Page 909«..1020..908909910911..920930..»

Machine learning tool simplifies one of the most widely used reactions in the pharmaceutical industry – Phys.org

This article has been reviewed according to ScienceX's editorial process and policies. Editors have highlighted the following attributes while ensuring the content's credibility:

fact-checked

peer-reviewed publication

trusted source

proofread

close

In the past two decades, the carbon-nitrogen bond forming reaction, known as the Buchwald-Hartwig reaction, has become one of the most widely used tools in organic synthesis, particularly in the pharmaceutical industry given the prevalence of nitrogen in natural products and pharmaceuticals.

This powerful reaction has revolutionized the way nitrogen-containing compounds are made in academic and industrial laboratories, but it requires lengthy, time-consuming experimentation to determine the best conditions for a highly effective reaction.

Now, Illinois researchers in collaboration with chemists at Hoffman La-Roche, a pharmaceutical company in Switzerland, have developed a machine learning tool that predicts in a matter of minutes the best conditions for a high-yielding reaction with no lengthy experimentation.

In a recently published article in Science, Illinois chemistry professor Scott Denmark and Ian Rinehart, a recent Ph.D. graduate in the Denmark lab, describe how they developed, trained, and tested their machine learning model to drastically accelerate the identification of substrate-adaptive conditions for this palladiumcatalyzed carbon-nitrogen bond forming reaction.

Denmark said this reaction is a very general transformation so there is much structural diversity among reactant pairings and a lot of "levers to pull" to make it work.

"And that's what we have figured out," Denmark said.

close

User guides and cheat sheets have evolved in the nearly 30 years since this reaction was discovered, and they can provide some direction, Rinehart explained, but experimentation is often necessary. Basically, a trial-and-error process in a lab.

"It's a problem that everyone in the pharmaceutical industry recognized was ripe for intervention by informatics methods," Denmark said. "Lots of people have tried to use the US Patent and Trademark Office or Chemical Abstracts or other huge databases to try to model to make predictive tools for this one very important reaction. But they haven't been able to do very well because the information in the literature is just not very reliable."

The design and construction of their machine learning tool required the generation of an experimental dataset that explores a diverse network of reactant pairings across a set of reaction conditions. A large scope of CN couplings was actively learned by neural network models by using a systematic process to design experiments.

The challenge for a project like this, Denmark said, was the amount of potential data to collect and the thousands and thousands of experiments required to build a database of information for modeling.

"One of Ian's biggest contributions was figuring out the workflow to decide what experiments to do to get a valid predictive model with about 3,500 experiments and still be able to make predictions without an enormous database," Denmark said.

They also experimentally validated the predictions from the machine learning tool.

"We tested them and found with pretty good statistics that the conditions were producing compounds when we expected," Denmark said.

The researchers report that their models showed good performance in experimental validation: Ten products were isolated in more than 85% yield from a range of couplings with out-of-sample reactants designed to challenge the models.

Rinehart said they taught machine learning models to have a kind of chemical intuition like what an expert has.

"So, we have now run or talked about so many of these couplings that we have a good intuition about what's going to happen, but someone who hadn't run hundreds or thousands of these might not have a good first guess. We have taught a model at a much more granular level [than user guides] to have an intuition. It's not perfect. But that's kind of the point. It doesn't have to be. It just has to get you to the answer faster," Rinehart said.

And the coolest part, Rinehart explained, is that intuition gets honed over time as more people use the machine learning tool. The developed workflow continually improves the prediction capability of the tool as the corpus of data grows.

"It's an exciting time as data science merges with chemistry," Denmark said. "And this is the perfect marriage. A lot of people recognized this, but no one has done it, at least not in a meaningful way that is experimentally validated."

The Denmark group is creating a cloud-based version of the workflow to enable scientists around the world to use this tool which will continuously add data to improve the model as more structurally diverse substrates are tested and different catalysts and conditions are added to the database.

Rinehart said the code is public and on an open-source license, so anyone can download and use it. Also, he is currently working on a more user-friendly interface that will allow someone to draw the two molecules they want to react, copy and paste them into the program, and get predictions in minutes instead of hours, depending on the complexity of the molecules.

"I think it's really exciting to do something like that," Rinehart said. "We don't often publish a paper and put out a tool in the public domain that people can use in the field. People in academic labs like ours could use this tool and get an answer faster in their own research."

More information: N. Ian Rinehart et al, A machine-learning tool to predict substrate-adaptive conditions for Pd-catalyzed CN couplings, Science (2023). DOI: 10.1126/science.adg2114

Journal information: Science

Go here to see the original:
Machine learning tool simplifies one of the most widely used reactions in the pharmaceutical industry - Phys.org

Read More..

UWMadison part of effort to advance fusion energy with machine … – University of Wisconsin-Madison

Steffi Diem (middle) participating in a panel at the White House Summit on Developing a Bold Decadal Vision for Commercial Fusion Energy. Diem has joined a collaboration across multiple institutions that will use machine learning to better understand magnetic fusion energy.

Researchers at the University of WisconsinMadison are taking part in a new collaboration built on open-science principles that will use machine learning to advance our knowledge of promising sources of magnetic fusion energy.

The U.S. Department of Energy has selected the collaboration, led by researchers at the Massachusetts Institute of Technology, to receive nearly $5 million over three years. The teams including researchers at UWMadison, William & Mary, Auburn University and the HDF group (a non-profit data management technology organization) are tasked with creating a platform to publicly share data they glean from several unique fusion devices and optimize that data for analysis using artificial intelligence tools. Student researchers from each institutionwill also have an opportunity to participate ina subsidized summer program that will focus on applying data science and machine learning to fusion energy.

The data sources will include UWMadisons Pegasus-III experiment, which is centered around a fusion device known as a spherical tokamak. Pegasus-III is a new Department of Energy funded experiment that began operations in summer 2023 and represents the latest generation in a long-running set of tokamak experiments at UWMadison. A primary goal of the experiment is to study innovative ways to start up future fusion power plants.

Im incredibly excited to be a part of projects like this one as we continue to push innovation both in the analysis and development of experimental devices and diverse workforce development initiatives, says Steffi Diem, a professor of nuclear engineering and engineering physics, who leads the Pegasus-III experiment.

Diem is an emerging leader in the fusion research world. In 2022, she was invited to present at the White Houses Bold Decadal Vision for Commercial Fusion Energy that launched several efforts focused on commercializing fusion energy. In a field traditionally dominated by men, Diem is also one of four women leading the new collaboration.

UWMadison researchers are using the new Pegasus-III experiment to study innovative techniques for starting a plasma. Joel Hallberg

Throughout much of my career, I have often been one of the few women in the room, so it is great to be a part of a collaboration where four out of the five principal investigators are women, Diem says.

The collaboration is based around the principles of open science Diem and her colleagues will make the wealth of data coming from Pegasus-III and other fusion experiments more accessible and usable to others, particularly for machine learning platforms.

While this approach is designed to accelerate knowledge of magnetic fusion devices, its also aimed at providing a more accessible path into fusion research programs for students with wider skillsets and backgrounds, particularly in data sciences. Building a more diverse fusion workforce will be tantamount going forward, says Diem.

Fusion isnt just plasma physicists anymore, she says. As fusion moves out of the lab and toward the goal of providing clean energy to communities, it requires an interdisciplinary approach with engineers, data scientists, skilled technical staff, community members and more.

UWMadison is supporting a broader push to diversify the fusion field. Some of the student researchers who will be participating in the new collaboration are part of the student-led Solis group, which provides gender-inclusive support for students studying plasma physics on campus.

The new collaboration fits well with Diems other research, funded through the Wisconsin Alumni Research Foundation, focused on reimagining fusion energy system design. That work centers energy equity and environmental justice early in the design phase to support a just and equitable energy transition.

While there are still many challenges that lie ahead for fusion, the potential benefits are huge as we drive towards a cleaner, more sustainable, equitable and just future, says Diem.

Continued here:
UWMadison part of effort to advance fusion energy with machine ... - University of Wisconsin-Madison

Read More..

Revolutionizing Drug Development Through Artificial Intelligence … – Pharmacy Times

The field of drug development stands at a pivotal crossroads, where the convergence of technological advancements and medical innovation is transforming traditional paradigms. At the forefront of this transformation lies artificial intelligence (AI) and machine learning (ML), powerful tools that are revolutionizing the drug discovery and development processes. The seamless integration of AI/ML has the potential to accelerate research and enhance efficiency in a new era of personalized medicine.

Image credit: Tierney | stock.adobe.com

The FDA acknowledges the growing adoption of AI/ML across various stages of the drug development process and across diverse therapeutic domains. There has been a noticeable surge in the inclusion of AI/ML components in drug and biologic application submissions in recent years.

Moreover, these submissions encompass a broad spectrum of drug development activities, spanning from initial drug discovery and clinical investigations to post-market safety monitoring and advanced pharmaceutical manufacturing.1 In a recent reflection paper, the European Medicine Agency acknowledges the rapid evolution of AI and the need for a regulatory process to support the safe and effective development, regulation, and use of human and veterinary medicines.2

AI and ML tools possess the capability to proficiently aid in data acquisition, transformation, analysis, and interpretation throughout the lifecycle of medicinal products. Their utility spans various aspects, including substituting, minimizing, and improving the use of animal models in preclinical development through AI/ML modeling approaches. During clinical trials, AI/ML systems can assist in identifying patients based on specific disease traits or clinical factors, while also supporting data collection and analysis that will subsequently be provided to regulatory bodies as part of marketing authorization procedures.

AI/ML technologies offer unprecedented capabilities in deciphering complex biological data, predicting molecular interactions, and identifying potential drug candidates. These technologies empower researchers to analyze vast datasets with greater speed and precision than ever before. For example, AI algorithms can sift through enormous databases of chemical compounds to identify molecules with the desired properties, significantly expediting the early stages of drug discovery.

One of the critical challenges in drug development is the identification and validation of suitable drug targets. AI/ML algorithms can analyze genetic, genomic, and proteomic data to pinpoint potential disease targets. By recognizing patterns and relationships in biological information, AI can predict the likelihood of a target's efficacy, enabling researchers to make informed decisions before embarking on laborious and costly experimental processes.

The process of screening potential drug candidates involves evaluating their impact on biological systems. AI/ML models can predict the behavior of compounds within complex cellular environments, streamlining the selection of compounds for further testing. This predictive approach saves time and resources, as only the most promising candidates advance to the next stages of development.

AI/ML-driven computational simulations are transforming drug design by predicting the interaction between molecules and target proteins. These simulations aid in designing drugs with enhanced specificity, potency, and minimal adverse effects. Consequently, AI-guided rational drug design expedites the optimization of lead compounds, fostering precision medicine initiatives.

The utilization of AI/ML in clinical trials has immense potential to improve patient recruitment, predict patient responses, and optimize trial designs. These technologies can analyze patient data to identify potential participants, forecast patient outcomes, and tailor treatment regimens for individual subjects. This leads to more efficient trials, reduced costs, and improved success rates.

Although the integration of AI/MI technologies into drug development has the potential to revolutionize the field, it also comes with several inherent risks and challenges that must be carefully considered:

AI and ML are reshaping the drug development landscape, from target identification to clinical trial optimization. Their ability to analyze complex biological data, predict molecular interactions, and expedite decision-making has the potential to accelerate drug discovery, reduce costs, and improve patient outcomes.

As AI/ML continues to evolve, it will undoubtedly play an increasingly pivotal role in driving innovation and transforming the pharmaceutical industry, leading us toward a more efficient and personalized approach to drug development and health care. Although AI and ML hold immense promise in revolutionizing drug development, their adoption is not without risks.

Careful consideration of these challenges, along with robust validation, regulation, and transparent reporting, are essential to harness the benefits of AI/ML while mitigating potential pitfalls in advancing pharmaceutical innovation.

References

Read more:
Revolutionizing Drug Development Through Artificial Intelligence ... - Pharmacy Times

Read More..

Open source in machine learning: experts weigh in on the future – CryptoTvplus

In a recent event by the University of California, Berkeley, focused on Open Source vs. Closed Source: Will Open Source Win? Challenges & Future in Open Source LLM, experts in the field of machine learning shared their insights into the role of open source technology in shaping the future of this dynamic industry.

In the world of AI development, the acronym LLM typically stands for Language Model, more specifically, Large Language Models. These sophisticated AI models are designed with the purpose of understanding and generating human language.

Through rigorous training using vast amounts of data, they acquire the remarkable ability to tackle diverse tasks like natural language understanding, text generation, and translation, among others. An exemplary illustration of such language models is GPT-3 (Generative Pre-trained Transformer 3).

Recently, the use of AI has become a huge topic for discussion around the world. An integral part of the conversation is whether open source will be the future of machine learning as it relates to AI or a closed system.

Ion Stoica, Professor of Computer Science at the University of California, Berkeley, outlined three key reasons why open-source technology will play a pivotal role in the future of machine learning.

Firstly, he said that the current limitation in the availability of high-quality data for training machine learning models is a challenge for further development.

However, with the use of open-source systems, more quality data becomes accessible, and the cost of training models will decrease, making larger models more effective.

Secondly, Ion pointed out that machine-learning technology is becoming increasingly strategic for many countries.

Unlike search technology which still requires human intervention, machine learning models can make autonomous decisions, rendering them highly valuable for specific applications.

He also added that there is a need for fine-tuning machine learning models for particular tasks rather than creating general-purpose models.

He believes that experts should focus on developing models that excel in specific use cases. And an open-source model will make this even easier to implement.

Another speaker at the event, Nazneen Rajani, Research Lead at Hugging Face, said that open-source technology is essential for crafting smaller, more specialized language models tailored for specific use cases.

She revealed that most companies and consumers do not require large, general intelligence models; instead, they need models that excel at specific tasks.

The Researcher also expressed excitement about Metas entry into the open-source arena, anticipating increased funding and resources for open-source projects, paving the way for further innovation and development.

In support of the first two speakers, Tatsunori Hashimoto, an Assistant Professor at Stanford University, proposed that language models could become a public good and serve as a foundational layer for intelligent agents.

He cited initiatives like the UKs Brit-GPT, government-run language models available to everyone, as examples. Once these models are open and accessible, they can form the basis of an open-source innovation ecosystem.

Tatsunori also noted that the future of open source depends on who provides the base layer and how much innovation is generated atop it.

More here:
Open source in machine learning: experts weigh in on the future - CryptoTvplus

Read More..

Machine-Learning Tool Sorts Tics From Non-Tics on Video – Medscape

COPENHAGEN A novel machine-learning tool that can distinguish between tics in patients with tic disorders and non-tic movements in healthy controls could potentially save clinicians time and improve the accuracy of tic identification, German researchers suggest.

Videos of more than 60 people with tic disorders were assessed manually to provide a set of clinical features related to facial tics. These were then fed into a machine-learning tool that was trained on nearly 290 videos of patients and controls, and then tested on a further 100 videos.

The resulting tool is "useful to detect tics and distinguish between tics and other movements in healthy controls, said lead author Leonie F. Becker, MD, Institute of Systems Motor Science, University of Lbeck, Lbeck, Germany, and colleagues.

The findings were presented here at the International Congress of Parkinson's Disease and Movement Disorders (MDS) 2023.

The applications of the machine-learning algorithm could eventually extend well beyond analyzing videos of patients recorded in the doctor's office, said Becker.

"Having patients in our clinic is really artificial because they may suppress their tics," she told Medscape Medical News. It is "a really different situation at home or at school."

She hopes that in the future, patients could record themselves on video sitting at home and have that video analyzed by the machine-learning tool. The tool could even be used longitudinally to assess the impact of medication, she said.

For the moment, however, Becker stressed that they have a tool that can simply differentiate between tics and normal movements.

Before it can be released as a clinical application, the tool needs to be able to distinguish between "tics and functional tics, and between tics and myoclonus and every other hyperkinetic movement," and it needs to be validated, she said.

"I think it's years before we have this as an app for your patient."

Becker explained that their group recently conducted a study of healthy individuals, demonstrating that "even people without a tic disorder sometimes move a little bit," although all participants had been asked to sit still.

The team, therefore, wanted to develop a means of reliably distinguishing between these "extra movements" in healthy control participants and tics in people with tic disorders.

One challenge of this task is that rating tics on video recordings is time-consuming and cumbersome; the team reasoned that an automated, machine-learning system could be a more efficient means of assessment, as well as potentially improving classification accuracy.

The researchers used a dataset of 63 videos of people with tic disorders to train a Random Forest classifier to detect tics per second of video.

They first identified 170 facial landmarks and manually tracked the features of tics to indicate whether a tic greater than or equal to a predefined threshold for severity had occurred within 1 second. The severity threshold was chosen as a score of 3 on the Yale Global Tic Severity Scale, which Becker said is a tic which "everybody who looks at it would recognize."

This information was fed into the machine-learning tool to train it to predict the presence of tics in each second. These per-second predictions were aggregated over the whole video to calculate a series of clinical "meta-features," including the number of tics per minute, the maximum duration of a continuous tic, the average duration of tic-free segments, the average size of a tic cluster, and the number of clusters per minute.

The features were then combined into a logistic regression model, which was trained on a dataset of 124 videos of individuals with tic disorders, and 162 videos of health controls.

To determine the accuracy of the model, it was then tested on a dataset of 50 videos of patients with tic disorders and 50 videos of healthy controls.

The machine-learning tool was able to identify severe tics with a test accuracy of 84%, and an F-1 score, which combines the positive predictive value with the sensitivity, of 83%.

The area under the receiver operating characteristics curve was 0.896, and the authors report that the tool revealed significant differences in all meta-features between patients and healthy controls.

Approached for comment, Christos Ganos, MD, Department of Neurology, Charit University Medicine Berlin, Germany, said that the current study is one of several looking at ways of "automatically classifying patterns of behavior."

He told Medscape Medical News that it has the potential to not only "reinforce our clinical decision-making" by demonstrating that "the way we classify phenomenon has been correct all along," but also by showing ways of improving it.

He noted that a new classification of facial tics is being developed, and the phenomenological aspect is "so broad" that machine-learning models could help with some aspects of this, although it will take some time to have useful information from current efforts.

He emphasized, however, that there are "several caveats" to the use of artificial intelligence in this manner, the first being the quality of the data that is fed into the machine-learning tools in the first place.

The information needs to be "correctly labelled," said Ganos, and he is convinced that there will, initially, be a "lot of white noise" from studies that have trained tools using poorly classified data.

Another fundamental aspect, and one that is "going to be talked about a lot" in the future, is that of data protection, he added.

"I worry increasingly" over stories in the media of "videos being re-circulated and re-posted," he said. "Many of these datalabeled and fed into certain algorithms will exist forever."

"Forever means a long time," he stressed, "and it has many implications for generations to come, so we should be aware of that."

"Of course, [machine learning] has great possibilities to be used in therapeutic trials, to monitor symptoms over the large scale, and all of this is very positive," Ganos told Medscape Medical News. "But our role, in many ways, is to make sense of the data, and of what data we feed into these type of approaches, and of how best to leverage it."

Davide Martino, MD, associate professor of neurology in the Department of Clinical Neurosciences at the University of Calgary in Canada, commented in a press release that "an algorithm that measures frequency and clustering of tics from video recordings has strong translational value in routine clinical practice and clinical research."

This is because "it would likely optimize reliability and efficiency of these measurements," he explained.

"Although limited to facial/head tics, the same approach can be extended to other body regions and phonic tics," he added.

"It is also important to point out that video recording-based measures will inevitably still need to be integrated with other domains of tic severity," such as interference with daily routines and functional impact, "in order to achieve a truly comprehensive assessment of tics," Martino underlined.

The study had no specific funding. The investigators report no relevant financial relationships.

International Congress of Parkinson's Disease and Movement Disorders (MDS) 2023: Abstract 951. Presented August 29, 2023.

For more Medscape Neurology news, join us on Facebook and X (formerly Twitter)

See the rest here:
Machine-Learning Tool Sorts Tics From Non-Tics on Video - Medscape

Read More..

Machine learning and thought, climate impact on health, Alzheimer’s … – Virginia Tech

One of the worlds leaders in computational psychiatry will kick off the upcomingMaury Strauss Distinguished Public Lecture Seriesat the Fralin Biomedical Research Institute at VTC in September.

The public lectures bring innovators and thought leaders in science, medicine, and health from around the globe to the Health Sciences and Technology campus in Roanoke.

Leading the series with a discussion of machine learning and human thought is Read Montague, the Virginia Tech Carilion Vernon Mountcastle Research professor anddirector of theCenter for Human Neuroscience Researchat the Fralin Biomedical Research Institute at VTC.

Montagues research led to the development of the prediction error reward hypothesis among the most influential ideas at the basis for human decision-making in health and in neuropsychiatric disorders and recently to first-of-their-kind observations in the human brain of how the neurochemicals dopamine and serotonin shape peoples perceptions of the world around them.

He will share details of his data-driven neuroscience applications to machine learning to better identify and treat diseases of the brain at 5:30 p.m. on Sept. 28 at the institute.

Montague, who is working with clinicians and research centers worldwide to gather data on brain signaling, is also a professor in the department of physics at Virginia Techs College of Science.

Next in the series is J. Marshall Shepherd, who started his career as a meteorologist and became a leading international expert in weather and climate. He is an elected member of three of the nations influential scientific academies: the National Academy of Sciences, the National Academy of Engineering, and the American Academy of Arts and Sciences.

How is his work part of a series on health? The World Health Organization recognizes climate change as the single biggest health threat facing humanity. Shepherd will address the intersection of climate, risk and perception.

Bookending the series in May 2024 is Rick Woychik, director of the National Institute of Environmental Health Sciences at the National Institutes of Health. The molecular geneticist oversees federal funding for biomedical research related to environmental influences, including climate change, on human health and disease.

Other lectures in the series address Alzheimers disease, infant nutrition, dementia, COVID-19 and cardiovascular outcomes, and locomotor learning in children with brain injury.

We look forward to joining with members of the wider community to better understand these exciting new innovations and insights that are germane to health, said Michael Friedlander, Virginia Techs vice president for health sciences and technology and executive director of the Fralin Biomedical Research Institute. This is an incredible collection of speakers who represent some of the best thinking in science, medicine, and policy in the context of improving health. We are also proud that our own Read Montague is among them, and we look forward to sharing this research with the wider community.

The free public lectures are named for Maury Strauss, a Roanoke businessman and longtime community benefactor who recognized the value of welcoming leaders in science, medicine, and health to share their work. The 2023-24 series, which began in 2011, highlights the research institutes commitment to the community.

The full 2023-24 Maury Strauss Distinguished Public lectures include:

The public is invited to attend the lectures, which begin with a 5 p.m. reception. Presentations begin at 5:30 p.m. in 2 Riverside at the Fralin Biomedical Research Institute.All are free, in person, and open to the public. Community attendance is encouraged. To make the lectures accessible to a wider audience, most are streamed live via Zoom and archived.

In addition to the Maury Strauss Distinguished Public Lectures, the Fralin Biomedical Research Institute also hostsPioneers in Biomedical Research Seminars, theTimothy A. Johnson Medical Scholar Lecture Series, as well as other conferences, programs, lectures, and special events.

See the article here:
Machine learning and thought, climate impact on health, Alzheimer's ... - Virginia Tech

Read More..

Advanced Space-led Team Applying Machine Learning to Detect … – Space Ref

Advanced Space LLC., a leading space tech solutions company, is pleased to announce that an Advanced Space-led team has been chosen to apply Machine Learning (ML) capabilities to detect, track and characterize space debris for the IARPA Space Debris Identification and Tracking (SINTRA) program.

Space debrisitems due to human activity in spacepresents a major hazard to space operations. Advanced Space and its teammates Orion Space Solutions and ExoAnalytic Solutions are applying advanced ML techniques to finding and identifying small debris (0.1-10 cm) under a new Space Debris Identification and Tracking (SINTRA) contract from Intelligence Advanced Research Projects Activity (IARPA).

Space debris is an exponentially growing problem that threatens all activity in space, which Congress is now recognizing as critical infrastructure, said Principal Investigator Nathan R. The well-known Kessler syndrome will inevitably make Earth orbit unusable unless we mitigate it, and the first step is developing the capability to maintain persistent knowledge of the debris population. Through our participation in the SINTRA program, our team aims to revolutionize the global space communitys knowledge of the space debris problem.

Currently, there are over 100 million objects greater than 1 mm orbiting the Earth; however, less than 1 percent of the debris that could cause mission-ending damage are currently tracked. The Advanced Space teams solutionthe Multi-source Extended-Range Mega-scale AI Debris (MERMAID) systemwill feature a sensing system to gather data; ground data processing incorporating ML models to observe, detect, and characterize debris below the threshold of traditional methods; and a catalog of this information. A key component of this solution is that the team will use ML methods to decrease the Signal-to-Noise-Ratio (SNR) required for detecting debris signatures in traditional optical and radar data.

Advanced Space CEO Bradley Cheetham said, Monitoring orbital debris is critical to the sustainable, exploration, development and settlement of space. We are proud of the work the team is doing to advance the state of the art by bringing scale and automation to this challenge.

ABOUT ADVANCED SPACE:

Advanced Space (https://advancedspace.com/) supports the sustainable exploration, development, and settlement of space through software and services that leverage unique subject matter expertise to improve the fundamentals of spaceflight. Advanced Space is dedicated to improving flight dynamics, technology development, and expedited turn-key missions to the Moon, Mars, and beyond.

See original here:
Advanced Space-led Team Applying Machine Learning to Detect ... - Space Ref

Read More..

Machine Learning Regularization Explained With Examples – TechTarget

What is regularization in machine learning?

Regularization in machine learning is a set of techniques used to ensure that a machine learning model can generalize to new data within the same data set. These techniques can help reduce the impact of noisy data that falls outside the expected range of patterns. Regularization can also improve the model by making it easier to detect relevant edge cases within a classification task.

Consider an algorithm specifically trained to identify spam emails. In this scenario, the algorithm is trained to classify emails that appear to be from a well-known U.S. drugstore chain and contain only a single image as likely to be spam. However, this narrow approach runs the risk of disappointing loyal customers of the chain, who were looking forward to being notified about the store's latest sales. A more effective algorithm would consider other factors, such as the timing of the emails, the use of images and the types of links embedded in the emails to accurately label the emails as spam.

This more complex model, however, would also have to account for the impact that each of these measures added to the algorithm. Without regularization, the new algorithm risks being overly complex, subject to bias and unable to detect variance. We will elaborate on these concepts below.

In short, regularization pushes the model to reduce its complexity as it is being trained, explained Bret Greenstein, data, AI and analytics leader at PwC.

"Regularization acts as a type of penalty that gets added to the loss function or the value that is used to help assign importance to model features," Greenstein said. "This penalty inhibits the model from finding parameters that may over-assign importance to its features."

As such, regularization is an important tool that can be used by data scientists to improve model training to achieve better generalization, or to improve the odds that the model will perform well when exposed to unknown examples.

Adnan Masood, chief architect of AI and machine learning at digital transformation consultancy UST, said his firm regularly uses regularization to strike a balance between model complexity and performance, adeptly steering clear of both underfitting and overfitting.

Overfitting, as described above, occurs when a model is too complex and learns noise in the training data. Underfitting occurs when a model is too simple to capture underlying data patterns.

"Regularization provides a means to find the optimal balance between these two extremes," Masood said.

Consider another example of the use of regularization in retail. In this scenario, the business wants to develop a model that can predict when a certain product might be out of stock. To do this, the business has developed a training data set with many features, such as past sales data, seasonality, promotional events, and external factors like weather or holiday.

This, however, could lead to overfitting when the model is too closely tied to specific patterns in the training data and as a result may be less effective at predicting stockouts based on new, unseen data.

"Without regularization, our machine learning model could potentially learn the training data too well and become overly sensitive to noise or fluctuations in the historical data," Masood said.

In this case, a data scientist might apply a linear regression model to minimize the sum of the squared difference between actual and predicted stockout instances. This discourages the model from assigning too much importance to any one feature.

In addition, they might assign a lambda parameter to determine the strength of regularization. Higher values of this parameter increase regularization and lower the model coefficients (weights of the model).

When this regularized model is trained, it will balance fitting the training data and keeping the model weights small. The result is a model that is potentially less accurate on the training data and more accurate when predicting stockouts on new, unseen data.

"In this way, regularization helps us build a robust model, better generalizes to new data and more effectively predicts stockouts, thereby enabling the business to manage its inventory better and prevent loss of sales," Masood said.

He finds that regularization is vital in managing overfitting and underfitting. It also indirectly helps control bias (error from faulty assumptions) and variance (error from sensitivity to small fluctuations in a training data set), facilitating a balanced model that generalizes well on unseen data.

Niels Bantilan, chief ML engineer at Union.ai, a machine learning orchestration platform, finds it useful to think of regularization as a way to prevent a machine learning model from memorizing the data during training.

For example, a home automation robot trained on making coffee in one kitchen might inadvertently memorize the quirks and layouts of that specific kitchen. It will likely break when presented with a new kitchen where ingredients and equipment differ from the one it memorized.

In this case, regularization forces the model to learn higher-level concepts like "coffee mugs tend to be stored in overhead cabinets" rather than learning specific quirks of the first kitchen, such as "the coffee mugs are stored in the top left-most shelf."

In business, regularization is important to operationalizing machine learning, as it can mitigate errors and save cost, since it is expensive to constantly retrain models on the latest data.

"Therefore, it makes sense to ensure they have some generalization capacity beyond their training data, so the models can handle new situations up to a certain point without having to retrain them on expensive hardware or cloud infrastructure," Bantilan said.

The term overfitting is used to describe a model that has learned too much from the training data. This can include noise, such as inaccurate data accidentally read by a sensor or a human deliberately inputting bad data to evade a spam filter or fraud algorithm. It can also include data specific to that particular situation but not relevant to other use cases, such as a store shelf layout in one store that might not be relevant to different stores in a stockout predictor.

Underfitting occurs when a model has not learned to map features to an accurate prediction for new data. Greenstein said that regularization can sometimes lead to underfitting. In that case, it is important to change the influence that regularization has during model training. Underfitting also relates to bias and variance.

Bantilan described bias in machine learning as the degree to which a model's predictions agree with the actual ground truth. For example, a spam filter that perfectly predicts the spam/not-spam labels in training data would be a low-bias model. It could be considered high-bias if it was wrong all the time.

Variance characterizes the degree to which the model's predictions can handle small perturbations in the training data. One good test is removing a few records to see what happens, Bantilan said. If the model's predictions remain the same, then the model is considered low-variance. If the predictions change wildly, then it is considered high-variance.

Greenstein observed that high variance could be present when a model trained on multiple variations of data appears to learn a solution but struggles to perform on test data. This is one form of overfitting, and regularization can assist with addressing the issue.

Bharath Thota, partner in the advanced analytics practice of Kearney, a global strategy and management consulting firm, said that some of the common use cases in industry include the following:

Regularization needs to be considered as a handy technique in the process of improving ML models rather than a specific use case. Greenstein has found it most useful when problems are high-dimensional, which means they contain many and sometimes complex features. These types of problems are prone to overfitting, as a model may fail to identify simplified patterns to map features to objectives.

Regularization is also helpful with noisy data sets, such as high-dimensional data, where examples vary a lot and are subject to overfitting. In these cases, the models may learn the noise rather than a generalized way of representing the data.

It is also good for nonlinear problems since problems that require nonlinear algorithms can often lead to overfitting. These kinds of algorithms uncover complex boundaries for classifying data that map well to the training data but are only partially applicable to real-world data.

Greenstein noted that regularization is one of many tools that can assist with resolving challenges with an overfit model. Other techniques, such as bagging, reduced learning rates and data sampling methods, can complement or replace regularization, depending on the problem.

There are a range of different regularization techniques. The most common approaches rely on statistical methods such as Lasso regularization (also called L1 regularization), Ridge regularization (L2 regularization) and Elastic Net regularization, which combines both Lasso and Ridge techniques. Various other regulation techniques use different principles, such as ensembling, neural network dropout, pruning decision tree-based models and data augmentation.

Masood said the choice of regularization method and tuning for the regularization strength parameter (lambda) largely depends on the specific use case and the nature of the data set.

"The right regularization can significantly improve model performance, but the wrong choice could lead to underperformance or even harm the model's predictive power," Masood cautioned. Consequently, it is important to approach regularization with a solid understanding of both the data and the problem at hand.

Here are brief descriptions of the common regularization techniques.

Lasso regression AKA L1 regularization. The Lasso regularization technique, an acronym for least absolute shrinkage and selection operator, is derived from calculating the median of the data. A median is a value in the middle of a data set. It calculates a penalty function using absolute weights. Kearney's Thota said this regularization technique encourages sparsity in the model, meaning it can set some coefficients to exactly zero, effectively performing feature selection.

Ridge regression AKA L2 regularization. Ridge regulation is derived from calculating the mean of the data, which is the average of a set of numbers. It calculates a penalty function using a square or other exponent of each variable. Thota said this technique is useful for reducing the impact of irrelevant or correlated features and helps in stabilizing the model's behavior.

Elastic Net (L1 + L2) regularization. Elastic Net combines both L1 and L2 techniques to improve the results for certain problems.

Ensembling. This set of techniques combines the predictions from a suite of models, thus reducing the reliance on any one model for prediction.

Neural network dropout. This process is sometimes used in deep learning algorithms comprised of multiple layers of neural networks. It involves randomly dropping out the weights of some neurons. Bantilan said this forces the deep learning algorithm to learn an ensemble of sub-networks to achieve the task effectively.

Pruning decision tree-based models. This is used in tree-based models like decision trees. The process of pruning branches can simplify the decision rules of a particular tree to prevent it from relying on the quirks of the training data.

Data augmentation. This family of techniques uses prior knowledge about the data distribution to prevent the model from learning the quirks of the data set. For example, in an image classification use case, you might flip an image horizontally, introduce noise, blurriness or crop an image. "As long as the data corruption or modification is something we might find in the real world, the model should learn how to handle those situations," Bantilan said.

Read the original:
Machine Learning Regularization Explained With Examples - TechTarget

Read More..

Optimization of therapeutic antibodies for reduced self-association … – Nature.com

Jain, T. et al. Biophysical properties of the clinical-stage antibody landscape. Proc. Natl Acad. Sci. USA 114, 944949 (2017).

Article CAS PubMed PubMed Central Google Scholar

Makowski, E. K., Wu, L., Gupta, P. & Tessier, P. M. Discovery-stage identification of drug-like antibodies using emerging experimental and computational methods. mAbs 13, 1895540 (2021).

Labrijn, A. F., Janmaat, M. L., Reichert, J. M. & Parren, P. Bispecific antibodies: a mechanistic review of the pipeline. Nat. Rev. Drug Discov. 18, 585608 (2019).

Article CAS PubMed Google Scholar

Shim, H. Bispecific antibodies and antibody-drug conjugates for cancer therapy: technological considerations. Biomolecules 10, 360 (2020).

Article CAS PubMed PubMed Central Google Scholar

Drago, J. Z., Modi, S. & Chandarlapaty, S. Unlocking the potential of antibodydrug conjugates for cancer therapy. Nat. Rev. Clin. Oncol. 18, 327344 (2021).

Article PubMed PubMed Central Google Scholar

Dean, A. Q., Luo, S., Twomey, J. D. & Zhang, B. Targeting cancer with antibody-drug conjugates: promises and challenges. mAbs 13, 1951427 (2021).

Carter, P. J. Potent antibody therapeutics by design. Nat. Rev. Immunol. 6, 343357 (2006).

Article CAS PubMed Google Scholar

Carter, P. J. & Rajpal, A. Designing antibodies as therapeutics. Cell 185, 27892805 (2022).

Article CAS PubMed Google Scholar

Leavy, O. Therapeutic antibodies: past, present and future. Nat. Rev. Immunol. 10, 297 (2010).

Article CAS PubMed Google Scholar

Chames, P., Van Regenmortel, M., Weiss, E. & Baty, D. Therapeutic antibodies: successes, limitations and hopes for the future. Br. J. Pharmacol. 157, 220233 (2009).

Article CAS PubMed PubMed Central Google Scholar

Makowski, E. K. et al. Co-optimization of therapeutic antibody affinity and specificity using machine learning models that generalize to novel mutational space. Nat. Commun. 13, 3788 (2022).

Article CAS PubMed PubMed Central Google Scholar

Gupta, P. et al. Antibodies with weakly basic isoelectric points minimize trade-offs between formulation and physiological colloidal properties. Mol. Pharm. 19, 775787 (2022).

Article CAS PubMed PubMed Central Google Scholar

Rabia, L. A., Desai, A. A., Jhajj, H. S. & Tessier, P. M. Understanding and overcoming trade-offs between antibody affinity, specificity, stability and solubility. Biochem. Eng. J. 137, 365374 (2018).

Article CAS PubMed PubMed Central Google Scholar

Kingsbury, J. S. et al. A single molecular descriptor to predict solution behavior of therapeutic antibodies. Sci. Adv. 6, eabb0372 (2020).

Article CAS PubMed PubMed Central Google Scholar

Starr, C. G. et al. Ultradilute measurements of self-association for the identification of antibodies with favorable high-concentration solution properties. Mol. Pharm. 18, 27442753 (2021).

Article CAS PubMed Google Scholar

Makowski, E. K., Wu, L., Desai, A. A. & Tessier, P. M. Highly sensitive detection of antibody nonspecific interactions using flow cytometry. mAbs 13, 1951426 (2021).

Xu, Y. et al. Addressing polyspecificity of antibodies selected from an in vitro yeast presentation system: a FACS-based, high-throughput selection and analytical tool. Protein Eng. Des. Sel. 26, 663670 (2013).

Article CAS PubMed Google Scholar

Ahmed, L. et al. Intrinsic physicochemical profile of marketed antibody-based biotherapeutics. Proc. Natl Acad. Sci. USA 118, e2020577118 (2021).

Yadav, S., Laue, T. M., Kalonia, D. S., Singh, S. N. & Shire, S. J. The influence of charge distribution on self-association and viscosity behavior of monoclonal antibody solutions. Mol. Pharm. 9, 791802 (2012).

Article CAS PubMed Google Scholar

Yadav, S. et al. Establishing a link between amino acid sequences and self-associating and viscoelastic behavior of two closely related monoclonal antibodies. Pharm. Res. 28, 17501764 (2011).

Article CAS PubMed Google Scholar

Xolair. Prescribing Information (Genentech Inc., 2021).

Dyson, M. R. et al. Beyond affinity: selection of antibody variants with optimal biophysical properties and reduced immunogenicity from mammalian display libraries. mAbs 12, 1829335 (2020).

Wang, N. et al. Opalescence of an IgG1 monoclonal antibody formulation is mediated by ionic strength and excipients. Biopharm Int. 22, 3647 (2009).

Salinas, B. A. et al. Understanding and modulating opalescence and viscosity in a monoclonal antibody formulation. J. Pharm. Sci. 99, 8293 (2010).

Article CAS PubMed PubMed Central Google Scholar

Goldberg, D. S., Bishop, S. M., Shah, A. U. & Sathish, H. A. Formulation development of therapeutic monoclonal antibodies using high-throughput fluorescence and static light scattering techniques: role of conformational and colloidal stability. J. Pharm. Sci. 100, 13061315 (2011).

Article CAS PubMed Google Scholar

Shi, G. H. et al. Subcutaneous injection site pain of formulation matrices. Pharm. Res. 38, 779793 (2021).

Article CAS PubMed Google Scholar

Chabra, S. et al. Ixekizumab citrate-free formulation: results from two clinical trials. Adv. Ther. 39, 28622872 (2022).

Article CAS PubMed PubMed Central Google Scholar

Grinshpun, B. et al. Identifying biophysical assays and in silico properties that enrich for slow clearance in clinical-stage therapeutic antibodies. mAbs 13, 1932230 (2021).

Htzel, I. et al. A strategy for risk mitigation of antibodies with fast clearance. mAbs 4, 753760 (2012).

Neergaard, M. S., Nielsen, A. D., Parshad, H. & Van De Weert, M. Stability of monoclonal antibodies at high-concentration: head-to-head comparison of the IgG1 and IgG4 subclass. J. Pharm. Sci. 103, 115127 (2014).

Article CAS PubMed Google Scholar

Lai, P. K. et al. Differences in human IgG1 and IgG4 S228P monoclonal antibodies viscosity and self-interactions: experimental assessment and computational predictions of domain interactions. mAbs 13, 1991256 (2021).

Sickmier, E. A. et al. The panitumumab EGFR complex reveals a binding mechanism that overcomes cetuximab induced resistance. PLoS ONE 11, e0163366 (2016).

Article PubMed PubMed Central Google Scholar

Bohrmann, B. et al. Gantenerumab: a novel human anti-A antibody demonstrates sustained cerebral amyloid- binding and elicits cell-mediated removal of human amyloid-. J. Alzheimers Dis. 28, 4969 (2012).

Article CAS PubMed Google Scholar

Weihofen, A. et al. Development of an aggregate-selective, human-derived -synuclein antibody BIIB054 that ameliorates disease phenotypes in Parkinsons disease models. Neurobiol. Dis. 124, 276288 (2019).

Article CAS PubMed Google Scholar

De Groot, A. S. & Martin, W. Reducing risk, improving outcomes: bioengineering less immunogenic protein therapeutics. Clin. Immunol. 131, 189201 (2009).

Article PubMed Google Scholar

De Groot, A. S. & Scott, D. W. Immunogenicity of protein therapeutics. Trends Immunol. 28, 482490 (2007).

Article PubMed Google Scholar

Apgar, J. R. et al. Modeling and mitigation of high-concentration antibody viscosity through structure-based computer-aided protein design. PLoS ONE 15, e0232713 (2020).

Article CAS PubMed PubMed Central Google Scholar

Tomar, D. S. et al. In-silico prediction of concentration-dependent viscosity curves for monoclonal antibody solutions. mAbs 9, 476489 (2017).

Boughter, C. T. et al. Biochemical patterns of antibody polyreactivity revealed through a bioinformatics-based analysis of CDR loops. eLife 9, e61393 (2020).

Lai, P. K., Gallegos, A., Mody, N., Sathish, H. A. & Trout, B. L. Machine learning prediction of antibody aggregation and viscosity for high concentration formulation development of protein therapeutics. mAbs 14, 2026208 (2022).

Han, X., Shih, J., Lin, Y., Chai, Q. & Cramer, S. M. Development of QSAR models for in silico screening of antibody solubility. mAbs 14, 2062807 (2022).

Mason, D. M. et al. Optimization of therapeutic antibodies by predicting antigen specificity from antibody sequence via deep learning. Nat. Biomed. Eng. 5, 600612 (2021).

Article CAS PubMed Google Scholar

Saka, K. et al. Antibody design using LSTM based deep generative model from phage display library for affinity maturation. Sci. Rep. 11, 5852 (2021).

Article CAS PubMed PubMed Central Google Scholar

Hie, B. L. et al. Efficient evolution of human antibodies from general protein language models and sequence information alone. Nat. Biotechnol. https://doi.org/10.1038/s41587-023-01763-2 (2023).

Shin, J. E. et al. Protein design and variant prediction using autoregressive generative models. Nat. Commun. 12, 2403 (2021).

Article CAS PubMed PubMed Central Google Scholar

Neal, B. L., Asthagiri, D. & Lenhoff, A. M. Molecular origins of osmotic second virial coefficients of proteins. Biophys. J. 75, 24692477 (1998).

Article CAS PubMed PubMed Central Google Scholar

Lomakin, A., Asherie, N. & Benedek, G. B. Aeolotopic interactions of globular proteins. Proc. Natl Acad. Sci. USA 96, 94659468 (1999).

Article CAS PubMed PubMed Central Google Scholar

Elcock, A. H., Sept, D. & McCammon, J. A. Computer simulation of proteinprotein interactions. J. Phys. Chem. B 105, 15041518 (2001).

Article CAS Google Scholar

Sharma, V. K. et al. In silico selection of therapeutic antibodies for development: viscosity, clearance, and chemical stability. Proc. Natl Acad. Sci. USA 111, 1860118606 (2014).

Article CAS PubMed PubMed Central Google Scholar

Raybould, M. I. J. et al. Five computational developability guidelines for therapeutic antibody profiling. Proc. Natl Acad. Sci. USA 116, 40254030 (2019).

Article CAS PubMed PubMed Central Google Scholar

Negron, C., Fang, J., McPherson, M. J., Stine, W. B. Jr. & McCluskey, A. J. Separating clinical antibodies from repertoire antibodies, a path to in silico developability assessment. mAbs 14, 2080628 (2022).

Connolly, B. D. et al. Weak interactions govern the viscosity of concentrated antibody solutions: high-throughput analysis using the diffusion interaction parameter. Biophys. J. 103, 6978 (2012).

Article CAS PubMed PubMed Central Google Scholar

Kelly, R. L. et al. Chaperone proteins as single component reagents to assess antibody nonspecificity. mAbs 9, 10361040 (2017).

Datta-Mannan, A. et al. The interplay of non-specific binding, target-mediated clearance and FcRn interactions on the pharmacokinetics of humanized antibodies. mAbs 7, 10841093 (2015).

Chung, S. et al. An in vitro FcRn- dependent transcytosis assay as a screening tool for predictive assessment of nonspecific clearance of antibody therapeutics in humans. mAbs 11, 942955 (2019).

Liu, Y. et al. High-throughput screening for developability during early-stage antibody discovery using self-interaction nanoparticle spectroscopy. mAbs 6, 483492 (2014).

Sule, S. V., Dickinson, C. D., Lu, J., Chow, C. K. & Tessier, P. M. Rapid analysis of antibody self-association in complex mixtures using immunogold conjugates. Mol. Pharm. 10, 13221331 (2013).

Article CAS PubMed Google Scholar

Sun, T. et al. High throughput detection of antibody self-interaction by bio-layer interferometry. mAbs 5, 838841 (2013).

Mouquet, H. et al. Polyreactivity increases the apparent affinity of anti-HIV antibodies by heteroligation. Nature 467, 591595 (2010).

Article CAS PubMed PubMed Central Google Scholar

Wardemann, H. et al. Predominant autoantibody production by early human B cell precursors. Science 301, 13741377 (2003).

Article CAS PubMed Google Scholar

Jacobs, S. A., Wu, S. J., Feng, Y., Bethea, D. & ONeil, K. T. Cross-interaction chromatography: a rapid method to identify highly soluble monoclonal antibody candidates. Pharm. Res. 27, 6571 (2010).

See the original post here:
Optimization of therapeutic antibodies for reduced self-association ... - Nature.com

Read More..

Machine Learning, Numerical Simulation Integrated To Estimate … – Society of Petroleum Engineers

In the complete paper, the authors analyzed a robust, well-distributed parent/child well data set of the Delaware Basin Wolfcamp formation using a combination of available empirical data and numerical simulation outputs, which was used to develop a predictive machine-learning model (consisting of a multiple linear regression model and a simple neural network). This model has been implemented successfully in field developments to optimize child-well placement and has enabled improvements in performance predictions and net present value.

Pervasive parent/child well pairs have complicated the development of the Delaware Basin Wolfcamp formation by introducing the need to forecast child-well performance reliably. This problem is made more difficult by the complex nature of the physical processes involved in parent/child well interactions and the variety of geometrical configurations that can be realized. In broad terms, the following three classifications of child wells can be recognized based on their spatial relationship to the associated parent well and other offset wells (Fig. 1 above):

To narrow the range of complexities in the study, the authors focused on Type 2 child wells because this configuration will be used most often in future development activities and because it had the most existing field examples.

The principal objective of this assessment was to generate accurate quantitative predictions of the diminished production performance of child wells because of pre-existing parent wells.

In this work, a novel, hybrid approach is detailed involving a combination of machine-learning techniques and numerical simulations.

Read this article:
Machine Learning, Numerical Simulation Integrated To Estimate ... - Society of Petroleum Engineers

Read More..