AI-based pipeline for early screening of lung cancer: integrating radiology, clinical, and genomics data.

Background: The prognosis of lung carcinoma has changed since the discovery of molecular targets and their specific drugs. Somatic Epidermal Growth Factor Receptor (EGFR) mutations have been reported in lung carcinoma, and these mutant proteins act as substrates for targeted therapies. However, in a resource-constrained country like India, panel-based next-generation sequencing cannot be made available to the population at large. Additional challenges such as adequacy of tissue in case of lung core biopsies and locating suitable tumour tissues as a result of innate intratumoral heterogeneity indicate the necessity of an AI-based end-to-end pipeline capable of automatically detecting and learning more effective lung nodule features from CT images and predicting the probability of the EGFR-mutant. This will help the oncologists and patients in resource-limited settings to achieve near-optimal care and appropriate therapy. Methods: The EGFR gene sequencing and CT imaging data of 2277 patients with lung carcinoma were included from three cohorts in India and a White population cohort collected from TCIA. Another cohort LIDC-IDRI was used to train the AIPS-Nodule (AIPS-N) model for automatic detection and characterisation of lung nodules. We explored the value of combining the results of the AIPS-N with the clinical factors in the AIPS-Mutation (AIPS-M) model for predicting EGFR genotype, and it was evaluated by area under the curve (AUC). Findings: AIPS-N achieved an average AP50 of 70.19% in detecting the location of nodules within the lung region of interest during validation and predicted the score of five lung nodule properties. The AIPS-M machine learning (ML) and deep learning (DL) models achieved AUCs ranging from 0.587 to 0.910. Interpretation: The AIPS suggests that CT imaging combined with a fully automated lung-nodule analysis AI system can predict EGFR genotype and identify patients with an EGFR mutation in a cost-effective and non-invasive manner. Funding: This work was supported by a grant provided by Conquer Cancer Foundation of ASCO [2021IIG-5555960128] and Pfizer Products India Pvt. Ltd.

DNASCANNER v2: A Web-Based Tool to Analyze the Characteristic Properties of Nucleotide Sequences.

Throughout the process of evolution, DNA undergoes the accumulation of distinct mutations, which can often result in highly organized patterns that serve various essential biological functions. These patterns encompass various genomic elements and provide valuable insights into the regulatory and functional aspects of DNA. The physicochemical, mechanical, thermodynamic, and structural properties of DNA sequences play a crucial role in the formation of specific patterns. These properties contribute to the three-dimensional structure of DNA and influence their interactions with proteins, regulatory elements, and other molecules. In this study, we introduce DNASCANNER v2, an advanced version of our previously published algorithm DNASCANNER for analyzing DNA properties. The current tool is built using the FLASK framework in Python language. Featuring a user-friendly interface tailored for nonspecialized researchers, it offers an extensive analysis of 158 DNA properties, including mono/di/trinucleotide frequencies, structural, physicochemical, thermodynamics, and mechanical properties of DNA sequences. The tool provides downloadable results and offers interactive plots for easy interpretation and comparison between different features. We also demonstrate the utility of DNASCANNER v2 in analyzing splice-site junctions, casposon insertion sequences, and transposon insertion sites (TIS) within the bacterial and human genomes, respectively. We also developed a deep learning module for the prediction of potential TIS in a given nucleotide sequence. In the future, we aim to optimize the performance of this prediction model through extensive training on larger data sets.

Vaxi-DL: An Artificial Intelligence-Enabled Platform for Vaccine Development.

Vaccine development is a complex and long process. It involves several steps, including computational studies, experimental analyses, animal model system studies, and clinical trials. This process can be accelerated by using in silico antigen screening to identify potential vaccine candidates. In this chapter, we describe a deep learning-based technique which utilizes 18 biological and 9154 physicochemical properties of proteins for finding potential vaccine candidates. Using this technique, a new web-based system, named Vaxi-DL, was developed which helped in finding new vaccine candidates from bacteria, protozoa, viruses, and fungi. Vaxi-DL is available at: https://vac.kamalrawal.in/vaxidl/ .

A Data-Driven Approach to Construct a Molecular Map of Trypanosoma cruzi to Identify Drugs and Vaccine Targets.

Chagas disease (CD) is endemic in large parts of Central and South America, as well as in Texas and the southern regions of the United States. Successful parasites, such as the causative agent of CD, Trypanosoma cruzi have adapted to specific hosts during their phylogenesis. In this work, we have assembled an interactive network of the complex relations that occur between molecules within T. cruzi. An expert curation strategy was combined with a text-mining approach to screen 10,234 full-length research articles and over 200,000 abstracts relevant to T. cruzi. We obtained a scale-free network consisting of 1055 nodes and 874 edges, and composed of 838 proteins, 43 genes, 20 complexes, 9 RNAs, 36 simple molecules, 81 phenotypes, and 37 known pharmaceuticals. Further, we deployed an automated docking pipeline to conduct large-scale docking studies involving several thousand drugs and potential targets to identify network-based binding propensities. These experiments have revealed that the existing FDA-approved drugs benznidazole (Bz) and nifurtimox (Nf) show comparatively high binding energies to the T. cruzi network proteins (e.g., PIF1 helicase-like protein, trans-sialidase), when compared with control datasets consisting of proteins from other pathogens. We envisage this work to be of value to those interested in finding new vaccines for CD, as well as drugs against the T. cruzi parasite.

Identification of vaccine targets & design of vaccine against SARS-CoV-2 coronavirus using computational and deep learning-based approaches.

An unusual pneumonia infection, named COVID-19, was reported on December 2019 in China. It was reported to be caused by a novel coronavirus which has infected approximately 220 million people worldwide with a death toll of 4.5 million as of September 2021. This study is focused on finding potential vaccine candidates and designing an in-silico subunit multi-epitope vaccine candidates using a unique computational pipeline, integrating reverse vaccinology, molecular docking and simulation methods. A protein named spike protein of SARS-CoV-2 with the GenBank ID QHD43416.1 was shortlisted as a potential vaccine candidate and was examined for presence of B-cell and T-cell epitopes. We also investigated antigenicity and interaction with distinct polymorphic alleles of the epitopes. High ranking epitopes such as DLCFTNVY (B cell epitope), KIADYNKL (MHC Class-I) and VKNKCVNFN (MHC class-II) were shortlisted for subsequent analysis. Digestion analysis verified the safety and stability of the shortlisted peptides. Docking study reported a strong binding of proposed peptides with HLA-A*02 and HLA-B7 alleles. We used standard methods to construct vaccine model and this construct was evaluated further for its antigenicity, physicochemical properties, 2D and 3D structure prediction and validation. Further, molecular docking followed by molecular dynamics simulation was performed to evaluate the binding affinity and stability of TLR-4 and vaccine complex. Finally, the vaccine construct was reverse transcribed and adapted for E. coli strain K 12 prior to the insertion within the pET-28-a (+) vector for determining translational and microbial expression followed by conservancy analysis. Also, six multi-epitope subunit vaccines were constructed using different strategies containing immunogenic epitopes, appropriate adjuvants and linker sequences. We propose that our vaccine constructs can be used for downstream investigations using in-vitro and in-vivo studies to design effective and safe vaccine against different strains of COVID-19.

Vaxi-DL: A web-based deep learning server to identify potential vaccine candidates.

The development of a new vaccine is a challenging exercise involving several steps including computational studies, experimental work, and animal studies followed by clinical studies. To accelerate the process, in silico screening is frequently used for antigen identification. Here, we present Vaxi-DL, web-based deep learning (DL) software that evaluates the potential of protein sequences to serve as vaccine target antigens. Four different DL pathogen models were trained to predict target antigens in bacteria, protozoa, fungi, and viruses that cause infectious diseases in humans. Datasets containing antigenic and non-antigenic sequences were derived from known vaccine candidates and the Protegen database. Biological and physicochemical properties were computed for the datasets using publicly available bioinformatics tools. For each of the four pathogen models, the datasets were divided into training, validation, and testing subsets and then scaled and normalised. The models were constructed using Fully Connected Layers (FCLs), hyper-tuned, and trained using the training subset. Accuracy, sensitivity, specificity, precision, recall, and AUC (Area under the Curve) were used as metrics to assess the performance of these models. The models were benchmarked using independent datasets of known target antigens against other prediction tools such as VaxiJen and Vaxign-ML. We also tested Vaxi-DL on 219 known potential vaccine candidates (PVC) from 37 different pathogens. Our tool predicted 175 PVCs correctly out of 219 sequences. We also tested Vaxi-DL on different datasets obtained from multiple resources. Our tool has demonstrated an average sensitivity of 93% and will thus be a useful tool for prioritising PVCs for preclinical studies.

Identification of vaccine targets in pathogens and design of a vaccine using computational approaches.

Antigen identification is an important step in the vaccine development process. Computational approaches including deep learning systems can play an important role in the identification of vaccine targets using genomic and proteomic information. Here, we present a new computational system to discover and analyse novel vaccine targets leading to the design of a multi-epitope subunit vaccine candidate. The system incorporates reverse vaccinology and immuno-informatics tools to screen genomic and proteomic datasets of several pathogens such as Trypanosoma cruzi, Plasmodium falciparum, and Vibrio cholerae to identify potential vaccine candidates (PVC). Further, as a case study, we performed a detailed analysis of the genomic and proteomic dataset of T. cruzi (CL Brenner and Y strain) to shortlist eight proteins as possible vaccine antigen candidates using properties such as secretory/surface-exposed nature, low transmembrane helix (< 2), essentiality, virulence, antigenic, and non-homology with host/gut flora proteins. Subsequently, highly antigenic and immunogenic MHC class I, MHC class II and B cell epitopes were extracted from top-ranking vaccine targets. The designed vaccine construct containing 24 epitopes, 3 adjuvants, and 4 linkers was analysed for its physicochemical properties using different tools, including docking analysis. Immunological simulation studies suggested significant levels of T-helper, T-cytotoxic cells, and IgG1 will be elicited upon administration of such a putative multi-epitope vaccine construct. The vaccine construct is predicted to be soluble, stable, non-allergenic, non-toxic, and to offer cross-protection against related Trypanosoma species and strains. Further, studies are required to validate safety and immunogenicity of the vaccine.