Data Sciences Institute

After months of dedicated data science learning and exploration, the Data Sciences Institute’s Summer Undergraduate Data Science (SUDS) Opportunities Program reached its highly anticipated finale—a full day of showcase where 37 exceptional undergraduate students unveiled their research projects. The atmosphere buzzed with a blend of excitement, eager anticipation, and unwavering enthusiasm as the culmination of their efforts took center stage. 

The SUDS program, known for its cross-disciplinary approach, provided an enriching summer experience for students to apply data science techniques in diverse fields, ranging from humanities and life sciences to engineering and public health. Supervised by Data Sciences Institute (DSI) researchers, the scholars had the chance to explore real-world applications of data science methods and tools. Their research included a diverse array of research topics, spanning from genetic covariance analysis in fruit flies, investigations into the linguistic dynamics of political discourse, to school dropout prediction using machine learning, showcasing the program’s broad spectrum of data science applications. 

In addition to their research, SUDS Scholars are provided with a full set of data sciences networking, academic, and professional development opportunities. They delved into the Data Science Bootcamp, gaining valuable skills in Unix Shell, R, Python, and Machine Learning. This technical foundation supported their research endeavors. In addition to technical training, the SUDS cohort program emphasizes career growth and professional development. The scholars participated in professional development sessions, ranging from scientific abstract writing to effective networking. Notably, they had the opportunity of learning from industry experts like Zia Babar, PhD, Director of Cloud Engineering at PwC Canada, who shared insights on Accelerating Machine Learning Development with GitHub Copilot. 

DSI’s mission is to nurture collaboration, research, and excellence in data science. Professor Laura Rosella, DSI Associate Director of Education and Training, described the showcase as the pinnacle of the scholars’ journey. “With their findings presented to their peers and supervisors, the room buzzed with excitement and celebration, encapsulating the remarkable culmination of their hard work. Without a doubt, the DSI SUDS program has launched these aspiring scholars into promising careers in Data Science.” 

“I enjoyed seeing the growth my student has achieved in just over 3 months. She is motivated to continuously work and expand her research skills and I am delighted to learn that she is planning to apply for graduate school,” says one supervisor, anonymously. 

“As is often the case when working with students outside of astrophysics, I appreciated the fresh perspective on our research area from a student arriving without preconceptions about the field. They were eager to learn and highly professional in their conduct, making the research project a breeze,” says another supervisor, anonymously. 

The SUDS showcase offered a platform for the scholars to share their final findings and also allowed students to recognize their peers’ exceptional posters and presentations. Awards were given out to Shuyu Van Kerkwijk, Anton Sugolov and Nicholas Taylor for their exceptional posters, while Sanchaai Mathiyarasan and Akil Huang were celebrated for their outstanding presentations. 

SUDS Scholars praise the research opportunities and SUDS cohort program 

Nicholas Taylor, who was voted for a top poster for his project, Quantum Machine Learning for Regression Tasks in Computational Chemistry, tackled the challenge of balancing accuracy and computational cost in chemical property predictions. He explains, “Such information holds significant implications for drug discovery and material science.” Reflecting on his experience, Nicholas says, “From not knowing the first thing about academic research to building quantum machine learning methods, I’ve learned a lot that I can take with me to future applications.” 

Lu Huang, who has been diligently dedicated to her research project, Bayesian Analysis of the Genetic Covariance Between Mating Success and Fitness in Drosophila serrata, aims to uncover the genetic interrelation between mating success and fitness in fruit flies. The goal is to ascertain whether mating success can serve as a viable indicator of overall fitness in the context of evolutionary studies. Existing research suggests that female Drosophila serrata possess the capacity to assess and choose mates based on olfactory and chemical cues. 

Reflecting on the program, Lu Huang says, “The weekly seminars provided a valuable opportunity for people from different backgrounds to engage in discussions about the daily tasks of data scientists, enhance networking skills, and strategize for resume improvement. It was a great learning opportunity.” 

One research project emerging from the SUDS program focused on School Dropout Prediction Using Machine Learning: An Interactive Presentation of the Evolving Landscape. Ziqi Shu collaborated with Professor Zahra Shakeri from the Dalla Lana School of Public Health at U of T, alongside Dr. Manuel Garcia-Herranz, a Data Principal Researcher at UNICEF, and Karen Avanesyan, a Statistics and Monitoring Education Specialist from the Division of Data, Analytics, Planning and Monitoring at UNICEF. Their collective effort aimed to combat school dropout rates through the utilization of data science. Notably, this venture marked one of the program’s initial steps toward external partnerships. Encouraged by this growing network, the SUDS program envisions an expansion of such projects and looks forward to fostering collaborations with diverse organizations. 

“Through this program, I understood how AI can address vital educational challenges by working on real-world cases. It gave me a sense of purpose, knowing my work could contribute to improving education access worldwide,” says Ziqi Shu. 

The Data Sciences Institute and the Department of Statistical Sciences jointly spearhead the Data Sciences Café, aimed at addressing research challenges through statistical advice. The weekly Data Sciences Café, which brings together researchers from diverse backgrounds, is an exceptional platform for non-statistical researchers seeking to harness statistical techniques to enhance their work. 

Since its start in 2022, the Data Sciences Café has garnered attention, attracting over 40 students and faculty members from the University of Toronto. Every week, participants convene for coffee, engaging in productive discussions and presentations, receiving valuable statistical advice tailored to their specific datasets. The Café’s structure allows attendees to tap into the expertise of a team comprising faculty members, graduate students, and senior statistical consultant students, all working collaboratively to assist in refining research methodologies and analyzing data effectively. 

The sessions begin with researchers presenting their projects and the challenges they face, articulating their needs for statistical guidance. Following these presentations, a 30-minute consultation session is conducted by Dr. Samantha-Jo, Assistant Professor, Teaching Stream, Department of Statistical Sciences and the driving force behind the Café’s success. 

Diego Proano Falconi, a second-year PhD student, Faculty of Dentistry, shares his experience of how the Café benefited his research. Working on a project centered on evaluating the financial hardship of dental out-of-pocket expenses in Canada, Diego needed to analyze complex datasets. He shares, “The Data Sciences Café was an invaluable experience that allowed me to articulate my thesis project and gain insights and methodological clarity from my fellow statistician colleagues.”  

Diego adds, “I’m very thankful for the friendly and academically enriching environment. Following my presentation, engaged students offered constructive feedback, shedding light on areas that could strengthen my analysis. This collaborative atmosphere not only improved my work but also opened doors to future collaborations. Whenever I encountered statistical challenges, I knew I could rely on this network for guidance.” 

“This café has emerged as a remarkable platform, supporting both faculty and students in leveraging data science to overcome research obstacles. The utilization of statistical techniques to enhance data analysis has been instrumental in achieving more robust results. The Café’s ability to unite researchers from various disciplines has further fostered collaboration, sparking innovative solutions through the lens of statistics,” says Dr. Samantha-Jo   

Amanda Ng, Statistics and Mathematics student, Department of Statistical Sciences, reflects on her involvement as a statistical student consultant, “Participating in the weekly meetings, where graduate students presented their research, enabled me to cultivate skills in understanding multidisciplinary datasets. I gained the expertise to recommend appropriate statistical methodologies and identify potential biases within current research study methods. The Data Sciences Café creates an informal environment for students to communicate with researchers from different academic backgrounds, facilitating connections that extend beyond the sessions. In fact, I secured my first research assistantship through a connection made at the Café.” 

This sentiment is echoed by Sofia Panasiuk, a PhD student who served as a participant during the Café sessions. Sofia explains, “My primary aim was to find a platform where I could share and receive feedback on my initial research ideas, especially from data science students who were more experienced with the technique than me. The Café surpassed my expectations, as the students offered insightful comments, highlighted potential limitations, and proposed solutions to the challenges I was encountering. It was here that Amanda and I connected, leading to a valuable collaboration.” 

The Café has also proven to be a catalyst for meaningful collaborations. Amanda Ng’s partnership with Sofia led to a notable accomplishment — presenting the project’s outcomes at the 11th Annual Canadian Statistics Student Conference and securing first place for an undergraduate presentation. 

“The insights gained from the Café led me towards methodological papers that would have taken me ages to find. Someone had the reference I needed immediately and that saved me a significant amount of time streamlining my research process,” says Sofia. 

The Data Sciences Institute– a multi-divisional, tri-campus, and multidisciplinary hub for data science activities at U of T — plays a pivotal role in driving these collaborative efforts. Through initiatives like the Data Sciences Café, DSI fosters research connections, innovation, and enhances the teaching and learning experience in data sciences.

As the academic year resumes, the Café is set to recommence its weekly gatherings on September 28. For those intrigued by the prospect of collaborative problem-solving and statistical exploration, sign-ups for consultation are now open here. Join the Data Sciences Café to be part of this dynamic community at the forefront of leveraging statistics to conquer research challenges, all while enjoying a cup of coffee. 

How does social influence operate within the realm of social media? DSI members Professors Peter Marbach (Computer Science, Faculty of Arts & Science), Vanina Leschziner (Sociology, Faculty of Arts & Science) and Daniel Silver (Sociology, University of Toronto Scarborough), are exploring the relationship between social media and social influence with the aim of validating a theoretical model proposed decades ago. 

Recognizing the profound impact of social media on society, the researchers are unraveling the complex nature of influence in the digital age. Their work seeks to provide a comprehensive understanding of how individuals acquire, accumulate, and exercise influence within the realm of social media.  

Data science is inherently interdisciplinary, and building capacity in data science has the potential to advance research frontiers across a broad spectrum of fields. With the support of the DSI Catalyst Grant, this collaborative research team of sociologists and a computer scientist embodies the DSI mission of supporting interdisciplinary research for emerging societal issues.  

Professor Leschziner explains, “Though influence is a core phenomenon in sociology and research on social media, it is poorly understood. We lack a thorough understanding of how individuals acquire and maintain (or lose) influence within a social system.” Professor Marbach adds, “Answering these questions is crucial in order to understand social media and possible regulation of social media.” 

The sociologist Talcott Parsons put forward the hypothesis that influence in a social system operates similarly to money in a market economy. While money coordinates action within the economic domain (e.g., production, trade, consumption), influence coordinates action within the social domain (e.g., attention, association, support, recognition). This hypothesis, which has sparked critical discussion among sociological theorists, has never been verified. 

Building on a mathematical model of influence that was developed in the group of Professor Marbach, the researchers use a combination of data science and computational methods to investigate, and potentially validate, Parson’s hypothesis.  Additionally, they aim to examine the distribution of influence within online communities and understand how influence changes over time. 

By harnessing the power of data science and computational methods, the researchers are investigating whether influence in social media can be understood as a general system of interchange, similar to money and power. “Our research utilizes a data science approach to study how influence is acquired, accumulated, and circulated within social media. We develop new methodologies to characterize the demand and supply of social media content, study the flow of attention and content within a community, and analyze the causes of changes in individual community members’ influence,” says Marbach. 

The research holds significant implications for the broader discourse on social influence, social media and inequality. “Our findings have the potential to inform the development of safeguards against the manipulation and abuse of influence on social media platforms. By gaining a deeper understanding of how influence operates within social systems, it becomes possible to promote responsible design of social media platforms and social media algorithms such as content recommendation,” says Marbach. 

Professor Marbach shares that this project is a new interdisciplinary collaboration between sociology and computer science. “We use data science in order to contribute to foundational theory in sociology.” He adds, “The DSI Catalyst Grant was the key to initiating this collaboration and providing the resources to carry out the research. Our goal is to use this project as a catalyst to build a long-term research collaboration between researchers in foundational sociological theory and computer science at U of T.” 

Their groundbreaking work serves as a timely reminder of the profound impact of social media on society, urging further exploration of the dynamics of influence in our increasingly interconnected digital world. 

In a significant collaboration aimed at advancing data science research and training, the Data Sciences Institute (DSI) at the University of Toronto is partnering with the United Nations Children’s Fund (UNICEF)’s Frontier Data and Tech team to leverage data for addressing complex challenges concerning children. This collaborative effort aligns with DSI’s strategic goal of fostering knowledge mobilization to promote the greater public good. This partnership represents a significant milestone in the journey towards leveraging the immense potential of data for effecting positive social change.  

DSI will work with UNICEF to strengthen UNICEF’s knowledge and capacities to use data science and methodologies to innovate learning, through joint research and training. This collaboration will involve joint research and training initiatives.  DSI collaborates with organizations committed to supporting world-class researchers, educators, and trainees who are at the forefront of advancing data sciences.  

“This partnership is a significant milestone for our Frontier Data Network, a global community of practice that leverages data science to positively impact the lives of children worldwide. Together, we are poised to unlock new insights, drive evidence-based decision-making, and pave the way to a brighter future for children everywhere,” says Yves Jaques, Chief of the Frontier Data and Technology Unit, UNICEF. 

As a first collaboration, Dr. Manuel Garcia-Herranz, Data Principal Researcher and Karen Avanesyan, Statistics and Monitoring education specialist at UNICEF’s Division of Data, Analytics, Planning and Monitoring (DAPM) at UNICEF, are collaborating with Professor Zahra Shakeri, Dalla Lana School of Public Health on a 2023 Summer Undergraduate Data Science (SUDS) Opportunities Program. The SUDS project, Understanding Predictive Models that can be Used to Prevent School Dropouts aims to revolutionize early warning systems in education through the application of cutting-edge AI technology. The SUDS opportunity allows a SUDS Scholar, Ziqi Shu, to gain practical experience by working on fictional yet reality-based case studies focusing on social problems affecting children. By identifying at-risk students and schools with high dropout rates, UNICEF aims to support countries with a strong Education Management Information System (EMIS) and household survey data.  

The SUDS Scholar project aims to use and generate new sources of real-time information to better inform decision makers in the development and humanitarian ecosystem. UNICEF’s Frontier Data Tech Network is a global initiative to explore and use frontier data technologies to address the most complex challenges for children in an ethical way.  

“Our aim is to develop a pilot tool that provides a comprehensive representation of the machine learning-based school dropout prediction landscape, bridging the knowledge gap in this area. This tool will utilize innovative data analysis and visualization techniques, benefiting researchers, practitioners, and other stakeholders in exploring the factors influencing school dropout among children. The long-term goal of this project is to harness the power of data science and create an adaptable, publicly accessible system that could support countries in addressing the critical issue of school dropouts. By leveraging AI technology and early warning systems, our aim is to identify and support at-risk students and schools, ultimately safeguarding every child’s right to education,” says Zahra Shakeri, Director of HIVE Lab, Institute of Health Policy, Management, and Evaluation, Dalla Lana School of Public Health. 

The UNICEF-DSI partnership paves the way for further research and training collaborations. There will be opportunities to connect with the DSI community during its DSI Research Day on September 27, 2023. Dr. Manuel Garcia-Herranz will deliver the keynote address and Yves Jaques will participate in a panel discussion on Developing an Effective Data Science Workforce. The discussion will focus on equipping graduates with essential Data Science skills required in today’s diverse fields and industries. The DSI Research Day showcases the work of the DSI community, fostering connections and engagement among academia, industry, and government stakeholders. 

“By combining our community’s expertise in data science with UNICEF’s commitment to driving results for children globally, we have the opportunity to make a profound impact. Through our joint efforts, we aim to strengthen UNICEF’s knowledge and capacities in utilizing data science methodologies, fostering innovation in learning and ultimately creating a brighter future for children worldwide,” says Lisa Strug, Director, Data Sciences Institute.  

Can reproducibility pave the way for groundbreaking advancements in the field of precision oncology and transform cancer treatment decisions? A resounding answer emerges from an exciting reproducibility project born out of the DSI Student-Led Reproducibility Challenge. This project, led by DSI members and Professor Benjamin Haibe-Kains (University Health Network and Medical Biophysics, Temerty Faculty of Medicine, University of Toronto) and Bo Wang (Department of Laboratory Medicine & Pathobiology, University of Toronto) and a team of U of T student researchers including Emily So and Grace Fengqing Yu, is currently making significant strides in advancing research within the field. 

Reproducibility and Reusability in Action 

In a recent Reusability report Evaluating reproducibility and reusability of a fine-tuned model to predict drug response in cancer patient samples published in Nature Machine Intelligence, the team successfully reproduced and applied a new Artificial Intelligence (AI) method, called Transfer of Cellular Response Prediction (TCRP), originally published by the Ideker group at the University of California San Diego, in Nature Cancer in 2021, to clinical trial data. 

The project originated from the DSI Thematic Program in Reproducibility, which aims to raise awareness of reproducibility, including a Student-Led Reproducibility Challenge in 2022. Given the increasing utilization of large-scale and intricate datasets and computational methods across various disciplines, the challenge of reproducibility has come to the forefront. Establishing reproducibility standards for research has emerged as a foundational aspect of data science. Therefore, it becomes essential to clearly articulate and widely integrate standards for open, reproducible research with big data. This integration is crucial not only within the University of Toronto but also on an international scale. 

Emily So, a master’s student and co-researcher, reflects on the importance of reproducibility and open science principles in the context of groundbreaking methods like AI and machine learning, “In agreement with FAIR (Findability, Accessibility, Interoperatibility and Reusability) principles well established in research, usually new articles will come with data and computer code available for the scientific community. To fully understand the impact of new innovations and uncover their applications to new scientific problems, it is imperative that available resources are fully reproducible and can produce expected results easily.“ 

The DSI Student-Led Reproducibility Challenge attracted researchers and trainees dedicated to exploring reproducibility. “DSI support was instrumental in organizing the Challenge where students showcased their efforts in reproducing key papers in the field of engineering, social and health sciences. Emily So and Grace Yu were part of one of these teams. Their results were so exciting that we decided to push the analysis further and publish it as a Reusability Reports in Nature Machine Intelligence,“ says Benjamin Haibe-Kains. 

“We were able to demonstrate the gaps that exist in open science for computational biology. This outreach made available by the DSI has allowed our group to project our experience to the scientific community as well as provide further rationale for our subsequent documentation about our project,“ says Emily So. 

The team’s work aims to address two key objectives: confirming the performance of the TCRP model in its published context and expanding its application to a larger compendium of preclinical pharmacogenomic and clinical trial data.  

Through extensive evaluation, the researchers found that the TCRP method surpassed established statistical and machine learning approaches in predicting drug response in novel clinical contexts. This remarkable finding highlights the superiority of TCRP in both preclinical and clinical settings. 

“Our results highlight the immense potential of the TCRP method and its ability to outperform existing approaches. This opens new avenues for optimizing clinical trial design and improving patient outcomes,“ says Haibe-Kains. 

In the field of precision oncology, ensuring the reliability and generalizability of new techniques in clinical settings is crucial. Reproducibility studies play a vital role in verifying claims made by predictive models, while reusability studies assess their applicability in diverse contexts. The publication of the Reusability Report in Nature Machine Intelligence signifies a significant step forward in promoting reproducibility and reusability in the field. 

“Our work emphasizes the importance of reproducibility and reusability, which are essential for advancing precision oncology. By documenting new data contexts and exploring the model’s reusability, we can drive further progress in tailored cancer treatments,“ says Haibe-Kains 

“Reproducing the results of this method was no easy task, but it provided a glimpse into the power and impact it could have. It was an exciting endeavor to explore the possibilities of this machine learning approach,“ shares Emily So, masters student and co-researcher. 

Collaboration, Transparency, and Future Applications 

The impact of this work extends beyond the research community. The study’s reliance on open science principles, where authors share their code and data, highlights the importance of collaboration and transparency. By making their materials publicly available, the researchers contribute to education, enabling the training of future health data scientists, bioinformaticians and computational biologists. 

Emily So emphasizes the potential future applications of their models, “This evaluation is timely because there is a potential future application of these models in assisting clinicians in the treatment decision process. Setting a reproducibility standard is crucial to properly evaluate machine learning approaches suitable for preclinical and clinical settings, ultimately optimizing the course of action for patients.“ 

With the successful reproduction of the TCRP model and its outperformance of existing approaches, the potential for optimized clinical trial design and improved patient outcomes becomes a tangible reality.