Computers Math

Newly developed artificial intelligence (AI) programs accurately predicted the role of DNA’s regulatory elements and three-dimensional (3D) structure based solely on its raw sequence, according to two recent studies in Nature Genetics. These tools could eventually shed new light on how genetic mutations lead to disease and could lead to new understanding of how genetic sequence influences the spatial organization and function of chromosomal DNA in the nucleus, said study author Jian Zhou, Ph.D., Assistant Professor in the Lyda Hill Department of Bioinformatics at UTSW.
“Taken together, these two programs provide a more complete picture of how changes in DNA sequence, even in noncoding regions, can have dramatic effects on its spatial organization and function,” said Dr. Zhou, a member of the Harold C. Simmons Comprehensive Cancer Center, a Lupe Murchison Foundation Scholar in Medical Research, and a Cancer Prevention and Research Institute of Texas (CPRIT) Scholar.
Only about 1% of human DNA encodes instructions for making proteins. Research in recent decades has shown that much of the remaining noncoding genetic material holds regulatory elements — such as promoters, enhancers, silencers, and insulators — that control how the coding DNA is expressed. How sequence controls the functions of most of these regulatory elements is not well understood, Dr. Zhou explained.
To better understand these regulatory components, he and colleagues at Princeton University and the Flatiron Institute developed a deep learning model they named Sei, which accurately sorts these snippets of noncoding DNA into 40 “sequence classes” or jobs — for example, as an enhancer for stem cell or brain cell gene activity. These 40 sequence classes, developed using nearly 22,000 data sets from previous studies studying genome regulation, cover more than 97% of the human genome. Moreover, Sei can score any sequence by its predicted activity in each of the 40 sequence classes and predict how mutations impact such activities.
By applying Sei to human genetics data, the researchers were able to characterize the regulatory architecture of 47 traits and diseases recorded in the UK Biobank database and explain how mutations in regulatory elements cause specific pathologies. Such capabilities can help gain a more systematic understanding of how genomic sequence changes are linked to diseases and other traits. The findings were published this month.
In May, Dr. Zhou reported the development of a different tool, called Orca, which predicts the 3D architecture of DNA in chromosomes based on its sequence. Using existing data sets of DNA sequences and structural data derived from previous studies that revealed the molecule’s folds, twists, and turns, Dr. Zhou trained the model to make connections and evaluated the model’s ability to predict structure at various length scales.
The findings showed that Orca predicted DNA structures both small and large based on their sequences with high accuracy, including for sequences carrying mutations associated with various health conditions including a form of leukemia and limb malformations. Orca also enabled the researchers to generate new hypotheses about how DNA sequence controls its local and large-scale 3D structure.
Dr. Zhou said that he and his colleagues plan to use Sei and Orca, which are both publicly available on web servers and as open-source code, to further explore the role of genetic mutations in causing the molecular and physical manifestations of diseases — research that could eventually lead to new ways to treat these conditions.
The Orca study was supported by grants from CPRIT (RR190071), the National Institutes of Health (DP2GM146336), and the UT Southwestern Endowed Scholars Program in Medical Science.
Story Source:
Materials provided by UT Southwestern Medical Center. Note: Content may be edited for style and length. More

When users want to send data over the internet faster than the network can handle, congestion can occur — the same way traffic congestion snarls the morning commute into a big city.
Computers and devices that transmit data over the internet break the data down into smaller packets and use a special algorithm to decide how fast to send those packets. These congestion control algorithms seek to fully discover and utilize available network capacity while sharing it fairly with other users who may be sharing the same network. These algorithms try to minimize delay caused by data waiting in queues in the network.
Over the past decade, researchers in industry and academia have developed several algorithms that attempt to achieve high rates while controlling delays. Some of these, such as the BBR algorithm developed by Google, are now widely used by many websites and applications.
But a team of MIT researchers has discovered that these algorithms can be deeply unfair. In a new study, they show there will always be a network scenario where at least one sender receives almost no bandwidth compared to other senders; that is, a problem known as starvation cannot be avoided.
“What is really surprising about this paper and the results is that when you take into account the real-world complexity of network paths and all the things they can do to data packets, it is basically impossible for delay-controlling congestion control algorithms to avoid starvation using current methods,” says Mohammad Alizadeh, associate professor of electrical engineering and computer science (EECS).
While Alizadeh and his co-authors weren’t able to find a traditional congestion control algorithm that could avoid starvation, there may be algorithms in a different class that could prevent this problem. Their analysis also suggests that changing how these algorithms work, so that they allow for larger variations in delay, could help prevent starvation in some network situations. More

Researchers from Santa Clara University, New Jersey Institute of Technology and the University of Hong Kong have been able to successfully teach microrobots how to swim via deep reinforcement learning, marking a substantial leap in the progression of microswimming capability.
There has been tremendous interest in developing artificial microswimmers that can navigate the world similarly to naturally-occuring swimming microorganisms, like bacteria. Such microswimmers provide promise for a vast array of future biomedical applications, such as targeted drug delivery and microsurgery. Yet, most artificial microswimmers to date can only perform relatively simple maneuvers with fixed locomotory gaits.
In the researchers’ study published in Communications Physics, they reasoned microswimmers could learn — and adapt to changing conditions — through AI. Much like humans learning to swim require reinforcement learning and feedback to stay afloat and propel in various directions under changing conditions, so too must microswimmers, though with their unique set of challenges imposed by physics in the microscopic world.
“Being able to swim at the micro-scale by itself is a challenging task,” said On Shun Pak, associate professor of mechanical engineering at Santa Clara University. “When you want a microswimmer to perform more sophisticated maneuvers, the design of their locomotory gaits can quickly become intractable.”
By combining artificial neural networks with reinforcement learning, the team successfully taught a simple microswimmer to swim and navigate toward any arbitrary direction. When the swimmer moves in certain ways, it receives feedback on how good the particular action is. The swimmer then progressively learns how to swim based on its experiences interacting with the surrounding environment.
“Similar to a human learning how to swim, the microswimmer learns how to move its ‘body parts’ — in this case three microparticles and extensible links — to self-propel and turn,” said Alan Tsang, assistant professor of mechanical engineering at the University of Hong Kong. “It does so without relying on human knowledge but only on a machine learning algorithm.”
The AI-powered swimmer is able to switch between different locomotory gaits adaptively to navigate toward any target location on its own.
As a demonstration of the powerful ability of the swimmer, the researchers showed that it could follow a complex path without being explicitly programmed. They also demonstrated the robust performance of the swimmer in navigating under the perturbations arising from external fluid flows.
“This is our first step in tackling the challenge of developing microswimmers that can adapt like biological cells in navigating complex environments autonomously,” said Yuan-nan Young, professor of mathematical sciences at New Jersey Institute of Technology.
Such adaptive behaviors are crucial for future biomedical applications of artificial microswimmers in complex media with uncontrolled and unpredictable environmental factors.
“This work is a key example of how the rapid development of artificial intelligence may be exploited to tackle unresolved challenges in locomotion problems in fluid dynamics,” said Arnold Mathijssen, an expert on microrobots and biophysics at the University of Pennsylvania, who was not involved in the research. “The integration between machine learning and microswimmers in this work will spark further connections between these two highly active research areas.”
Story Source:
Materials provided by New Jersey Institute of Technology. Note: Content may be edited for style and length. More

A research partnership at the Advanced Quantum Testbed (AQT) at Lawrence Berkeley National Laboratory (Berkeley Lab) and Chicago-based Super.tech (acquired by ColdQuanta in May 2022) demonstrated how to optimize the execution of the ZZ SWAP network protocol, important to quantum computing. The team also introduced a new technique for quantum error mitigation that will improve the network protocol’s implementation in quantum processors. The experimental data was published this July in Physical Review Research, adding more pathways in the near term to implement quantum algorithms using gate-based quantum computing.
A Smart Compiler for Superconducting Quantum Hardware
Quantum processors with two- or three-dimensional architectures have limited qubit connectivity where each qubit interacts with only a limited number of other qubits. Furthermore, each qubit’s information can only exist for so long before noise and errors cause decoherence, limiting the runtime and fidelity of quantum algorithms. Therefore, when designing and executing a quantum circuit, researchers must optimize the translation of the circuit made up of abstract (logical) gates to physical instructions based on the native hardware gates available in a given quantum processor. Efficient circuit decompositions minimize the operating time because they consider the number of gates and operations natively supported by the hardware to perform the desired logical operations.
SWAP gates — which swap information between qubits — are often introduced in quantum circuits to facilitate interactions between information in non-adjacent qubits. If a quantum device only allows gates between adjacent qubits, swaps are used to move information from one qubit to another non-adjacent qubit.
In noisy intermediate-scale quantum (NISQ) hardware, introducing swap gates can require a large experimental overhead. The swap gate must often be decomposed into native gates, such as controlled-NOT gates. Therefore, when designing quantum circuits with limited qubit connectivity, it is important to use a smart compiler that can search for, decompose, and cancel redundant quantum gates to improve the runtime of a quantum algorithm or application.
The research partnership used Super.tech’s SuperstaQ software enabling scientists to finely tailor their applications and automate the compilations of circuits for AQT’s superconducting hardware, particularly for a native high-fidelity controlled-S gate, which is not available on most hardware systems. This smart compiling approach with four transmon qubits allows the SWAP networks to be decomposed more efficiently than standard decomposition methods. More

Researchers have developed a new chip-based beam steering technology that provides a promising route to small, cost-effective and high-performance lidar (or light detection and ranging) systems. Lidar, which uses laser pulses to acquire 3D information about a scene or object, is used in a wide range of applications such as autonomous driving, free-space optical communications, 3D holography, biomedical sensing and virtual reality.
“Optical beam steering is a key technology for lidar systems, but conventional mechanical-based beam steering systems are bulky, expensive, sensitive to vibration and limited in speed,” said research team leader Hao Hu from the Technical University of Denmark. “Although devices known as chip-based optical phased arrays (OPAs) can quickly and precisely steer light in a non-mechanical way, so far, these devices have had poor beam quality and a field of view typically below 100 degrees.”
In Optica, Optica Publishing Group’s journal for high-impact research, Hu and co-author Yong Liu describe their new chip-based OPA that solves many of the problems that have plagued OPAs. They show that the device can eliminate a key optical artifact known as aliasing, achieving beam steering over a large field of view while maintaining high beam quality, a combination that could greatly improve lidar systems.
“We believe our results are groundbreaking in the field of optical beam steering,” said Hu. “This development lays the groundwork for OPA-based lidar that is low cost and compact, which would allow lidar to be widely used for a variety of applications such as high-level advanced driver-assistance systems that can assist in driving and parking and increase safety.”
A new OPA design
OPAs perform beam steering by electronically controlling light’s phase profile to form specific light patterns. Most OPAs use an array of waveguides to emit many beams of light and then interference is applied in far field (away from the emitter) to form the pattern. However, the fact that these waveguide emitters are typically spaced far apart from each other and generate multiple beams in the far field creates an optical artifact known as aliasing. To avoid the aliasing error and achieve a 180° field of view, the emitters need to be close together, but this causes strong crosstalk between adjacent emitters and degrades the beam quality. Thus, until now, there has been a trade-off between OPA field of view and beam quality.
To overcome this trade-off, the researchers designed a new type of OPA that replaces the multiple emitters of traditional OPAs with a slab grating to create a single emitter. This setup eliminates the aliasing error because the adjacent channels in the slab grating can be very close to each other. The coupling between the adjacent channels is not detrimental in the slab grating because it enables the interference and beam formation in the near field (close to the single emitter). The light can then be emitted to the far field with the desired angle. The researchers also applied additional optical techniques to lower the background noise and reduce other optical artifacts such as side lobes.
High quality and wide field of view
To test their new device, the researchers built a special imaging system to measure the average far-field optical power along the horizontal direction over a 180° field of view. They demonstrated aliasing-free beam steering in this direction, including steering beyond ±70°, although some beam degradation was seen.
They then characterized beam steering in the vertical direction by tuning the wavelength from 1480 nm to 1580 nm, achieving a 13.5° tuning range. Finally, they showed the versatility of the OPA by using it to form 2D images of the letters “D,” “T” and “U” centered at the angles of -60°, 0° and 60° by tuning both the wavelength and the phase shifters. The experiments were performed with a beam width of 2.1°, which the researchers are now working to decrease to achieve beam steering with a higher resolution and a longer range.
“Our new chip-based OPA shows an unprecedented performance and overcomes the long-standing issues of OPAs by simultaneously achieving aliasing-free 2D beam steering over the entire 180° field of view and high beam quality with a low side lobe level,” said Hu.
This work is funded by VILLUM FONDEN and Innovationsfonden Denmark.
Story Source:
Materials provided by Optica. Note: Content may be edited for style and length. More

A research team from the lab of Quing Zhu, the Edwin H. Murty Professor of Engineering in the Department of Biomedical Engineering at the McKelvey School of Engineering at Washington University in St. Louis, has combined optical coherence tomography (OCT) and machine learning to develop a colorectal cancer imaging tool that may one day improve the traditional endoscopy currently used by doctors.
The results were published in the June issue of the Journal of Biophotonics.
Screening for colon cancer now relies on human visual inspection of tissue during a colonoscopy procedure. This technique, however, does not detect and diagnose subsurface lesions.
An endoscopy OCT essentially shines a light in the colon to help a clinician see deeper to visualize and diagnose abnormalities. By collaborating with physicians at Washington University School of Medicine and with Chao Zhou, associate professor of biomedical engineering, the team developed a small OCT catheter, which uses a longer wavelength of light, to penetrate 1-2 mm into the tissue samples.
Hongbo Luo, a PhD student in Zhu’s lab, led the work.
The technique provided more information about an abnormality than surface-level, white-light images currently used by physicians. Shuying Li, a biomedical engineering PhD student, used the imaging data to train a machine learning algorithm to differentiate between “normal” and “cancerous” tissue. The combined system allowed them to detect and classify cancerous tissue samples with a 93% diagnostic accuracy.
Zhu also is a professor of radiology at the School of Medicine. Her team worked with Vladimir Kushnir and Vladimir Lamm at the School of Medicine, Zhu’s team of PhD students, including Tiger Nie, started a trial in patients in July 2022.
Story Source:
Materials provided by Washington University in St. Louis. Original written by Brandie Jefferson. Note: Content may be edited for style and length. More

Artificial intelligence (AI) has created new possibilities for designing tailor-made proteins to solve everything from medical to ecological problems. A research team at the University of Bayreuth led by Prof. Dr. Birte Höcker has now successfully applied a computer-based natural language processing model to protein research. Completely independently, the ProtGPT2 model designs new proteins that are capable of stable folding and could take over defined functions in larger molecular contexts. The model and its potential are detailed scientifically in Nature Communications.
Natural languages and proteins are actually similar in structure. Amino acids arrange themselves in a multitude of combinations to form structures that have specific functions in the living organism — similar to the way words form sentences in different combinations that express certain facts. In recent years, numerous approaches have therefore been developed to use principles and processes that control the computer-assisted processing of natural language in protein research. “Natural language processing has made extraordinary progress thanks to new AI technologies. Today, models of language processing enable machines not only to understand meaningful sentences but also to generate them themselves. Such a model was the starting point of our research. With detailed information concerning about 50 million sequences of natural proteins, my colleague Noelia Ferruz trained the model and enabled it to generate protein sequences on its own. It now understands the language of proteins and can use it creatively. We have found that these creative designs follow the basic principles of natural proteins,” says Prof. Dr. Birte Höcker, Head of the Protein Design Group at the University of Bayreuth.
The language processing model transferred to protein evolution is called “ProtGPT2.” It can now be used to design proteins that adopt stable structures through folding and are permanently functional in this state. In addition, the Bayreuth biochemists have found out, through complex investigations, that the model can even create proteins that do not occur in nature and have possibly never existed in the history of evolution. These findings shed light on the immeasurable world of possible proteins and open a door to designing them in novel and unexplored ways. There is a further advantage: Most proteins that have been designed de novo so far have idealised structures. Before such structures can have a potential application, they usually must pass through an elaborate functionalization process — for example by inserting extensions and cavities — so that they can interact with their environment and take on precisely defined functions in larger system contexts. ProtGPT2, on the other hand, generates proteins that have such differentiated structures innately, and are thus already operational in their respective environments.
“Our new model is another impressive demonstration of the systemic affinity of protein design and natural language processing. Artificial intelligence opens up highly interesting and promising possibilities to use methods of language processing for the production of customised proteins. At the University of Bayreuth, we hope to contribute in this way to developing innovative solutions for biomedical, pharmaceutical, and ecological problems,” says Prof. Dr. Birte Höcker.
Story Source:
Materials provided by Universität Bayreuth. Note: Content may be edited for style and length. More

Researchers have developed and demonstrated the potential benefit of a simple set of physical gestures that participants in online group video meetings can use to improve their meeting experience. Paul D. Hills of University College London, U.K., and colleagues from University College London and the University of Exeter, U.K., present the technique, which they call Video Meeting Signals (VMS™), in the open-access journal PLOS ONE on August 3, 2022.
During the COVID-19 pandemic, online video conferencing has been a useful tool for industry, education, and social interactions. However, it has also been associated with poor mental well-being, poor communication, and fatigue.
To help overcome the challenges of online video meetings, Hills developed VMS, a set of simple physical gestures that can be used alongside verbal communication during a video meeting. The gestures — including two thumbs up to signal agreement or a hand over the heart to show sympathy — are meant to improve experiences by serving a similar function as subtle face-to-face signals, such as raised eyebrows, while being more visible in a small video setting.
To investigate the potential of VMS, Hills and colleagues first tested it among more than 100 undergraduate students. After half were trained on the technique, the students participated in two video-based seminars in groups of about 10 students each, before answering a survey about their experience.
Analysis of the survey results showed that, compared to students without VMS training, those with VMS training reported a better personal experience, better feelings about their seminar group, and better learning outcomes. Analysis of seminar transcripts also suggested that students with VMS training were more likely to use positive language.
Similar results were seen in a follow-up experiment with participants who were not students. This experiment also suggested that participants trained to use emojis instead of VMS gestures did not experience the same improved experience as participants with VMS training.
These findings suggest that VMS may be an effective technique to help overcome the challenges of video conferencing. In the future, the researchers plan to continue to study VMS, for instance by investigating the mechanisms that may underlie its effects and how to apply it for maximum benefit.
Paul D. Hills adds: “Our research indicates that there’s something about the use of gestures specifically which appears to help online interactions and help people connect and engage with each other. This can improve team performance, make meetings more inclusive and help with psychological wellbeing.”
Daniel C. Richardson adds: “Because you can’t make eye contact or pick up on subtle nods, gestures and murmurs of agreement or dissent in video conferences, it can be hard to know if people are engaged with what you’re saying. We found strong evidence that encouraging people to use more natural hand gestures had a much better effect on their experience.”
Story Source:
Materials provided by PLOS. Note: Content may be edited for style and length. More