Data Science · Behavioral Neuroscience · Computation

Where the brain
meets the algorithm.

Motivated by understanding how brain circuits generate behavior and using computational tools to turn that understanding into therapies that improve human health.

My Story GitHub LinkedIn
α δ γ
About

A story of curiosity
and computation.

I study how brain circuits produce behavior and how computational tools can help reveal the structure of complex biological systems. I am currently an undergraduate at Northeastern University pursuing a combined major in Data Science and Behavioral Neuroscience.

My interests lie at the intersection of neural circuit biology, data analysis, and translational neuroscience. I am particularly interested in how large-scale biological datasets can be used to better understand brain function and inform the development of new therapies.

Ultimately, I hope to work in pharmaceutical or biomedical research where computational and experimental approaches are combined to translate discoveries in neuroscience into treatments for neurological and psychiatric disease.

🧠 Andermann Lab · Harvard Medical School
Andermann Lab · Computational Neuroscience Co-op
Mu-Opioid Receptors · Pain · LLMs for Spatial Transcriptomics
3
Research Labs & Industry Roles
7+
Programming Languages & Tools
μ-opioid receptors
Experience

The research journey.

May 2026 – Present
Computational Neuroscience Co-op
Andermann Lab · Harvard Medical School, Boston, MA
  • Studying mu-opioid receptor circuits and pain processing using computational methods
  • Leveraging large language models to predict spatial gene expression patterns from tissue data
  • Working at the frontier of AI-assisted neuroscience and spatial transcriptomics
May 2025 – April 2026
Research Assistant
Shansky Neuroanatomy Lab · Northeastern University, Boston, MA
  • Built Python pipelines to clean, synchronize, and structure multi-channel fiber photometry datasets
  • Implemented TTL-based event detection and alignment, reducing manual segmentation time and improving reproducibility
  • Reconstructed missing signal segments via linear interpolation, preserving data continuity
  • Trained deep learning pose estimation models (SLEAP) for automated animal tracking, eliminating manual behavioral scoring
June – July 2025
Summer Intern
Cambridge Mobile Telematics, Boston, MA
  • Built automated spreadsheet pipelines and dashboards to track employment trends and improve stakeholder visibility
  • Partnered with external clients to translate real-world business questions into actionable data analyses
N1 N2 N3
Projects

Building things that matter.

SLEAP pose tracking · live demo
Behavioral Neuroscience · Computer Vision
Automated Rat Behavior Classification via Pose Estimation & Velocity Analysis
PythonSLEAPPose EstimationKinematics
  • Trained SLEAP deep learning models to track rat body keypoints across behavioral video recordings
  • Computed frame-by-frame velocity and movement trajectories from pose coordinate time series
  • Classified scanning and darting behaviors using kinematic signatures to replace manual hand-scoring
  • Built an automated, reproducible pipeline to enable scalable batch processing of behavioral experiments
2025 – 2026
Computational Neuroscience · Signal Processing
Fiber Photometry Signal Processing & Artifact Correction Pipeline
PythonNumPySignal Processing
  • End-to-end pipeline integrating artifact correction and experiment-aligned segmentation
  • TTL-based event detection to align neural signals with behavioral stimuli
  • Derivative-based artifact detection for fluorescence time series
  • Linear interpolation reconstruction with synchronized multi-channel processing
December 2025
Clinical ML · Healthcare
Heart Failure Mortality Prediction
Pythonscikit-learnLogistic RegressionKNN
  • Logistic Regression and K-Nearest Neighbors classifiers — 82% accuracy
  • Chi-square tests and t-tests for statistically significant correlations
  • Key risk factors: serum creatinine, age, and ejection fraction
  • Interpreted model coefficients to assess clinical relevance of predictors
November 2025
Medical AI · Deep Learning
Alzheimer's MRI Classification Model
PythonTensorFlowKerasTransfer Learning
  • Deep learning model to classify Alzheimer's disease stages from MRI images
  • TensorFlow and Keras architectures for image classification
  • Transfer learning via pre-trained model to enhance accuracy
October 2024
View All on GitHub →
GCaMP 470nm 405nm ctrl TTL
Skills

The toolkit.

Languages & Software
PythonRSQLJavaScriptHTMLRacketSPSSSLEAPLaTeXExcel
Machine Learning
K-Nearest NeighborsLogistic RegressionSVDscikit-learnTensorFlowKerasMatplotlib
Data Engineering
Data PipelinesDatabase DesignData CleaningArtifact CorrectionSignal ProcessingData Visualization
Neuroscience Methods
Fiber PhotometryPose EstimationTTL Event DetectionBehavioral ScoringSpatial Transcriptomics
N N N
Education & Recognition

Grounded in science,
driven by community.

Northeastern University

B.S. Data Science & Behavioral Neuroscience

Honors & Certifications
🏅
NU Accelerate ScholarshipNortheastern University merit award
📊
NUView Data Visualization CertificationNortheastern University
🔬
ROP Biotechnology Canvas Certification
💻
Data Science CertificationGirls Who Code
Activities & Involvement
WREN Scholar — Women's Research Engagement Network
Member, ViTAL — Northeastern Healthcare Innovation Club
Evolve Partnership Associate
HHIC — Husky Health Innovation Challenge
Nu.in Madrid — Global Study Program
Relevant Coursework
Foundations of Data ScienceIntermediate Programming with DataIntro to DatabasesStatistics in Psychological ResearchNeurobiologyPsychopharmacologyDevelopmental PsychologyGenetics & Molecular BiologyOrganic ChemistryImmunopathology
Research Interests

Computational approaches to pain & opioid circuits · Spatial transcriptomics & LLM applications · Clinical ML for disease prediction · Neural signal processing & behavior quantification · Pharma + AI drug discovery pipelines