MiCM Scholars program - Meet the 2020 Summer Scholars
Applicants of the summer 2020 MiCM scholar program, share what they learned from
their experience after participating in the program.
Name: Anny Hang
Department: Computer Science and Biology
1. Can you tell me a bit about yourself?
I will be a U4 student in joint Computer Science and Biology. I am interested in genetics, data analysis and machine learning.
2. Can you tell us about the type of work you were involved in this summer?
I got to work with Dr. Mari Kaartinen on profiling differential gene expressions of the adipose tissue in weight gain. I was given a microarray dataset of pairs of weight discordant twins, and my job was to find ways to visualize the different ways to show differential expression of the genes in the adipose tissue between the heavy and lean twins.
Most of the analysis was done with R and R packages from Bioconductor. I did data preprocessing with the help of bioinformatics pipelines for microarrays. Then, I visualized the results in plots such as volcano plots and heatmaps.
3. Briefly note new skills, techniques and knowledge gained from the internship?
I learned to program in R, which is an important language to know in bioinformatics and computational medicine. I learned how to handle data and to make our results more credible by doing quality control. I also learned that there is a lot more resources that can be found online such as softwares that generate the plots I needed or even the entire human genome.
4. Did you feel the internship was a valuable experience in relation to your studies or career goals? Please elaborate
As a Computer Science and Biology student, this internship was very valuable in opening the doors to practicing what I am studying. Working in Biology now involves a lot of computational work, and MiCM offered the opportunity to show how the two fields overlap.
5. How did the pandemic affect the internship (i.e work, collaboration)?
Initially, my supervisor Dr. Mari Kaartinen had planned on two projects, but due to delays caused by the pandemic, one of the projects had to be cancelled. However, for the one I did do, I am grateful that I had all the data needed to complete it. Help wise, I found that the resources we had to communicate virtually were great despite the pandemic.
6. Could you suggest any additional computational/statistical workshops that would be beneficial for next year’s interns?
Introducing packages or libraries of programming languages could be beneficial for interns who have little experience in bioinformatics. Also, a lot of interns worked on prediction models, so I think learning about methods in machine learning would be interesting.
7. Would you recommend this internship to other students?
Of course! I found this internship to be very beneficial especially for students who are interested in interdisciplinary fields involving statistics, computer science and biology.
8. Anything else you would like to contribute about your internship experience?
This was a great experience for me to not only learn but to step into the working world of research. I appreciate the opportunity of this project given by Dr. Mari Kaartinen, the help that was provided by our program manager Dr. Amadou Barry, as well as the contribution of Mansi Arora.
Name: Grace Yu
Department: Undergraduate: Physiology (Joint Major in Physiology and Mathematics), Research: School of Communication Sciences and Disorders
1. Can you tell me a bit about yourself?
I am passionate about mathematics and physiology, and especially about the research that lies in their intersection. I hope to learn how to apply mathematics and computer science to biomedical problems in ways that improve people’s lives.
2. Can you tell us about the type of work you were involved in this summer?
I worked on developing computational models that predict the performance of various biomaterials for intervertebral discs. Specifically, I worked on developing an agent-based model that simulates the cellular and biochemical components of intervertebral disc biomaterials. I also worked on coupling the agent-based model with a finite-element model, in order to integrate the cellular, chemical, and physical components of biomaterials.
3. Briefly note new skills, techniques and knowledge gained from the internship?
From literature review, I learned about intervertebral discs, their disease and degeneration, and biomaterial therapies developed for intervertebral disc disorders. I also learned about optimization techniques, especially differential evolution, and I learned how to apply them to parameter estimation problems. Furthermore, I learned some basics of finite-element modelling in order to design a workflow that considers their inputs, outputs, and spatial and temporal discretization.
4. Did you feel the internship was a valuable experience in relation to your studies or career goals? Please elaborate
This internship provided me with a valuable experience to build on my knowledge from my studies and learn how to apply it to research. I was very grateful to do a project that applies my mathematical and computational skills to a problem that is clinically relevant. The experience will help me as I plan to pursue computational medicine research in future studies and careers.
5. How did the pandemic affect the internship (i.e work, collaboration)?
Because of the pandemic, I was unable to meet other members of my lab, collaborators, or MiCM in person. Moreover, I was missing some data because our collaborators experienced restrictions to lab access.
6. Could you suggest any additional computational/statistical workshops that would be beneficial for next year’s interns?
I think it would be beneficial to have workshops on high-performance computing or artificial intelligence.
7. Would you recommend this internship to other students?
Yes; it was a good opportunity for learning a lot about computational medicine research, not only from your own research project, but also from other scholars.
8. Anything else you would like to contribute about your internship experience?
Thank you to my supervisor, Dr. Li-Jessen; the organizers from MiCM; Amadou Barry for organizing our meetings; and the other scholars for sharing about their work!
Name: Jacob Shkrob
Department: Mathematics and Statistics
1. Can you tell me a bit about yourself?
I’m interested in applications of statistical computation and optimization algorithms in fields of biology, epidemiology, and genetics. I also have a passion in general for abstract mathematics and probability theory. I also really enjoy making music, studying music theory, and writing creative poetry outside of school.
2. Can you tell us about the type of work you were involved in this summer?
During the summer, I was involved with Dr. Sapir-Pichhadze and Prof. Yi Yang’s project on analyzing the effect of eplet mismatching on kidney graft failure. The goal for my project was to introduce novel computation approaches in survival analysis to find optimal donor-recipient matches based on HLA epitope compatibility.
3. Briefly note new skills, techniques and knowledge gained from the internship?
I learned a lot of theoretical information about survival analysis, as well as computational algorithms that are used in optimization problems with non-differentiable constraints. I also learned, through my personal experience, how to code efficient algorithms using R, and how to organize good, reproducible simulations.
4. Did you feel the internship was a valuable experience in relation to your studies or career goals? Please elaborate
I think that the internship was a great learning experience for me, especially with regards to how to become self-motivated and research methods on your own. Although I’m not really sure exactly how the internship will help with career goals, I believe that as a researcher it has helped me become more patient and persevere through any of the misunderstandings or roadblocks that may occur while investigating future problem.
5. How did the pandemic affect the internship (i.e work, collaboration)?
The pandemic made meetings and any subsequent communication with my mentors challenging, but not impossible. We ended up using Zoom a lot more than I anticipated, which got me used to this new paradigm shift that everyone is facing nowadays, as well as Slack and Dropbox. Besides this, however, I was also never really able to access the clinical data that the doctor collected, so most of my research was done purely theoretically and validated using simulation studies, which is not nearly as interesting or exciting as using real data. Collaboration, however, was still active and strong.
6. Could you suggest any additional computational/statistical workshops that would be beneficial for next year’s interns?
I think basics of statistical inference and machine learning would benefit most interns, especially since most ended up using some sort of machine learning algorithm/architecture in their research.
7. Would you recommend this internship to other students?
I think that the internship is great for students who are interested in a more multifaceted approach to computational biology i.e. those who wish to combine many different fields together and relate them to biology to discover something interesting. I’m not sure how interesting it would be for someone who is solely in biology or solely in mathematics, since it’s so interdisciplinary. For myself, I knew very little about immunology but ended up learning these concepts on my own.
8. Anything else you would like to contribute about your internship experience?
Thanks a ton for your hard work and effort over the summer, even during such unprecedented circumstances, I really appreciate it. And I would like to thank Arber and Amadou for guiding our projects and giving us personalized advice, it was great to hear Amadou’s research which I really enjoyed listening to!
Name: Kusha Sareen
Department: Physiology
1. Can you tell me a bit about yourself?
I’m an undergraduate student in Physiology and Physics going into my second year. I’m passionate about applying quantitative methods to biology and using computer science in physiological problems. In my free time, I like to read, watch British sitcoms, and play basketball.
2. Can you tell us about the type of work you were involved in this summer?
This summer, I worked on developing a model for calcium transients in oligodendrocytes. Cacium is an important secondary messenger responsible for a number of intreacellular processes. Recently, calcium oscillations in oligodendrocytes were found to be linked to myelin sheath growth and retraction. It’s necessary to understand these oscillations to better understand demyelinating disorers. These oscillations have also shown to depend on the activity of the neuron being enwrapped. This creates a framework for activity-dependent myelin placticity where the signal transduction of a neuron depends on it’s own firing rate. I worked on developing a data-based differential equation model for these calcium oscillations in oligodendrocytes in hopes of better understanding the system’s dynamics.
3. Briefly note new skills, techniques and knowledge gained from the internship?
Throughout the summer, I worked mostly in MATLAB and Python. I didn’t have much experience in MATLAB prior to this and it made for a great learning experience. I also learned about the diversity of intracellular calcium signalling and the mechanisms that influence it. I tried my hand at analyzing a system expressing nonlinear dynamics and learned some techniques for this analysis. I gained experience reading academic papers and doing literature review.
4. Did you feel the internship was a valuable experience in relation to your studies or career goals? Please elaborate
This internship was a very valuable experience for me going forward. I learned what research in quantitative biology looks like and better understood the types of questions researchers in this field seek to answer. This information is invaluable in making career decisions. Also, the work garnered my interest in some of classes I’ll be taking in my degree and also opened my eyes to other things I’d like to learn about.
5. How did the pandemic affect the internship (i.e work, collaboration)?
Unfortunately, due to the pandemic I wasn’t able to meet professors, other students and program advisors/coordinators in person. However, frequent video calls made it easy to collaborate in the lab, get advice from coordinators, and learn about everyone else’s work.
6. Could you suggest any additional computational/statistical workshops that would be beneficial for next year’s interns?
I attended a number of the Centre for Applied Mathematics in Bioscience and Medicine (CAMBAM) Seminars and found them to be both interesting and relevant to my work. In addition to the workshops this year, I think it would be useful to give an introduction to programming languages applicable to computational medicine like MATLAB, Python and R. It would also be cool to learn about techniques that are often used to solve computational problems in medicine like signal processing or radiological methods.
7. Would you recommend this internship to other students?
I would definitely recommend this internship to other students interesting at looking at biology through a quantitative lens. It was wonderful experience! It was truly special to learn something new about math or biology and then get to apply it first hand.
8. Anything else you would like to contribute about your internship experience?
I thoroughly enjoyed this experience and am thankful for everybody that supported me and made it possible.
Name: Michelle Wang
Department: Neuroscience
1. Can you tell me a bit about yourself?
I am an undergraduate student going into my last year doing a major in Neuroscience and a minor in Computer Science. I am interested in research at the intersection of computer science and biology, and I have previously worked on projects involving the analysis of neural oscillations using magnetoencephalography data. I am also passionate about neurotechnology and human-computer interfaces.
2. Can you tell us about the type of work you were involved in this summer?
The goal of my project was to determine genetic and psychosocial factors associated with major depressive disorder (MDD). I worked with both genotype data (specifically information about single-nucleotide polymorphisms, or SNPs) and phenotype data (in the form of a questionnaire and variables derived from answers in that questionnaire). I performed genome-wide association analyses and used novel statistical techniques to determine which, if any, SNPs and psychosocial intermediate phenotypes were associated with MDD. I was supervised in this project by Dr. Xiangfei Meng and Dr. Yue Li.
3. Briefly note new skills, techniques and knowledge gained from the internship?
Going into this project, I did not have a strong background in genetics, so this project gave me the opportunity to learn a lot about genome-wide association studies, polygenic risk scores, and statistical genetics in general.
On the more technical side, I learned how to use software tools commonly used in the field of genetics (for example, the PLINK program to perform quality control of genotype data as well as perform simple association analyses). I also improved my programming skills by writing shell scripts to automate analysis pipelines that required the use of command-line programs. Finally, I gained more familiarity the programming language R and improved my data visualization skills in both Python (using Matplotlib and Seaborn) and R (using ggplot2).
4. Did you feel the internship was a valuable experience in relation to your studies or career goals? Please elaborate
Yes. I learned many new and useful skills for future graduate studies and a potential career in research, and this internship also helped me decide what I want to do once I graduate. I also had the chance to meet people with similar interests as me and expand my professional network.
5. How did the pandemic affect the internship (i.e work, collaboration)?
All of my work was done remotely, and I communicated with my supervisors through weekly Zoom meetings and emails.
6. Could you suggest any additional computational/statistical workshops that would be beneficial for next year’s interns?
Depending on the interns’ levels of experience, I think anything from beginner/intermediate workshops on Python and/or R libraries for data science to more advanced workshops on problems from a specific research field could be beneficial for future interns. In particular, for research in genomics, I think a workshop on the Bioconductor software could be pertinent.
7. Would you recommend this internship to other students?
Yes. I think it’s an excellent opportunity to get hands-on research experience and to learn more about applying quantitative/computational techniques to life science data.
8. Anything else you would like to contribute about your internship experience?
It was a very rewarding (though sometimes challenging) experience. I learned a lot and am very grateful to have had this opportunity.
Name: Yujing Zou
Department: Medical Physics (M.Sc. Fall 2020); Joint major: Physiology & Mathematics, Minor: Physics (B.Sc. Class of 2020)
1. Can you tell me a bit about yourself?
I completed my undergrad this May where I pursued a joint major in physiology and mathematics with a minor in physics. Starting Fall 2020, I will begin my master’s in Medical Physics at McGill. Throughout my undergraduate degree, I have been inspired and drawn to interdisciplinary research. Specifically using mathematical modeling and computational tools to uncover non-linear dynamics problems in biology, as well as using machine learning and Radiomics to investigate various diagnostics imaging modalities in medical physics.
Outside of academics, I am very passionate about song-writing, recording, producing and performing music, as well as learning new programming tricks and languages.
2. Can you tell us about the type of work you were involved in this summer?
Head and Neck (H&N) cancer is a group of neoplasms originating from the squamous cells that line the mucosal surfaces of the oral cavity, paranasal sinuses, pharynx or larynx. These cancer patients undergoing radiation therapy receive both anatomical CT and metabolic imaging (PET/CT). The prognosis of any individual patient is still often poorly determined. We recognize that from the tremendous amount of data generated by PET and CT imaging when a patient receives cancer care, much of which is currently not systematically used to its full potential.
For our proposed project, we are further developing a novel deep learning framework that can take pre/during-treatment PET/CT images, H&N cancer patients’ clinical data and treatment planning radiation dose distributions, as inputs to augment the prediction of H&N cancer patient outcomes. We hypothesized that our architecture involving a novel training methodology where both PET and CT image branches are trained independently prior to being merged with a clinical data branch will obtain results superior than the current state-of-the-art models with only CT data incorporated as inputs.
We have a working deep learning model to make outcomes predictions for head and neck cancer patients. This model has been based on data from 4 hospitals in the Montreal area. We are now testing the model using data from a 5th hospital. With the help of a research assistant, novel model frameworks were explored. With the help of a clinical medical physicist, we developed a workflow of curating sufficient data for eligible patients that include the necessary PET/CT, anatomical CT data, dose distribution information as well as their clinical data; image registrations were subsequently performed. The Varian Medical System also assisted us with importing patient data into our Eclipse Testbox. Furthermore, in the coming weeks, we will further develop the DL model while testing the data curated.
Furthermore, we will also evaluate the impact missing data has on our model to determine its robustness. Therefore, we hope our model can accurately discern between high-risk patients and low-risk patients which will eventually lead to personalized treatments in the future. This project serves an incredible opportunity to combine my passion in machine learning and cancer research.
3. Briefly note new skills, techniques and knowledge gained from the internship?
- Using the Eclipse Treatment Planning System (Varian Medical System) to curate selected patient data and image registration
- Introduced to various deep learning frameworks
- How to use Git and Github
- Learnt about Precision Medicine principles
- Introduced to Nextflow for cleaning and reproducible computation projects
- Introduced to and practiced with the R programming language
- Creating effective interactive Python Visualization with Jupyter Lab and web browser
4. Did you feel the internship was a valuable experience in relation to your studies or career goals? Please elaborate
This internship was an very valuable experience for my future graduate studies and career objectives. I felt incredibly suppored by the MiCM community led by Dr. Amadou Barry, who initiates our weekly meetings with a fun and understanding environment while creating curiosity-driven conversations. All members share with each other our research updates, challenges and most importantly, seeing interdisciplanry research across various topics unfold. It shows the importance of constant knowledge-sharing and collaborations in the scientific community and help guide my career.
5. How did the pandemic affect the internship (i.e work, collaboration)?
The COVID-19 Pandanmic has mostly slowed down our data curation process. Since it would have been done at the McGill University Health Centre using its computer servers for collecting Head & Neck patient data under REB protocol. The pandanmic demanded us to work on virtual machines to access the same data, thus it took us a lot longer to get things in order. However, with the patient guidance from my PI supervisor, clinical physicist, and MUHC admin, it eventually got done.
6. Could you suggest any additional computational/statistical workshops that would be beneficial for next year’s interns?
- Further R packages workshop
- Intro to Keras / Tensorflow in Python
- Intro to C++
7. Would you recommend this internship to other students?
I would certainly recommend this internship to other students and you should apply regardless of your research experience levels. Be open-minded to knowledge from across disciplines and don’t be afraid to ask questions about others’ projects.
8. Anything else you would like to contribute about your internship experience?
I’d like to thank my P.I. Dr. Jan Seuntjens and clinical physicist Monica Serban for their constant help for me; Drs. Amadou Barry and Anotonio Ciampi for our weekly MiCM meetings discussions, as well as MiCM for organizing impactful workshops.
Name: Yumika Shiba
Department: Computer Science and Biology
1. Can you tell me a bit about yourself?
I am a rising junior at McGill pursuing Joint Honours Computer Science and Biology. I am deeply touched whenenever I feel that I could hear the voice of data. To me, data is not merely numbers or facts, but representation of individual lives with stories and history. On a totally unrelated note, I have two budggies and two cokatiels, one of whom is actually sitting in front of me as I write this, looking curious.
2. Can you tell us about the type of work you were involved in this summer?
- Examining the effect of sex and gender in testing positive for COVID-19 using UK Biobank.
- Literature review: on previous studies that were conducted on COVID-19 using UK Biobank, a retrospective cohort study with over 500,000 participants.
- Exploration of data dictionary: to understand the databse better.
- Data-cleaning: in preparation to performing analysis.
- Creation of descriptive tables: on different variables (e.g. age, BMI, education level, comorbidities e.g. high bloor pressure, stroke, asthma, etc.).
- Exploration and selection of machine learning methods: for creating predictive model.
- Manuscript writing: Introduction and Methods.
- Implementation of federated analysis.
The international consortium that my PI was leading (GOING-FWD) wanted to do a comparative study between Canada and Austria; however, due to legal (privacy) issues, the actual data could not be transported outside the countries. There was a need to implement an analysis method called federated analysis, and I worked on to answer the question, “How can we do federated analysis and what do we need”. By the end, I have created a demo showing how to do it, presented it to GOING-FWD, and created a report on the rest of things that needs to be addressed to.
3. Briefly note new skills, techniques and knowledge gained from the internship?
- More experiences with Pandas.
- Knowledge of how to incorporate sex and gender in research.
- Knowledge about federated analysis
- How to do it (using DataSHIELD)
- Improved ability on how to work in a team.
4. Did you feel the internship was a valuable experience in relation to your studies or career goals? Please elaborate
I did. As someone studying Computer Science and Biology, the internship was very relevant and gave me hands-on experiences. It was a great opportunity to apply what I have learned both classrooms and outside.
The internship also introduced me to different research areas. Last summer, I was working in a bioinformatics lab and the focus was on genes. The lab I worked in this year had more focus on the clinial side as well as interests in the effect of sex and gender, latter of which were very new to me.
5. How did the pandemic affect the internship (i.e work, collaboration)?
Because of Zoom, emails, and phones, I did not feel that collaboration became significantly more difficult; however, I admit that if the internship was on-site, communication (e.g. asking and answering questions) could have been a lot easier i.e would have saved a lot of time for those who answered questions for me.
I have not been able to meet any of my lab members, my friends (fellow scholars), Amadou (the program manager and mentor), and Antonio (Dr. Ciampi), which is the sad part; nevertheless, I have felt the sense of bonding with and among lab members and other scholars thanks to the countless meetings.
6. Could you suggest any additional computational/statistical workshops that would be beneficial for next year’s interns?
For those in lower-years, a workshop going over the essential contents of MATH324 (Statistics) at McGill may be of great help. Perhaps also introductory and or advanced workshops on some machine learning topics.
7. Would you recommend this internship to other students?
I would. The internship would be a great opportunity to expand knowledge, improve technical skills, and to gain hands-on experience. The internship added a new dimension to my thinking. I also met so many cool and inspiring people!
8. Anything else you would like to contribute about your internship experience?
This might have been just me, but after being selected as a summer scholar, I had to go through three rounds of interview to be part of my lab. It may be something to be aware of for future scholars.
I am very thankful for the opportunity that I was given, and thank you for everyone who gave birth to the summer program as well as everyone involved in it.
