Aishwarya Jayagopal

About

I am a PhD candidate at the Clinical Data Analytics Lab, School of Computing, National University of Singapore, advised by Dr. Vaibhav Rajan. My work lies at the intersection of AI and healthcare, specifically in building AI based treatment recommendation systems in data scarce settings, with applications in precision oncology. My research interests include AI for personalization, healthcare applications and transfer learning in data-scarce domains. I have also worked as a Cloud Engineer with a focus on automated deployment and maintainenance of SaaS offerings in production environments. In my spare time, I enjoy reading, trying new cuisines and learning languages.

Master of Computing, School of Computing, National University of Singapore, Singapore
Bachelor of Technology, Amrita School of Engineering, Amrita Vishwa Vidyapeetham, India
CV

Publications

Accepted Papers

Soham Dasgupta, Aishwarya Jayagopal, Abel Lim Jun Hong, Ragunathan Mariappan, and Vaibhav Rajan. 'Adverse drug event prediction using noisy literature-derived knowledge graphs: algorithm development and validation'. JMIR Medical Informatics 9, no. 10 (2021): e32730. Paper | Code Repo

Ragunathan Mariappan, Aishwarya Jayagopal, Ho Zong Sien, and Vaibhav Rajan. 'Neural Collective Matrix Factorization for integrated analysis of heterogeneous biomedical data'. Bioinformatics 38, no. 19 (2022): 4554-4561. Paper | Code Repo

Herty Liany, Aishwarya Jayagopal, Dachuan Huang, Jing Quan Lim, Nur Izzah Nbh, Anand Jeyasekharan, Choon Kiat Ong, and Vaibhav Rajan. "ASTER: A Method to Predict Clinically Relevant Synthetic Lethal Genetic Interactions." IEEE Journal of Biomedical and Health Informatics (2024). Paper | Code Repo

Robert J. Walsh, Rebecca Ong, Seng Wee Cheo, Peter Q. Low, Aishwarya Jayagopal, Matilda Lee, Natalie Ngoi et al. "Molecular profiling of metastatic breast cancer and target-based therapeutic matching in an Asian tertiary phase I oncology unit." Frontiers in Oncology 14: 1342346. Paper

Kumar Shubham, Aishwarya Jayagopal, Syed Mohammed Danish, Prathosh AP, and Vaibhav Rajan. "WISER: Weak supervISion and supErvised Representation learning to improve drug response prediction in cancer". 41st International Conference on Machine Learning ICML 2024. Paper | Code Repo

Aishwarya Jayagopal, Hansheng Xue, Ziyang He, Robert J. Walsh, Krishna Kumar Hariprasannan, David Shao Peng Tan, Tuan Zea Tan, Jason J. Pitt, Anand D. Jeyasekharan, and Vaibhav Rajan. "Personalised Drug Identifier for Cancer Treatment with Transformers using Auxiliary Information." ACM SIGKDD Conference on Knowledge Discovery and Data Mining KDD 2024. Paper | Code Repo

Conference Presentations

Aishwarya Jayagopal, Lin Jing, Folefac Aminkeng, Kee Yuan Ngiam and Vaibhav Rajan. 'Unsupervised discovery of biomedical associations from clinical and auxiliary data'. Presented at Conference on Health IT and Analytics, CHITA 2023.

Poster Presentations

Nicole Ren Jiahui, Aishwarya Jayagopal, Anand D Jeyasekharan and Vaibhav Rajan. 'Cancer Drug Response in Patients via Semi-supervised Deep Co-training'. (TransMed COSI), 32nd Conference on Intelligent Systems for Molecular Biology ISMB 2024

Robert J. Walsh, Aishwarya Jayagopal, Tuan Zea Tan, Jason J. Pitt, Raghav Sundar, S.C. Lee, B.C. Goh, Vaibhav Rajan, David S.P. Tan and Anand D. Jeyasekharan. '229TiP A phase II trial of a neural network-based treatment decision support tool in patients (pts) with refractory solid organ malignancies'. ESMO Annals of Oncology 2024. Abstract

Robert J. Walsh, Aishwarya Jayagopal, Raghav Sundar, S.C. Lee, B.C. Goh, David S.P. Tan, Vaibhav Rajan and Anand D. Jeyasekharan. 'A phase ii trial of a neural network-based treatment decision support tool in patients with refractory solid organ malignancies'. NCIS Annual Research Meeting (NCAM), 2024.

Preprints

Aishwarya Jayagopal, Robert J. Walsh, Krishna Kumar Hariprasannan, Ragunathan Mariappan, Debabrata Mahapatra, Patrick William Jaynes, Diana Lim et al. "A multi-task domain-adapted model to predict chemotherapy response from mutations in recurrently altered cancer genes." Paper | Code Repo

Academic Projects

Cancer Drug Recommendation (Ongoing)

Developing deep learning methods for recommending chemotherapy drugs to cancer patients, based on their genetic profiles from diagnostic panels (in collaboration with oncologists at the National University Hospital, Singapore).

DruID Code Repo | DruID Preprint

PREDICT-AI Code Repo | PREDICT-AI Preprint

Transfer Learning for Genomic Data Augmentation

Developed a genomic data augmentation strategy, guided by transfer learning, using diffusion models, to avoid overfitting issues in low data domains

Code Repo

LLM Chain of Thought Evaluation for Healthcare

Developed a metric that evaluates reasoning ability of LLMs in medical question-answer tasks, using medical knowledge graphs, to remove the need for human expert evaluation.

Code Repo

Multi-modal book genre identification

Developed a multi-modal deep learning method to identify the genre of a book, given its blurb and cover image

Code Repo | Preprint

Sentiment Analysis from Tweets

Analyzed user sentiments from tweets collected during the peak of the COVID-19 pandemic, using Natural Language Processing techniques and clustering.

Drug Response Prediction in Cell Lines

Developed a drug response prediction algorithm using graph neural networks, to predict how cancer cells respond to treatment, while incorporating auxiliary biological knowledge data sources

Code Repo

Predicting COVID-19 Policy Effectiveness

Developed a data-driven approach to identify the best policy to handle COVID-19 crisis at a country-level, using probabilistic graphical models.

Code Repo

Pathogen Detection from input genomic sequence

Leveraged machine learning algorithms to identify various species of pathogenic microorganisms in a given sample

Batch Effect Quantification Metric

Proposed a strategy to quantify batch effects in varied genomic datasets, based on both label and data distribution

Confident Mutation Calling

Leveraged machine learning algorithms to identify true mutations based on predictions from 4 mutation calling algorithms

Knowledge discovery for cancer phenotyping (Ongoing)

Using deep learning to analyze clusters of patients, suffering from Hodgkin's Lymphoma, from their clinical and genetic features (in collaboration with the National University Health System, Singapore).

Music Genre Classification

Performed music genre classification on song snippets collected from Spotify, using attention neural network and multi layer perceptron.

Work Experience

Research Assistant

Clinical Data Analytics Lab, National University of Singapore

May 2021 - Aug 2021

Polypharmacy Side Effect Prediction: Leveraged matrix factorization and graph machine learning based models to predict side effects arising from simultaneous consumption of drugs.

Cloud Application Engineer

Oracle India Private Limited, Hyderabad, India

Mar 2019 - Nov 2020

Cloud Provider Migration: Facilitated the migration of Aconex to Oracle Cloud Infrastructure, using orchestration tools like Puppet, Ansible and infrastructure management tool Terraform

Certifications: Certified Oracle Cloud Infrastructure Architect Associate and Professional.

Associate Cloud Application Engineer

Oracle India Private Limited, Hyderabad, India

Jul 2016 - Mar 2019

Oracle Linux Version Migration: Named Employee of the Month, for orchestrating the application of security patches, scaling of instances and migration of Oracle Linux version on Oracle Primavera and Prime technology stacks, using Chef Client and Server.

Project Intern

Oracle India Private Limited, Hyderabad, India

Jan 2016 - Jul 2016

Log Monitoring: Performed log monitoring and analysis of Oracle Primavera Unifier using ElasticSearch, Logstash, Kibana (ELK) stack.