Syllabus
You must familiarize yourself with this document. It is thorough and covers our expectations and policies.
Professor: Abhijit Dasgupta
Email: abhijit.dasgupta@georgetown.edu
Class Time: Wednesdays, 3:30-6:00 PM
Class location: Car Barn 202
First class: August 28, 2024
Office Hours: By appointment only. All office hours will be held on Zoom. Appointments may be made at this link. You’re also free to talk after class, though I’ll have a hard stop at 7:00pm
- Viviana Luccioli: Office Hours W 2-3pm in DSAN Suite or by appt
- Sai Prerana Mandalika: Office Hours M 2-3pm & Fr 11-12 in DSAN Suite or by appt
This syllabus is a living document and is subject to change at any time
We are bombarded everyday with multiple claims of health risks (doing this will ruin your health), new treatments and cures (just take this for 30 days for a new you), and better lifestyle choices. How are these claims made, evaluated and validated using data science? Data drives our knowledge of biology, disease and effective treatments. This data is diverse, complex, large, and in many respects unique. This data drives our understanding of whether risk factors or treatments causally change our health outcomes, whether our genes or our environment affects our health, and decisions about drugs, protocols and public health that affect all of us everyday. In this class we explore this rich, diverse data landscape and the specialized methods needed to make sense of it, leveraging the instructor’s decades-long experience in collaborative epidemiological and biomedical research across academia, government and industry. We will explore designing good experiments to extract causal relationships, and how we might still make valid decisions even in non-ideal settings. We will explore high-dimensional multivariate data and evaluate the validity of finding a “needle in a haystack” biomarker that can be targeted for treatment. We will see how statistical modeling (survival analysis in particular), machine learning, AI, and explainable AI have made an impact in helping us understand this world within. We will see how data-driven decision making works. This journey will take us through real-life applications in bioinformatics (understanding how genes, proteins and other molecular markers affect disease), epidemiology (what might cause diseases and how can interventions prevent it) and clinical research (clinical trials, observational studies, case-control studies).
The focus of the class will be on data science methodologies, with more of an emphasis on statistical foundations, inference, associations and causality. As such, we will not go deeply into the biology, but use it to provide real-life context. We will also find that many of the methods we’ll learn have applications outside the life sciences, often in manufacturing, business and finance.
Course resources
Web
The primary source of information for this course is the course website at https://gu-dsan.github.io/6150-fall-2024. This site will contain all the course materials, including the syllabus, course notes, slides, project information and other supplementary resources.
We will also use Canvas for teaching modules, course links, quizzes, discussions, grades and other administrative materials. You can look up your grades, and online surveys will also be conducted here. Students in this course are required to visit this page once a day.
Links to required materials will be posted on the course website and on Canvas. We will do our best to keep the website and Canvas aligned, and both will serve as definitive sources of course material. If you discover discrepancies between the two, inform the instructor ASAP to resolve it.
Text books and course materials
There is no required textbook for this course. There will be extensive course notes that will serve as the primary resource for this class. These notes are a distillation of various references, and the instructor’s experience.
Various readings will be available and assigned, and will be posted on Canvas. An extensive set of online resources, including open access textbooks, blogs, and papers, will be provided both via Canvas and via the class website at https://gu-dsan.github.io/6150-fall-2024.
Communication
The primary mode of communication will be Slack. The course’s Slack workspace is https://dsan6150fall2024.slack.com.. You will receive an invitation to join.
The preferred way of contacting the professor privately is via email. Please read the communication and Slack rules.
Learning objectives
- Promoting analytic and critical thinking skills, developing the ability to make logical conclusions from data that are generalizable and robust
- Understanding different levels of evidence, and how design of experiments can help
- Learning how to plan and design studies to answer particular questions
- Understanding the difference between association and causality
- Understanding the pros and cons of statistical hypothesis testing
- Understanding why we need to correct for multiple testing
- Handling high-dimesional data.
- Understanding how resampling can help make robust inference
- Seeing the role Bayesian inference can play in making decisions
- Understanding how to handle missing data statistically
- Learning how survival analysis/reliability methods can help us understand time-to-event data, while accounting for particular missing data structures
- Learning how to validate models and model assumptions
- Learning the role machine learning can play even in with small sample sizes
- Learning how to assess explainability of AI models
Pre-requisites
- Basic knowledge of statistics and machine learning
- Fluency in using and the ecosystem.
- Everything you learned in your first year of the program.
Required resources
Computer
You should have a laptop (no Chromebooks, please). Windows, Mac or Linux machines are acceptable. Please bring your machine to class, since we will be having interactive activities and labs. You should also have version 4.3 or above installed on your computer, with at least the tidyverse meta-package installed.
Learning activities
Class format
This class might seem a bit different from other classes you have taken. It will require you to be an active participant in your learning, to think critically, and to apply what you have learned to real-world problems. Together, we will explore approaches to data science that are used in the life sciences, what the pros and cons of different choices are, and how to make decisions based on data and scientific context.
We will generally be following a flipped classroom model. This means that you will be expected to read the material before class, and come prepared to discuss and work on problems in class. There will be some didactic elements during class, but the emphasis will be on discussion, examples/case studies, computer experiments and participation. You will be expected to come with questions and discussion points in each class. We will also do small group activities as needed.
Learning materials for the class, that you will be expected to read before class, will include course notes, readings and online tutorials. There will be quizzes every class to reinforce the material for the week, to be done in class.
In-class evaluations, like quizzes and participation, cannot be made up later. You will be allowed to drop a maximum of 3 quizzes from your grade.
We will have a distinct laboratory section during each class, where we will work on case studies and examples that expand on the topic we have been exploring and understanding.
Generally, you are expected to attend class. Participating in discussions and learning from questions is an important part of the learning process. Class time will provide learning and understanding that may not be fully appreciated from the formal course materials.
- Lectures and labs will not be recorded.
- You will start the labs in class but you will most likely not finish. It is your responsibility to complete the labs to enable your learning. Completing the labs succesfully is also part of your grade.
Readings
Readings will be assigned to supplement course notes and other materials. These readings should take an hour or less per week. Reading materials will be provided through in PDF format via Canvas.
Quizzes will partly be based on the readings, so it is important that you complete them before class.
Lab completions
Most labs will have a deliverable. Completing the labs is essential for you to learn the skills presented each week.
The lab deliverables can sometimes be completed during lab time, however, it is your responsibility to complete the deliverable as part of your work outside of lecture/lab time. Labs will be graded for completion.
Homework assignments
There will be weekly homework assignments. These assignments are meant to solidify concepts and learning objectives each week, as we build skills and knowledge throughout the semester. Submissions will happen through Github Classroom, and will be Quarto documents or presentations.
Assignments may involve designing experiments, doing statistical analysis, performing simulation experiments and doing research on a particular topic. Deliverables will include conceptual questions (multiple choice or short ansers), R/Python code to apply the concepts of the week to data and interpretation of the results.
Term project
You will assemble into groups of 3 to 4 students. You will have choice around the type of project you would want to do. Projects can be of two types:
- Data analysis projects where you use publicly available data to answer a biological or biomedical question. You must state your question(s) clearly, explain why your data set(s) are appropriate for the question, perform data analysis and modeling as appropriate, and show that your results are robust and generalizable. Your analytic methods must be concordant with the study design used to collect the data. It is recommended that you use at least two datasets, one to develop your analytic workflow, and the rest to validate your results. There is flexibility around this depending on the question and analytic methods you plan using for the project. All analytic code (in or ) must be submitted as part of the project, in the form of a research compendium. The analytic code must be in the form of a reproducible workflow.
- Review projects where you do a literature review around methods to answer partcular analytic questions applicable to the life sciences. This will involve developing a well-annotated bibliography, data analysis or in silico experiments to demonstrate the methods you are reviewing and highlight their properties, a clear discussion on the strengths and limitations of the methods for applications, and or code to implement the method, either as a well-annotated set of scripts forming a workflow, or a package
In both cases, you will be expected to present your work in a short final presentation, and submit both a final report and a slide deck of no more than 10 slides to describe the work you have done. Reports may be in the form of Quarto documents/webpages/websites, and can incorporate WebAssembly technology (webR or pyodide) to add interactive elements, but no Shiny/Dash/Streamlit applications will be allowed. Slide decks must contain only static material.
Example topics will be provided in Week 2 of the class, and you will form groups and submit a proposal in Week 3. We will have one intermediate milestone check-in with a mini-submission as well as 15 minute group meetings with the professor. This mini-submission will be for completion and feedback, but the project will be graded holistically at the end of term. Further details will be made available on the project website by Week 3.
Evaluation
- Assignments : 25%
- Lab completions and quizzes: 15%
- Participation: 25%
- Group project : 35%
The project will have milestones that are cumulative in nature. Therefore, we will grade the project after the final submission with a holistic project rubric. We will grade the milestones in a qualitative way, and we will provide feedback and a trending grade with each milestone. It is up to you to incorporate the feedback provided. If your milestone trending grade is lower than you expected, and you do not incorporate the feedback we provide for improvement, do not expect your final project grade to improve.
In addition, each team member will complete a peer evaluation for their group and provide feedback to everyone’s contribution. Every team member is expected to contribute equally to their project. If peer evaluations indicate that students within a team are not contributing equally, those students will receive a grade penalty and a lower grade than the rest of their team.
Total is 100%. There is no plan to curve the final grade, and the final letter grade will be:
- A: >= 92.5
- A-: >= 89.5, < 92.5
- B+: >= 87.99, < 89.5
- B: >= 81.5, < 87.99
- B-: >= 79.5, < 81.5
- C: >= 70, < 79.5 (last passing grade)
- D: >= 60, < 70
- F: < 60
Failing this course is highly unlikely but definitely possible. Reasons for failing include but are not limited to:
- Consistently delivering work that is significantly below expectations
- Consistently not participating in class
- Consistently missing deliverables
- Consistently missing class
- Being found in violation of academic integrity
Grading philosophy
We will provide detailed rubrics for each deliverable, as far as feasible, to set the expectations for each assignment. Some parts of the assignment may be qualitative and open-ended and will be graded holistically.
Deliverables that:
- Exceed the requirements and expectations are typically considered A/A- level work.
- Just meet the requirements and expectations are typically considered B+/B level work.
- Do not meet the requirements are typically considered B- or lesser level work.
Partial credit will be given where appropriate.
All deliverables must meet general quality requirements that are expected from students in the second year of a Masters program as well as specific requirements that will be provided for each deliverable.
Points will be deducted for any of the following reasons:
- Your technical approach is fundamentally flawed
- Your analytical decisions are unjustified
- You did not follow any direct and specific instructions
- Your deliverable has missing sections
- Your overall presentation and/or writing is sloppy
- Your code does not follow best coding practices
- Your code has no comments (including the areas where GenAI was used)
- Your repository has either more or less files than those requested
- You use absolute references (file paths, urls, etc.) paths in your scripts
- You alter the repository structure in any way
- You do not use GitHub Classroom
- You do not use
giteffectively - You manually upload files to GitHub through the web and do not use
git - You use incorrect file names (wrong extensions, wrong case, etc.)
Submitting your work
GitHub Classroom
We use Github Classroom for all class deliverables: assignments, labs, and the final project. Submitting your work is the process of committing your files and results to your local repository and then pushing it to GitHub.
You must submit everything through GitHub!
Use the final-submission commit message
When you are ready for your work to be evaluated, you MUST use the commit message final-submission. If you do not use the commit message final-submission we will assume that you are still working in the repository and we will only grade what is present. By submitting that commit message, you are stating that you are finished with the assignment and are ready for feedback.
Make sure you understand the difference between a git commit and a push, and that you push your repository successfully to GitHub.
In case you need to make a correction after your final-submission and the submission deadline has not yet passed, then you can amend your previous commit. See amending a commit for instructions. Do not change the commit message, it should continue say “final-submission” after the amend.
No further edits to your GitHub repository are allowed after using the final-submission commit message.
We will use commit datetime and commit message to assess lateness.
Due dates
- Labs and assignments are due at 11:59 PM on the Monday after a class meeting. These are based on material from the previous week, and should be completed as quickly as possible so you can move your attention to the next week’s material. These are not busy work, but ways to reinforce the material you have learned. The time and effort required to do these deliverables will be commensurate with the time provided. Labs will primarily be checked for completion, while assignments will be checked for accuracy and quality.
- Quizzes will be available 1 hour before class and will be due by the end of class. Quizzes are based on the material and readings for the current week, that will be discussed in class. The quizzes will test if you have read and understand the week’s material.
Late policy
In lieu of extensions, there is a tiered deduction scale if a deliverable is late. Late penalties only apply to labs and assignments.
We will assess exceptional circumstances on a case-by-case basis, and only if we are made aware before a deliverable’s deadline, not after.
- A late penalty of 10% per day, up to 2 days, will be assessed for assignments and labs that are submitted with a
final-submissioncommit message after the deadline. You may still submit a missed lab or assignment up until the last day of class (May 2) with a maximum possible grade of 60%. - Missed in-class quizzes cannot be made up and will receive a grade of zero.
- Project deadlines are fixed and have no extensions or late penalty. A missed project deliverable will receive a grade of zero.
You may drop a maximum of 3 quizzes and 2 assignments from your final grade.
Other course policies
Attendance and punctuality
Attendance is mandatory and will be taken. Given the technical nature of this course, and the breadth of topics discussed, you are expected to attend each class, to complete all readings, and to participate actively in lectures, discussions and exercises. We understand there may be times you may need to miss class, please inform us in advance if you are not able to attend class for any reason. However, it is up to you to keep up.
Participation
We love participation. Read. Raise your hand. Ask questions. Make comments. Challenge us. Acknowledge us. This is an expectation. There is significant participation credit, and expect to be called on if you don’t try to participate.
However, We do acknowledge that some students may not be comfortable speaking up in class. If you are one of these students, please let us know. We will find ways to make sure you are participating in a way that is comfortable for you.
Laptop and phone use
You must bring your laptop to class to work on labs. No phone use is allowed during lecture. You may use your laptop to take notes, but please refrain from other activities. We reserve the right to ask you to put your phones and laptops away. You may not use your computer or phone while your peers or guest speakers are presenting.
Communication and Slack Rules
- All announcements will be posted on Canvas and Slack
- Use Slack for any question you may have about the course, about assignments or any technical issue. This way everyone can learn from each others questions. We will be monitoring and providing answers on a regular basis. Make sure you understand what is allowed in Slack.
- All communication with the professors should be either on general Slack channels or via email. E-mail is preferred for any communication of a personal nature as opposed to questions about class materials.
- Slack DMs are not to be used unless we DM you first and you can respond to our message. Students may not initiate DMs.
- Any email sent to the instructor containing any course question that is not personal in nature will not be answered; these are expected to go on Slack for general discussion and peer contributions.
- E-mails of a personal nature (personal issues or difficulties, questions regarding grades, seeking help with a personal issue, etc.) should be sent to the instructor’s e-mail (abhijit.dasgupta@georgetown.edu).
- Keep an eye on the questions posted in Slack. Use the search function. It’s very possible that we have already answered a question, and we reserve the right to point you to the syllabus, previous Slack messages, or other document containing the information requested.
- Assignment, lab and project questions will only be answered on Slack up to 12 hours before something is due.
Open Door Policy
Please approach or get in touch with me if something is not working for you regarding the class, methods, etc. My pledge to you is to provide the best learning experience possible. If you have any issue please do not wait until the last minute to speak with me. You will find that I am fair, reasonable, and flexible and care deeply about your learning and success.
Academic Integrity
As a Jesuit, Catholic university, committed to the education of the whole person, Georgetown expects all members of the academic community, students and faculty, to strive for excellence in scholarship and in character.The University spells out the specific minimum standards for academic integrity in its Honor Code, as well as the procedures to be followed if academic dishonesty is suspected.
Over and above the honor code, in this course we will seek to create an engaged and passionate learning environment, characterized by respect and courtesy in both our discourse and our ways of paying attention to one another.
The code of academic integrity applies to all courses at Georgetown University. Please become familiar with the code. All students are expected to maintain the highest level of academic integrity throughout the course of the semester.Please note that acts of academic dishonesty during the course will be prosecuted and harsh penalties may be sought for such acts. Students are responsible for knowing what acts constitute academic dishonesty. The code may be found at https://bulletin.georgetown.edu/regulations/honor/.
We have a ZERO TOLERANCE POLICY and students found to be in violation will be reported and penalized. The consequences of any violation may include: additional points penalty, getting a grade of zero, automatically failing the course, and suspension or expulsion from the program.
Definition of collaboration
In the spirit of fostering a collective and inclusive learning environment, we acknowledge that you will work and study with your peers. We also acknowledge that you use web resources (code examples specifically), and that in writing a program many of you will most likely use the same libraries, functions and other similar instructions in your scripts. However:
- You must write your own code. This will be verified for every assignment against every submission, and any similarity greater than 60% between students on a given assignment will be considered to be unauthorized collaboration.
What is allowed
- Collaborating with other students during in-class labs to facilitate collective learning
- Using Slack for helping one-another as long as:
- You do not provide answers directly but only discuss potential approaches
- You only share up to a few lines of code for everyone’s benefit for the resolution of a specific question or issue
- Using anything (code, resources, tips, approaches, etc.) provided by the instructional team
What is forbidden
The following actions are not permitted in any way and are considered a violation of academic integrity:
- Copying and sharing code between students in individual assignments or across groups in the group project
- Sharing anything on any individual assignment
- Using code snippets found online (stack overflow, etc.) and not commenting the source
- Plagiarism of any kind
- Using any Generative Artificial Intelligence tool without acknowledging it
- Making your private GitHub repos public
- Sharing or posting any course materials anywhere
- Faking or tampering with git commit dates or messages
Use of Generative AI tools
We recognize the recent availability of very powerful generative AI tools like Chat-GPT, GitHub Copilot, and others. These tools can help us be more effective and we embrace their use.
You are allowed to use GAI tools in a non substantial way.
What does non substantial mean?
It means that whatever is generated by GAI must not make up the majority of the work you do.
Any use of these tools must abide to the following rules:
- You must acknowledge the use of GAI tools
- You must comment which code blocks were generated by GAI
- You must note which written sections were generated by GAI
- If you used a prompt to ask the GAI tool to do something, you must include it
For this course, valid uses of gen-ai can be:
- Generating a code snippet or single function to perform a task. It’s likely you’ll need to modify it anyway
- Commenting code
- Using it as a writing aid (spelling, grammar, word choice, limited phrase translation) on content created by you, not the actual writing. Note: non-native English speakers cannot use gen-ai to fully translate content written in another language.
- Generating visualization starter code (you can accelerate the generation of the starting point, but you still need to customize the viz with all the best practices learned in this course)
Any deviation from these rules is considered a violation of academic integrity and will be acted on.
You typically KNOW when you are crossing the line into un-ethical territory. As a general rule, If you feel like you might be crossing a line, then you probably are!
In addition to what we are stating here, please take a look at the Data Science and Analytics Program’s ChatGPT usage guidelines.
Georgetown University resources and policies
Georgetown University’s Plagiarism Policy
Plagiarism or academic dishonesty in any form will not be tolerated and may result in a failing grade. All Honor Code violations will be submitted to the Honor Council.
Academic integrity is central to the learning and teaching process. Students are expected to conduct themselves in a manner that will contribute to the maintenance of academic integrity by making all reasonable efforts to prevent the occurrence of academic dishonesty. Academic dishonesty includes (but is not limited to) obtaining or giving aid on an examination, having unauthorized prior knowledge of an examination, doing work for another student, and plagiarism of all types, including copying code.
Plagiarism is the intentional or unintentional presentation of another person’s idea or product as one’s own. Plagiarism includes, but is not limited to the following: copying verbatim all or part of another’s written work; using phrases, charts, figures, illustrations, code, or mathematical/scientific solutions without citing the source; paraphrasing ideas, conclusions, or research without citing the source; and using all or part of a literary plot, poem, film, musical score, or other artistic product without attributing the work to its creator. Students can avoid unintentional plagiarism by following carefully accepted scholarly practices. Notes taken for papers and research projects should accurately record sources cited, quoted, paraphrased, or summarized sources and articles should be acknowledged in footnotes.
Honor System
All students are expected to maintain the highest standards of academic and personal integrity in pursuit of their education at Georgetown. Academic dishonesty, including plagiarism, in any form, is a serious offense, and students found in violation are subject to academic penalties that include, but are not limited to, failure of the course, termination from the program, and revocation of degrees already conferred. All students are held to the Georgetown University Honor Code. For more information about the Honor Code http://gervaseprograms.georgetown.edu/honor/
Academic Integrity and Courtesy
As a Jesuit, Catholic university committed to the education of the whole person, Georgetown expects all members of the academic community, students and faculty, to strive for excellence in scholarship and in character. The University spells out the specific minimum standards for academic integrity in its Honor Code and the procedures to be followed if academic dishonesty is suspected. Over and above the honor code, in this course, we will seek to create an engaged and passionate learning environment characterized by respect and courtesy in both our discourse and our ways of paying attention to one another.
Academic Resource Center
The Academic Resource Center (ARC) is the campus office responsible for reviewing medical documentation and determining reasonable accommodations for students with disabilities. You can reach the ARC via email at arc@georgetown.edu.
Counseling and Psychiatric Services (CAPS)
As Georgetown faculty, you are among the most important individuals in some of the students’ lives. They may turn to you when they are struggling and in times of need, or you may be one of the first to notice when they are distressed.
The CAPS website has tips for faculty on how to deal with struggling or distressed students. 202.687.6985 or after hours, call (833) 960-3006 to reach Fonemed, a telehealth service; individuals may ask for the on-call CAPS clinician.
Emergency Preparedness and HOYAlert
We encourage all faculty to become familiar with Georgetown’s Office of Emergency Management and sign up for HOYAlert to receive important safety and University operating status updates. Faculty teaching at the Georgetown Downtown campus might also want to sign up for AlertDC to obtain safety and traffic updates.
Office of Institutional Compliance and Ethics
The Office of Institutional Compliance and Ethics supports and coordinates many compliance-related activities the University undertakes. With the endorsement and assistance of the University’s senior leadership, this Office is responsible for leading the development, implementation, and operation of the Georgetown Institutional Compliance and Ethics Program.
Office of Institutional Diversity, Equity and Affirmative Action (IDEAA)
The mission of IDEAA is to promote a deep understanding and appreciation among the diverse members of the University community to result in justice and equality in educational, employment, and contracting opportunities, as well as to lead efforts to create an inclusive academic and work environment.
Title IX/Sexual Misconduct
Georgetown University and its faculty are committed to supporting survivors and those impacted by sexual misconduct, which includes sexual assault, sexual harassment, relationship violence, and stalking. Georgetown requires faculty members unless otherwise designated as confidential, to report all disclosures of sexual misconduct to the University Title IX Coordinator or a Deputy Title IX Coordinator. Suppose you disclose an incident of sexual misconduct to a professor in or outside of the classroom (except disclosures in papers). In that case, that faculty member must report the incident to the Title IX Coordinator or Deputy Title IX Coordinator. The coordinator will, in turn, reach out to the student to provide support, resources, and the option to meet—[Please note that the student is not required to meet with the Title IX coordinator.]. More information about reporting options and resources can be found on the Sexual Misconduct Website.
If you would prefer to speak to someone confidentially, Georgetown has a number of fully confidential professional resources that can provide support and assistance. These resources include:
- Health Education Services for Sexual Assault Response and Prevention: confidential email sarp@georgetown.edu
- Counseling and Psychiatric Services (CAPS): 202.687.6985 or after hours, call (833) 960-3006 to reach Fonemed, a telehealth service; individuals may ask for the on-call CAPS clinician
Title IX Sexual Misconduct Statement Please know that as faculty members, we are committed to supporting survivors of sexual misconduct, including relationship violence and sexual assault. However, university policy also requires us to report any disclosures about sexual misconduct to the Title IX Coordinator, whose role is to coordinate the University’s response to sexual misconduct.
Georgetown has a number of fully confidential professional resources who can provide support and assistance to survivors of sexual assault and other forms of sexual misconduct. These resources include:
- Getting Help
- Jen Schweer, MA, LPC
Associate Director of Health Education Services for Sexual Assault Response and Prevention (202) 687-032
jls242@georgetown.edu - Erica Shirley, Trauma Specialist
Counseling and Psychiatric Services (CAPS)
(202) 687-6985
els54@georgetown.edu
Threat Assessment
Georgetown University established its Threat Assessment program as part of an extensive emergency planning initiative. The program at Georgetown has been developed and implemented to meet current best practices and national standards for hazard planning in higher education institutions and workplace violence prevention.
Special Accommodations
If you believe that you have a disability that will affect your performance in this class, don’t hesitate to get in touch with the Academic Resource Center for further information. The center is located in the Leavey Center, Suite 335. The Academic Resource Center is the campus office responsible for reviewing documentation provided by students with disabilities and determining reasonable accommodations according to the Americans with Disabilities Act (ADA) and University policies.