Nick Weir Email and Phone Number

Data Scientist in the ML Specialty Group at Amazon Web Services Worldwide Public Sector Professional Services.

● Senior Data Scientist executing computer vision research projects and software development projects for CosmiQ Works, an In-Q-Tel lab● Led the 4th SpaceNet Challenge for Off-Nadir Building Footprint Detection, including developing a baseline algorithm and writing several blog posts analyzing the dataset and results● Created Solaris, a software stack for performing computer vision/deep learning analysis on overhead imagery

Co-leader of the SpaceNet 4: Off-Nadir Building Footprint Extraction Challenge.● Co-managed challenge operations during the challenge● Performed all solution validation for the top 10 competitors. ● Analyzed competitors' algorithms, wrote analysis blog posts for The DownlinQ (www.medium.com/the-downlinq) and Towards Data Science, and presented conclusions to interested parties within and outside of USG.● Lead author on a research article describing a MultiView Overhead Imagery analysis baseline alongside members of CosmiQ Works and the Intel AI Lab.

● Built a web application using Python that predicts when dogs will be adopted from pet adoption agencies using data from Petfinder.com listings● Predicted pet adoption time to 70% accuracy using NLP, survival regression methods, and random forests

● Contributed to software for Deep Learning-based segmentation of microscopy data● Developed R/Shiny interactive visualizations for CRISPR screen experiments: crispr.deniclab.com● Generalized and enhanced modularity of automated fluorescence microscopy analysis, as well as training other scientists' in use of these methods● Projects:→ Interactive data visualizations of high-throughput screen results (see publications and crispr.deniclab.com)→ Guidance of the laboratory subgroup studying Msp1 function (with Dr. Denic)→ Deep learning-based microscopy image segmentation (with the Garner Lab)→ Ported laboratory databases to cloud-based systems using Python/Flask, AWS, and MySQL

Computational and quantitative analysis‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾● Developed Python and R packages for quantitative image and flow cytometry analysis, now used throughout the lab● Analyzed genetic screen and Next-Gen Sequencing results with Python and R● Became the in-lab expert in high-throughput image analysis and other big data analyses using Python and R● Completed courses in Mathematical Modeling and Mathematics for Biology (Linear Algebra and Probability)● Quantitative methods:→ Regression Analysis: curve fitting, model comparison→ Probability and Statistics→ Support Vector Machines→ Gillespie Simulation→ Computer vision methods: SIFT, edge detection, watershed segmentation, binary morphology→ Data Viz in R and Python● Programming languages:→ Python:scikit-image (contributor) and scikit-learn, pandas, matplotlib, numpy/scipy, others→ R: tidyverse, Shiny, numerous stats packages → git● See www.github.com/nrweir for publicly available analysis packagesBiochemistry and cell biology‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾● Characterized Msp1-mediated protein quality control using quantitative microscopy● Published discoveries in the journals Nature and eLife (see Publications)● Presented research findings at the Keystone Mitochondria Communication Symposium● Extensive bench research experience:→ Confocal fluorescence microscopy→ Next-Gen Sequencing→ Flow cytometry: sample preparation, running, and analysis→ In vitro protein biochemistry: protein purification, activity assays, etc.→ Yeast cell biology: live-cell imaging, organelle isolation, protein purification, and in vitro assays → High-throughput screening: screen preparation, execution, and analysisLeadership and mentoring‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾● Mentored six graduate students and undergraduates in bench research and computational analysis● Independently planned, performed, and analyzed all experiments, guiding projects alongside Dr. Denic

● Led laboratory sections for Harvard's introductory cell and molecular biology course, MCB 52, and the core physical biochemistry course for undergraduates, MCB 56● Prepared and led interactive review sessions on course material with a focus on achieving high levels of engagement with students through the use of active learning techniques● MCB 56: Co-authored problem sets, exams, and laboratory section materials alongside course faculty and another teaching fellow● Recognized for teaching excellence after receiving perfect scores in undergraduate feedback forms for MCB 56 (see Honors & Awards)

● Characterized cytokinin signaling pathways in Arabidopsis and rice● Published research findings as the co-leading author on a paper in the peer-reviewed journal Plant Physiology (see Publications)● Mentored two undergraduates as they joined the lab

● Studied similarities and differences between plant hormone signaling pathways in different species● Completed an Honors thesis that received high honors and two departmental thesis prizes (see Honors & Awards)● Learned molecular cloning, live-cell imaging, and plant physiology techniques● Established rice as a research model in the Schaller Lab