Biology subjects

Lathwal, A.

Publications and source records attributed to Lathwal, A..

6 recordsLinked to original sources

bioRxiv2021

In silico model for predicting IL-2 inducing peptides in human

Interleukin-2 (IL-2) based immunotherapy has been approved for treating certain types of cancer, as IL-2 plays a crucial role in regulating the immune system. In this study, we developed a method for predicting IL-2-inducing peptides. Our method was trained, tested, and validated on a main dataset containing 6,574 experimentally validated Major histocompatibility complex (MHC) binders, including 3,429 IL-2-inducing and 3,145 non-inducing peptides. A primary analysis of IL-2 inducing and non-inducing peptides revealed that certain residues, such as alanine and leucine, are more abundant in IL-2-inducing peptides. Initially, we developed alignment-based methods, which demonstrated high precision but limited coverage. Subsequently, we developed artificial intelligence-based models, including machine learning (ML), deep learning (DL), and large language models (LLM), to predict IL-2-inducing peptides. Our Extra Tree-based model, developed using dipeptide composition and peptide length, achieved a maximum AUC of 0.82. Finally, we constructed ensemble models that combined artificial intelligence and alignment-based methods. Our best ensemble model, which integrates the Extra Tree-based model with MERCI, achieved the highest AUC of 0.84 and an MCC of 0.51 on the main dataset. One limitation of the main dataset is that both IL-2-inducing and non-inducing peptides are MHC binders. To address this limitation, we created two additional datasets: Alternate Dataset 1, consisting of 3,429 IL-2-inducing peptides and 3,429 non-inducing peptides (MHC non-binders), and Alternate Dataset 2, consisting of 3,429 IL-2-inducing peptides and 3,439 non-inducing peptides (MHC binders + MHC non-binders). Our best ensemble model achieved AUCs of 0.9 and 0.8 with MCCs of 0.61 and 0.44 on Alternate Datasets 1 and 2, respectively. To assist the scientific community, we have integrated the best models from this study into a standalone software and web server, IL2pred, which enables users to predict, scan, and design IL-2-inducing peptides (https://webs.iiitd.edu.in/raghava/il2pred/). HighlightsO_LIDevelopment of alignment-based techniques for predicting IL-2-inducing peptides. C_LIO_LIIdentification of amino acid patterns associated with IL-2 induction. C_LIO_LIImplementation of machine learning, deep learning, and LLM-based models for peptide prediction. C_LIO_LIEnsemble approaches combining alignment-based and AI-driven methods and integration into the webserver. C_LI

bioinformatics↗

bioRxiv2021

Prediction of pancreatic adenocarcinoma patient risk status using alternative splicing events

In literature, several mRNA, miRNA, lncRNA based biomarkers are identified by genomic analysis to stratify the patients into high and low risk groups of pancreatic adenocarcinoma (PAAD). The identified biomarkers are of limited use in terms of sensitivity and prediction ability. Thus, we aimed to identify the prognostic alternative splicing events and their related mutations in the PAAD. PAAD splicing data of 174 samples (17874 AS events in 6209 genes) and corresponding clinical information was obtained from the SpliceSeq and The Cancer Genome Atlas (TCGA), respectively. Prognostic-index based modeling was used to obtain the best predictive models for the seven AS types. However, model based on multiple spliced events genes (APP; LATS1; MRPL4; LAS1L; STARD10; PHF21A; NMRAL1) outperformed the single event models with a remarkable HR of 9.13 (p-value = 6.42e-10) as well as other existing models. Results from g:Profiler suggest that transcription factors ZF5, ER81, E2F-1/2/3, ER81, Erg, and PEA3 are most related to the prognostic spliced genes. We also identified 565 mutations across 160 spliced genes that have a strong association with the prognostic AS events. The analysis revealed that around 560 of these mutations were not reported before in context to splice event/region. Overall, we conclude that altered AS events may serve as strong indicators for overall survival in pancreatic cancer patients, and novel linkage of the known mutations to the survival-related AS events may provide a new dimension to the advancement of diagnostic and therapeutic interventions in these patients.

bioinformatics↗

bioRxiv2021

Integrative multi-omics approach for stratification of tumor recurrence risk groups of Hepatocellular Carcinoma patients

Postoperative tumor recurrence is one of the major concerns associated with the poor prognosis of HCC patients. There is yet to elucidate a standard surveillance system for HCC recurrence risk owing to complexity of this malignancy. Generation of multi-omics data from patients facilitate the identification of robust signatures for various diseases. Thus, the current study is an attempt to develop the prognostic models employing multi-omics data to significantly (p-value <0.05) stratify the recurrence high-risk (median Recurrence Free Survival time (RFS) =<12 months) and low-risk groups (median RFS >12 months). First, we identified key 90RNA, 50miRNA and 50 methylation features and developed prognostic models; attained reasonable performance (C-Index >0.70, HR >2.5), on training and validation datasets. Subsequently, we developed a prognostic (PI) model by integrating the four multi-omics features (SUZ12, hsa-mir-3936, cg18465072, and cg22852503), that are biologically inter-linked with each other. This model achieved reasonable performance on training and validation dataset, i.e. C-Index 0.72, HR of 2.37 (1.61 - 3.50), p-value of 6.72E-06, Brier score 0.19 on training dataset, and C-Index 0.72 (95% CI: 0.63 - 0.80), HR of 2.37 (95% CI: 1.61 - 3.50), p-value of 0.015, Brier score 0.19 on validation dataset. Eventually, Drugbank data was investigated to elucidate therapeutic potential of these signatures. We have identified nine potential drugs against three genes (CA9, IL1A, KCNJ15) that are positively correlated with the tumor recurrence. We anticipate these results from our study will help researchers and clinicians to improve the HCC recurrence surveillance, eventually outcome of patients.

bioinformatics↗

bioRxiv2020

OvirusTdb: A Repository of Oncolytic Viruses used in Cancer Treatment

One of the emerging technologies to fight against cancer is oncolytic virus-based immunotherapy which directly lysis tumor cells. Recently, the FDA approved an oncolytic virus named T-vec for the treatment of melanoma; several hundred other viruses are in clinical trials. In order to facilitate the scientific community to fight against cancer, we build a repository of oncolytic viruses called OvirusTdb (https://webs.iiitd.edu.in/raghava/ovirustdb/). This is a manually curated repository where information is curated from research papers and patents. The current version of the repository maintains comprehensive information on therapeutically important oncolytic viruses with 5927 records where each record has 25 fields such as the virus species, cancer cell line, synergism with anti-cancer drugs, and many more. It stores information on 09 types of DNA and 15 types of RNA viruses; 300 recombinant and 09 wildtype viral strains; tested against 124 cancer types and 427 cancer cell lines. Approximately, 1047 records show improved anti-cancer response using combinatorial approach of chemotherapeutic agents with virus strains. Nearly, 3243 and 1506 records show cancer cell death via apoptosis induction and immune activation, respectively. In summary, a user-friendly web repository of oncolytic viruses for information retrieval and analysis have been developed to facilitate researchers in designing and discovering new oncolytic viruses for effective cancer treatment.

bioinformatics↗

bioRxiv2019

Prediction of risk scores for colorectal cancer patients from the concentration of proteins involved in mitochondrial apoptotic pathway

One of the major challenges in managing the treatment of colorectal cancer (CRC) patients is to predict risk scores or level of risk for CRC patients. In past, several biomarkers, based on concentration of proteins involved in type-2/intrinsic/mitochondrial apoptotic pathway, have been identified for prognosis of colorectal cancer patients. Recently, a prognostic tool DR MOMP has been developed that can discriminate high and low risk CRC patients with reasonably high accuracy (Hazard Ratio, HR = 5.24 and p-value = 0.0031). This prognostic tool showed an accuracy of 59.7% when used to predict favorable/unfavorable survival outcomes. In this study, we developed knowledge based models for predicting risk scores of CRC patients. Models were trained and evaluated on 134 stage III CRC patients. Firstly, we developed multiple linear regression based models using different techniques and achieved a maximum HR value of 6.34 with p-value = 0.0032 for a model developed using LassoLars technique. Secondly, models were developed using a parameter optimization technique and achieved a maximum HR value of 38.13 with p-value 0.0006. We also predicted favorable/unfavorable survival outcomes and achieved maximum prediction accuracy value of 71.64%. The performance of our models were evaluated using five-fold cross-validation technique. For providing service to the community we also developed a web server CRCRpred, to predict risk scores of CRC patients, which is freely available at https://webs.iiitd.edu.in/raghava/crcrpred.

bioinformatics↗

bioRxiv2019

Computing wide range of protein/peptide features from their sequence and structure

MotivationIn last three decades, a wide range of protein descriptors/features have been discovered to annotate a protein with high precision. A wide range of features have been integrated in numerous software packages (e.g., PROFEAT, PyBioMed, iFeature, protr, Rcpi, propy) to predict function of a protein. These features are not suitable to predict function of a protein at residue level such as prediction of ligand binding residues, DNA interacting residues, post translational modification etc.\n\nResultsIn order to facilitate scientific community, we have developed a software package that computes more than 50,000 features, important for predicting function of a protein and its residues. It has five major modules for computing; composition-based features, binary profiles, evolutionary information, structure-based features and patterns. The composition-based module allows user to compute; i) simple compositions like amino acid, dipeptide, tripeptide; ii) Properties based compositions; iii) Repeats and distribution of amino acids; iv) Shannon entropy to measure the low complexity regions; iv) Miscellaneous compositions like pseudo amino acid, autocorrelation, conjoint triad, quasi-sequence order. Binary profile of amino acid sequences provides complete information including order of residues or type of residues; specifically, suitable to predict function of a protein at residue level. Pfeature allows one to compute evolutionary information-based features in form of PSSM profile generated using PSIBLAST. Structure based module allows computing structure-based features, specifically suitable to annotate chemically modified peptides/proteins. Pfeature also allows generating overlapping patterns and feature from whole protein or its parts (e.g., N-terminal, C-terminal). In summary, Pfeature comprises of almost all features used till now, for predicting function of a protein/peptide including its residues.\n\nAvailabilityIt is available in form of a web server, named as Pfeature (https://webs.iiitd.edu.in/raghava/pfeature/), as well as python library and standalone package (https://github.com/raghavagps/Pfeature) suitable for Windows, Ubuntu, Fedora, MacOS and Centos based operating system.

bioinformatics↗