#malaria detection using image processing and machine learning | Explore Tumblr Posts and Blogs

vsplusonline · 4 years

Text

Monitor the spread of COVID-19 with Artificial Intelligence in Geospatial Domain - Times of India

New Post has been published on https://apzweb.com/monitor-the-spread-of-covid-19-with-artificial-intelligence-in-geospatial-domain-times-of-india/

Monitor the spread of COVID-19 with Artificial Intelligence in Geospatial Domain - Times of India

In today’s world, we are moving towards automation of the applications for societal benefits. In this context, Artificial Intelligence (AI), Machine Learning (ML), and Deep Learning (DL) techniques are providing an extra edge to the process of automatization and model building. Artificial intelligence (AI) refers to the simulation of human intelligence in machines that are programmed to think like humans and mimic their actions.

Geospatial Technology is an emerging field of study that includes Geographic Information System (GIS), Remote Sensing (RS) and Global Positioning System (GPS). It enables us to acquire data that is referenced to the earth and use it for analysis, modelling, simulations and visualization. It can provide quick, easy and economic solutions in almost every field of life including health, education, agriculture, drinking water, sanitation, smart city planning and disaster management. The geospatial technology when coupled with the advanced AI algorithms can tremendously enhance the processing of big spatial data and can also produce accurate predictions.

There are numerous applications of AI and ML in the geospatial domain including Disease outburst identification, Urban and Rural Planning, Illegal Construction or Encroachment Detection, Crop Mapping and Yield Prediction, Business, Tourism, Disaster Management and many more.

A brief description of some of the important applications is summarised below:

Disease Outburst Identification

The satellite images along with the AI-enabled system can be used to map and monitor the spread of several diseases such as malaria, dengue etc. The recent threat due to novel COVID-19 disease can also be mapped geographically and monitor the spread of the same using the spatial data. These digital maps can be used by the Govt. authorities for effective planning at the local level towards preventing the spread of the disease in other areas.

Urban and Rural Planning

Geospatial technology plays a very important role in smart city planning and rural development. The existing land and water resources in the cities and villages can be mapped using the high-resolution satellite images and strategies for their utilisation in various applications can be identified. Also, geotagging of the essential infrastructures such as schools/colleges, medical centres/dispensaries, overhead tanks, ration distribution centres, landfill sites etc. can be carried out to identify the gap areas for any region in GIS.

Illegal Construction

Land is a costly commodity, and its encroachment for various uses is a major problem in most of the cities in India. In the current scenario, the identification of the encroached areas is a very challenging and time-consuming task. Towards that, automatic extraction of buildings from high-resolution satellite images can provide as one of the solutions for finding the encroached areas. The geo-visualization tool and AI-based DSS can be developed to enable the Govt. authorities to quickly act upon in case of any illegal construction in their land areas.

Disaster Management

Geospatial technology is effectively being utilised for mapping and prediction of the several natural disasters including floods, droughts, landslides, forest fires etc. Usually, mapping and prediction of such disasters involve the analysis of the satellite datasets acquired at different dates (temporal dataset).

In collaboration with AICTE and other international organizations, Bennett University has set up the largest Artificial Intelligence (AI) Skilling Platform in India called Leadingindia.ai.

The Computer Science Engineering (CSE) Department of the Bennett University is leading the initiative by analysing the satellite images of different spatial and spectral resolution using AI techniques for extracting the several landcover features such as roads, agricultural fields, water bodies, settlements etc. The students are also working towards developing a framework for extracting building footprints from high spatial resolution images using deep learning architectures to tackle with the problem of illegal construction in Government lands, techniques for monitoring the growth of the crops and predicting the crop yield and mapping of forest fires based on satellite observations.

This article is written by Dr Kuldeep, Assistant Professor, School of Engineering & Applied Sciences, Bennett University.

Source link

#ai course in india #AI courses in India #artificial intelligence course in india #Bennett university #Bennett University courses #BU AI course #Career

0 notes

craigbrownphd-blog-blog · 6 years

Text

[New] Handbook of Deep Learning Applications (Springer)

#ICYDK: This book presents a broad range of deep-learning applications related to vision, natural language processing, gene expression, arbitrary object recognition, driverless cars, semantic image segmentation, deep visual residual abstraction, brain–computer interfaces, big data processing, hierarchical deep learning networks as game-playing artifacts using regret matching, and building GPU-accelerated deep learning frameworks. Deep learning, an advanced level of machine learning technique that combines class of learning algorithms with the use of many layers of nonlinear units, has gained considerable attention in recent times. Unlike other books on the market, this volume addresses the challenges of deep learning implementation, computation time, and the complexity of reasoning and modeling different type of data. As such, it is a valuable and comprehensive resource for engineers, researchers, graduate students and Ph.D. scholars. Find it on Linkedin | Amazon | Springer. This book * Provides a concise and structured presentation of deep learning applications * Introduces a large range of applications related to vision, speech, and natural language processing * Includes active research trends, challenges, and future directions of deep learning * This book presents a broad range of deep-learning applications Deep learning, an advanced level of machine learning technique that combines class of learning algorithms with the use of many layers of nonlinear units, has gained considerable attention in recent times.Unlike other books on the market, this volume addresses the challenges of deep learning implementation, computation time, and the complexity of reasoning and modeling different type of data. As such, it is a valuable and comprehensive resource for engineers, researchers, graduate students and Ph.D. scholars. Content * Designing a Neural Network from Scratch for Big Data Powered by Multi-node GPUs * Deep Learning for Scene Understanding * An Application of Deep Learning in Character Recognition: An Overview * Deep Learning for Driverless Vehicles * Deep Learning for Document Representation * Applications of Deep Learning in Medical Imaging * Deep Learning for Marine Species Recognition * Deep Molecular Representation in Cheminformatics * A Brief Survey and an Application of Semantic Image Segmentation for Autonomous Driving * Phase Identification and Workflow Modeling in Laparoscopy Surgeries Using Temporal Connectionism of Deep Visual Residual Abstractions * Deep Learning Applications to Cytopathology: A Study on the Detection of Malaria and on the Classification of Leukaemia Cell-Lines * Application of Deep Neural Networks for Disease Diagnosis Through Medical Data Sets * Why Dose Layer-by-Layer Pre-training Improve Deep Neural Networks Learning? * Deep Learning in eHealth * Deep Learning for Brain Computer Interfaces * Reducing Hierarchical Deep Learning Networks as Game Playing Artefact Using Regret Matching * Deep Learning in Gene Expression Modeling About the author: Sanjiban Sekhar Roy is an Associate Professor in the School of Computer Science and Engineering, Vellore Institute of Technology(VIT), India. He joined VIT in the year of 2009 as an Asst. Professor. Prior to joining VIT University Sanjiban had nine months of research experience in Dept. Computer Sc and Eng, Indian Institute of Technology(IIT) Kharagpur. His research interests include Deep Learning and AI. He has published around 45 articles in international journals and conferences. He also is editorial board members of international journals. Besides, he has edited four books with reputed international publishers like Elsevier, Springer and IGI Global. Below links will give you more idea about his work. You can contact him through linked in. * www.linkedin.com/in/sanjiban-roy * https://www.researchgate.net/profile/Sanjiban_Roy http://bit.ly/2FheJ5x

0 notes

theresawelchy · 6 years

Text

Using deep learning to detect malaria in images

Adapted from CIDR

Carlos Atico Ariza was an Insight Fellow in Fall 2018, where he deployed a web application that utilizes image analysis to diagnose and prioritize malaria patients — reducing clinician labor by 85%. Before Insight, Carlos worked as a Data Science consultant building end-to-end machine learning solutions like an unsupervised anomaly detection system. During his PhD in Chemical and Biological Engineering, he investigated a broad set of modalities to control stem cells; contributing to the field of regenerative medicine.

Interested in transitioning to career in health data science? Find out more about the Insight Health Data Science Fellows Program in Boston and Silicon Valley, apply today, or sign up for program updates.

Small but deadly foes

Mosquitoes are more than a mere nuisance for more than half the world’s population. Infectious diseases spread, in part, thanks to the elegant yet lethal life cycles of parasites that depend on mosquitoes. Malarial parasites, for example, have evolved specialized forms…for uptake into mosquitoes and reproduction in red blood cells. Capitalizing on the proliferative nature of mosquitoes, malaria parasites infect more than 200 million people and cause more than 400,000 deaths per year!

A bottleneck in malaria diagnosis

Microscopic examination of blood is the best known method for diagnosis of malaria. A patient’s blood is smeared on a glass slide and stained with a contrasting agent that facilitates identification of parasites within red blood cells. A trained clinician examines 20 microscopic fields of view at 100 X magnification, counting red blood cells that contain the parasite out of 5,000 cells (WHO protocol).

Malaria diagnosis blood-smear workflow. Image sources: Microscopist, Wendy Saravagy. Illustrations of blood smears. Microscopist examining blood smears

As you can imagine, manually counting 5,000 cells is a slow process. This can easily burden clinic staff, especially where outbreaks occur. Therefore, I wanted to determine how image analysis and machine learning could reduce the burden on clinicians and help prioritize patients.

What the F-beta!?

Missing a single parasite in what appears to be a parasite-free sample can be deadly. In cases where no parasites are found, blood-smears and cell counts are repeated every eight hours. If no parasites are found after three repetitions, the patient is cleared. This is done to minimize the number of missed diagnoses (false negatives) that could lead to death. Therefore, to build a screening tool for malaria diagnoses, I would need to minimize false negatives.

I also care about limiting false positives to save clinicians’ time. If I built a tool that falsely predicts the majority of cells as infected, clinicians would have to spend as much time confirming predictions of single cell images as they would have counting cells through a microscope. So, I used an F-beta score, the F2 score, which places twice as much importance on minimizing false negatives than false positives, as the metric for comparing the ML classifiers I explored.

Hurray for open source data

I found a great dataset that consists of 27,558 single cell images with an equal number of infected and uninfected cells. The cells are from 200 patients where three out of every four patients had malaria. Single cells were segmented from images of microscope fields of view. One of the coolest things about this dataset is that the images were captured using a cell phone! Not some fancy camera attached to the microscope.

All images were manually annotated by an expert slide reader. For more information, please visit the US National Library of Medicine through your favorite internet portal. Cheers to the US NLM and all the researchers that collected, annotated, and made this data public.

Infographic for dataset used to train Malaria Hero

Interpretable feature engineering

Convolutional neural networks are known for being excellent image classifiers. Practical advice when building machine learning models, however, is to start with a simple model and then iterate quickly based on model performance. Therefore, I first stared by engineering visually salient features, leveraging a less complex model, and measuring the relevancy of the features to the overall classification.

Stained parasites detected as BLOBs with OpenCV’s BLOB detection

I engineered features that were indicative of cell color, area, convexity, and roundness. I also created features to determine if parasites were visible in cells. Since the parasites differ in color from the cell cytoplasm, we have a good use case for binary large object (BLOB) detection. BLOB detection identifies groups of connected pixels that are different in intensity from surrounding pixels. More about BLOBs here and here. Lastly, I included the number of detected BLOBs in each cell in my feature set because multiple parasites can be found in one cell.

Building the model

After engineering features, I reserved 20% of the data for testing and performed 3-fold cross validation on the remaining 80%. I then compared four ML classifiers and selected a Random Forest model which had a F2 score of 0.8. Not bad!

Workflow: features extracted from infected (blue outline) and uninfected (orange outline) single-cell images to provide data for model training, comparison, and selection. The greatest F2 metric among models was 0.80.

However, I also wanted to compare this to a CNN because I noticed the BLOB detector was not performing as well as I desired. BLOB detection seems to do poorly around the edges or perimeter of the cell. Also, there are some parasites that were not thoroughly stained with the contrasting agent, making the difference in color between the parasite and cell too subtle for BLOB detection.

Infected cells that were misclassified (false negatives) with an interpretable model. Notice the middle cell seems to contain a poorly-stained parasite at the bottom right corner, making it difficult to correctly classify.

Some infected cells were challenging to characterize. Take the following image, for example. A parasite is not visible. Yet, the expert slide reader deemed the cell as infected. The slide reader may have spotted the small white spots on the cell that I have encircled in the image. These may be adhesion knobs, which do occur on infected cells.

Potential adhesion knobs on an infected cell. Illustration source

Regardless of whether or not the above are adhesion knobs, subtle features like these that are indicative of parasitic infection are difficult to extract. Therefore, instead of continuing to engineer features, I moved on to implementing a convolution neural network.

Things Got Convoluted

I generated features from a trained convolution neural network: Inception v3. Inception v3 was trained on ImageNet images to classify myriad objects like puppies and pedestrians, but not to determine whether a cell has been attacked by a parasite. Thus, to re-purpose Inception v3, I removed the classification layer and generated 2048 features for each image. I then reduced the dimensionality to 100 features using PCA and trained ML classifiers. After training with 3-fold cross-validation, testing, and comparing four ML classifiers, I obtained an F2 score of 0.92 with L2 regularized logistic regression, which was much better than the random forest model. The obvious choice was to use a repurposed CNN as the back end for Malaria Hero.

Simplified CNN pipeline: Features extracted from single-cell images with a pre-trained CNN were used for model training, comparison, and selection. The greatest F2 metric among models was 0.92.

Malaria Hero lives at malariahero.org

To deploy Malaria Hero I learned to use Dash. The Dash tutorial is great at getting you started. After orchestrating Dash, Flask, gunicorn, nginx, Docker, and AWS, Malaria Hero was live…phew!

To use the web app, a clinician would upload images of single cells from patients. Every cell would be classified as infected or uninfected. Three regular expressions extract metadata from each image, including patient ID number. The results are then grouped by patient and sorted according to infection rate.

Malaria Hero web application interface

If you don’t have images of single cells just lying around that you would like to classify, feel free to press the demo button on malariahero.org. This takes single-cell images from two patients that I have stored on AWS and classifies each image, as described above, to demonstrate output.

Major takeaways

Estimated time spent manually counting cells/parasites compared to Malaria Hero.

Malaria Hero saves time. Instead of manually counting, a clinician could capture images of each field of view and upload images that have cells counted and classified automatically. I used to culture stem cells and counting cells through a microscope was part of the job. I’ve estimated that about 85% of a clinician’s time would be saved using Malaria Hero. This translates to seeing 1,400 more patients a month based on a normal 9–5 M-F work schedule.

The output produced allows clinicians to prioritize patients based on infection rate, expediting treatment to sicker patients. Since results are sorted based on infection rate, clinicians can look at the list and quickly prioritize their patients.

A doctor, encountering a potentially high number of infected patients. Malaria Hero would help him quickly diagnosing and prioritizing his patients!

Remember that the images in the dataset were captured using a smart phone. Malaria Hero demonstrates the potential of providing mobile doctors or resource-constrained clinics with a valuable yet affordable tool. This would empower mobile doctors that visit remote locations or perform house calls to upload images and receive a quick diagnosis.

Furthermore, diagnosing malaria with a microscope is a skill that, without practice, becomes prone to errors. Providing re-training helps clinicians improve their classification abilities as described here. One can imagine that images uploaded to Malaria Hero could be shared with a clinician that regularly practices malarial parasite detection. In this manner, a more experienced clinician could confirm ML classification results or provide assistance to clinicians that are inexperienced or do not routinely practice malaria diagnosis.

Code

The code for this project is publicly available on my GitHub.

#Technology #Finance

0 notes

kathleenseiber · 5 years

Text

Drones keep an eye on tropical disease hotspots

Satellite images, drone photos, and even Google Earth could help identify communities most at risk for schistosomiasis, one of the world’s worst tropical diseases, researchers report.

A new study shows that clues in the environment can help identify transmission hotspots for the parasitic disease that is second only to malaria in its global health impact. Researchers used rigorous field sampling and aerial images to precisely map communities that are at greatest risk.

“This is a game-changer for developing-country public health agencies, because it will make it possible for them to efficiently find the villages that need their help the most,” says Chelsea Wood, an assistant professor in the University of Washington School of Aquatic and Fishery Sciences and lead author of the paper, published in PNAS.

Freshwater snails that transmit schistosomiasis thrive in unrooted, floating vegetation that can be seen in aerial images. In this photo, the dark, patchy vegetation in the water is the ideal habitat for snails. (Credit: Andrew Chamberlin/Stanford)

More than 200 million people have schistosomiasis, which is treatable but has been difficult to eliminate from some regions of the world.

Schistosomes, the worms that cause the disease, grow within freshwater snails, where they multiply and enter the waters of rivers, lakes, and streams. To infect people, the worms penetrate the skin when they swim, bathe, or wade.

Schistosomiasis causes bloody urine and stool and abdominal pain, and can damage the liver, spleen, intestines, lungs, and bladder. In children, the infection can stunt growth and impair cognitive development.

The disease is found across sub-Saharan Africa, in South America, the Caribbean, the Middle East, and East and Southeast Asia. Though schistosomiasis is treatable with the drug praziquantel, it’s easy for a person to become re-infected after treatment if they swim or bathe in freshwater where the parasite is present.

Researchers process the vegetation from a sampling point in northwestern Senegal, May 2016. (Credit: Chelsea Wood/U. Washington)

Count the snails

The World Health Organization recently recognized that efforts to slow transmission of the disease through drug distribution weren’t working in some regions. In addition to drug distribution, WHO now recommends targeting the types of snails that transmit the parasitic worms, which is how this research team got involved.

“The ecological side of the problem is what’s holding us back from schistosomiasis control and elimination—and now ecologists are stepping in and filling that gap,” Wood says. “It’s an exciting time because there’s so much for us to learn. The kind of innovation we have introduced is just the beginning of what ecologists have to contribute to the control of schistosomiasis.”

The researchers worked across more than 30 sites in northwestern Senegal, where villages use a local river and lake for everything from bathing and swimming to washing dishes and clothes. This location was the epicenter of the largest schistosomiasis outbreak ever recorded, in the mid-1980s.

The field team uses a wooden canoe and protective clothing during snail sampling at Kheune, Senegal. (Credit: Chelsea Wood/U. Washington)

The researchers first set out to methodically count and map the distribution of snails across each site over two years. The fieldwork was difficult and exhausting—they couldn’t let the schistosome-infested water touch their skin while they waded chest-deep to sample mud and plants. It was hot and humid, and the thick shoreline vegetation was full of mosquitoes, spiders, snakes—and even feral dogs.

They found snails in the river in patchy and inconsistent distributions over time. Snails might be present in one location, then completely absent three months later. Given the snails’ ephemeral nature, the researchers realized that targeting aggregations of snails for removal might not be an efficient way to reduce schistosomiasis transmission.

A village’s river water access point, as seen from a drone, in northwestern Senegal. People use river waters for many purposes, including bathing, swimming, and washing dishes and clothes. (Credit: Andrew Chamberlin/Stanford)

A better way to find schistosomiasis

Instead, they shifted their focus to the habitat where snails live. The snails thrive in unrooted, floating vegetation that is visible in images from satellites and drones.

Considering these habitat features, plus other data they had gathered about each site such as snail density, village size, and location, they used models to evaluate which factors could best predict schistosomiasis transmission. The total area of a water access point and the area of floating vegetation were the two best indicators that human infection would occur nearby.

These habitat features are all easy to measure in satellite or drone imagery.

“Counting snails is not an easy undertaking, and it also produces data that are not as useful as the data you can get from a drone,” Wood says. “Once we understand the association between snail presence and particular habitat features, we can use drone and satellite imagery to detect those habitat features. This cuts the time needed to evaluate the risk of schistosomiasis infection down to a fraction of what it would be if you were just looking at snails.”

Coauthor Simon Senghor uses a microscope to screen snails for schistosome infection in St. Louis, Senegal, May 2015. (Credit: Chelsea Wood/U. Washington)

Public health agencies in Senegal can now look at aerial images across their jurisdiction, find areas with the most floating vegetation in water access points, and target those villages for schistosomiasis treatment, the researchers say.

“Now we can take these aerial images season to season and have an idea of how the pathogenic landscape changes in time and space. This can give us a better idea of infection rates,” says coauthor Giulio De Leo, a biology professor at Stanford University.

Can machine learning help?

The team is also trying to use machine learning to automate the identification of floating vegetation in photos, making it even easier for agencies to use the information. They plan to test their approach in other parts of Africa at a broader scale, using publicly available infection data and satellite imagery.

“We’re cautiously optimistic, but we still have some work to do to generalize our findings to new contexts,” says coauthor Susanne Sokolow, a research scientist at Stanford University.

“If, indeed, we find that the predictors for schistosomiasis are scalable and automatable, then we will have a powerful new tool in the fight against the disease, and one that fills a critical capacity gap: a way to efficiently target environmental interventions alongside human treatment to combat the disease.”

Additional coauthors are from Stanford University; the Royal Belgian Institute of Natural Sciences; Virginia Tech; the University of Washington; the University of North Carolina Wilmington; the University of California, Los Angeles; Notre Dame, London’s Natural History Museum; the University of London; and the Biomedical Research Center EPLS in Saint Louis, Senegal.

The University of Michigan, the Alfred P. Sloan Foundation, the Wellcome Trust, the Bill and Melinda Gates Foundation, Stanford University, the National Institutes of Health, and the National Science Foundation funded the work.

Source: University of Washington

The post Drones keep an eye on tropical disease hotspots appeared first on Futurity.

Drones keep an eye on tropical disease hotspots published first on https://triviaqaweb.weebly.com/

0 notes

kayawagner · 7 years

Text

Beating the Bloodsuckers: How AI Takes a Swat at Mosquitoes and Malaria

When it comes to advancing science, Marianne Sinka has some skin in the game. Some itchy skin.

The Oxford University entomologist has regularly sacrificed her flesh (and blood) as mosquito bait to further her research. Now she’s using AI to track the irksome insects and battle the deadly diseases they carry.

“Today, the best way to detect what species are in a place is to sit down, roll up your trousers, and see what mosquitoes bite you,” Sinka said. “There are obviously some issues with that.”

Instead, Sinka and a group of other Oxford researchers are using cheap mobile phones and GPU-accelerated deep learning to detect mosquitoes. They also want to determine whether the bugs belong to a species that transmits malaria or other life-threatening illnesses.

The goal is to help cash-strapped governments in the regions where malaria is rampant know where and when to deploy insecticides, vaccinations and other actions to prevent disease.

Killer Bugs

Few creatures are as hated as mosquitoes, and with good reason: They’re the world’s deadliest animals, killing more people than tigers, snakes, sharks and wolves put together. The blood-sucking insects carry a many life-threatening illnesses, including malaria, the Zika virus, dengue and yellow fever.

A female (top of picture) and male (bottom of picture) Anopheles gambiae mosquito, the principal carrier of malaria in Africa. Image courtesy of the Centers for Disease Control.

In 2016, malaria alone infected more than 200 million people — 90 percent of them in Africa — and killed some 445,000, according to the World Health Organization. UNICEF reports that most these deaths occured in children less than five years old.

Among some 3,500 species of mosquitoes, only 75 can infect people with malaria, and of these, about 40 are considered the primary carriers of the parasite that causes the disease. To identify mosquito species today, researchers capture the insects (either with human lures or costly light traps) and examine them under the microscope.

For some important species, they must then use molecular methods, such as examining the mosquito’s DNA to ensure an accurate identification. These methods can be costly and time-consuming, Sinka said.

Catching a Buzz

Instead of getting up close with the vexatious vermin, the researchers put a smartphone with a sound-sensing app within biting range. Like people, animals and machines the bugs have a unique sound signature.

“It’s those distinctive buzzing tones we all hate from mosquitoes,” said Ivan Kiskin, an Oxford doctoral student with expertise in signal processing who is working on the mosquito project. The project, dubbed Humbug, is a partnership between Oxford University and London’s Kew Gardens.

Researchers are using recordings of captured mosquitoes and NVIDIA GPUs to train a neural network to recognize wing noise. So far, the deep learning-based software reports the likelihood that the buzzing comes from furiously flapping mosquito wings, which beat up to 1000 times a second. In numerous tests, the algorithms have outperformed human experts.

Humbug researchers are beginning to distinguish species as well, Kiskin said. But further progress is stymied by the need for additional training data, he added.

Beating Malaria

To collect more sound, the team is deploying mobile phones to research groups around the world. In addition, researchers developed an Android app called MozzWear to enlist help from ordinary people. MozzWear will record mosquito buzzing, along with the time and location — data that users can send to the citizen science web portal, Zooniverse.

“Malaria is a disease of the poor,” said Sinka, the bug expert. Although the disease is present in developed countries, it’s more common in regions where people live near their livestock and are often too poor to afford air conditioning, window screens or even protective netting to drape over beds.

“Ultimately, we could use our best algorithm and the phones to map malaria prevalence over a region or country,” Kiskin said. “Then we could tackle malaria by targeting aid to places in need.”

The post Beating the Bloodsuckers: How AI Takes a Swat at Mosquitoes and Malaria appeared first on The Official NVIDIA Blog.

Beating the Bloodsuckers: How AI Takes a Swat at Mosquitoes and Malaria published first on https://supergalaxyrom.tumblr.com

0 notes

repmywind02199 · 7 years

Text

SynBioBeta and the current biorevolution

Startups and individuals on the cusp of biological breakthroughs.

San Francisco is largely a collection of peninsulas and inlets, irregular land masses that singularly jut out into cold Pacific waters and isolate themselves by virtue of unavoidable geography. Travel to different parts of the bustling metropolis and you’ll witness an array of cultures and styles so distinctive they become complementary in their diversity alone; Mission District, Fisherman’s Wharf, Little Italy, Chinatown, each with individual aesthetics and atmosphere adding to the depiction of San Francisco as a microcosm for the world.

Unsurprisingly, the city’s tendency toward eclecticism doesn’t cease with street style. Industry, even at the highest levels of technological development, is pervaded by this intense desire for diversification coupled with community building. There is no better example of such initiative than SynBioBeta, an annual synthetic biology conference founded by Brown alumnus and NASA affiliate, John Cumbers. If San Francisco is a microcosm for the world, then surely SynBioBeta is the synthetic biology industry’s own miniature.

The 2017 San Francisco convention, housed within UCSF’s Mission Bay Conference Center, is an energetic forum for industry innovators and investors alike. The reception lobby is buzzing. Business-clad professionals mingle over coffee and work descriptions, all the while seeking opportunities for advancement of their companies’ roles in the network. The growing magnitude of businesses here is akin to adaptive radiation as one group—science-minded individuals—has rapidly speciated to fill several different industry niches. This diverse collection of producers is accurately described by CEO and co-founder of Twist Bioscience, Emily Leproust.

Leproust views the synthetic biology industry as an “ecosystem that will grow the pie,” with each company specializing in one area and driving efficiency in that way. There is an overarching attitude that it will take many companies, not one monopoly, to further development, and in this conception of the industry, Twist Bioscience, a leading manufacturer in the commercial synthesis of DNA, sees itself as a “facilitator for exponential growth.”

The company just announced its unprecedented one billion synthetic base pair deal with Ginkgo Bioworks that will support biological expansion into new industries. Twist’s production capabilities enable this type of large-scale manufacturing, producing something close to one-third of the world’s synthetic DNA, due to their main point of difference: a silicon platform. While DNA is typically synthesized on a 96-well plastic plate, Twist has developed a silicon alternative that, according to Leproust, “microscales 1 gene to 10,000 genes” and “gives you more scale while reducing your price per base.” This enables purchasers of synthetic DNA to receive their orders on a faster time scale and at a larger volume. Leproust believes this process impacts researchers in that “the more DNA you get, the faster you learn,” and in an industry where time is money, efficiency seems to be key.

With this type of technology becoming available, it isn’t difficult to imagine a world where synthetic biology enters the mainstream market. In fact, Leproust paints an intriguing picture of the market in which biology not only becomes a factor of production, but becomes a commonplace one.

“Cool things become the product. What enables the iPhone is hardcore physics, but what consumers have is a product,” says Leproust. She envisions a future in which “[consumers] forget about the biology that is behind the products” and instead simply enjoy the benefits of such goods or services.

Figure 1. Emily LeProust, CEO of Twist Bioscience. Image source: SynBioBeta, used with permission.

Twist Bioscience certainly isn’t the only believer in the future of synthetic biology. The numerous panels, presentations, and booths at SynBioBeta all revolve around the idea of a “biorevolution” and how producers can address global problems.

The main themes of the conference include biomaterials and consumer products, cell factories for biopharmaceuticals, and big data and artificial intelligence’s connection to biology. Each segment highlights pioneering individuals with specific visions for the future of synthetic biology and innovative companies working to produce high through-put in order to impact the state of today’s market.

Biomaterials and consumer products

The science of biomaterials is about 50 years old, an infant in the grand scale of scientific discoveries. Two companies featured at SynBioBeta are taking the concept of engineered substances for consumers and bringing it to the fashion industry.

Modern Meadow, a biofabrication company, poses the question of how to clothe the world’s growing population. Its answer comes in the form of synthetic leathers, an attempt to turn an animal product into a textile. The idea is that while an animal takes two years to raise, a certain synthetic leather process can be carried out in two weeks without the use of tissue engineering, the company’s initial business endeavor. Modern Meadow alters DNA base pairs to create instructions for cells to multiply and produce collagen. The produced collagen then self-assembles into a triple helix molecule, and the molecules link together to form an interwoven network of fibers. Modern Meadow uses an unspecified process to further assemble fibers into the desired material, a synthetic leather product, which can be tanned and treated for commercialization. The company has officially launched its brand Zoa, a name meant to evoke the idea of life coming into materials.

In a related field, startup Colorifix is addressing the environmental concerns associated with textile dyeing. The textile industry is the second largest polluter of water in the world, but Colorifix’s process claims to produce less than 1% of dye waste along with a 20% reduction in energy expenditure. The company uses sugar molasses feedstock to grow microorganisms in fermentation, harvests the organisms directly from fermentation, and applies them to fabrics as a part of the dyeing process. Once the dye transfer is complete, the organisms are removed from the product with high temperatures and detergents that eliminate lipids, carbohydrates, and proteins, which essentially comprise the entire organism. Colorifix promotes chemical safety but also the feasibility of its process. It is partnered with companies such as H&M and will soon be introducing its products to stores nationwide.

Figure 2. Modern Meadow animal-free leather fabrication and Colorifix textile dyeing. Sources: Modern Meadow, Colorifix, used with permission. Cell factories for biopharmaceuticals

Arguably one of the more well-known applications of biotech comes in the form of pharmaceuticals and their work in producing novel medicines. Leaders in synthetic biology are creating a new concept of “living medicines” that respond to cues from the human body itself.

Biopharma company Synlogic Therapeutics specializes in Synthetic Biotic medicines that manipulate naturally occurring microbes to achieve desired medical results. Synlogic’s work is centralized on the functions of the human microbiome, the quadrillion genes of microbial cells that inhabit the human body. The microbiome has certain established capabilities, and the pharma company means to expand these capabilities through the programming of probiotic bacteria. The chassis for Synlogic is E. coli Nissle, a proteobacteria indigenous to the microbiota. This bacteria is engineered to carry genetic circuits that allow the Synthetic Biotic medicines to detect and interpret a patient’s body signals, leading to the subsequent activation or inactivation of a specific metabolic pathway.

Synlogic currently hopes to treat patients with genetic metabolic diseases such as Urea Cycle Disorder and Phenylketonuria. However, as research continues to become available, the company intends to provide treatments for inflammatory bowel disease, Crohn’s disease, and ulcerative colitis as well.

Figure 3. Synlogic’s Synthetic Biotic medicine pipeline. Source: Synlogic Therapeutics, used with permission. Big data and artificial intelligence’s connection to biology

Artificial intelligence is an up-and-coming field, and one with many potential applications to the realm of synthetic biology. In a highly anticipated “fireside chat,” Vinod Khosla, venture capitalist, and George Church, professor of genetics at Harvard Medical School, discuss the implications of deep learning in working with big data.

Deep learning is a subfield of machine learning that uses artificial neural networks, algorithms modeled after the human brain. It is thought to be particularly useful in analyzing big data sets because it can extract high-level abstractions from large quantities of unsupervised data. Perhaps for this reason, Khosla and Church agree on the importance of integrating such deep learning tools into biotech technologies.

According to Church, “scientific literature is biased against less-than-super-exciting positive results.” However, new artificial intelligence allows for the publishing of big data sets, most of which can be negative (for example, “this RNA or protein is not expressed in this sequence”). Khosla believes that with deep learning, negative results can be just as valuable as positive results and, therefore, every piece of data contributes in some way.

While Khosla and Church delve into the many intricacies of artificial intelligence, the point of the matter is that the advancement of this technology is leading people closer and closer to re-interpreting global problems in inventive ways. Rather than making mosquitoes resistant to malaria, why not engineer human resistance? Or rather than enforcing strategies to prevent the persistence of global warming, why not instead develop methods to reverse it?

Figure 4. Left to right: Vinod Khosla and George Church. Source: SynBioBeta, used with permission. The future is synthetic biology

Amidst the enthralling presentations and tangible enthusiasm of conference participants, it’s plain to see that there is a promising future in the diversity of synthetic biology. We live in a world where scientific breakthroughs are being made daily, a world where science fiction like Gattaca is becoming a reality. Our goals are evolving to funnel a more advanced understanding of biology into new projects like DNA data storage and prosthetics made from fruits.

The amount of prospective technological change, however, begs another question: will consumers readily accept products synthesized through biological means? Emily Leproust thinks so.

“Explain cause and benefit, and people will get it,” says Leproust. “Synthetic biology has the potential to touch more parts of society and provide a greater benefit to humanity."

Continue reading SynBioBeta and the current biorevolution.

http://ift.tt/2ixxdpv

#FEED 10 TECHNOLOGY

0 notes

doorrepcal33169 · 7 years

Text

SynBioBeta and the current biorevolution

Startups and individuals on the cusp of biological breakthroughs.

Figure 1. Emily LeProust, CEO of Twist Bioscience. Image source: SynBioBeta, used with permission.

Biomaterials and consumer products

Figure 2. Modern Meadow animal-free leather fabrication and Colorifix textile dyeing. Sources: Modern Meadow, Colorifix, used with permission. Cell factories for biopharmaceuticals

Figure 3. Synlogic’s Synthetic Biotic medicine pipeline. Source: Synlogic Therapeutics, used with permission. Big data and artificial intelligence’s connection to biology

Figure 4. Left to right: Vinod Khosla and George Church. Source: SynBioBeta, used with permission. The future is synthetic biology

The amount of prospective technological change, however, begs another question: will consumers readily accept products synthesized through biological means? Emily Leproust thinks so.

“Explain cause and benefit, and people will get it,” says Leproust. “Synthetic biology has the potential to touch more parts of society and provide a greater benefit to humanity."

Continue reading SynBioBeta and the current biorevolution.

from FEED 10 TECHNOLOGY http://ift.tt/2ixxdpv

#FEED 10 TECHNOLOGY

0 notes

csemntwinl3x0a1 · 7 years

Text

SynBioBeta and the current biorevolution

Startups and individuals on the cusp of biological breakthroughs.

Figure 1. Emily LeProust, CEO of Twist Bioscience. Image source: SynBioBeta, used with permission.

Biomaterials and consumer products

Figure 2. Modern Meadow animal-free leather fabrication and Colorifix textile dyeing. Sources: Modern Meadow, Colorifix, used with permission. Cell factories for biopharmaceuticals

Figure 3. Synlogic’s Synthetic Biotic medicine pipeline. Source: Synlogic Therapeutics, used with permission. Big data and artificial intelligence’s connection to biology

Figure 4. Left to right: Vinod Khosla and George Church. Source: SynBioBeta, used with permission. The future is synthetic biology

The amount of prospective technological change, however, begs another question: will consumers readily accept products synthesized through biological means? Emily Leproust thinks so.

“Explain cause and benefit, and people will get it,” says Leproust. “Synthetic biology has the potential to touch more parts of society and provide a greater benefit to humanity."

Continue reading SynBioBeta and the current biorevolution.

http://ift.tt/2ixxdpv

#FEED 10 TECHNOLOGY

0 notes

kayawagner · 7 years

Text

Beating the Bloodsuckers: How AI Takes a Swat at Mosquitoes and Malaria

When it comes to advancing science, Marianne Sinka has some skin in the game. Some itchy skin.

“Today, the best way to detect what species are in a place is to sit down, roll up your trousers, and see what mosquitoes bite you,” Sinka said. “There are obviously some issues with that.”

The goal is to help cash-strapped governments in the regions where malaria is rampant know where and when to deploy insecticides, vaccinations and other actions to prevent disease.

Killer Bugs

A female (top of picture) and male (bottom of picture) Anopheles gambiae mosquito, the principal carrier of malaria in Africa. Image courtesy of the Centers for Disease Control.

Catching a Buzz

Humbug researchers are beginning to distinguish species as well, Kiskin said. But further progress is stymied by the need for additional training data, he added.

Beating Malaria

The post Beating the Bloodsuckers: How AI Takes a Swat at Mosquitoes and Malaria appeared first on The Official NVIDIA Blog.

Beating the Bloodsuckers: How AI Takes a Swat at Mosquitoes and Malaria published first on https://supergalaxyrom.tumblr.com

0 notes