Mediaboss Marketing

Machine learning shows promise as a complementary approach to chromatographic (mixture separation) techniques for assessing biosimilarity and stability, according to a recent study.

Investigators evaluated machine learning vs chromatographic analysis in the study of 3 trastuzumab biosimilars and their reference product (Herceptin) under control and stress conditions. They concluded the machine learning results correlated with the chromatographic data and revealed patterns elucidating the effects of pH and thermal stress conditions.

Trastuzumab, a monoclonal antibody to human epidermal growth factor receptor 2 (HER2), is approved as a treatment for metastatic breast cancer, early breast cancer, and metastatic gastric cancer. The investigators found that the biosimilars showed high similarity under control conditions, but differences in degradation patterns were detected underforced degradation conditions in the study.

First, physicochemical characteristics of the reference product and biosimilar trastuzumab products (approved for use in Egypt; and referred to as B1, B2, and B3 in the study) were determined by size exclusion chromatography, cation exchange chromatography, and peptide mapping. The biologics were evaluated under control conditions and under pH and thermal stress. The investigators then used unsupervised machine learning techniques to find patterns in the chromatographic data.

Chromatographic Analysis

The authors said primary structure and size and charge variants are quality attributes expected to affect the quality, safety, and efficacy of biologic drugs including trastuzumab. These attributes were similar in the biosimilars and reference product under control conditions, the authors found.

Thermal and pH stress, the authors noted, are among the most studied stress conditions in forced degradation studies due to their direct effect on the size and charge variant profiles of [monoclonal antibodies] mAbs through deamidation and oxidation. Under thermal and pH stress, the investigators did find differences in the degradation of the different products.

Size variants

Based on size exclusion chromatography, B2 and B3 showed a tendency to form high- and low-molecular weight variants under acidic and basic stress, and B2 showed 83% degradation by the 2-week time point under acidic stress. Under thermal stress, B3 showed the greatest degradation, 39% after 2 weeks.

Charge variants

Under acidic stress, the products varied from 19.9% degradation of the main variant of the reference product at 2 weeks to 93% for B2. Under basic stress, all samples showed a comparable increase in abundance of acidic variants. Under thermal stress, the charge variant distribution of B2 and B3 were similar to charge variant distribution for the reference product, while B1 showed a greater abundance of acidic variants.

Principal Component Analysis

The investigators used unsupervised machine learning techniques, which find patterns in data with no prior training or predefined subcategories. Principal component analysis (PCA) is a method for reducing complexity in high-dimensional data to a small number of components that explain the greatest percentage of the variance in the data set.

The authors plotted size exclusion chromatography and cation exchange chromatography data on 2-dimensional coordinates representing the 2 components (PC1 and PC2) that explained the most variance to identify patterns in the data. Primary component analysis of chromatographic and peptide mapping data of the control samples showed no outliers, which the authors said supports biosimilarity of the products.

The plot of control and acidic stressed samples showed that the control samples were separated along the primary component 1 (PC1) axis, while the stressed samples were distributed along the PC2 axis. Samples of the same product were clustered relevantly close to each other, the authors said, and their PCA results on control and acidic-stressed samples suggested 41% of the variance in the data was due to the applied stress, and 25% was due to inherent differences in the chromatographic profiles of the products.

Clustering Analysis

The investigators also used 2 clustering techniques, k-means and density-based spatial clustering of applications with noise (DBSCAN), on the data from the top 2 PCs from their primary component analysis. According to the authors, cluster analysis is an unsupervised exploratory technique aiming to find natural grouping in data so that items in the same cluster are more similar to each other than to those from different clusters.

Due to the inherent variability and large number of possible structural variants of monoclonal antibodies, the authors said, machine learningaided approaches have great value for assessing their critical quality attributes. They cited previous research using PCA to reveal patterns in the data on biosimilarity and stability of other biologics, recombinant human growth hormone and infliximab.

K-means clustering of the unstressed samples segregated the products into 3 clusters, with the reference product and B2 each forming their own cluster, and B1 and B3 allocated to the same cluster. DBSCAN segregated each product to its own cluster.

K-means clustering was able to separate control and pH-stressed samples into different clusters, although B2 control samples were clustered with the stressed reference product and B3 samples. Cluster analysis suggested B3 was most similar to the reference product under acidic stress, while B2 was most similar under thermal stress, and all products had a similar response to basic pH stress. The greatest variability between control samples was between the reference product and B2.

Finally, application of principal component and clustering analyses to the collective data set from all the applied chromatographic techniques supported biosimilarity of the products, the authors said. This principal component analysis identified no samples that were significantly different from the others; k-means identified 3 clusters (reference product, B1 + B3, and B2), and DBSCAN identified 4 clusters, one containing each product.

The authors concluded their results supported the biosimilarity of the products analyzed, and highlighted that regarding the charge and size profiles of the studied products, B2 showed higher variability (than B1 and B3) compared to HC under both control and stress conditions. They said that the chromatographic fingerprints and machine learning results were correlated and were able to reveal patterns related to the effect of different stress conditions on the different investigated products. They recommended future studies explore other machine learning tools to interpret physicochemical data on biologic products.

For Further Reading

The European Medicines Authority reports on a pilot experiment in tailoring development of biosimilars, or eliminating unnecessary testing, and the World Health Organization develops guidelines to support the tailoring concept.

Reference

Shatat SM, Al-Ghobashy MA, Fathalla FA, Abbas SS, Eltanany BM. Coupling of trastuzumab chromatographic profiling with machine learning tools: a complementary approach for biosimilarity and stability assessment. J Chromatogr B Analyt Technol Biomed Life Sci. 2021;1184:122976. doi:10.1016/j.jchromb.2021.122976

Read more:
Machine Learning Clarifies Stress-Based Degradation of Biosimilars - The Center for Biosimilars

26 November 2021

Sheppard Mullin Richter & Hampton

To print this article, all you need is to be registered or login on Mondaq.com.

The Food and Drug Administration recently sought comments on therole of transparency for artificial intelligence and machinelearning-enabled medical devices. The FDA invited comments infollow up to a recent workshop on the topic.

The workshop was part of a series of efforts the FDA has had inthis space. These include its Digital Health Center ofExcellence and a five-part Action Plan for AI andmachine-learning enabled medical devices. As part of the actionplan, the FDA indicated it wants to issue guidance on softwarelearning over time and help the industry be"patient-centered." In other words, that companies betransparent when using AI and machine learning-enabled softwarewith patients. These initiatives are especially important given theincrease in AI/ML in healthcare.

Workshop participants explored how to provide transparency. One idea proposed was using a "nutritionfact label" approach to give individuals enough information tomake informed decisions. The graphic would be similar to a foodlabel, disclosing quickly and visually the key things patientsmight want to know. (This is similar to an approach launched byApple late last year, which we discussed here.) Other agencies havelooked at machine learning and AI with similar transparencyrecommendations. We have written about those in the past, includingfor the financial servicesindustry. Advice about use of these tools has also been issuedby the FTC and the EU.

Putting it Into Practice: While the FDA continues toexplore this area, companies are reminded that the FDA (like otherregulators) expects transparency with consumers. From a privacyperspective, the workshop reminds digital health companies thisincludes telling users when AI or ML-enabled software is beingused.

The content of this article is intended to provide a generalguide to the subject matter. Specialist advice should be soughtabout your specific circumstances.

POPULAR ARTICLES ON: Technology from United States

Willkie Farr & Gallagher LLP

Last week, the Federal Trade Commission ("FTC") amended its Gramm-Leach-Bliley Act ("GLBA") Safeguards Rule (or "Rule") to, among other things, modify the scope of companies...

Bull Blockchain Law LLP

Virtual Currencies Comparative Guide for the jurisdiction of United States, check out our comparative guides section to compare across multiple countries

Read more here:
FDA Joins Other Regulators In Focus On AI And Machine Learning - Technology - United States - Mondaq News Alerts

IBM Research Europe and Thieme Chemistry have announced the first results of their collaboration which were evaluated by seven eminent synthetic chemistry experts and their research groups from China, Germany, Switzerland, New Zealand, and the USA.

Professor Dame Margaret Brimble from the University of Auckland, New Zealand comments: This innovative IBM/Thieme Chemistry platform provides an efficient tool for synthetic chemistry researchers to provide validation for their own retrosynthetic plans whilst also being presented with alternative solutions. It enables a rigorous assessment for the retrosynthetic design phase of a given synthesis which no doubt will pay dividends when the selected synthetic plan is implemented.

The partnership between IBM Research Europe and Thieme Chemistry builds on the synergies between high-quality data and state-of-the-art machine learning models for organic chemistry synthesis predictions. RXN For Chemistry, a cloud platform using artificial intelligence (AI) has recently been trained with high quality, human-curated datasets from Thiemes Science of Synthesis and Synfacts.

Organic compounds can react with each other in hundreds of thousands different ways. Experiential knowledge is key for organic chemists to avoid spending hours and hours in the laboratory with countless trials and errors. To improve synthesis planning, IBM Research and Thieme Chemistry have combined the expert human-curated datasets from Thiemes full-text resource for methods in synthetic organic chemistry, Science of Synthesis, and the reviewed content from the journal Synfacts with the artificial intelligence model called Molecular Transformer in RXN for Chemistry by IBM.

The Molecular Transformer, a neural machine translation model, was created to reliably predict the outcome of chemical reactions and was later enhanced to include retrosynthetic analysis i.e. to first determine the chemicals needed to create a given target molecule. The model has proven to be very successful at learning the information of chemical reactivity present in datasets of chemical reactions. It is, however, limited to the content and correctness of these datasets.

Science of Synthesis and Synfacts cover a wide area of reaction space. Typically, models trained on commercially available patent datasets perform poorly on many such reactions. Science of Synthesis and Synfacts have a higher quality of chemical records, reflected by a larger percentage of usable records. This consistency in Thiemes dataset facilitates the learning process of the AI models, resulting in more consistent predictions: Results show that Thieme-trained models on the RXN for Chemistry platform increase prediction accuracy by a factor of three for forward predictions, and a factor of nine for retrosynthesis.

The collaborative work between Thieme and IBM Research Europe shows the impact high-quality chemical reaction data can have on future AI chemical synthesis tools. Integrating high-quality, curated data from Science of Synthesis and Synfacts provides a unique opportunity to boost the performance of RXN for chemistry to unprecedented levels as it unleashes the entire knowledge contained in hundreds of thousands of chemical reaction records.

Professor Richmond Sarpong from the University of California, Berkeley, USA states: A sustainable future for synthesis will include minimising the number of unproductive strategies that are pursued by running only those reactions that lead to a productive end. This is only possible through the marrying of computer designed and human-designed efforts, which makes this collaboration with IBM and Thieme Chemistry exciting.

Also involved in testing the retrained models were Professor Alois Frstner (MPI Mlheim, Germany), Professor Karl Gademann and Professor Cristina Nevado (University of Zurich, Switzerland), Professor Ang Li (Shanghai Institute of Organic Chemistry, China), Professor Dirk Trauner (New York University, USA) and their research groups.

View post:
IBM Research and Thieme Chemistry partnership brings together machine learning and human-curated data - Scientific Computing World

IBL News | New York

Artificial Intelligence (AI) and machine learning, cloud computing, and 5G will be the most important technologies in 2022, according to a survey to global technology leaders from the U.S., U.K., China, India, and Brasil, conducted by IEEE.

These 350 chief technology and information officers and IT directors agreed that the pandemic accelerated the adoption of those tools.

The survey, titled The Impact of Technology in 2022 and Beyond: an IEEE Global Study, stated that 95% of tech leaders said that AI will drive the majority of innovation across nearly every industry sector in the next 1 to 5 years.

These surveyed executives consider eight areas as most benefited from 5G:

As for industry sectors impacted by technology in 2022, technology leaders cited manufacturing (25%), financial services (19%), healthcare (16%), and energy (13%).

In terms of workplace strategies and technologies, respondents say that their companies are working closely with Human Resources to implement tools for office check-in, space usage data and analytics, COVID and health protocols, employee productivity, engagement, and mental health.

Looking ahead, 81% agree that in the next five years, one-quarter of what they do will be enhanced by robots, and 77% agree that in the same time frame, robots will be deployed across their organization to enhance nearly every business function from sales and human resources to marketing and IT.

A majority of respondents agree (78%) that in the next ten years, half, or more, of what they do will be enhanced by robots. As for the deployments of robots that will most benefit humanity, according to the survey, those are manufacturing and assembly (33%), hospital and patient care (26%), and earth and space exploration (13%).

Regarding blockchain technology, the most important uses in the next year will be:

See the rest here:
AI and Machine Learning, Cloud Computing, and 5G Will Dominate in 2022 - IBL News

This artist's illustration shows the planetary system K2-138, which was discovered by citizen scientists in 2017 using data from NASA's Kepler space telescope.

After the first exoplanet was identified almost three decades earlier, in 1992, humanity has come a long way in terms of exoplanet discovery. As of today, we have spotted over 4000 validated exoplanets that revolve around their respective suns.

Exoplanets are celestial bodies that exist outside our vast solar system. Equipped with cutting-edge technology, many research groups have been identifying these exoplanets left, right and centre.

However, for the first time ever, 301 validated planets were added to the ever-growing exoplanet tally all at once!

Wondering how? The US space agency NASA reported that a new deep neural network called 'ExoMiner' was responsible for this incredible scientific feat.

The ExoMiner leverages NASA's Pleiades supercomputer and, like any deep neural network, can automatically learn a task when provided with enough data. ExoMiner is designed with various tests, properties human experts use to confirm new exoplanets, past confirmed exoplanets, and false-positive cases in mind. Thus, it could tell apart actual exoplanets from imposters, making this technology and its predictions highly reliable.

"Unlike other exoplanet-detecting machine learning programs, ExoMiner isn't a black boxthere is no mystery as to why it decides something is a planet or not," said Jon Jenkins, an exoplanet scientist at NASA's Ames Research Center in California's Silicon Valley. "We can easily explain which features in the data lead ExoMiner to reject or confirm a planet."

It is a highly tedious process to comb vast datasets from missions like Kepler, which has hundreds of stars in its range of view, each with the potential to house numerous possible exoplanets. In such cases, the ExoMiner is the perfect substitute as it reduces the burden of astronomers in sifting through data and determining what is and isn't a planet.

"When ExoMiner says something is a planet, you can be sure it's a planet," said Hamed Valizadegan, ExoMiner project lead and machine learning manager with the Universities Space Research Association at Ames. "ExoMiner is highly accurate and in some ways more reliable than both existing machine classifiers and the human experts it's meant to emulate because of the biases that come with human labelling."

NASA said that all 301 machine-validated planets were originally detected by the Kepler Science Operations Center and were promoted to planet candidate status by the Kepler Science Office. But until ExoMiner, no one was able to validate them as planets.

And while none of the newly discovered planets is thought to be Earth-like or in their parent stars' habitable zones, they share some traits with the rest of the verified exoplanet population in our galaxy.

According to Jon Jenkins, the 301 discoveries will help researchers better understand planets and solar systems beyond our own and what makes ours so unique.

**

For weather, science, and COVID-19 updates on the go, download The Weather Channel App (on Android and iOS store). It's free!

Read this article:
ExoMiner Goes Planet Hunting! NASA's Machine Learning Network Validates 301 New Exoplanets at One Go | The Weather Channel - Articles from The Weather...