Janiel Jawahar

Mr. Janiel Jawahar

orcid

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 August 2024 in Indonesian Journal of Electrical Engineering and Computer Science
Verified
Journal Article
Open access
PDF file
Janiel JawaharJaniel Jawahar
Janiel Jawahar
PRParamasivan Selvi Rajendran
Paramasivan Selvi Rajendran
Pancreatic cancer is often diagnosed at an advanced stage when treatment options are limited. Being one of the deadliest cancers that mandates longer medication and treatment phases, there is an inevitable need to have the knowledge of drug response of anti-pancreatic cancer drugs before it is recommended for a patient. AI-driven drug response prediction has proven potential to personalize treatment strategies, improve therapeutic outcomes, and reduce adverse effects and treatment costs for cancer patients. In this research work, we have accounted for the use of different drug descriptors and their core structures known as scaffolds along with three cell line features, chromatin profiling, reverse phase protein array, and metabolomics data to build a feature engineered dataset for drug response prediction tested on various computational learning models. The 53 unique drugs against 18 unique pancreatic cancer cell lines were taken as the raw dataset. The initial dataset having a large dimension was feature selected using an ensemble method derived from five different techniques. The dataset was evaluated on various computational methods and an accuracy of 89% was achieved using the TabNet architecture. Furthermore, the common scaffolds that were persistently found among the drugs that possess high IC50-valued drug clusters were also recorded.


10 April 2026 in Preprints.org
Verified
Preprint
Open access
PDF file
Janiel JawaharJaniel Jawahar
Janiel Jawahar
SJSamuel James
Samuel James
The interplay between the environmental exposome and the cancer genome remains a critical "blind spot" in precision oncology. While somatic mutational signatures genomic fossils imprinted by exposures such as ultraviolet radiation, tobacco smoke, and industrial pollutants are well characterized for their etiological significance, their functional impact on therapeutic efficacy remains largely unexplored. We hypothesized that these environmental "genomic scars" induce distinct pharmacogenomic vulnerabilities (collateral sensitivity) and resistance mechanisms (collateral resistance) that vary by geographical exposure patterns. Here, we present the first global "Geo-Pharmacogenomic" atlas, integrating 41 COSMIC mutational signatures with drug response profiles from 1,001 cancer cell lines across four large-scale pharmacogenomic screens (GDSC1, GDSC2, CTRP, CCLE). By harmonizing disparate drug sensitivity metrics and applying rigorous statistical controls for tissue lineage, we identified and validated 608 significant signature-drug interactions (P < 0.01). We demonstrate that UV-associated signature SBS7a is a broad-spectrum driver of therapeutic resistance, conferring intrinsic insensitivity to BRAF inhibitors (PLX-4720, P < 10-4) and Notch inhibitors globally. Conversely, we uncover a novel synthetic lethal vulnerability wherein pollution-driven oxidative stress (SBS18) sensitizes tumors to p38 MAPK inhibition (VX-702, r = -0.45, P < 10-9). Synthesizing these findings with satellite-derived atmospheric data (World Bank/NASA AOD), we constructed a Kriging-interpolated risk surface spanning 122 nations. This analysis predicts distinct "Resistance Landscapes with high-intensity drug resistance predicted in pollution-dense megacities (e.g., Beijing, New Delhi) challenging the paradigm of uniform drug efficacy. Our results establish environmental history as a functional biomarker, necessitating a paradigm shift towards geographically stratified precision medicine.

18 May 2026 in Journal of Xenobiotics
Verified
Journal Article
Open access
PDF file
Janiel JawaharJaniel Jawahar
Janiel Jawahar
SJSamuel James
Samuel James
The interplay between the environmental exposome and the cancer genome remains a critical gap in precision oncology. While somatic mutational signatures—genomic fossils imprinted by exposures such as ultraviolet radiation; tobacco smoke; and industrial pollutants—are well characterised for their etiological significance; their functional impact on therapeutic efficacy remains largely unexplored. We hypothesised that these environmental genomic scars induce distinct pharmacogenomic vulnerabilities and resistance mechanisms that vary by geographical exposure patterns. This study employs two complementary analytical frameworks. First, a linear regression-based pharmacogenomic screen across four datasets (GDSC1, GDSC2, CTRP, CCLE; 1001 cell lines, 31 cancer types) identified 608 statistically significant (p < 0.01) mutational signature–drug interactions, revealing that UV-associated signature SBS7a is associated with broad-spectrum therapeutic resistance, including to BRAF inhibitors (PLX-4720, p < 10−4), while pollution-driven oxidative stress (SBS18) is associated with sensitivity to p38 MAPK inhibition (VX-702, r = −0.45, p < 10−9). Second, an XGBoost predictive model trained exclusively on 33,679 GDSC2 records using a 1265-feature matrix integrating 40 SBS signatures, drug chemistry descriptors, proteomic features, and two satellite-derived environmental variables (NASA PM2.5 and UV)—achieved R2 = 0.7973 on a 20% holdout set (grouped cross-validation R2 = 0.7296). SHAP analysis revealed that satellite-derived PM2.5 (Zone_PM25) ranked 7th of 1265 features, exceeding all 40 individual SBS mutational signatures. Synthesising these findings with satellite-derived atmospheric data, we constructed an exploratory spatially interpolated risk surface spanning 122 nations, generating the hypothesis that uniform drug efficacy assumptions may not apply globally. These findings suggest that a patient’s environmental exposure history may constitute a measurable pharmacogenomic variable. This exploratory framework warrants validation in independent datasets and with individual-level geographic data before clinical application.