Data Science for Bioinformatics (BM70006W)

Assessment Brief and Assessment Criteria

Assessment Brief

Students will be assessed through one main method: a portfolio.

Students are required to produce a single MS Word document in Arial 11 or other sans serif typeface of equivalent size, which details a set of pieces of creative work created by students to display their data science skills.

Deadline

by 23:59 on Sunday 21 January 2024, through Blackboard Turnitin How to submit your Portfolio

· On the module menu, click ‘Assessments’,

· Scroll down the text by clicking on the scroll bar to locate the ‘Assessment submission area’ link,

· Click ‘Assessment submission area’, then

· Click ‘Portfolio’.

· On the Assignment Dashboard, click ‘Upload Submission’, click ’Choose file’ to upload your work from your local computer, click ‘Upload and Review’, then click ’Submit to Turnitin’.

· The submission link will be available three weeks before the deadline.

· Students can submit multiple times to the assignment and receive a new similarity report.

· After three resubmissions, they will need to wait 24 hours after a resubmission to see a new report.

· Students can use their similarity reports to refine and improve their assignment before the deadline.

Note that

· Plagiarism results in an automatic fail in the assignment or substantial loss of marks.

· Up to 10 marks will be deducted for an overlength report or a short report.

· Up to 10 marks will be deducted for an overlength logbook.

· Up to 10 marks will be deducted if the source code is presented as an image.

· Up to 10 marks will be deducted for a higher similarity index.

· Up to 15 marks will be deducted for submitting a non MS Word document.

Assessment 1 (A1): Portfolio

Assessment Task

The assessment for this module will consist of two parts: a technical report and logbooks for weekly practicals for this module.

2500-word technical report:

Write a technical report (2500 words) that critically reflects on your development in order now

1) planning, design and organisation of data science practice,

2) review of practices in computational and statistical modelling and machine learning,

3) practical implementation of programming or command line work, and

4) communication and collaboration in data science for bioinformatics.

The report must include an abstract that concisely convey the key aspects of your work, including its objectives, methods, results, and conclusions.You are advised to use the template provided below to structure and write your technical report.

You should demonstrate a sustained understanding of the existing literature - demonstrating engagement with research in the relevant areas of data science.

Logbooks for weekly practicals:

The logbooks for weekly practicals for this module should accompany the report.

The logbooks should not run more than 30 pages in total and must be completed in single-spaced typescript in Arial 11 or other sans serif typeface of equivalent size, with margins of at least 2 cm. Arial narrow and Calibri are not allowable font types.

Attend the practical sessions for the module that are available on the Blackboard course on a weekly basis.

Each logbook should suit the specific requirements of the data science task. The important thing is to keep a record of the steps taken, observations made, conclusions reached, and action points for future reference.

It is recommended that you include the logbooks for the 10 weekly practicals (e.g. Weeks 2-11) in your assignment.

The task will be evaluated based on Completeness, Organisation, Accuracy, Relevance, Clarity, Evidence of critical thinking, and Evidence of problem-solving skills.

Assessment criteria mapped to learning outcomes 

Generic marking criteria 

Distinction >= 70:

Portfolio demonstrates: (i) complete understanding of the material to be presented showing high critical or analytical ability as relevant, (ii) clear and logical organisation of the material, (iii) excellent use of appropriate resources and teaching aids and (iv) preparatory work including substantial background reading.

LO1 Critically apply the theories of probability, statistical inference and statistical learning techniques to carry out bioinformatics calculations.

Merit 60 - 69:

Portfolio has the following features, but without fully achieving one of them: (i) shows a clear understanding of the material with an accurate account that demonstrates good critical or analytical ability, (ii) good use of resources, (iii) evidence of appropriate background reading, and (iv) succeeds in delivering all the relevant material clearly to the audience so that they appreciate its significance.

Pass 50 - 59:

Portfolio (i) shows a solid grasp of the material, (ii) gives a mainly accurate account of most of the relevant material, (iii) shows evidence of some background reading, and (iv) successfully delivers most of the material to the audience in a way that they can understand it, but does not go beyond that.

LO2 Apply data analytics, statistical and modelling techniques such as machine learning and artificial intelligence (AI) to computational biology and life science problems

Fail < 50

Portfolio (i) shows only a basic grasp of the material (ii) shows evidence of little background reading or preparation, (iii) delivers most of the material accurately but makes errors or omissions resulting in a poor learning experience for the audience.

Guidance on writing the technical report