LSMA

LONDON SCHOOL OF MULTIOMICS & AI

Free course

Free course

0 of 35 lessons

Optional

Further reading

Further reading

Further reading

Optional reading for the free course Introduction to Python. It follows the course's four modules: Python basics, figures that tell the truth, coding with AI assistants, and machine learning. Read it at your own pace. Nothing here is submitted or marked.

⏱ 7 min readFree
Lesson at a glance5 steps · about 7 min
  1. Module by module
  2. Papers and guides
  3. Tool manuals
  4. Glossary
  5. Going further
Download the PDF PDF · 8 pages · 202 KB · updated October 2026
  • Start with the module cards. Each module has two or three key readings. If you read only those, you have the core of the subject.
  • Most of it is free to read. Papers with a free full text link to PubMed Central or the publisher; the few that may need a subscription are marked.
  • The questions have no answer key. Use them to check your understanding after a module, or to discuss with other learners.

Module by module

The key readings for each module, and questions to think about once you have finished it. Full references are under Papers and guides.

Module 1 · FoundationsPython basics

Python reads like plain English. Functions, pandas tables and small tested modules turn one-off notebooks into tools you can reuse.

Read
Think about
  • Why might a function that works in your notebook fail when someone else imports it?
  • When would you choose a dictionary over a list?
Module 2 · IntermediateFigures that tell the truth

A figure answers one question. Show the data, say what error bars mean, use colour that everyone can read, and start bars at zero.

Read
Think about
  • When is a bar chart the right choice?
  • Which figure in a recent paper you read would you redraw, and how?
Module 3 · IntermediateCoding with AI assistants

Assistants write plausible code quickly. Reading, testing and checking it, and keeping data and secrets out of prompts, are what make it safe to use.

Read
Think about
  • An assistant suggests pip install for a package you have never heard of. What do you check first?
  • What would you write in a methods section about how you used an assistant?
Module 4 · AdvancedMachine learning

A model is only as good as its evaluation. Keep test data separate, avoid leakage, compare with a simple baseline and report how the model was checked.

Read
Think about
  • Your model scores 0.99 accuracy. What three things would you check before believing it?
  • Why must feature scaling be fitted inside cross-validation, not before it?

Papers and guides

The papers, books and guidance behind the course, grouped by module.

Module 1 · Python basics

If you read one item here, make it Wilson et al. (2017): its habits for naming files and organising a project will save you time in every later module.

  1. Python Software Foundation. The Python Tutorial. official documentation. The official Python tutorial.
  2. Cock PJA et al. (2009). Biopython: freely available Python tools for computational molecular biology and bioinformatics. Bioinformatics 25:1422–1423. The Biopython library paper.
  3. Wilson G et al. (2017). Good enough practices in scientific computing. PLOS Computational Biology 13:e1005510. Simple habits for reproducible projects.

Module 2 · Figures that tell the truth

Read Weissgerber et al. (2015) with one of your own figures beside you, and check it against the ten rules of Rougier et al. (2014) before you next submit work.

  1. Weissgerber TL et al. (2015). Beyond bar and line graphs: time for a new data presentation paradigm. PLOS Biology 13:e1002128. The case for showing every data point.
  2. Crameri F, Shephard GE, Heron PJ (2020). The misuse of colour in science communication. Nature Communications 11:5444. Colour maps that do not mislead.
  3. Rougier NP, Droettboom M, Bourne PE (2014). Ten simple rules for better figures. PLOS Computational Biology 10:e1003833. Ten rules that apply to every figure.
  4. Waskom ML (2021). seaborn: statistical data visualization. Journal of Open Source Software 6:3021. The seaborn library paper.

Module 3 · Coding with AI assistants

These are less about any one tool than about checking: read the package-hallucination study before you next install something an assistant suggests, and check your target journal’s current policy, since guidance on AI use changes often.

  1. Wilson G et al. (2014). Best practices for scientific computing. PLOS Biology 12:e1001745. Testing, review and version control for scientific code.
  2. Spracklen J et al. (2024). We have a package for you! A comprehensive analysis of package hallucinations by code generating LLMs. arXiv preprint 2406.10279. Measures how often code assistants suggest packages that do not exist.
  3. International Committee of Medical Journal Editors. Recommendations for the conduct, reporting, editing, and publication of scholarly work in medical journals. see the section on artificial intelligence. Journal guidance on disclosing AI-assisted work.

Module 4 · Machine learning

Start with Chicco (2017) for practical tips, then Kapoor and Narayanan (2023) to see how often leakage reaches published work. Keep TRIPOD+AI to hand when you write up a model of your own.

  1. Pedregosa F et al. (2011). Scikit-learn: machine learning in Python. Journal of Machine Learning Research 12:2825–2830. The scikit-learn library paper.
  2. Chicco D (2017). Ten quick tips for machine learning in computational biology. BioData Mining 10:35. Practical tips for biological data.
  3. Varma S, Simon R (2006). Bias in error estimation when using cross-validation for model selection. BMC Bioinformatics 7:91. Why tuning and testing on the same data biases results (Tuning, interpreting and reporting).
  4. Kapoor S, Narayanan A (2023). Leakage and the reproducibility crisis in machine-learning-based science. Patterns 4:100804. Data leakage across many fields (Cross-validation and data leakage).
  5. Greener JG et al. (2022). A guide to machine learning for biologists. Nature Reviews Molecular Cell Biology 23:40–55. A broad guide to machine learning for biologists. May need a subscription
  6. Collins GS et al. (2024). TRIPOD+AI statement: updated guidance for reporting clinical prediction models that use regression or machine learning methods. BMJ 385:e078378. Reporting standard for prediction models.

Tool manuals

The libraries used in the course, with the versions the code was tested on. Google Colab includes all of them except pytest.

ToolWhat it doesModuleVersion in the course
PythonThe languageAll3.13
pandasTables1, 2, 43.0.5
matplotlibFigures1, 2, 43.11.2
seabornStatistical figures1, 2, 40.13.2
BiopythonSequences11.88
pytestTesting3Current PyPI
scikit-learnMachine learning41.9.1
SciPyStatistics2, 41.18.1

Glossary

Baseline
A simple model to beat, such as always predicting the most common class.
Cross-validation
Training and testing on different splits of the data, several times.
Data leakage
Information from the test data reaching the model during training.
DataFrame
pandas' table: labelled rows and columns.
Feature
A measured input to a model.
Function
A named, reusable block of code.
Hallucination
Plausible output from an AI tool that is not supported by facts.
Module
A Python file of functions that other code can import.
Overfitting
Learning noise in the training data, so the model fails on new data.
Precision and recall
Of the predicted positives, how many are right; of the true positives, how many are found.
Prompt
The instruction you give an AI assistant.
ROC AUC
How well a model ranks positives above negatives; 0.5 is chance.
Test (unit test)
Code that checks another piece of code gives the expected answer.
Tuning
Choosing a model's settings using validation data.

Going further

Back to the overviewPDF

Up next

Finish

Course complete

Ask BioTutor

Create a free website with Framer, the website builder loved by startups, designers and agencies.