We are pleased to announce our next webinar co-hosted with Indatech and the University of Tours dedicated to Raman Spectrosocpy and Machine Learning for bioprocessing optimization

During this webinar, discover how to couple in-line Raman spectroscopy with Machine Learning tools to optimize the non-destructive analysis of CHO cell cultures and the production of monoclonal antibodies (mAbs). Through real-time monitoring of critical process parameters (CPPs) and critical quality attributes (CQAs), such as mAb, nutrient and metabolite concentrations or viable cell density , yield and batch reproducibility may be significantly improved.

Alongside 2 of our partners in CLIMBIN project, Julien Louet from Indatech and Pr. Igor Chourpa from the NMNS laboratory at the University of Tours, Sylvie Roussel will present the results obtained inthe context of CLIMBIN.

Sylvie Roussel,
Dirigeante d’Ondalys

CLIMBIN is a collaborative project that aims to develop an innovative solution in process analytical technology (PAT) by molecular optical spectrometry, to improve CHO-type suspension cultures in various types of bioreactors. Dedicated to the bioprodcution sector, this real-time monitoring of critical process and quality parameters offers disruptive advantages in terms of control, industrial performance and CSR.

Expert in spectral data analysis (NIR, MIR, Raman, UV), the Ondalys team supports you in all your issues of processing your spectroscopic data and your bioproduction data.

To know more about bioprocessing monitoring.
.

The post Dec.10th, 2024 – Webinar: Raman and Machine Learning for bioprocessing appeared first on Ondalys.

Join our webinar on October 15, 2024 at 5 pm (CEST)

Batch monitoring based on Process Data and Spectroscopy.
Model developments and implementation

We are pleased to announce our upcoming webinar organized in partnership with Sartorius, the publisher of SIMCA^®, data analysis software, and SIMCA^®-Online, process monitoring software. During this webinar, Lennart Eriksson from Sartorius and Sébastien Preys from Ondalys will discuss fusion of spectral and multivariate process data (such as temperature, pH, etc.) for advanced batch modeling.

Attend to learn how to build a process monitoring model and implement it using the SIMCA and SIMCA-Online software suite from our partner Sartorius.

During this 45-minute webinar, you will discover how these techniques can:

• improve process understanding and control
• enhance product quality
• optimize operational efficiency
• develop and implement process monitoring models using SIMCA^® and SIMCA^®-Online software

Sébastien Preys
Project manager, Ondalys

Registration to the webinar in English on Oct 15, 2024 at 5pm

During this webinar, you will discover real-time monitoring by combining spectral data with multivariate process parameters such as temperature, pH, etc. for process real-time supervision.

You will learn how to achieve consistent quality control by developing and implementing robust data analysis and machine learning models with SIMCA^® and SIMCA^®-Online and consistently meet quality requirements.

You will see how to optimize the Process Development phase by exploring methods to make the most of your resources and drive operational efficiency.

With a rich experience in Chemometrics and Machine Learning for process supervision, Sébastien Preys will share his expertise with you.

Don’t miss this opportunity to enhance your knowledge and discover the latest innovations in the field of industry 4.0.

To know more about process monitoring, look at our dedicated article.

The post October 15, 2024 – Webinar on batch process monitoring with Sartorius appeared first on Ondalys.

Chemomics aims to bring together the 2 communities of Chemometrics and Metabolomics to improve the understanding of the chemometrics and metabolomics methods and to build methodological bridges between these two communities.

Discussions and exchanges will be the priority of this school. Chemomics is organized on the principle of the barcamp and workshops whose content is adapted to the participants expectations.

3 thematic days will be dedicated to

• the regression, linear and non-linear alternative methods
• the discrimination
• the exploratory and discriminant multi-block methods, time effect

This shcool will be led by experts in Chemometrics and/or Metabolomics: Julien Boccard, Jean-Claude Boulet, Marion Brandolini-Bunlon , Binta Diémé, Mohamed Hanafi, Benoit Jaillais, Eric Latrille, Jean-Michel Roger, Virginie Rossard, Douglas Rutledge, Rémi Servien.

The aim of this 4th edition is to increase synergies between these two communities, and to initiate areas of joint work that will continue beyond the school.

Ondalys, an expert in Chemometrics and Machine Learning, supports its clients in the analysis of OMICS data (chromatography, NMR, mass spectrometry, etc.). Visit our page dedicated to physico-chemical data analysis

The post September 30 to 3 October 3, 2024 – Chemomics IV in Montpellier appeared first on Ondalys.

Ondalys will participate in the 9th Bioproduction Congress – BIOPC2024, organized by MabDesign on 25 & 26 of September 2024, in Tours.

This congress will be an opportunity for the partners of the CLIMBIN collaborative project to present the progress of their research work.

Indeed, on this occasion, Igor Chourpa, from the NMNS laboratory of the University of Tours, coordinator of the CLIMBIN project will speak about:

Molecular optical spectroscopy as
a PAT tool in USP bioprocessing

He will give an overview of advances in implementation of molecular optical spectroscopy as a PAT tool in upstream processing of therapeutic antibodies. The CLIMBIN project uses Rayleigh and Raman spectroscopies for quantitative monitoring of multiple critical process parameters (CPPs).

The R&D work carried out makes it possible to improve the relevance and robustness of PAT approaches in terms of

• measuring instrument,
• data processing using advanced Machine Learning methods,

for the purpose of industrial implementation of the PAT approach.

Come and meet the project partners in the occasion of this BIOPC2024 congress:

• the NMNS – Nanomedicines and NanoSondes – laboratory from the University of Tours
• LRGP – Reactions and Process Engineering – Laboratory from the University of Lorraine / CNRS
• the Bio3 of the University of Tours – IMT group
• INDATECH – Chauvin Arnoux
• Ondalys
• Technologie Servier

To know more on CLIMBIN project

You wish to improve your knowledge on how to implement a PAT approach using data analysis and Machine Learning for bioproduction monitoring ? Look at our webpage dedicated to PAT – Process Analytical Technology and QbD – Quality-by-Design.

The post September 25 & 26, 2024 – CLIMBIN’s results presented at BIOPC2024 Congress appeared first on Ondalys.

The Analytical Chemistry team of Nano-Medicine and Nano-Probe (NMNS) of the University of Tours organizes the 1^st Bio-processing Tours, a workshop dedicated to bioproduction in Tours on September 6^th, 2024.

On this occasion, with its partners NMNS ans INDATECH, the Ondalys team will present the results of the data analysis works carried out as part of the CLIMBIN project.

This day will focus on 3 essential points of bioproduction : USP – Upstream process, DSP – Downstream process and PAT – Process Analytical Technology.

This will be the opportunity to bring together French and European key players in bio-production, in order to exchanges, develop knowledge and new synergies between the various research projects.

The provisional program promises high-quality presentations with speakers such as:

• Sylvain Arnould, Technologie Servier
• Ioscani Jimenez Del Val, Univeristy College Dublin
• Patrick Perré, Centrale Supélec
• Michael Buler, NIBRT
• David James, Advanced Biomanufacturing Centre
• Gregory Batt, INRIA/ Institut Pasteur
• Annina Kemmer, Technische Universität Berlin
• Igor Chourpa, Université de Tours
• Julien Louet, INDATECH
• Sylvie Roussel, Ondalys

???? Visit the workshop website to know more about Bio-processingTours 2024

The CLIMBIN project, presented at the Bioprocessing Tours 2024, aimed to provide the bio-production sector with an innovative solution in Process Analytical Technology using Molecular Optical Spectrometry adapted to suspended cultures (CHO, etc.) in various types of bioreactors. For this project, the partners used Raman and Rayleigh spectroscopies for quantitative monitoring of several critical process parameters (CPP).

The post September 6, 2024 – Workshop Bio-processing Tours 2024 appeared first on Ondalys.

Register to the webinar :

Take on the challenge of modeling complex spectroscopic data using Machine Learning

On May 30, 2024 at 11 am (CEST), Astrid Maléchaux will present the most common advanced machine learning methods. During this 45-minute webinar, you will discover ML’s methods to go further in the analysis of your complex spectroscopic data.

These methods are usually used to:

• deal with non-linear relationships
• analyze heterogeneous databases
• predict complex parameters
• take into account variability factors
• and all this even with few samples!

Program of the webinar:

• What do we call complex data?
• Overview of Machine Learning Methods
• Local Regression (LWR)
• Support Vector Machines (SVM)
• Artificial neural networks (ANN)
• Decision trees and ensemble methods (CART and RF / XGBoot)
• Comparison between methods on a practical case
• Conclusion
• Questions & answers

Astrid Maléchaux,
Data Scentist Ondalys

Registration

For each Machine Learning method, the optimization of the model as well as the advantages and disadvantages will be detailed. They will be illustrated by a practical case and a comparison with PLS (Least Squares Regression Method).

With a strong experience in Chemometrics and Machine Learning, Astrid Maléchaux will share her expertise with you.

The Ondalys team supports its industrial clients in processing their complex data. Whether it is instrumental data (spectroscopic data, hyperspectral images, etc.), physico-chemical data (chromatography data, OMICS, etc.) or process data, Ondalys supports you to optimize their analysis and extract all relevant information.

The post May 30, 2024 – Webinar on advanced methods of Machine Learning appeared first on Ondalys.

It is a pleasure for the Ondalys team to participate this year again to the France bioproduction 2024 congress – CFB 2024, organized by POLEPHARMA and Medicen on April 3 and 4, 2024 at the Paris-Saclay Convention Center in Massy.

Sponsor of the congress, the Ondalys team is waiting for you on booth n ° 17 to discuss the topics of Data Analysis, Machine Learning and Artificial Intelligence (AI) for PAT (Process Analytical Technology) implementation and production in the Biotechs.

During this congress, Sandra Aubert will present with our partner Sartorius a workshop entitled :

Machine Learning
for cell culture monitoring in bioreactor

The discussion will focus on monitoring cell cultures in bioreactors and large databases, process parameters, online measurements such as oxygen or pH, and data from online analyzers like Raman spectroscopy, at-line measurements, etc.

The importance of data analysis and Machine Learning to best extract the information contained in these large and complex databases will also be emphasized. Furthermore, the discussion will address how the developed models enable optimal characterization of the bioreactor’s behavior, either by predicting Critical Quality Attributes (CQAs) during the culture process or by globally monitoring the process

The workshop will consist of two phases, blending theory and practice. One part will be dedicated to presenting bioreactors and data collection, and the other to creating models for monitoring concentrations in bioreactors along with a demonstration.

The workshop will consist of 2 phases, mixing theory and practice. The firts part will be dedicated to the presentation of bioreactors and the data collect; the second one to the models development for concentration monitoring in bioreactors. It will be illustrated by a demonstration.

???? More information about the congress on the France Bioproduction 2024 website.

Look at Sylvie Roussel interview (in French)
during France Bioproduction Congress 2024

To know more about Machine Learning and data analysis for the bio-pharmaceutical and biotechnology industries,
have a look to our dedicated pages.

The post April 2024 – France bioproduction Congress – Polepharma – CFB 2024 appeared first on Ondalys.

The post The Ondalys team wishes you a vibrant and bright year 2024! appeared first on Ondalys.

How to process hyperspectral images ?

During this webinar, Julien Boyer from Ondalys and Mathieu Marmion from Specim, a manufacturer of hyperspectral imaging solutions, will present everything you need to know to optimize the acquisition and processing of hyperspectral images.

Discover step by step the methodology for analyzing hyperspectral images, from their acquisition, to the application of chemometrics / Machine Learning methods to images, including image processing methods for their segmentation.

• What’s a hyperspectral image ?
• Recommendation for image acquisition
• Hyperspectral image analysis methodology
• Application example for quantitative prediction
• Questions / Answers

Come and listen to the experts in Machine Learning and hyperspectral imaging, from Ondalys and Specim :

Julien Boyer – Ondalys and Mathieu Marmion – Specim

accompanied by Alice Croguennoc and Jordane Poulain – Ondalys

Webinar registration

This webinar will be illustrated by a practical case of hyperspectral image processing carried out using SOLO+MIA from our partner Eigenvector Research Inc.

The application example presented comes from our collaboration on the VINIoT SUDOE project supported by INRAE and l’Institut français de la vigne et du vin (IFV).

Ondalys is a reseller of chemometrics, machine learning and hyperspectral image analysis software from Eigenvector Research Inc.

If your are interested in MIA_Toolbox or MIA+SOLO software, image processing software, contact-us.

To go further… What is the analysis of hyperspectral or multispectral images and how is Machine Learning interesting in the processing of these images?

A hyperspectral (or multispectral) imager is an imaging system for acquiring images in which each pixel contains data representing a broad electromagnetic spectrum (for example near infrared, infrared, Raman spectrum). Unlike traditional imaging which records only three spectral bands (red, green and blue) and only allows spatial analysis of colour, hyperspectral imaging records hundreds of spectroscopic wavelengths, allowing chemical analysis of products. This is why hyperspectral imaging is also called chemical imaging.

So, if you want to collect the same chemical information as that of a near-infrared spectrometer but spatialized, then a near-infrared hyperspectral imager is the suitable sensor! Because it makes it possible to obtain spatial chemical information, which is very useful in the case of heterogeneous samples (heterogeneous solid samples, powders, mixtures, etc.).

This technique finds applications in many industrial fields such as agriculture, the pharmaceutical and chemical sectors, remote sensing, and scientific research. For example, in agriculture, hyperspectral image analysis can detect crop diseases, optimize fertilizer use, and monitor plant growth. In the pharmaceutical industry, particularly in the quality control of raw materials and finished products, hyperspectral imaging makes it possible to characterize the homogeneity of powders and detect the presence of agglomerates, verify the integrity of lyophilisates of biotechnology products, prove the tablet compliance. In the field of environmental monitoring and remote sensing, it can detect and monitor water, air and soil pollution.

Hyperspectral image analysis has many advantages over traditional imaging techniques. It allows more precise identification of products based on their chemical composition, better discrimination between visually similar products, and more sensitive detection to subtle changes such as particle size or molecular composition. However, manually analyzing these images can be time-consuming and tedious, requires extensive expertise and is sometimes simply impossible! This is where chemometric methods and Machine Learning applied to spectroscopy and imaging come in to enable this analysis and provide classification results (e.g., compliant or non-compliant tablet) or quantification results (e.g. example, the distribution of sugar concentration in the grains of a bunch of grapes).

The post November 28, 2023 – Webinar on hyperspectral image processing appeared first on Ondalys.

Member of MabDesign, Ondalys will attend this congress in Lyon

The Bioproduction Congress is the yearly event of the biopharmaceutical production field where european stakeholders gather together to discuss about the latest innovations in bioprocessing.

Machine Learning and data analysis (Chemometrics), play a crucial role in improving bioproduction.

Experts in data analysis and Machine Learning, we developed a strong experience in the field of biotechs industry. These skills allow us to decipher the complex data of the biomedicine industry and offer solutions for process optimization.
With our expertise, we offer tailor-made and innovative solutions that help biotechnology companies solve production problems, optimize yields and make informed decisions.

Look at our know-how for biotechs and biopharmaceuticals industries :

– Machine Learning and data analysis for your PAT and QbD procedures
– the supervision of industrial bioprocesses

 MabDesign is the French biotherapy industry association. Founded in 2014, MabDesign aims to structure the biopharmaceutical industry in France from the R&D stages to production and marketing of biopharmaceuticals. It also aims to support the creation of innovative startups from academic research.

The post 5 & 6 October 2023, Bioproduction congress in Lyon appeared first on Ondalys.