Alok is a translational researcher working in systems biomedicine, healthcare data science, and disease modeling. His expertise uses AI, ML models for multi-dimensional omics, and diagnostic imaging data to predict risk, disease association, and relapse. His background in tumorigenesis, metastasis, tumor evolution, and cell-cell communication. yielded clinically translational biomarkers for gynecologic cancers, breast cancer, pancreatic cancer, multiple myeloma, and prostate cancer. He also developed several novel methods for biomarker discovery such as graph motif mining, Kirchoff's law traversal, graph convolution neural network, and the semantic web. His recent research is focused on explaining mosaicism genetics for cardiac amyloidosis and multiple myeloma.
Affiliated Faculty, Center for Artificial Intelligence in Medicine & Imaging (2020 - Present)
Honors & Awards
(CLARIFY) Cancer Long Survivors Artificial Intelligence Follow Up Co-PI, European Commission Horizon2020 (H2020-SC1-DTH-2019) https://cordis.europa.eu/project/id/875160 (1 January 2020-31 December 2022)
PhD, Data Science Institute, National University of Ireland, Galway, Data Science, Cancer Genomics, Machine Learning, Biomarker Discovery (2019)
Research Intern, Beth Israel Deaconess Medical Center (Exchange Student), Harvard University, Pancreatic and prostate cancer Metastasis (2017)
MS, Manipal University, Udupi, India, Medical Data Science, Genomics (2014)
BS, Memchandracharya North Gujarat University, Gujarat, India, Electronics and Communication (2010)
Current Research and Scholarly Interests
Systems biomedicine, Genetic Risk score, Tumor modelling, Radiomics
A community effort to create standards for evaluating tumor subclonal reconstruction.
2020; 38 (1): 97–107
Tumor DNA sequencing data can be interpreted by computational methods that analyze genomic heterogeneity to infer evolutionary dynamics. A growing number of studies have used these approaches to link cancer evolution with clinical progression and response to therapy. Although the inference of tumor phylogenies is rapidly becoming standard practice in cancer genome analyses, standards for evaluating them are lacking. To address this need, we systematically assess methods for reconstructing tumor subclonality. First, we elucidate the main algorithmic problems in subclonal reconstruction and develop quantitative metrics for evaluating them. Then we simulate realistic tumor genomes that harbor all known clonal and subclonal mutation types and processes. Finally, we benchmark 580 tumor reconstructions, varying tumor read depth, tumor type and somatic variant detection. Our analysis provides a baseline for the establishment of gold-standard methods to analyze tumor heterogeneity.
View details for DOI 10.1038/s41587-019-0364-z
View details for PubMedID 31919445
Clinical impact of COVID-19 on patients with cancer (CCC19): a cohort study.
Lancet (London, England)
Data on patients with COVID-19 who have cancer are lacking. Here we characterise the outcomes of a cohort of patients with cancer and COVID-19 and identify potential prognostic factors for mortality and severe illness.In this cohort study, we collected de-identified data on patients with active or previous malignancy, aged 18 years and older, with confirmed severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection from the USA, Canada, and Spain from the COVID-19 and Cancer Consortium (CCC19) database for whom baseline data were added between March 17 and April 16, 2020. We collected data on baseline clinical conditions, medications, cancer diagnosis and treatment, and COVID-19 disease course. The primary endpoint was all-cause mortality within 30 days of diagnosis of COVID-19. We assessed the association between the outcome and potential prognostic variables using logistic regression analyses, partially adjusted for age, sex, smoking status, and obesity. This study is registered with ClinicalTrials.gov, NCT04354701, and is ongoing.Of 1035 records entered into the CCC19 database during the study period, 928 patients met inclusion criteria for our analysis. Median age was 66 years (IQR 57-76), 279 (30%) were aged 75 years or older, and 468 (50%) patients were male. The most prevalent malignancies were breast (191 [21%]) and prostate (152 [16%]). 366 (39%) patients were on active anticancer treatment, and 396 (43%) had active (measurable) cancer. At analysis (May 7, 2020), 121 (13%) patients had died. In logistic regression analysis, independent factors associated with increased 30-day mortality, after partial adjustment, were: increased age (per 10 years; partially adjusted odds ratio 1·84, 95% CI 1·53-2·21), male sex (1·63, 1·07-2·48), smoking status (former smoker vs never smoked: 1·60, 1·03-2·47), number of comorbidities (two vs none: 4·50, 1·33-15·28), Eastern Cooperative Oncology Group performance status of 2 or higher (status of 2 vs 0 or 1: 3·89, 2·11-7·18), active cancer (progressing vs remission: 5·20, 2·77-9·77), and receipt of azithromycin plus hydroxychloroquine (vs treatment with neither: 2·93, 1·79-4·79; confounding by indication cannot be excluded). Compared with residence in the US-Northeast, residence in Canada (0·24, 0·07-0·84) or the US-Midwest (0·50, 0·28-0·90) were associated with decreased 30-day all-cause mortality. Race and ethnicity, obesity status, cancer type, type of anticancer therapy, and recent surgery were not associated with mortality.Among patients with cancer and COVID-19, 30-day all-cause mortality was high and associated with general risk factors and risk factors unique to patients with cancer. Longer follow-up is needed to better understand the effect of COVID-19 on outcomes in patients with cancer, including the ability to continue specific cancer treatments.American Cancer Society, National Institutes of Health, and Hope Foundation for Cancer Research.
View details for DOI 10.1016/S0140-6736(20)31187-9
View details for PubMedID 32473681
Gene Signatures to Distinguish Amyloid Cardiomyopathy Risk in Multiple Myeloma Patients
LIPPINCOTT WILLIAMS & WILKINS. 2019
View details for Web of Science ID 000511467800441
GenomicsKG: A Knowledge Graph to Visualize Poly-Omics Data
Journal of Advances in Health
2019; 2 (2): 70-84
View details for DOI 10.3724/SP.J.2640-8686.2019.0063
Abstract 750: Gene Signatures to Distinguish Amyloid Cardiomyopathy Risk in Multiple Myeloma Patients
View details for DOI 10.1161/res.125.suppl_1.750
Alteration in ventricular pressure stimulates cardiac repair and remodeling.
Journal of molecular and cellular cardiology
The mammalian heart undergoes complex structural and functional remodeling to compensate for stresses such as pressure overload. While studies suggest that, at best, the adult mammalian heart is capable of very limited regeneration arising from the proliferation of existing cardiomyocytes, how myocardial stress affects endogenous cardiac regeneration or repair is unknown. To define the relationship between left ventricular afterload and cardiac repair, we induced left ventricle pressure overload in adult mice by constriction of the ascending aorta (AAC). One week following AAC, we normalized ventricular afterload in a subset of animals through removal of the aortic constriction (de-AAC). Subsequent monitoring of cardiomyocyte cell cycle activity via thymidine analog labeling revealed that an acute increase in ventricular afterload induced cardiomyocyte proliferation. Intriguingly, a release in ventricular overload (de-AAC) further increases cardiomyocyte proliferation. Following both AAC and de-AAC, thymidine analog-positive cardiomyocytes exhibited characteristics of newly generated cardiomyocytes, including single diploid nuclei and reduced cell size as compared to age-matched, sham-operated adult mouse myocytes. Notably, those smaller cardiomyocytes frequently resided alongside one another, consistent with local stimulation of cellular proliferation. Collectively, our data demonstrate that adult cardiomyocyte proliferation can be locally stimulated by an acute increase or decrease of ventricular pressure, and this mode of stimulation can be harnessed to promote cardiac repair.
View details for DOI 10.1016/j.yjmcc.2019.06.006
View details for PubMedID 31220468
- One Size Does Not Fit All: Querying Web Polystores IEEE ACCESS 2019; 7: 9598–9617
Ranked MSD: A New Feature Ranking and Feature Selection Approach for Biomarker Identification
Cross Domain Conference for Machine Learning and Knowledge Extraction co-located with ARES 2019
View details for DOI 10.1007/978-3-030-29726-8_10
Determination of system level alterations in host transcriptome due to Zika virus (ZIKV) Infection in retinal pigment epithelium
2018; 8: 11209
Previously, we reported that Zika virus (ZIKV) causes ocular complications such as chorioretinal atrophy, by infecting cells lining the blood-retinal barrier, including the retinal pigment epithelium (RPE). To understand the molecular basis of ZIKV-induced retinal pathology, we performed a meta-analysis of transcriptome profiles of ZIKV-infected human primary RPE and other cell types infected with either ZIKV or other related flaviviruses (Japanese encephalitis, West Nile, and Dengue). This led to identification of a unique ZIKV infection signature comprising 43 genes (35 upregulated and 8 downregulated). The major biological processes perturbed include SH3/SH2 adaptor activity, lipid and ceramide metabolism, and embryonic organ development. Further, a comparative analysis of some differentially regulated genes (ABCG1, SH2B3, SIX4, and TNFSF13B) revealed that ZIKV induced their expression relatively more than dengue virus did in RPE. Importantly, the pharmacological inhibition of ABCG1, a membrane transporter of cholesterol, resulted in reduced ZIKV infectivity. Interestingly, the ZIKV infection signature revealed the downregulation of ALDH5A1 and CHML, genes implicated in neurological (cognitive impairment, expressive language deficit, and mild ataxia) and ophthalmic (choroideremia) disorders, respectively. Collectively, our study revealed that ZIKV induces differential gene expression in RPE cells, and the identified genes/pathways (e.g., ABCG1) could potentially contribute to ZIKV-associated ocular pathologies.
View details for DOI 10.1038/s41598-018-29329-2
View details for Web of Science ID 000439686700032
View details for PubMedID 30046058
View details for PubMedCentralID PMC6060127
Using Machine Learning to Distinguish Infected from Non-infected Subjects at an Early Stage Based on Viral Inoculation
International Conference on Data Integration in the Life Sciences
View details for DOI 10.1007/978-3-030-06016
- Features’ compendium for machine learning in NGS data Analysis Journal of Advanced Research in Biology 2018; 1 (2)
- Deep Convolution Neural Network Model to Predict Relapse in Breast Cancer IEEE. 2018: 351–58
Linked Data Based Multi-omics Integration and Visualization for Cancer Decision Networks
International Conference on Data Integration in the Life Sciences
View details for DOI 10.1007/978-3-030-06016-9_16
- FedS: Towards Traversing Federated RDF Graphs SPRINGER INTERNATIONAL PUBLISHING AG. 2018: 34–45
E-selectin ligands recognised by HECA452 induce drug resistance in myeloma, which is overcome by the E-selectin antagonist, GMI-1271
2017; 31 (12): 2642–51
Multiple myeloma (MM) is characterized by the clonal expansion and metastatic spread of malignant plasma cells to multiple sites in the bone marrow (BM). Recently, we implicated the sialyltransferase ST3Gal-6, an enzyme critical to the generation of E-selectin ligands, in MM BM homing and resistance to therapy. Since E-selectin is constitutively expressed in the BM microvasculature, we wished to establish the contribution of E-selectin ligands to MM biology. We report that functional E-selectin ligands are restricted to a minor subpopulation of MM cell lines which, upon expansion, demonstrate specific and robust interaction with recombinant E-selectin in vitro. Moreover, an increase in the mRNA levels of genes involved in the generation of E-selectin ligands was associated with inferior progression-free survival in the CoMMpass study. In vivo, E-selectin ligand-enriched cells induced a more aggressive disease and were completely insensitive to Bortezomib. Importantly, this resistance could be reverted by co-administration of GMI-1271, a specific glycomimetic antagonist of E-selectin. Finally, we report that E-selectin ligand-bearing cells are present in primary MM samples from BM and peripheral blood with a higher proportion seen in relapsed patients. This study provides a rationale for targeting E-selectin receptor/ligand interactions to overcome MM metastasis and chemoresistance.
View details for DOI 10.1038/leu.2017.123
View details for Web of Science ID 000417177100013
View details for PubMedID 28439107
View details for PubMedCentralID PMC5729350
Towards precision medicine: discovering novel gynecological cancer biomarkers and pathways using linked data
JOURNAL OF BIOMEDICAL SEMANTICS
2017; 8: 40
Next Generation Sequencing (NGS) is playing a key role in therapeutic decision making for the cancer prognosis and treatment. The NGS technologies are producing a massive amount of sequencing datasets. Often, these datasets are published from the isolated and different sequencing facilities. Consequently, the process of sharing and aggregating multisite sequencing datasets are thwarted by issues such as the need to discover relevant data from different sources, built scalable repositories, the automation of data linkage, the volume of the data, efficient querying mechanism, and information rich intuitive visualisation.We present an approach to link and query different sequencing datasets (TCGA, COSMIC, REACTOME, KEGG and GO) to indicate risks for four cancer types - Ovarian Serous Cystadenocarcinoma (OV), Uterine Corpus Endometrial Carcinoma (UCEC), Uterine Carcinosarcoma (UCS), Cervical Squamous Cell Carcinoma and Endocervical Adenocarcinoma (CESC) - covering the 16 healthy tissue-specific genes from Illumina Human Body Map 2.0. The differentially expressed genes from Illumina Human Body Map 2.0 are analysed together with the gene expressions reported in COSMIC and TCGA repositories leading to the discover of potential biomarkers for a tissue-specific cancer.We analyse the tissue expression of genes, copy number variation (CNV), somatic mutation, and promoter methylation to identify associated pathways and find novel biomarkers. We discovered twenty (20) mutated genes and three (3) potential pathways causing promoter changes in different gynaecological cancer types. We propose a data-interlinked platform called BIOOPENER that glues together heterogeneous cancer and biomedical repositories. The key approach is to find correspondences (or data links) among genetic, cellular and molecular features across isolated cancer datasets giving insight into cancer progression from normal to diseased tissues. The proposed BIOOPENER platform enriches mutations by filling in missing links from TCGA, COSMIC, REACTOME, KEGG and GO datasets and provides an interlinking mechanism to understand cancer progression from normal to diseased tissues with pathway components, which in turn helped to map mutations, associated phenotypes, pathways, and mechanism.
View details for DOI 10.1186/s13326-017-0146-9
View details for Web of Science ID 000411379200001
View details for PubMedID 28927463
View details for PubMedCentralID PMC5606033
- A linked data approach to discover HPV oncoprotiens and RB1 induced mutation associations for the retinoblastoma research AMER ASSOC CANCER RESEARCH. 2017
- Drug Dosage Balancing Using Large Scale Multi-omics Datasets SPRINGER INTERNATIONAL PUBLISHING AG. 2017: 81–100
Querying Web Polystores
IEEE. 2017: 3190–95
View details for Web of Science ID 000428073703029
A 13-Glycosylation Gene Signature in Multiple Myeloma Can Predicts Survival and Identifies Candidates for Targeted Therapy (GiMM13)
AMER SOC HEMATOLOGY. 2016
View details for Web of Science ID 000394452504034
- A Linked Data Visualiser for Finite Element Biosimulations INTERNATIONAL JOURNAL OF SEMANTIC COMPUTING 2016; 10 (2): 219–45