Both of the grants are nearing their end, which is why we are advertising only a short term opportunity (1 year of funding). This is a great opportunity though because there is great data available and there is a possibility of writing / contributing to two papers.
Preferred qualifications:
I am looking for someone with experience and interest in several of the following domains: evolution, virology, bioinformatics (next-gen sequencing data) and statistics. If you are interested…
Hailey during the 2019 Genentech’s Campus Engagement Day, which was her first introduction to Genentech.
My biggest advice when pursuing an internship, career, degree, etc. is to be your authentic self, know you are good enough, and do what is best for your growth.
How did you decide to get a degree in biology? What interested you in making this choice?
My interest in science stems from wanting to understand how the human body works in order to have a better knowledge when understanding medical conditions my loved ones suffer from. When I was a child, my father had a stroke — my family’s frustrations from not fully understanding how my father was affected by this incident and the doctors not having all of the answers is what initially piqued my interest in studying science, I wanted to be able to understand and answer those questions.
Why are you interested in a career in Biotech? What inspires you about this work?
Initially, I thought I wanted to pursue a career in medicine or healthcare; this seemed like the most obvious choice to use my biology degree to help others, more than just my loved ones. However, throughout my college experiences, I realized that I love benchwork, research, and working to answer biological questions. I am interested in a career in Biotech because I find this industry a perfect mesh between day-to-day scientific research and that research being directly related to drug development and impacting the advancement of medicine to help people.
The more I talk to others in this industry, the more I realize that my career journey does not have to be a linear path.
What do you want to do in your future career? What are you aiming for?
I don’t know. I used to have a set plan. Originally, my goal was to pursue a PhD in neuroscience, in honor of my dad, and then a permanent career in biotech. The further I get in my career, the more possibilities I discover. The more I talk to others in this industry, the more I realize that my career journey does not have to be a linear path.
In your opinion, why should a student at SF State consider a career in Biotech?
Working in Biotech is a great opportunity to discover the potential for scientific research, how your work can impact the world and others, and what kind of research suits you based on your passions or interests, even if this results in a career shift to healthcare or academia. With the enthusiastic and collaborative community in this industry, there is the opportunity to be exposed to a wide variety of research projects and disease areas, whether you are participating in the project, attending seminars, or networking with other scientists.
Can you tell us something interesting about yourself?
I debated between pursuing a degree in biology or in art. Those are my two greatest interests. Although I did not pursue an artistic degree or career, I still paint, take classes, go to museums, and indulge in it as much as I do with biology in my career now. Having a passion for science and research is important when pursuing a career in this field, but it definitely does not have to be your only interest!
Regarding the SFSU PINC program, are there coding classes you took for your current position?
The coding classes I took in college for the PINC program do not directly relate to the current work I am doing now. However, because I have that coding background, there are more opportunities for me to integrate myself and my projects in the informatics space.
How did you find the job at Genentech? Where did you find the announcement, what materials did you have to send, who helped you, how did the interview go.
In a SFSU science newsletter, I found an announcement for Genentech’s Campus Engagement Day event in fall 2019. After attending this networking event, I searched for summer internships at Genentech through gene.com/careers. During this search for an internship, I stumbled across an application for DSRP, my current position.
My biggest advice when seeking these types of opportunities is to always keep your eyes open, even if you are […] not exactly sure what you are looking for. My current position is what I was always searching for, without even knowing that a program like DSRP existed. When applying for this position, I was not entirely confident in what I was doing or how to apply, but I was confident in myself. My biggest advice when pursuing an internship, career, degree, etc. is to be your authentic self, know you are good enough, and do what is best for your growth. Keeping these key things in mind, I feel, is what made me successful during the interview process.
Pleuni: Faye Orcales is a recent SFSU alum and I am lucky enough to be working with her this year thanks to an NSF supplement for post-bacc students. She is also a PINC alum and PINC mentor (for my class CSC 508: Machine Learning and Data Science for Personalized Medicine). This past summer, Faye was an intern at Genentech. We asked her to write about her experience!
My name is Faye and I’m a recent graduate from San Francisco State University. I obtained a bachelor’s degree in Cell and Molecular Biology with a minor in Computing Applications from the PINC Program.
I’m currently working under Daniel Le as a bioinformatics intern for Genentech’s Next Generation Sequencing Department.
In my junior year I got introduced to coding when I had to take a mandatory elective course. At first, I didn’t think I would like the subject. In contrast I found out that I had a genuine interest in coding, and mentioned it to a counselor. They told me about the PINC Program at SFSU, which is a coding program offered primarily to students majoring in biology, chemistry, or biochemistry. My interests aligned with the program, so I spent my last two years of university taking coding classes along with my regular biology courses.
I first obtained research and informatics experience under PINC’s Summer Program in 2020, where I worked with Dr. Rori Rohlfs and a group of other students. I went on to do more research with Dr. Pleuni Pennings in the CoDE Lab where I utilized machine learning to study impacts on fitness cost in Hepatitis C.
“I’ve known about Genentech ever since I was in middle school”
In senior year my PINC Program Director Dr. Nina Hosmane informed me about Genentech’s Summer Internship Program. I’ve known about Genentech ever since I was in middle school, so I’ve seen the scientific innovations that Genentech has built throughout the years. I decided to challenge myself and apply to the internship because I wanted to strengthen my coding skills and see what industry standard research looks like.
I was able to obtain the internship with much support from my connections in the PINC Program. They took the time to help me strengthen my resume and provide me interview resources. I highly recommend to anyone interested in applying to Genentech, or somewhere similar, to have their trusted peers or professors give them lots of feedback on their application materials.
My work ethic and inspiration to pursue higher learning came from my parents. My family came to the United States as immigrants when I was very young. I’ve seen my mom stay up long nights studying and my dad juggle three jobs all while raising two kids. My parents’ hard work allowed our family to survive in a new country, and taught me the importance of education and perseverance.
“My scientific inspirations came from my middle school science teachers.”
My scientific inspirations came from my middle school science teachers. They were all women of color, so their representation had a big impact on me. Every lab I did in their classes were memorable. Their passion for science influenced my current curiosity for life and the universe.
In the future I would like to become a physician-scientist. At first, I only wanted to become a doctor. After my experience in the PINC Program and Genentech, I realized that I still wanted to continue doing research as a career. To have the best of both worlds, I hope to one day get accepted into an MD-PhD program to fulfill my biggest career goal.
Outside of research and science, I’m a big fan of food. Whenever I can, I love trying out new restaurants with friends. Luckily, I live in the bay area which is rich in cultural diversity.
“PSP led me through my first research project and allowed me to present on the summer project. PSP has given me confidence in my ability to do scientific research and analyze the results of the research. Most importantly, I had the opportunity to improve my public speaking through our research symposium at the end of the program.”
What is the PINC Summer Program?
The PINC Summer Program is a part-time program where students work in teams with a peer-mentor. They learn coding skills as well as work on a research project with their mentor and a faculty advisor. At the end of the 9-week program, the teams give a talk about their work at a research symposium.
We have run a similar program since 2017 and written about it here. Most importantly: (1) The program is part-time on purpose to allow students to join who have other obligations, like jobs and families; (2) the students work in teams and all work takes place during team meetings – this way there is always a friendly person nearby (on zoom these days) when you are stuck; and (3) the coding skills they learn are applied to biology or chemistry research immediately.
Who participated in the 2021 PINC summer program?
Many people are involved in the PINC Summer Program.
First of all, there are about 30 student participants, more about them in the next paragraph. The 30 students were organized in 6 teams. Each team had a peer mentor and a faculty advisor. The peer mentors were Angela Lane (grad student and CC lecturer), Carmen Gonzalez, Elissa Vazquez, Liz Mathiasen, Jason Hernandez and Patra Holmes (all PINC students and GenPINC scholars). The faculty advisors this year were Drs Gretchen Lebuhn, Jaime Chavez, Rori Rohlfs, Jessica Weng, Nicole Adelstein and Derrick Groom.
In addition to those groups, the staff consisted of Torey Jacques (mentor trainer), Dr Sophie Archambeault (weekly workshop organizer), Rochelle-Jan Reyes (all-around organizer). Pleuni Pennings, Nicole Adelstein and Rori Rohlfs were responsible for the entire program.
More about the students
The PINC Summer Program reaches a diverse group of students, in terms of ethnicity, gender and majors (see image).
In terms of prior experience, 6 students had prior research experience, while 24 didn’t. 5 students had previously taken a coding class at SFSU while 25 didn’t. The 5 students who had coding experience were all part of the PINC program. We placed them all in the same team. Out of the 25 students with no coding experience, 9 signed up for CSC 306 (intro to python) in the fall of 2021.
Major Demographics of PSP 2021. 60% of students are majoring in Biology, 30% in Biochemistry, and 10% in Chemistry.
Race & Ethnicity Demographics of PSP 2021. The largest communities within this cohort were of Hispanic or Latinx descent (33.3%), Asian descent (30%), or identified with 2 or more ethnicities (16.7%).
Sex Demographics of PSP 2021. 70% of the cohort identified as female, 26.7% as male, and 3.3% as gender non-conforming.
How did it go?
Overall, the program worked well this summer, with a few hiccups. In one team, several students had to leave the program midway for personal reasons. We recruited one new student from another program (SCIP) to join the team that had gotten a little small.
At the end of the summer all teams did a presentation in our end-of-summer research symposium. It was really fun to hear the students talk about their research! Almost all students spoke for at least a few minutes.
Most students who did the post-program survey are expecting to use coding in their career.
We got answers such as “I want to pursue a career in medicinal research, and I envision using my coding skills to analyze and communicate my research with other scientists who share my interest in study.” However, a few students didn’t see it this way: “No I don’t because programming is a little too hard for me. I don’t see myself doing it seriously but for fun and for educational purposes, yes.”
Here are a few other interesting quotes from the post-program survey:
“PSP has really showed me how fun research and science can be if you’re in a group with people you get along with.”
“I think it was helpful because we were a small group with our mentor and advisor which made it more “relaxing”. We could easily ask questions, and reach to each other. It was a nice dynamic overall.”
“Relentlessly positive, but slightly chaotic”
What’s next?
During the program, we held a lab matchmaking event in order to help students meet faculty and see if their interests align with faculty labs from SFSU and UC Berkeley. At the end of the summer, several students joined a lab. Secondly, several signed up for a coding class. Some felt like they were too busy during the fall to do either coding or research. For a few students, we don’t know what their plans are.
Funding
The PINC Summer Program 2021 was paid for by a grant from the Genentech Foundation (PI Dr Frank Bayliss). The budget was $60,000 (roughly $9,000 for support staff, $6000 for the directors, $17000 for the mentors and $22,000 for the faculty advisors).
I was in my late thirties when I learned to drive a car. I grew up in The Netherlands, in an area with excellent bike and train infrastructure and I never felt the need to learn how to drive a car. Also, I didn’t want to spend money or time on learning to drive a car. But when I finally learned to drive a car, it turned out to be very useful! It gave me independence, and it gave me options I didn’t have before.
Recently, I added to my skillset. Two weeks ago, for the first time in my life, I drove a car over significant distances in The Netherlands. I thought driving in The Netherlands was scary – but when I finally did it, it wasn’t as scary as I thought!
Now, am I the best driver in The Netherlands? Surely not! But it’s real nice to be able to borrow my dad’s car to visit my cousin who runs a lego workshop to rent some legos. It gives me independence. And it makes my son happy too (see picture below).
If you are learning to code, you should consider your coding journey as a journey towards independence. After one semester or one summer of coding, you are not a star coder (sorry to break it to you 😉 ). But you have started! You have learned new things. You have learned new jargon and new tools. And maybe you can now analyze a small dataset by yourself. Or you know enough about coding to be able to ask for help in a smarter way. And next semester or next summer, or when you have time, you will learn more. And one day you’ll be able to drive a car in The Netherlands!
4 ways learning to drive a car is like learning to code
It gives you independence. Before I always had to ask my mom or my husband to drive if I needed to use a car, now I can do it myself. For coding tasks, you may depend on a lab mate or software like SPSS or SAS, but it’s just nicer if you can do it yourself.
It is not about being the best driver or the best coder. I can drive, but I will never be the best driver in any group of people. But who cares? I get from A to B safely and that’s what matters. For coding, it’s the same thing. If you want to use coding in your studies or work, you don’t need to be the best coder. You just need to get from A to B (or from raw data to a nice plot).
Practice is key. When I first got my license, I didn’t have access to a car and I didn’t drive for a few years. Clearly, that was not very good for my driving skills or confidence. Later, when I did have a car available, I would regularly take it to drive to a friend who lived just 5 miles away to have a coffee. These short trips helped me feel comfortable in the car. If you’ve learned some coding skills, try to find a way to keep using it, even if it is just for short 5-mile drives.
It opens up jobs and opportunities. For many jobs, you need to be able to drive a car. Not just jobs such as taxi driver, but also jobs that are utterly unrelated to driving. For me, I got the job at SFSU when I lived in Menlo Park. Public transport from Menlo Park to SFSU is so bad, that I really couldn’t do the job if I wasn’t able to drive to the SFSU campus. With coding it can be the same thing. I am a biologist and I am interested in evolution of viruses and bacteria – yet I couldn’t do that research without coding skills.
This past June and July, 130 participants improved their coding skills in the 2021 SCIP program at SF State University! I am so excited about this program and very grateful for the amazing team of people who ran SCIP 2021 (Rochelle Reyes, Ryan Fergusson, Olivia Pham).
I would like to share with you all how it went. The 130 participants were mostly biology and biochemistry students, but we also had some alums and staff who joined. Just over half of the participants were undergrads, and most had little or no coding experience.
Our participants were ethnically diverse and 63% identified as female, non-binary or gender non-conforming.
How was SCIP 2021 organized?
The participants were organized in teams of 5-7 people. This summer, we had 10 R teams, 11 Python teams and 2 ImageJ teams. For each team, we pick one member to be the team leader. Team leaders are chosen based on their leadership experience, not their coding experience.
MaryGracy Antony, an incoming SFSU Biology Master’s student was one of the team leaders – she had no coding experience at the beginning of the summer. Here is an image from one her zoom meetings. I asked MaryGracy how it went for her and she said: “I let my team know on the first day that I, like them, have no experience with Python and we will be helping each other out throughout our time in SCIP. It definitely worked. […] As the weeks went by, people who were further in the course were helping others and even me. It was a very fulfilling experience 🙂“
Each team met 4 times a week for 2 hours during 6 weeks (48 hours total). All meetings had a similar structure with time to talk and time to work quietly. The “I” in SCIP stands for immersion, which means that the learning is done during the zoom meetings. We discourage working on the materials outside of the zoom meetings, to avoid getting stuck on a coding problem with no help nearby. If the teams got stuck, they could ask questions on the Slack forum, which was monitored by the SCIP admin team.
Once a week we held a webinar for one hour, with speakers who use coding in biology, chemistry or biochemistry. This year, we hosted a teacher, a PhD student, someone who worked in the biotech industry and many others. Many of our guests were SFSU and PINC alums.
Outcomes
One of the main goals for SCIP is to allow participants to learn coding skills in a non-threatening, ungraded environment. We think we are succeeding in this for most participants, but to make sure our environment is as non-threatening as possible, we don’t test their coding knowledge and we don’t keep track of attendance. Still, there are several indicators that show that participants are learning and finding a community in SCIP. First, 97% participants would recommend SCIP to others. Second, self-reported coding confidence goes up a lot. Third, almost 90% of participants expect that coding will be part of their future career – that is huge, given that most of our participants had no prior coding experience.
New materials received very well
Participants in SCIP all learn from freely available online coding classes that we pick out for them. While these coding classes from Udacity and EdX work quite well, there are also some issues with these classes. They are not made for science students and they are mostly taught by white men. The SCIP team therefore created new materials this year.
These new materials included a series of videos about R made by Ryan Fergusson and coding projects designed by all of the SCIP admin team members (see here https://vimeo.com/showcase/8775548). More than 90% of the participants scored the new videos as a 4 or 5 (on a scale from 1 to 5) in terms of how helpful they were.
The story behind SCIP
Last summer, in 2020, many of our bio/chem students were stuck at home, without a job or summer research experience. In the meantime, Dr Megumi Fuse, was looking for something that our research students could do during the summer, while they were funded to do research but the labs were closed. We designed a community-focused online coding program to make the most of the summer of 2020. It worked great! 160 people joined in 2020, and most of them loved it and learned new coding skills! To learn more about SCIP have a look at our website.
The people behind SCIP 2021
The most important people behind SCIP 2021 were Rochelle-Jan Reyes, Olivia Pham and Ryan Fergusson. Rochelle did most of the admin work, Olivia ran the webinar series and Ryan created videos for learning the R programming language. All three of them answered many technical questions on the Slack channel.
Funding
Funding for SCIP 2021 came from the NSF-funded Center for Cellular Construction (NSF grant DBI-1548297) and the NIH MBRS-RISE grant (#R25-GM059298). Some of the SCIP participants, especially those who had learned ImageJ spent the second half of their summer in the CCC research workshop. Many SCIP participants are now in the PINC or GOLD programs (link).
Alennie (they/them) graduated from SFSU in 2021 and will be working as a Bioinformatics Programmer in the lab of Dr. Marina Sirota.
Pleuni: Hi Alennie, congratulations on graduating this semester!
Alennie: Thank you! I really enjoyed my time at SFSU and I’m excited to move onto the next chapter.
Pleuni: You told me that you are starting a job at UCSF soon. Would you mind telling me what you’ll be doing there and how you found that job?
Alennie: I’ll be working as a Bioinformatics Programmer in the lab of Dr. Marina Sirota. The work is very in line with the interdisciplinary concepts I learned through the PINC program–– coding meets life science and health data. Prior to getting the position, I heard about an event, “NIH Diversity Supplement Virtual Matchmaking,” from the PINC and SEO mailing list. At the event, I met with many different UCSF PIs and learned about their research. I kept in contact with some of the PIs I met whose research I thought was very interesting. From there I scheduled different meetings and interviews with each PI to see if we’d be a good match. I ended up moving forward with the Sirota lab because I wanted to be involved in their research and felt that I could learn a lot from the experience.
Pleuni: When did you start to learn coding?
Alennie: Honestly, I feel like my first stint with coding began with Tumblr. In middle and high school I picked up some HTML to personalize my Tumblr page. It was exciting to input strange strings of numbers and letters and churn out wacky graphics. When I stopped using Tumblr I didn’t seriously pick up coding until summer 2019 for the BDSP, where I learned that there were so many different ways programming could be used.
Pleuni: Did you always want to learn coding?
Alennie: When I was younger, I’d watch the crime show “Criminal Minds’” with my mother. One of my favorite characters was Penelope Garcia, the show’s FBI Technical Analyst. She fills the tech-savvy role of the group and I always enjoyed seeing how she’d help solve the case by unlocking “digital secrets” or finding classified information. Based on portrayals like that, I always considered coding as an exclusive skill limited to cyber security and creating complex software. So I was always interested in coding, but the idea of learning how seemed too daunting.
Pleuni: You did the entire PINC program – which part did you like most? Which part was frustrating?
Alennie: I enjoyed the creative freedom of the PINC program. Many of the classes I took had final projects that encouraged us to come up with our own ideas. It was satisfying and challenging to take all that I’ve learned so far and use that knowledge to come up with my own projects. One of my favorite projects was for CSC 307: Machine Learning for Life Science Data Scientists. The goal of my group’s project was to address the lack of diversity in dermatology datasets by applying a machine-learning model that could identify various skin disorders; our dataset consisted of skin image samples from People of Color. The assignment was especially rewarding because it allowed me to combine my passion for health equity, social justice, and programming into a single project.
The most frustrating part of the program was primarily due to the pandemic. It was difficult to communicate with my professors and classmates through a remote format. The experience sometimes felt isolating because I had been so used to seeing my mentors in-person or meeting up with classmates to work on an assignment/project. Thankfully, I had met many of the same classmates in person before switching to virtual learning so I felt like I had some familiar faces to interact with.
Pleuni: Sometimes it looks like coding is something for only some kinds of people. There are a lot of stereotypes associated with coding. How do you feel about that?
Alennie: This is a very good question, as there are many layers to the coder/programmer stereotype. If you were to ask people to draw a picture of a coder, the most common image you’d likely see is a lonely man furiously typing in a darkened room, hunched over in his chair and focused on screens covered with indecipherable numbers and symbols. Simply put, we often imagine a typical coder as a cisgender white man who typically exhibits loner or awkward behaviors. It’s a very narrow and negative stereotype which ultimately promotes negative connotations regarding neurodivergent individuals and excludes Women and People of Color from the narrative.
The stereotype does little to encourage or welcome most people. But in reality, the coding community at large desperately needs a diverse range of people who can contribute their unique perspectives. Stereotypes can be discouraging and unwelcoming, so it’s important for institutions to emphasize inclusivity to show how students can be fantastic coders and still be true to their unique identities.
…it’s important for institutions to emphasize inclusivity to show how students can be fantastic coders and still be true to their unique identities.
Pleuni: I know you are applying to medical school. Do you think it is useful for a doctor to know about computer science?
For example, by having some knowledge in computer science a doctor could aid in the design of an app that patients can use to let them know if they’re experiencing side effects to their medication, create a website that shows local doctors who are LGBTQ+ friendly, or even better navigate electronic health records. The possibilities are endless!
Alennie: I believe that computer science can be very useful to a physician because it can improve how they can take care of people. Since they are face-to-face with patients everyday, healthcare professionals are in a position where they can recognize and understand what unique problems need to be addressed in their communities.
Pleuni: Do you have any tips for students who are just starting out?
Alennie: Embrace your creativity! We often think of coding as a sterile and strict subject, but as you create new programs, websites, apps, etc you realize how much creative freedom you actually have. Learning how to code can be very daunting so when you personalize programs to fit your style or reflect things that you like, it makes the journey seem less scary and more fun. When I started coding, I had the most bare-bones of tools at my disposal, but I could still find ways to inject things to make my code feel like it belonged to me. The very first game I programmed, a basic recreation of Pong, I signed with my favorite color, pastel pink.
Alennie recreated the classic game of Pong with a little extra flair for one of their coding projects.
Berenice Chavez Rojas graduated from SFSU in 2021 with a major in biology and a minor in computing applications. She is moving to Boston to work in a lab at Harvard’s Medical School.
Pleuni: Hi Berenice, congratulations on graduating this semester! I know that you are starting a job at Harvard soon. Would you mind telling me what you’ll be doing there and how you found that job? Did your coding skills help you land this job?
Berenice: I’ll be working as a research assistant in a wet lab. The model organism is C. elegans and the project will focus on apical-basal polarity in neurons and glia. I found this job on Twitter! Having a science Twitter is a great way to find research and job opportunities as well as learn new science from other scientists. While I won’t be using my computational skills as part of this job, the research experience I have been able to obtain with my coding skills did help me.
“coding always seemed intimidating and unattainable”
Pleuni: When did you start to learn coding?
Berenice: I started coding after I was accepted to the Big Data Summer Program two years ago [Note from Pleuni: this is now the PINC Summer Program]. This was also my first exposure to research and I’m grateful I was given this opportunity. This opportunity really changed my experience here at SFSU and it gave me many new opportunities that I don’t think I would have gotten had I not started coding. Following the Big Data Summer Program I started working in Dr. Rori Rohlfs’ computational biology lab. I also received a fellowship [https://seo.sfsu.edu/] which allowed me to stop working my retail job, this gave me more time to focus on school and research.
Pleuni: Did you always want to learn coding?
Berenice: Not at all, coding always seemed intimidating and unattainable. After my first exposure to coding, I still thought it was intimidating and I was slightly hesitant in taking CS classes. Once I started taking classes and the more I practiced everything began to make more sense. I also realized that Google and StackOverflow were great resources that I could access at any time. To this day, I still struggle and sometimes feel like I can’t make any progress on my code, but I remind myself that I’ve struggled many times before and I was able to persevere all those times. It just takes time!
The forensic genetics team at the Big Data Science Program in the summer of 2019. Berenice Chavez Rojas is in the middle.
“At the end of this project, I was able to see how much I had learned and accomplished”
Pleuni: You did the entire PINC program – which part did you like most? Which part was frustrating?
Berenice: My favorite part of the PINC program was working on a capstone project of our choice. At the end of this project, I was able to see how much I had learned and accomplished as part of the PINC program and it was a great, rewarding feeling. As with any project, our team goals changed as we made progress and as we faced new obstacles in our code. Despite taking many redirections, we made great progress and learned so much about coding, working in teams, time management, and writing scientific proposals/reports.
Pleuni: Sometimes it looks like coding is something for only some kinds of people. There are a lot of stereotypes associated with coding. How do you feel about that?
Berenice: I think computer science is seen as a male-dominated field and this makes it a lot more intimidating and may even push people away. The PINC program does a great job of creating a welcoming and accepting environment for everyone. As a minority myself, this type of environment made me feel safe and I felt like I actually belonged to a community. Programs like PINC that strive to get more students into coding are a great way to encourage students that might be nervous about taking CS classes due to stereotypes associated with such classes.
“talking to classmates […] was really helpful”
Pleuni: Do you have any tips for students who are just starting out?
Berenice: You can do it! It is challenging to learn how to code and at times you will want to give up but you can absolutely do it. The PINC instructors and your classmates are always willing to help you. I found that talking to classmates and making a Slack channel where we could all communicate was really helpful. We would post any questions we had and anyone could help out and often times more than a few people had the same question. Since this past year was online, we would meet over Zoom if we were having trouble with homework and go over code together. Online resources such as W3Schools, YouTube tutorials and GeeksforGeeks helped me so much. Lastly, don’t bring yourself down when you’re struggling. You’ve come so far; you can and will accomplish many great things!
Pleuni: What’s your dog’s name and will it come with you to Boston?
Berenice: His name is Bowie and he’ll be staying with my family here in California.
Pleuni: Final question. Python or R?
Berenice: I like Python, mostly because it’s the one I use the most.
Pleuni: Thank you, Berenice! Please stay in touch!
This semester (spring 2021) I taught a new class together with my colleagues Dax Ovid and Rori Rohlfs: Exploratory Data Science for Scientists. This class is part of our new GOLD program through which Master’s students can earn a certificate in Data Science for Biology and Chemistry (link). We were happily surprised when 38 students signed up for the class!
In the last few weeks of the class I taught some machine learning and as their final project, students had to find their own images to do image classification with a convolutional neural network. Then they had to communicate their science to a wide audience through blog, video or twitter. Here are the results! I am very proud 🙂
If you are interested in the materials we used, let me know.
Videos
Two teams made videos about their final project:
Anjum Gujral, Jan Mikhale Cajulao, Carlos Guzman and Cillian Variot classified flowers and trees.
Ryan Acbay, Xavier Plasencia, Ramon Rodriguez and Amanda Verzosa looked at Asian and African elephants.
Twitter
Three teams decided to use Twitter to share their results.
Jacob Gorneau, Pooneh Kalhori, Ariana Nagainis, Natassja Punak and Rachel Quock looked at male and female moths.
Article by: Adrian Barrera-Velasquez, Rudy Cheong, Joel Martinez, Huy Do
Why Bagels and Donuts?
Our group was initially torn on what to use for our classification assignment but ended up deciding we wanted to do something fun outside of the usual science data/image sets given we’ve all been working all semester with these. The initial suggestion was McDonald’s vs Burger King’s chicken nuggets but that seemed like it wouldn’t work too well. Keeping with the food theme however, we decided on donuts vs bagels which is actually an interesting set to compare. Morphologically, these two items are very similar but in terms of food are very different. We as humans can tell the difference between donuts and bagels pretty easily so it was interesting to see if this was enough for our neural net.
Nature of the Image Sets
As we mentioned, donuts and bagels are very similar in terms of morphology but have a very clear distinction when it comes to food. As such, they are presented differently and we can see this even in our image set. We acquired our images by writing a Python script that would automatically download Google Image search results for donuts and bagels along with their link). From a cursory glance we can see that both items are usually displayed as multiples but one of the biggest differences is that the donuts are more colorful. In addition, often times the bagels are presented as sandwiches with things like cream cheese and smoked salmon. There is a variety within each set of images but we felt like this makes it more exciting to see how well the neural net performed.
What is VGG16?
Convolutional networks have made it easier than ever to conduct large scale image and video recognition analysis. In particular, the VGG16 convolutional neural network has demonstrated superior recognition capabilities compared to other convolutional neural networks because of its network architecture. Through using small 3 × 3 convolution filters in every layer the overall depth of the network is increased. This increase in depth is what ultimately leads VGG16 to achieve a very high level accuracy in classification and localization tasks.
Results
The VGG16 neural network returned accurate results in classifying the labels of the 10 tested bagel images and 10 tested donut images. The percentage of images classified correctly is 1.0, indicating perfect accuracy. The confusion matrix illustrates this performance where zero bagel true labels were misclassified as donuts (bottom left quadrant), and zero donut true labels were misclassified as bagels (top right quadrant).
The compositions of the tested bagel images present a wide variance along parameters such as individual bagel or an ensemble, varying profile angles, and with or without fillings or cream cheese spreads. Regardless of this variety, VGG16 predicted the true labels of the bagel images with perfect accuracy (bottom right quadrant). The following table shows the set of 10 tested bagel images:
The compositions of the tested donut images also present a wide variance along several parameters and VGG16 predicted the true labels of the donut images with perfect accuracy (top left quadrant). The following table shows the set of 10 tested donut images:
It is interesting to note that VGG16 accurately labeled bagel and donut image pairs that lack any major salient features useful in classifying one image as clearly bagel and the other as clearly donut. Such a pair is shown here:
The ability to make such a distinction with a minimum of distinguishing features is indicative of the power of the VGG16 neural network for images classification.
Discussion
The neural net performed so well in fact that we were left wondering if it found a very simple method of classifying these images. Personally as humans we thought that the color and toppings is an immediate dead giveaway so we think it might be a color space separation or some kind of edge density on the surface depicting textures. Unfortunately we cannot peer into the black box to see but nonetheless this was a very satisfying project and result.
Being A Better Scientist 