BEGIN:VCALENDAR
VERSION:2.0
PRODID:icalendar-ruby
CALSCALE:GREGORIAN
BEGIN:VEVENT
DTSTAMP:20261120T103826Z
UID:80551c93-d346-4f42-b372-8db30aad45cc
DTSTART:20270225T090000Z
DTEND:20270225T170000Z
DESCRIPTION:## Overview\n\nAI coding agents are tools that do more than sug
 gest a line of code: they plan\, edit files\, run commands and iterate on 
 the results. They are entering bioinformatics workflows quickly. They can 
 speed up routine work such as writing parsers\, debugging pipelines and ad
 ding tests\, but they can also produce code that runs cleanly and is quiet
 ly wrong: a shifted genomic coordinate\, a silently dropped record\, a wro
 ng constant.\n\nThis one-day\, hands-on course teaches how to use coding a
 gents in bioinformatics work effectively and responsibly. You will learn h
 ow agents work and how to frame tasks and give them the right context. You
  will then practice on realistic exercises built on synthetic data: parsin
 g a file format\, debugging a broken pipeline\, and reviewing agent-writte
 n code that contains a hidden error. The central skill of the course is su
 pervision\, meaning verifying and reviewing what an agent produces rather 
 than only prompting it. The course also covers data privacy\, reproducibil
 ity and scientific integrity\, and ends with a capstone in which you refac
 tor\, test and document a messy analysis script with an agent.\n\n## Audie
 nce\n\nThis course is designed for PhD students\, postdoctoral and other r
 esearchers in the life sciences from both academia and industry who write 
 code to analyse biological data and want to learn how to use AI coding age
 nts in their work productively and safely. It is aimed at participants who
  are new to agentic coding tools.\n\n## Learning outcomes\n\nAt the end of
  the course\, the participants should be able to:\n\n* **Explain** what an
  AI coding agent is and how it works (model\, harness\, state\, tools and 
 the agentic loop)\n* **Frame** tasks and **provide** context so that an ag
 ent produces useful code for common bioinformatics problems\n* **Use** an 
 agent for typical workflows such as parsing a bioinformatics file format a
 nd debugging a pipeline\n* **Review** and **verify** agent-generated code\
 , and **detect** silent errors such as coordinate-system off-by-one mistak
 es\, dropped data or wrong constants\n* **Identify** what must never be sh
 ared with an agent and **apply** good data-protection practice\n* **Docume
 nt** AI-assisted work so that it stays reproducible and scientifically sou
 nd\n\n## Prerequisites\n\n### Knowledge / competencies\n\nThis course is d
 esigned for users who already write some basic code for data analysis. The
 re is no requirement for prior experience with AI coding tools. You should
  be comfortable with:\n* Basic programming in Python (the exercises are in
  Python\; R users who can read Python are welcome)\n* Working on the comma
 nd line\n* Basic git usage\nBasic familiarity with common bioinformatics f
 ile formats (VCF\, SAM\, BED) is helpful but not required.\n\n### Technica
 l\n\nYou will need access to a computer (Windows\, macOS or Linux) on whic
 h you can install software and use a terminal. Python 3.10 or later\, git\
 , and the Python packages pandas and pytest are needed. You will also need
  a free personal account for the AI coding tool used during the course.\nS
 etup instructions and a short check script will be sent to registered part
 icipants before the course. Please complete the setup beforehand\, so that
  the course time is spent on the exercises.\nAll exercises use synthetic d
 ata. Please do not bring patient data or any other confidential data to th
 e course.\n\n\n## Schedule – CE(S)T time zone\n\n09:00 – 09:40 : Welco
 me and introduction: what AI coding agents are and how they work \n\n09:40
  – 10:20 : Context and task framing (hands-on)\n\n10:20 – 10:40 : *Bre
 ak*\n\n10:40 – 11:25 : Workflow 1: parsing a bioinformatics file format 
 (demo and exercise)\n\n11:25 – 12:10 : Workflow 2: debugging a broken pi
 peline (demo and exercise)\n\n12:10 – 13:10 : *Lunch*\n\n13:10 – 13:55
  : Verification and review of agent output (demo and exercise)\n\n13:55 
 – 14:15 : Data privacy and security\n\n14:15 – 14:35 : Reproducibility
  and scientific integrity\n\n14:35 – 14:55 : *Break*\n\n14:55 – 15:20 
 : Tooling landscape\, limitations and failure modes\n\n15:20 – 16:30 : C
 apstone: refactor\, test and document an analysis script with an agent\n\n
 16:30 – 17:00 : Wrap-up\, open questions and course evaluation\n\n## App
 lication\n\nThe registration fees for academics are **100CHF** and **500 C
 HF** for for-profit companies.\n\nWhile participants are registered on a f
 irst come\, first served basis\, exceptions may be made to ensure diversit
 y and equity\, which may increase the time before your registration is con
 firmed.\n\nApplications will close on **10/02/2027** or as soon as the pla
 ces will be filled up. Cancellation after **10/02/2027** will not be reimb
 ursed. Please note that participation in SIB courses is subject to our [ge
 neral conditions](https://www.sib.swiss/legal-documents).\n\nYou will be i
 nformed by email of your registration confirmation. Upon reception of the 
 confirmation email\, participants will be asked to confirm attendance by p
 aying the fees within **5 working days**.\n\n## Venue and Time\n\nThe cour
 se will take place at the University of Lausanne (https://planete.unil.ch/
 plan/) (Metro M1 line\, Sorge station).\n\n## Additional information\n\nCo
 ordination: Diana Marek\, SIB Training group.\n\nA **Certificate of Attend
 ance** will be sent provided you were present at the course\, whereas a **
 Certificate of Achievement** recommending 0.25 ECTS will be sent provided 
 you passed the exam.\n\nYou are welcome to register to the SIB courses mai
 ling list to be informed of all future courses and workshops\, as well as 
 all important deadlines using the form [here](https://lists.sib.swiss/mail
 man/listinfo/courses).\n\nSIB abides by the [ELIXIR Code of Conduct](https
 ://elixir-europe.org/events/code-of-conduct). Participants of SIB courses 
 are also required to abide by the same code.\n\nFor more information\, ple
 ase contact [training@sib.swiss](mailto://training@sib.swiss).
SUMMARY:Agent-Assisted Coding: Best Practices for Bioinformatics
URL;VALUE=URI:https://www.sib.swiss/training/course/20270222_AACBP
END:VEVENT
END:VCALENDAR
