Forum

[EOI open] Advanced workshop, March 2026

We are planning an advanced, hands-on asynchronous workshop for researchers who have completed our beginner course. The program will focus on complex study designs, including batch effects, longitudinal and time-course data and practical strategies for analysis with multivariate approaches.

If this is of interest, please submit a short expression of interest so we can tailor the workshop to your needs. You will also be first to hear when registrations open.

Workshop details

  • Dates: 2 – 27 March 2026 (4 weeks)
  • Format: Weekly focus topic with online resources, live Q&A sessions, and dedicated Slack support. Topics will include batch-effect management, multi-study integration, and longitudinal/time-course designs.
  • Capacity: Limited places to ensure personalised support from our team
  • Fees:
    • AUD $795 (~ €438) – Students
    • AUD $1,350 (~ €755) – Academic / Non-profit staff
    • AUD $2,250 (~ €1,260) – Industry participants
    Payment available via invoice or credit card
  • Certificate: All participants will receive a certificate of attendance
  • Platform: You will be among the first to use our new mixOmics PRO platform !

[open] Self-paced online course Feb 23 – April 11 2026

This course is designed for:
  • Beginners looking for an introduction to mixOmics methods for single – and multi-omics analyses.
  • Current mixOmics users who want to deepen their understanding of the mixOmics methods.
  • Users who would like more guidance on analyzing their own data (we also provide exemplar datasets).

The workshop is self-paced and spans across 7 weeks. There are 4 Q&A live sessions, and many opportunities to interact with the cohort and your instructor Prof Kim-Anh Lê Cao via Slack. BYO data is encouraged: we provide advice so that you can analyse your own data with mixOmics tools as part of your learning process.  A good working knowledge in R programming (e.g. handling data frame, perform simple calculations and display simple graphical outputs) is essential to fully benefit from the course*. 

According to our past participants, a time commitment of 5-8h/week was sufficient to feel that they were progressing. Here is some feedback from a previous course.

We provide a certificate of attendance or completion.

Register here, places are limited!

(make sure you put the right discount code, see tiered fees below)

Fees

Research Higher Degree students enrolled at a University: $550 AUD (incl. GST) [discount code: MIXO_RHD]

Staff and members from Universities & Not-for-profit organisations: $900 (incl. GST) [discount code: MIXO_NFP_STAFF]

Other industries: $1450 AUD (incl. GST)

Discounts of 5% for a group of 3-9 learners and 10% for 10+ learners, however, this will require a single invoice per group.

These funds go towards the support of a software developer to maintain the package. If you need an invoice, contact Student Support at continuing-education[at]unimelb.edu.au

Teaching Period Dates

Teaching commences: Monday, 23 Feb 2026, 9:00 am AEST (note Australian time!)

Q&A live webinars are scheduled on Thursdays 6pm AEST / 8am CET during the first 4 weeks (26th Feb, 5th, 12th and 19th March).

An additional session might be added on Fridays 9am AEST ( = Thursdays 2pm PST / 5pm EST / 9pm CET)

  • Teaching concludes: Friday, 20 March 2025, 11:59 pm AEST (after 4 weeks)
  • (non marked) Assessment due: Friday 5 April 2025 (2 weeks prep)
  • Peer-review of assessment due: Friday 11 April 2025 (1 week prep)

The course is divided into theory (50%) and hands-on practice, with the opportunity to analyse your own data. The exercises and assignments are in R. Participants are encouraged to use RStudio and Rmarkdown (template and R code provided).

*Need an R refresher?

Learners who are not proficient in R do not get the full benenefit of the course (based on their own, honest, feedback!) For those looking for an R refresher well ahead of the course:

https://monashdatafluency.github.io/r-intro-2/index.html

The R cheatsheets for reference: https://iqss.github.io/dss-workshops/R/Rintro/base-r-cheat-sheet.pdf

[completed] 3-day mixOmics workshop in person, 22 – 24 Sept 2025, Lund University

We have a few spots left for an in-person mixOmics workshop, which we would like to open to our wider community!

Modern high-throughput technologies generate complex biological data that require powerful yet accessible tools for analysis. This beginner-level workshop introduces participants to data integration and multivariate analysis using the R package mixOmics.

Through a series of hands-on sessions, we will explore how multivariate methods can uncover biological patterns, identify key molecular features (or ‘markers’), and integrate multiple omics datasets. The approach is hypothesis-free, flexible, and does not rely on strict statistical assumptions.

By the end of the workshop, participants will be familiar with the core mixOmics workflows for exploratory and supervised analysis. There will also be an opportunity to apply the methods to your own dataset, with expert guidance throughout.

Pre-requisite: Basic proficiency in R is essential (e.g. working with data frames, basic calculations, simple plots). Participants without R experience have reported difficulty keeping up and gaining value from the course.

Instructor: Prof Kim-Anh Lê Cao, the University of Melbourne

WHERE: Mon 22 to Wed 24 Sept 2025: 9am – 5pm, Lund University (Room: Maskrosen (E121), Ekologihuset, Lunds Universitet,Kontaktvägen 10,Lund 22362, Sweden; google map pin)

REGISTER Request an invoice by emailing Maggie at MIG-EA [at] unimelb.edu.au and we will follow up with you with instructions pre-workshop and full schedule.

Fees


Research Higher Degree students enrolled at a University: 350 EUR
Staff and members from Universities & Not-for-profit organisations: 575 EUR
Other industries:: 1200 EUR

Workshop schedule

Monday 22 Sept and Tuesday 23rd Sept: methods and hands-on. 

The following broad topics will be covered.

A. Key methodologies in mixOmics and their variants

  • Basic processing of count data
  • Exploration of one data set and how to estimate missing values
  • Identification of molecular signature to discriminate different treatment groups
  • Integration of two data sets and identification of biomarkers
  • Introduction to repeated measurements or longitudinal studies analysis
  • Integration of more than two data sets to identify multi omics signatures
  • Integration of independent but related studies (optional)

B. Review on the graphical outputs implemented in mixOmics

  • Sample plot representation
  • Variable plot representation for data integration
  • Other useful graphical outputs

C. Case studies and applications

Several microbiome and omics studies will be analysed using the methods presented above.

Wednesday 24th Sept: bring your own data. Participants will be given the opportunity to analyse their own data under the guidance and the advice of the instructor. Participants can also work in a team. Some data sets will also be provided for those unable to bring their own data.

Statistical concepts

The following statistical concepts will be introduced: covariance and correlation, multiple linear regression, classification and prediction, cross-validation, selection of markers, penalised regressions. Each methodology will be illustrated on a case study (theory and application will alternate).

Target group

The course is intended for computational biologists and biologists with some statistical knowledge and a good working knowledge in R. It will be particularly useful to those interested in:

Understanding and/or applying multivariate projection methodologies to large data sets.

Exploring data sets.

Selecting molecular / microbial features with methods implementing LASSO-based penalisations.

Using graphical techniques to better visualise data.

Anticipated outcomes

After completion of this workshop, participants will be able to

Apply those methods to high throughput microbiome studies, including their own studies.

Understand fundamental principles of multivariate projection-based dimension reduction technique.

Perform statistical integration and feature selection using recently developed multivariate methodologies.

Workshop registration cancellation policy

To confirm your place in this workshop, the registration fee is payable at the time of booking. This commitment helps us plan and deliver the workshop effectively for all participants.

Cancellations and Refunds: Refunds are only available if the workshop is cancelled or postponed by the organiser. In that case, a full refund (including any service fees) will be issued automatically.

No-Show Policy: If you do not attend the workshop, your registration fee will be non-refundable.

Illness or Exceptional Circumstances: We understand that unexpected situations can arise. If you are unable to attend due to illness or other exceptional circumstances, please contact us as soon as possible. While refunds cannot be issued, we will review your situation with care and may consider alternative options at the organiser’s discretion.

This policy is designed to ensure fairness to all participants and to support the smooth delivery of our workshops.

Feedback from workshops

From the Feb – March 2025 workshop

Best aspects of the program
Course materials were exceptionally well done
The MixOmics Vignette The R markdown template Kim-Anh’s Teaching Style and approachability
the modules explained in details the main principles of statistical analyses and the webinars were clear and brought additional informations to better understand the online courses.
That we started from basics and went to more advanced analysis
The online content that supported the live webinars
Hands-on experience and being able to use own data. The quality of the material was excellent, and the teacher is very knowledgeable and helpful.
Practical approach, resources to learn more, and the videoconference Q&A.
The course was extremely well structured, the continuous building of knowledge in a layered approach was very effective. I see how the block integration was easy to understand only because of the pre-work in the previous weeks to fully understand PCA, PLS, PLS-DA. Also, the instructor was very flexible in incorporating all our wishes for the little extras we were interested in. The discussions on slack were also very helpful. All in all, the best course I have attended.
I found the assignment really good and challenging.
Assignment on own work, slack
The MixOmics course allows one to learn at their own pace given international schedules. The course material was stimulating and the teacher took time and care to address students’ questions.
The weekly webinar
The assignment and slack and working with own data.
Nice exposure of different methodologies of omics data analysis, including the mathematical reasoning behind them. The assignment was useful to apply and reinforce the knowledge of the theory. The Q&As and the Slack channel were also very good sources for topic discussion.
Very usefull course, many hands on options, it is great that you can work on your own data for the assignment, I liked the live tutorials a lot
The support was very helpful but the data for the assignments could work on my R version for which I cannot changed it because of my platform
Learning how to use all the tools of the mixomics package
The practical application of the different analyses which was taught.
Practical work mixed with theoretical part of the program.
Hands on activities
Additional comments
Genuinely a very well run and well taught course. I will be recommending it to people!
Professor Kim-Anh Lê Cao was amazing and did a very good job, teaching, organizing us and replying very fast to every question
Please make the access to online content available for 6 months after the course. Need to improve the login link for external users. I could only access by going to the link in the email sent by Melbourne uni with was time consuming. The link would not work if copied and pasted to online favourites.
The training proved to be exceptionally valuable. Despite its considerable challenges, especially given my initial lack of knowledge in the field, I acquired a wider knowledge in the area and very valuable new skills. This experience has significantly contributed to my scientific development. Committing to this training was a wise decision, as it provided an excellent introduction to mixomics and multi-omics analysis in general. I look forward to applying these new skills in my future research studies.
Kim-Anh was a great instructor, very smart, and always available to help and answer any questions.
Thank you to the teachers of the course for their availability. It was a much appreciated experience.
The connexion to the website as external was only accessible from the first e-mail sent.
Longer course, also exploring more options of mixOmix – or an additional course.
Prof. Kim-Anh was exceptionally kind and ready to help. Her teaching was highly appreciated.
Very well organized and structured workshop but I missed more theoretical part of the course so I would not be lost when started my hands-on.

🚀 mixOmics v6.32.0 released on Bioconductor 3.21

mixOmics v6.32.0 is now available on Bioconductor 3.21, compatible with R 4.5.0. This update brings new features, bug fixes, and improvements based on your feedback.

What’s new since the last Bioconductor release:

🔬 New features and enhancements

  • plotLoadings() now supports ggplot2-style plots with fully customisable aesthetics
  • tune() has been enhanced to support tuning of components or variables
  • New function perf.assess() evaluates final model performance

⚙️ Improved performance and reproducibility

  • tune() and perf() now support parallel processing using the BPPARAM argument and accept a seed argument to improve reproducibility

🧹 Bug fixes and usability improvements

  • plotIndiv() now correctly handles pch ordering and ellipse colours
  • Better error message in perf() when a class has only one sample
  • Streamlined multiblock functions by removing unused arguments

📦 Install this version:

if (!require("BiocManager", quietly = TRUE))
  install.packages("BiocManager") 
BiocManager::install("mixOmics")

🔍 For a full list of changes, visit the README on our GitHub repo.

New Performance Assessment & Parameter Tuning – Beta test now!

We’ve streamlined performance assessment and parameter tuning functions, available for beta testing before the next Bioconductor release in April!

What’s New?

  • New perf.assess(): Assesses only the final model’s performance, returning key metrics (no plots). PR #344
  • Enhanced tune(): Now supports tuning components separately or alongside variables across multiple model types. PR #348
  • New documentation pages: Explore new webpages explaining key concepts and usage of these functions.

Get Involved

  • Install the latest development version using
    devtools::install_github("mixOmicsTeam/mixOmics", ref = "6.31.4")
  • Test the new functions on your models
  • Share feedback on the User Forum or identified bugs on Github Issues

Try it out and help us refine these features before official release!

Webinar: Φ-Space ST: a platform-agnostic method to identify cell states in spatial transcriptomics studies

We have a sequel to Φ-Space, Φ-Space ST developed by  Dr Jiadong Mao  for spatial transcriptomics studies! We are very excited about these new developments and the potential of Φ-Space for single cell annotation!

Φ-Space ST is:

  • A novel and fast approach for cell type composition analysis.
  • Platform-Agnostic and Scalable as it works across multiple spatial transcriptomics (ST) platforms, including CosMx, Visium, and Stereo-seq.
  • Accurate and integrative as it identifies cell states by leveraging multiple scRNA-seq references.
  • Segmentation-Free & Niche-Driven as it annotates cell states at subcellular resolution, uncovering niche-specific cell types and tumor-distinguishing patterns.

Φ-Space ST: a platform-agnostic method to identify cell states in spatial transcriptomics studies. Jiadong Mao, Jarny Choi, Kim-Anh Lê Cao. bioRxiv 2025.

Check Jiadong’s latest seminar he presented at Melbourne Integrative Genomics on Friday 14th February 2025:

Abstract

We introduce Φ-Space ST, a platform-agnostic method to identify continuous cell states in spatial transcriptomics (ST) data using multiple scRNA-seq references. For ST with supercellular resolution, Φ-Space ST achieves interpretable cell type deconvolution with significantly faster computation. For subcellular resolution, Φ-Space ST annotates cell states without cell segmentation, leading to highly insightful spatial niche identification. Φ-Space ST harmonises annotations derived from multiple scRNA-seq references, and provides interpretable characterisations of disease cell states by leveraging healthy references. We validate Φ-Space ST in three case studies involving CosMx, Visium and Stereo-seq platforms for various cancer tissues. Our method revealed niche-specific enriched cell types and distinct cell type co-presence patterns that distinguish tumour from non-tumour tissue regions. These findings highlight the potential of Φ-Space ST as a robust and scalable tool for ST data analysis for understanding complex tissues and pathologies.

mixOmics website update

We’re pleased to share that the mixOmics website has undergone a redesign to enhance your browsing experience and make it easier to access our resources.

What’s New?

  • ✨ Refreshed Design: A cleaner, more modern layout
  • 📚 Expanded Getting Started Pages: Helpful pages to help you get up and running with mixOmics
  • 🧭 Reorganized Navigation: A more intuitive menu to quickly find key resources
  • 🔗 Updated Social Links: Stay connected with the mixOmics community
  • 💬 Direct Links to the User Forum: If you haven’t already, join our mixOmics user forum to connect with over 500 other users and experts
  • 🧑‍💻 Updated About Pages: Learn more about the project and our team
  • 📅 Streamlined Workshops, Webinars, and News Sections: Easier access to events and updates
  • 🖥️ Embedded R Markdown Pages: Improved code presentation with syntax highlighting in our Methods, Plots, and Case Studies pages

We are continuing to make small improvements, so if you encounter any issues or have feedback, please feel free to contact us.

Thank you for your continued support of mixOmics.

The mixOmics Team

Page from R Markdown



Missing_Values.knit





All methodologies implemented in mixOmics can handle missing values.
In particular, (s)PLS, (s)PLS-DA,
(s)PCA utilise the NIPALS
(Non-linear Iterative
Partial Least
Squares) algorithm as part of their dimension reduction
procedures. This algorithm is built to handle NAs [1].

This is implemented through the nipals() function within
mixOmics. This function is called internally by the above methods but
can also be used manually, as can be seen below.

Usage in mixOmics

library(mixOmics)
data(liver.toxicity)
X <- liver.toxicity$gene[, 1:100] # a reduced size data set

## pretend there are 20 NA values in our data
na.row <- sample(1:nrow(X), 20, replace = TRUE)
na.col <- sample(1:ncol(X), 20, replace = TRUE)
X.na <- as.matrix(X)

## fill these NA values in X
X.na[cbind(na.row, na.col)] <- NA
sum(is.na(X.na)) # number of cells with NA
## [1] 20
# this might take some time depending on the size of the data set
nipals.tune = nipals(X.na, ncomp = 10)$eig
barplot(nipals.tune, xlab = 'Principal component', ylab = 'Explained variance')

FIGURE 1: Column graph of the explained variance of each Principal
Component.

If missing values need to be imputed, the package contains
impute.nipals() for this scenario. NIPALS
is used to decompose the dataset. The resulting components, singular
values and feature loadings can be used to reconstitute the original
dataset, now with estimated values where the missing values were
previously. To allow for the best estimation of missing values, there is
a large number of components being used (ncom = 10).

X.impute <- impute.nipals(X = X.na, ncomp = 10)
sum(is.na(X.impute)) # number of cells with NA
## [1] 0

The difference between the imputed and real values can be checked.
Here are the original values:

id.na = is.na(X.na) # determine position of NAs in dataframe

X[id.na] # show original values
##  [1]  0.09041 -0.04070  0.03497 -0.01712  0.01309  0.00233 -0.04142  0.11104
##  [9] -0.01519 -0.17034 -0.01641  0.15964  0.00557 -0.06217  0.04131  0.02157
## [17]  0.01226 -0.00753  0.03038 -0.00783

The values which were estimated via the NIPALS
algorithm:

X.impute[id.na] # show imputted values
##  [1]  0.0837747419 -0.0190061068  0.0004024897 -0.0180879247 -0.0094185656
##  [6] -0.0312362158 -0.0706920015  0.1400817774  0.0083359545 -0.1158255139
## [11]  0.0164817649  0.1007897385  0.0236184385  0.0191934144  0.0214240977
## [16]  0.0686280312 -0.0039198425  0.0085870558  0.0450234407  0.0013964758