HumCFS provides useful information about 125 human chromosomal fragile sites and their association with 4921 human protein-coding genes and 917 human miRNA's. CONCLUSION: User-friendly web-interface of HumCFS and hyper-linking with other resources will help researchers to search for genes, miRNAs efficiently and to intersect the relationship among them. For easy data retrieval and analysis, we have integrated standard web-based tools, such as JBrowse, BLAST etc. Also, the user can download the data in various file formats such as text files, gff3 files and Bed-format files which can be used on UCSC browser. Database URL: http://webs.iiitd.edu.in/raghava/humcfs/.

Novel in silico tools for designing peptide-based subunit vaccines and immunotherapeutics.

The conventional approach for designing vaccine against a particular disease involves stimulation of the immune system using the whole pathogen responsible for the disease. In the post-genomic era, a major challenge is to identify antigenic regions or epitopes that can stimulate different arms of the immune system. In the past two decades, numerous methods and databases have been developed for designing vaccine or immunotherapy against various pathogen-causing diseases. This review describes various computational resources important for designing subunit vaccines or epitope-based immunotherapy. First, different immunological databases are described that maintain epitopes, antigens and vaccine targets. This is followed by in silico tools used for predicting linear and conformational B-cell epitopes required for activating humoral immunity. Finally, information on T-cell epitope prediction methods is provided that includes indirect methods like prediction of Major Histocompatibility Complex and transporter-associated protein binders. Different studies for validating the predicted epitopes are also examined critically. This review enlists novel in silico resources and tools available for predicting humoral and cell-mediated immune potential. These predicted epitopes could be used for designing epitope-based vaccines or immunotherapy as they may activate the adaptive immunity. Authors emphasized the need to develop tools for the prediction of adjuvants to activate innate and adaptive immune system simultaneously. In addition, attention has also been given to novel prediction methods to predict general therapeutic properties of peptides like half-life, cytotoxicity and immune toxicity.

Computer-aided prediction of antigen presenting cell modulators for designing peptide-based vaccine adjuvants.

BACKGROUND: Evidences in literature strongly advocate the potential of immunomodulatory peptides for use as vaccine adjuvants. All the mechanisms of vaccine adjuvants ensuing immunostimulatory effects directly or indirectly stimulate antigen presenting cells (APCs). While numerous methods have been developed in the past for predicting B cell and T-cell epitopes; no method is available for predicting the peptides that can modulate the APCs. METHODS: We named the peptides that can activate APCs as A-cell epitopes and developed methods for their prediction in this study. A dataset of experimentally validated A-cell epitopes was collected and compiled from various resources. To predict A-cell epitopes, we developed support vector machine-based machine learning models using different sequence-based features. RESULTS: A hybrid model developed on a combination of sequence-based features (dipeptide composition and motif occurrence), achieved the highest accuracy of 95.71% with Matthews correlation coefficient (MCC) value of 0.91 on the training dataset. We also evaluated the hybrid models on an independent dataset and achieved a comparable accuracy of 95.00% with MCC 0.90. CONCLUSION: The models developed in this study were implemented in a web-based platform VaxinPAD to predict and design immunomodulatory peptides or A-cell epitopes. This web server available at http://webs.iiitd.edu.in/raghava/vaxinpad/ will facilitate researchers in designing peptide-based vaccine adjuvants.

CPPsite 2.0: a repository of experimentally validated cell-penetrating peptides.

CPPsite 2.0 (http://crdd.osdd.net/raghava/cppsite/) is an updated version of manually curated database (CPPsite) of cell-penetrating peptides (CPPs). The current version holds around 1850 peptide entries, which is nearly two times than the entries in the previous version. The updated data were curated from research papers and patents published in last three years. It was observed that most of the CPPs discovered/ tested, in last three years, have diverse chemical modifications (e.g. non-natural residues, linkers, lipid moieties, etc.). We have compiled this information on chemical modifications systematically in the updated version of the database. In order to understand the structure-function relationship of these peptides, we predicted tertiary structure of CPPs, possessing both modified and natural residues, using state-of-the-art techniques. CPPsite 2.0 also maintains information about model systems (in vitro/in vivo) used for CPP evaluation and different type of cargoes (e.g. nucleic acid, protein, nanoparticles, etc.) delivered by these peptides. In order to assist a wide range of users, we developed a user-friendly responsive website, with various tools, suitable for smartphone, tablet and desktop users. In conclusion, CPPsite 2.0 provides significant improvements over the previous version in terms of data content.

SATPdb: a database of structurally annotated therapeutic peptides.

SATPdb (http://crdd.osdd.net/raghava/satpdb/) is a database of structurally annotated therapeutic peptides, curated from 22 public domain peptide databases/datasets including 9 of our own. The current version holds 19192 unique experimentally validated therapeutic peptide sequences having length between 2 and 50 amino acids. It covers peptides having natural, non-natural and modified residues. These peptides were systematically grouped into 10 categories based on their major function or therapeutic property like 1099 anticancer, 10585 antimicrobial, 1642 drug delivery and 1698 antihypertensive peptides. We assigned or annotated structure of these therapeutic peptides using structural databases (Protein Data Bank) and state-of-the-art structure prediction methods like I-TASSER, HHsearch and PEPstrMOD. In addition, SATPdb facilitates users in performing various tasks that include: (i) structure and sequence similarity search, (ii) peptide browsing based on their function and properties, (iii) identification of moonlighting peptides and (iv) searching of peptides having desired structure and therapeutic activities. We hope this database will be useful for researchers working in the field of peptide-based therapeutics.

Electronic Transport via Homopeptides: The Role of Side Chains and Secondary Structure.

Many novel applications in bioelectronics rely on the interaction between biomolecules and electronically conducting substrates. However, crucial knowledge about the relation between electronic transport via peptides and their amino-acid composition is still absent. Here, we report results of electronic transport measurements via several homopeptides as a function of their structural properties and temperature. We demonstrate that the conduction through the peptide depends on its length and secondary structure as well as on the nature of the constituent amino acid and charge of its residue. We support our experimental observations with high-level electronic structure calculations and suggest off-resonance tunneling as the dominant conduction mechanism via extended peptides. Our findings indicate that both peptide composition and structure can affect the efficiency of electronic transport across peptides.

microRNA as biomarkers in tuberculosis: a new emerging molecular diagnostic solution.

Tuberculosis (TB) caused by Mycobacterium tuberculosis is a lethal infectious disease that is prevalent worldwide. During TB infection, host microRNAs change their expression in the form of up/down-regulation. The identification of unique host microRNAs during TB could serve as potential biomarkers in the early detection of TB. microRNAs fulfill the required criteria for being an ideal biomarker, such as sensitivity, high specificity, and accessibility. Therefore, the recognition of potential host microRNAs can be valuable for the diagnosis of TB. The field of miRNA biomarkers in TB requires more extensive research to identify potential biomarkers. This review provides an overview of the biogenesis and biological functions of microRNAs and presents the findings of various studies on the identification of potential biomarkers for TB. Research momentum is gaining in this field and we anticipate that miRNAs will become a routine approach in the development of reliable diagnostic and specific therapeutic interventions in future.

Network-based approach elucidates critical genes in BRCA subtypes and chemotherapy response in triple negative breast cancer.

Breast cancers (BRCA) exhibit substantial transcriptional heterogeneity, posing a significant clinical challenge. The global transcriptional changes in a disease context, however, are likely mediated by few key genes which reflect disease etiology better than the differentially expressed genes (DEGs). We apply our network-based tool PathExt to 1,059 BRCA tumors across 4 subtypes to identify key mediator genes in each subtype. Compared to conventional differential expression analysis, PathExt-identified genes exhibit greater concordance across tumors, revealing shared and subtype-specific biological processes; better recapitulate BRCA-associated genes in multiple benchmarks, and are more essential in BRCA subtype-specific cell lines. Single-cell transcriptomic analysis reveals a subtype-specific distribution of PathExt-identified genes in multiple cell types from the tumor microenvironment. Application of PathExt to a TNBC chemotherapy response dataset identified subtype-specific key genes and biological processes associated with resistance. We described putative drugs that target key genes potentially mediating drug resistance.

Electromechanically Reconfigurable Terahertz Stereo Metasurfaces.

Dynamic terahertz devices are vital for the next generation of wireless communication, sensing, and non-destructive imaging technologies. Metasurfaces have emerged as a paradigm-shifting platform, offering varied functionalities, miniaturization, and simplified fabrication compared to their 3D counterparts. However, the presence of in-plane mirror symmetry and reduced degree of freedom impose fundamental limitations on achieving advanced chiral response, beamforming, and reconfiguration capabilities. In this work, a platform composed of electrically actuated resonators that can be colossally reconfigured between planar and 3D geometries is demonstrated. To illustrate the platform, metadevices with 3D Split Ring Resonators are fabricated, wherein two counteracting driving forces are combined: i) folding induced by stress mismatch, which enables non-volatile state design and ii) unfolding triggered by the strain associated with insulator-to-metal transition in VO2, which facilitates volatile structural reconfiguration. This large structural reconfiguration space allows for resonance mode switching, widely tunable magnetic and electric polarizabilities, and increased frequency agility. Moreover, the unique properties of VO2, such as the hysteretic nature of its phase transition is harnessed to demonstrate a multi-state memory. Therefore, these VO2 integrated metadevices are highly attractive for the realization of 6G communication devices such as reconfigurable intelligent surfaces, holographic beam formers, and spatial light modulators.

Predicting gene expression changes upon epigenomic drug treatment.

Background: Tumors are characterized by global changes in epigenetic changes such as DNA methylation and histone modifications that are functionally linked to tumor progression. Accordingly, several drugs targeting the epigenome have been proposed for cancer therapy, notably, histone deacetylase inhibitors (HDACi) such as Vorinostatis and DNA methyltransferase inhibitors (DNMTi) such as Zebularine. However, a fundamental challenge with such approaches is the lack of genomic specificity, i.e., the transcriptional changes at different genomic loci can be highly variable thus making it difficult to predict the consequences on the global transcriptome and drug response. For instance, treatment with DNMTi may upregulate the expression of not only a tumor suppressor but also an oncogene leading to unintended adverse effect. Methods: Given the pre-treatment transcriptome and epigenomic profile of a sample, we assessed the extent of predictability of locus-specific changes in gene expression upon treatment with HDACi using machine learning. Results: We found that in two cell lines (HCT116 treated with Largazole at 8 doses and RH4 treated with Entinostat at 1µM) where the appropriate data (pre-treatment transcriptome and epigenome as well as post-treatment transcriptome) is available, our model distinguished the post-treatment up versus downregulated genes with high accuracy (up to ROC of 0.89). Furthermore, a model trained on one cell line is applicable to another cell line suggesting generalizability of the model. Conclusions: Here we present a first assessment of the predictability of genome-wide transcriptomic changes upon treatment with HDACi. Lack of appropriate omics data from clinical trials of epigenetic drugs currently hampers the assessment of applicability of our approach in clinical setting.

Network-based approach elucidates critical genes in BRCA subtypes and chemotherapy response in Triple Negative Breast Cancer.

Breast cancers exhibit substantial transcriptional heterogeneity, posing a significant challenge to the prediction of treatment response and prognostication of outcomes. Especially, translation of TNBC subtypes to the clinic remains a work in progress, in part because of a lack of clear transcriptional signatures distinguishing the subtypes. Our recent network-based approach, PathExt, demonstrates that global transcriptional changes in a disease context are likely mediated by a small number of key genes, and these mediators may better reflect functional or translationally relevant heterogeneity. We apply PathExt to 1059 BRCA tumors and 112 healthy control samples across 4 subtypes to identify frequent, key-mediator genes in each BRCA subtype. Compared to conventional differential expression analysis, PathExt-identified genes (1) exhibit greater concordance across tumors, revealing shared as well as BRCA subtype-specific biological processes, (2) better recapitulate BRCA-associated genes in multiple benchmarks, and (3) exhibit greater dependency scores in BRCA subtype-specific cancer cell lines. Single cell transcriptomes of BRCA subtype tumors reveal a subtype-specific distribution of PathExt-identified genes in multiple cell types from the tumor microenvironment. Application of PathExt to a TNBC chemotherapy response dataset identified TNBC subtype-specific key genes and biological processes associated with resistance. We described putative drugs that target top novel genes potentially mediating drug resistance. Overall, PathExt applied to breast cancer refines previous views of gene expression heterogeneity and identifies potential mediators of TNBC subtypes, including potential therapeutic targets.

Genetics, Nutrition, and Health: A New Frontier in Disease Prevention.

The field of nutrition research has traditionally focused on the effects of macronutrients and micronutrients on the body. However, it has become evident that individuals have unique genetic makeups that influence their response to food. Nutritional genomics, which includes nutrigenetics and nutrigenomics, explores the interaction between an individual's genetic makeup, diet, and health outcomes. Nutrigenetics studies the impact of genetic variation on an individual's response to dietary nutrients, while nutrigenomics investigates how dietary components affect gene regulation and expression. These disciplines seek to understand the impact of diet on the genome, transcriptome, proteome, and metabolome. It provides insights into the mechanisms underlying the effect of diet on gene expression. Nutrients can cause the modification of genetic expression through epigenetic changes, such as DNA methylation and histone modifications. The aim of nutrigenomics is to create personalized diets based on the unique metabolic profile of an individual, gut microbiome, and genetic makeup to prevent diseases and promote health. Nutrigenomics has the potential to revolutionize the field of nutrition by combining the practicality of personalized nutrition with knowledge of genetic factors underlying health and disease. Thus, nutrigenomics offers a promising approach to improving health outcomes (in terms of disease prevention) through personalized nutrition strategies based on an individual's genetic and metabolic characteristics.

Genetic differences among individuals affect the metabolism, gene regulation, and sensitivity of disease in response to diet therefore traditional nutrition research expands to integrate the influence of genetics on the dietary response of an individual.Nutritional genomics which includes the reciprocal and complementary field of nutrigenetics and nutrigenomics, studies the interactions between gene and dietary components.Nutrigenetics studies the genetic effect on the metabolism of nutrients while Nutrigenomics explores the impact of nutrients on genetic expression thus shaping personalized dietary requirements.A personalized dietary approach based on comprehensive genomic profiling (genomics, proteomics, metabolomics, transcriptomics) can help to promote health and prevent illness.

Pfeature: A Tool for Computing Wide Range of Protein Features and Building Prediction Models.

In the last three decades, a wide range of protein features have been discovered to annotate a protein. Numerous attempts have been made to integrate these features in a software package/platform so that the user may compute a wide range of features from a single source. To complement the existing methods, we developed a method, Pfeature, for computing a wide range of protein features. Pfeature allows to compute more than 200,000 features required for predicting the overall function of a protein, residue-level annotation of a protein, and function of chemically modified peptides. It has six major modules, namely, composition, binary profiles, evolutionary information, structural features, patterns, and model building. Composition module facilitates to compute most of the existing compositional features, plus novel features. The binary profile of amino acid sequences allows to compute the fraction of each type of residue as well as its position. The evolutionary information module allows to compute evolutionary information of a protein in the form of a position-specific scoring matrix profile generated using Position-Specific Iterative Basic Local Alignment Search Tool (PSI-BLAST); fit for annotation of a protein and its residues. A structural module was developed for computing of structural features/descriptors from a tertiary structure of a protein. These features are suitable to predict the therapeutic potential of a protein containing non-natural or chemically modified residues. The model-building module allows to implement various machine learning techniques for developing classification and regression models as well as feature selection. Pfeature also allows the generation of overlapping patterns and features from a protein. A user-friendly Pfeature is available as a web server python library and stand-alone package.

A path-based analysis of infected cell line and COVID-19 patient transcriptome reveals novel potential targets and drugs against SARS-CoV-2.

Most transcriptomic studies of SARS-CoV-2 infection have focused on differentially expressed genes, which do not necessarily reveal the genes mediating the transcriptomic changes. In contrast, exploiting curated biological network, our PathExt tool identifies central genes from the differentially active paths mediating global transcriptomic response. Here we apply PathExt to multiple cell line infection models of SARS-CoV-2 and other viruses, as well as to COVID-19 patient-derived PBMCs. The central genes mediating SARS-CoV-2 response in cell lines were uniquely enriched for ATP metabolic process, G1/S transition, leukocyte activation and migration. In contrast, PBMC response reveals dysregulated cell-cycle processes. In PBMC, the most frequently central genes are associated with COVID-19 severity. Importantly, relative to differential genes, PathExt-identified genes show greater concordance with several benchmark anti-COVID-19 target gene sets. We propose six novel anti-SARS-CoV-2 targets ADCY2, ADSL, OCRL, TIAM1, PBK, and BUB1, and potential drugs targeting these genes, such as Bemcentinib, Phthalocyanine, and Conivaptan.

A Path-Based Analysis of Infected Cell Line and COVID-19 Patient Transcriptome Reveals Novel Potential Targets and Drugs Against SARS-CoV-2.

Most transcriptomic studies of SARS-CoV-2 infection have focused on differentially expressed genes, which do not necessarily reveal the genes mediating the transcriptomic changes. In contrast, exploiting curated biological network, our PathExt tool identifies central genes from the differentially active paths mediating global transcriptomic response. Here we apply PathExt to multiple cell line infection models of SARS-CoV-2 and other viruses, as well as to COVID-19 patient-derived PBMCs. The central genes mediating SARS-CoV-2 response in cell lines were uniquely enriched for ATP metabolic process, G1/S transition, leukocyte activation and migration. In contrast, PBMC response reveals dysregulated cell-cycle processes. In PBMC, the most frequently central genes are associated with COVID-19 severity. Importantly, relative to differential genes, PathExt-identified genes show greater concordance with several benchmark anti-COVID-19 target gene sets. We propose six novel anti-SARS-CoV-2 targets ADCY2, ADSL, OCRL, TIAM1, PBK, and BUB1, and potential drugs targeting these genes, such as Bemcentinib, Phthalocyanine, and Conivaptan.

Azathioprine-Induced Marrow Suppression in Dermatology Patients - Analysis of 18 Patients.

Background: Azathioprine is an immunosuppressant used to treat several immunological disorders. As a purine analog, it inhibits DNA synthesis and cell multiplication. However, marrow suppression is a serious complication associated with azathioprine. Aim: To analyze the marrow suppression caused by azathioprine in dermatology patients. Material and Method: This is a retrospective analysis of the records of 18 patients who presented with marrow suppression secondary to azathioprine which was used for the treatment of various dermatological diseases. Results: The analysis includes 18 patients, 15 females and 3 males with the average age being 25.88 years. All except two patients received 1 mg/kg of oral azathioprine once daily. Leukopenia was seen in 13 patients (with severe leukopenia in 7 patients), thrombocytopenia in 8, and low hemoglobin in 14 patients. Isolated low hemoglobin was seen in four patients, isolated leukopenia in four patients, and only one patient presented with isolated thrombocytopenia. Six patients had pancytopenia. The duration from the starting dose to reporting of marrow suppression ranged from 10 days to 1 year. Eight out of 18 patients presented with anagen effluvium, 2 patients with oral ulcers, and 1 patient with an upper respiratory tract infection. All the patients recovered within 1 month. Conclusion: Marrow suppression due to azathioprine can occur with a low dose of 1 mg/kg. Hair loss and oral ulcers serve as early warning signs for marrow suppression.

Broad misappropriation of developmental splicing profile by cancer in multiple organs.

Oncogenesis mimics key aspects of embryonic development. However, the underlying mechanisms are incompletely understood. Here, we demonstrate that the splicing events specifically active during human organogenesis, are broadly reactivated in the organ-specific tumor. Such events are associated with key oncogenic processes and predict proliferation rates in cancer cell lines as well as patient survival. Such events preferentially target nitrosylation and transmembrane-region domains, whose coordinated splicing in multiple genes respectively affect intracellular transport and N-linked glycosylation. We infer critical splicing factors potentially regulating embryonic splicing events and show that such factors are potential oncogenic drivers and are upregulated specifically in malignant cells. Multiple complementary analyses point to MYC and FOXM1 as potential transcriptional regulators of critical splicing factors in brain and liver. Our study provides a comprehensive demonstration of a splicing-mediated link between development and cancer, and suggest anti-cancer targets including splicing events, and their upstream splicing and transcriptional regulators.

A Method for Predicting Hemolytic Potency of Chemically Modified Peptides From Its Structure.

In the present study, a systematic effort has been made to predict the hemolytic potency of chemically modified peptides. All models have been trained, tested, and evaluated on a dataset that contains 583 modified hemolytic peptides and a balanced number of non-hemolytic peptides. Machine learning techniques have been used to build the classification models using an immense range of peptide features that include 2D, 3D descriptors, fingerprints, atom, and diatom compositions. Random Forest based model developed using fingerprints as an input feature achieved maximum accuracy of 78.33% with AUC of 0.86 on the main dataset and accuracy of 78.29% with AUC of 0.85 on the validation dataset. Models developed in this study have been incorporated in a web server "HemoPImod" to facilitate the scientific community (http://webs.iiitd.edu.in/raghava/hemopimod/).