Small-molecule therapeutics treat a wide variety of diseases, but their effectiveness is often diminished because of their pharmacokinetics—what the body does to a drug. After administration, the body dictates how much of the drug is absorbed, which organs the drug enters, and how quickly the body metabolizes and excretes the drug again.

Nanoparticles, usually made out of lipids, polymers, or both, can improve the pharmacokinetics, but they can be complex to produce and often carry very little of the drug.

Some combinations of small-molecule cancer drugs and two small-molecule dyes have been shown to self-assemble into nanoparticles with extremely high payloads of drugs, but it is difficult to predict which small-molecule partners will form nanoparticles among the millions of possible pairings.

MIT researchers have developed a screening platform that combines machine learning with high-throughput experimentation to identify self-assembling nanoparticles quickly. In a study published in Nature Nanotechnology, researchers screened 2.1 million pairings of small-molecule drugs and “inactive” drug ingredients, identifying 100 new nanoparticles with potential applications that include the treatment of cancer, asthma, malaria, and viral and fungal infections.

“We have previously described some of the negative and positive effects that inactive ingredients can have on drugs, and here, through a concerted collaboration across our laboratories and core facilities, describe an approach focusing on the potential positive effects these can have on nanoformulation,” says Giovanni Traverso, the Karl Van Tassel (1925) Career Development Professor of Mechanical Engineering, and senior corresponding author of the study.

Their findings point to a strategy for that solves for both the complexity of producing nanoparticles and the difficulty of loading large amounts of drugs onto them.

“So many drugs out there don’t live up to their full potential because of insufficient targeting, low bioavailability, or rapid drug metabolism,” says Daniel Reker, lead author of the study and a former postdoc in the laboratory of Robert Langer. “By working at the interface of data science, machine learning, and drug delivery, our hope is to rapidly expand our tool set for making sure a drug gets to the place it needs to be and can actually treat and help a human being.”

Langer, the David H. Koch Institute Professor at MIT and a member of the Koch Institute for Integrative Cancer Research, is also a senior author of the paper.

A cancer therapy meets its match

In order to develop a machine learning algorithm capable of identifying self-assembling nanoparticles, researchers first needed to build a dataset on which the algorithm could train. They selected 16 self-aggregating small-molecule drugs with a variety of chemical structures and therapeutic applications and a diverse set of 90 widely available compounds, including ingredients that are already added to drugs to make them taste better, last longer, or make them more stable. Because both the drugs and the inactive ingredients are already FDA-approved, the resulting nanoparticles are likely to be safer and move through the FDA approval process more quickly.

The team then tested every combination of small-molecule drug and inactive ingredient, enabled by the Swanson Biotechnology Center, a suite of core facilities providing advanced technical services within the Koch Institute. After mixing pairings and loading 384 samples at a time onto nanowell plates using robotics in the High Throughput Sciences core, researchers walked the plates, often with quickly degrading samples, next door to the Peterson (1957) Nanotechnology Materials Core Facility core to measure the size of particles with high throughput dynamic light scattering.

Now trained on 1,440 data points (with 94 nanoparticles already identified), the machine learning platform could be turned on a much bigger library of compounds. Screening 788 small-molecule drugs against more than 2,600 inactive drug ingredients, the platform identified 38,464 potential self-assembling nanoparticles from 2.1 million possible combinations.

The researchers selected six nanoparticles for further validation, including one composed of sorafenib, a treatment commonly used for advanced liver and other cancers, and glycyrrhizin, a compound frequently used as both a food and drug additive and most commonly known as licorice flavoring. Although sorafenib is the standard of care for advanced liver cancer, its effectiveness is limited.

In human liver cancer cell cultures, the sorafenib-glycyrrhizin nanoparticles worked twice as well as sorafenib by itself because more of the drug could enter the cells. Working with the Preclinical Modeling, Imaging and Testing facility at the Koch Institute, researchers treated mouse models of liver cancer to compare the effects of sorafenib-glycyrrhizin nanoparticles versus either compound by itself. They found that the nanoparticle significantly reduced levels of a marker associated with liver cancer progression compared to mice given sorafenib alone, and lived longer than mice given sorafenib or glycyrrhizin alone. The sorafenib-glycyrrhizin nanoparticle also showed improved targeting to the liver when compared to oral delivery of sorafenib, the current standard in the clinic, or when injecting sorafenib after it has been combined with cremophor, a commonly-used drug vehicle that improves water solubility but has toxic side effects.

Personalized drug delivery

The new platform may have useful applications beyond optimizing the efficiency of active drugs: it could be used to customize inactive compounds to suit the needs of individual patients. In earlier work, members of the team found that inactive ingredients could provoke adverse allergic reactions in some patients. Now, with the expanded machine learning toolbox, more options could be generated to provide alternatives for these patients.

“We have an opportunity to think about matching the delivery system to the patient,” explains Reker, now an assistant professor of biomedical engineering at Duke University. “We can account for things like drug absorption, genetics, even allergies to reduce side effects upon delivery. Whatever the mutation or medical condition, the right drug is only the right drug if it actually works for the patient.”

The tools for safe, efficacious drug delivery exist, but putting all the ingredients together can be a slow process. The combination of machine learning, rapid screening, and the ability to predict interactions among different combinations of materials will accelerate the design of drugs and the nanoparticles used to deliver them throughout the body.

In ongoing work, the team is looking not just to improve effective delivery of drugs but also for opportunities to create medications for people for whom standard formulations are not a good option, using big data to solve problems in small populations by looking at genetic history, allergies, and food reactions.

The post Small-molecule therapeutics: Big data dreams for tiny technologies appeared first on Artificial Intelligence.

Traditional marketing approaches for kitchen and bath showrooms have generally involved identifying market opportunities from trends such as neighborhoods that your showroom serves, customer demographics and a healthy dose of throwing spaghetti against the wall to identify what would stick. However, this approach, while at times effective, is extremely inefficient.

Marketing today has been transformed from trial-and-error to a more sophisticated and scientific approach using data analytics to identify new and underserved markets and to develop growth strategies. Analytics were initially used by businesses to determine the effectiveness of marketing and advertising campaigns, measuring the impact of their value propositions and calls-to-action. The effectiveness of those efforts expanded the use of analytics to enable businesses to:

• Better understand market size, potential customers, customer preferences and behaviors.
• Enhance customer experiences.
• Test new products/services.
• Improve marketing spend and return on investment.
• Optimize pricing strategies.

Most kitchen and bath showroom owners are likely to believe that analytics are something that only big corporations use. They may erroneously believe that they don’t have time, the resources or the skill sets needed to employ analytics to help develop business growth strategies. But nothing could be further from the truth. The bottom line is that companies that use data – not simply gut instincts or guesswork – are going to win. Trade-area analytics could well prove a critical factor in assuring business growth.

Data can assist in isolating targetable areas for remodeling activity at different price points. It can help pinpoint where you’ll receive the greatest return on your marketing spend. It can also help you develop more effective marketing messages tailored to a specific demographic and improve the look, feel and effectiveness of your showroom by helping to assure a consistency of image between marketing and sales efforts and showroom displays.

How Do Analytics Work?

Trade-area analytics identify and evaluate targeted demographics in a service area, usually within 30 minutes’ drive of a showroom’s location. The process examines demographics and consumer purchasing behavior in specific zip codes within a service area. Typical criteria used to evaluate a showroom’s service territory are number of homeowners with discretionary income, owner-occupied heads of households aged 35-64, number of houses built 20 or more years ago, level of remodeling activity in that neighborhood, and the percentage of homeowners likely to purchase kitchen cabinets or renovate their kitchens or baths.

What’s eye-opening for most showrooms that are aware of trade-area analytics is that demographic information for every neighborhood in the U.S. is readily available at no cost from the U.S. Census. Within the Census, you can search any demographic that you want by income level, zip code or other criteria. Simmons National Consumer Surveys can also assist in determining the level of kitchen and bath remodeling activity in specific zip codes and neighborhoods surveyed.

After performing a zip code analysis of a service territory, the next step is to create a map of the showroom’s job history for the past two to three years and compare that to the trade area analysis that shows neighborhoods with the highest sales and remodeling potential. Some 80% to 90% of the time, there’s a disconnect between where opportunity exists and where a showroom has been servicing, and that disconnect shines a spotlight on growth opportunities.

“I was surprised by the ability to take a map and pinpoint exactly what you want,” says BKBG member Danny McGeady, of JEM Designs, in Beavercreek, OH. “The analytics identified specific neighborhoods that are ripe for remodeling, primarily those featuring production homes built more than 10 years ago. From old listings, brochures and other data, we could accurately estimate the size and configuration of existing kitchens and the number and size of cabinets.”

Using that information, McGeady says, he developed a direct-mail campaign that features a new kitchen in the homeowners existing home and what it would cost. In contrast, past marketing efforts, McGeady notes, employed TV advertising to help build his brand.

Another reason to target specific neighborhoods using data for growth opportunities is the concept of “homophily,” which suggests that people who live next to one another share similar characteristics and circumstances, and thus can be drawn to use similar products and services. People who live in the same neighborhood not only consume similar goods and services, they share what they like, and their endorsements are the most trusted of all.

Neil Pfeister, of Englewood, CO-based Enchanted Kitchens, used the information identified in the data analytics of his service territory to develop and implement a drip marketing campaign that generated 400 leads in the last year, resulting in nine new projects.

“We never realized the depth of data that was readily available to us. Far and away, analytics have generated the best cost of leads and sales returns that we’ve ever had,” Pfeister says.

Justin Leatherman, of Leatherman Supply, in Goshen, IN, notes that “some of the zip code opportunities identified by our trade-area analytics shocked us. We were missing opportunities in a neighborhood directly across the street from our showroom.”

Leatherman not only is using trade-area analytics as a cornerstone to grow sales; he also plans to use them to identify locations for potential new showrooms.

Understanding the Market

Most showroom owners understand their market dynamics, but not many have a comprehensive grasp of the depth of their market. For example, they know how far a customer will likely travel to use their showroom and they have a fairly good idea of the cost of homes in their service area, but what they don’t often understand is the number of homeowners that are potential customers and the potential volume of business in their market. Data analytics provides that information.

The vast majority of kitchen and bath showrooms do what they do because they’ve been doing the same thing forever. They may almost exclusively serve a specific price-point customer. But if you limit your sights only on the customers and demographics that you currently serve, you may be missing 35% to 40% of your market. Trade-area analytics identify that 35% to 40% of market potential most showrooms never know about.

Big data is not the exclusive province of big businesses. There is nothing to prevent a showroom of any size from using trade-area analytics to identify new and underserved markets in their own backyards. Best of all, the data you need to make better decisions and develop more effective growth strategies is available in a few clicks at absolutely no cost. 

Tom Cohn is the exec. v.p. of the Bath & Kitchen Business Group, a Bethesda, MD-based, shareholder-owned organization of independent kitchen and bath design firms. He has more than two decades of experience providing growth strategies for kitchen and bath and decorative plumbing and hardware showrooms.

The post Big Data for Small Showrooms appeared first on Artificial Intelligence.