New machine learning algorithm uncovers time-delayed interactions in cells
Biologists have long understood the various parts within the cell. But how these parts interact with and respond to each other is largely unknown.
Quoting Professor Neda Baqeri, a scientist working in the emergent field of systems and synthetic biology, phys.org wrote, “We want to understand how cells make decisions, so we can control the decisions they make.
“A cell might decide to divide uncontrollably, which is the case with cancer. If we understand how cells make that decision, then we can design strategies to intervene.”
To better understand the mysterious interactions that occur inside cells, Baqeri and her team have designed a new machine learning algorithm that can help connect the dots among the genes’ interactions inside cellular networks.
Called ‘Sliding Window Inference for Network Generation’, or SWING, the algorithm uses time-series data to reveal the underlying structure of cellular networks.
Supported by the National Science Foundation, National Institutes of Health, and Northwestern’s Biotechnology Training Program, the research was published in the Proceedings of the National Academy of Sciences.
Justin Finkle and Jia Wu, graduate students in Baqeri’s laboratory, served as co-first authors of the paper.
In biological experiments, researchers often perturb a subject by altering its function and then measure the subject’s response.
For example, researchers might apply a drug that targets a gene’s expression level and then observe how the gene and downstream components react.
But it is difficult for those researchers to know whether the change in genetic landscape was a direct effect of the drug or the effect of other activities taking place inside the cell.
Finkle said, “While many algorithms interrogate cue-signal responses, we used time-series data more creatively to uncover the connections among different genes and put them in a causal order.”
SWING puts together a more complete picture of the cause-and-effect interactions happening among genes by incorporating time delays and sliding windows.
Rather than only looking at the individual perturbations and responses, SWING uses time-resolved, highthroughput data to integrate the time it takes for those responses to occur.
Wu said, “Other algorithms make the assumption that cellular responses appear more-or-less uniformly in time.
“We incorporated a window that includes different temporal ranges, so it captures responses that have dynamic profiles or different delays in time.”
Baqeri added, “The dynamics are really important because it’s not just if the cell responds to a certain input, but how.
“Is it slow? Is it fast? Is it a pulselike or more dynamic? If I introduced a drug, for example, would the cell have an immediate response and then recover or become resistant to the drug? Understanding these dynamics can guide the design of new drugs.”
After designing the algorithm, Baqeri’s team validated it in the laboratory in both computer simulations and in vitro in E. coli and S. cerevisiae models.
The algorithm is open source and now available online. And although it was initially designed to probe the interior, mysterious life of cells, the algorithm can be applied to many subjects that display activity over time.
Baqeri said, “The framework is not specific to cell signaling or even to biological contexts.
“It can be used in very broad contexts, such as in economics or finance. We expect that it could have a great impact.” The US National Aeronautics and Space Administration (NASA) plans to keep using the Mars Reconnaissance Orbiter (MRO) past the mid-2020s.
Quoting Michael Meyer, lead scientist of NASA’S Mars Exploration Program at NASA’S Washington headquarters, xinhuanet.com reported, “We are counting on Mars Reconnaissance Orbiter remaining in service for many more years.
“It’s not just the communications relay that MRO provides, as important as that is.
“It’s also the science-instrument observations. Those help us understand potential landing sites before they are visited, and interpret how the findings on the surface relate to the planet as a whole.”
The spacecraft already has worked more than double its planned mission life since launch on August 12, 2005.
It reached Mars and went into orbit on March 10, 2006. The mission’s extended service provides data relay from assets on Red Planet’s surface and observations with its science instruments, despite some degradation in capabilities.
MRO is a critical element for NASA’S Mars Program to support other missions for the long haul, so the mission team is finding ways to extend the spacecraft’s longevity.
There are many ways to achieve the goal, according to NASA’S Jet Propulsion Laboratory (JPL), who partners with Lockheed Martin Space, Denver, in operating the spacecraft.
One is increased reliance on a star tracker and less on aging gyroscopes. Another step is wringing more useful life from batteries.
MRO Project Manager Dan Johnston of JPL said, “In flight operations, our emphasis is on minimizing risk to the spacecraft while carrying out an ambitious scientific and programmatic plan.”
At Mars, MRO’S attitude changes almost continuously, with relation to the Sun and other stars, as it rotates once per orbit to keep its science instruments pointed downward at Mars.
From the orbiter’s 2005 launch until last year, it always used an inertial measurement unit, containing gyroscopes and accelerometers, for attitude control.
Earlier this month, the spacecraft completed its final full-swapover test using only stellar navigation to sense and maintain its orientation, without gyroscopes or accelerometers.
The project is evaluating the recent test and planning to shift indefinitely to this ‘all-stellar’ mode in March.
Johnston said, “In all-stellar mode, we can do normal science and normal relay.
“The inertial measurement unit powers back on only when it’s needed, such as during safe mode, orbital trim maneuvers, or communications coverage during critical events around a Mars landing.”
The batteries are recharged by the orbiter’s two large solar arrays. To increase the battery’s capacity and lifespan, the mission team now charges the batteries higher than before.
The project is also planning to reduce the time the orbiter spends in Mars’ shadow, when sunlight can’t reach the solar arrays, currently for about 40 minutes of every two-hour orbit.
By shifting the orbit to later in the afternoon, mission managers could reduce the amount of time the spacecraft spends in Mars’ shadow each orbit.
However, this option to prolong battery life would not be used until after MRO has supported new Mars mission landings in 2018 and 2021 by receiving transmissions during the landers’ critical arrival events.
MRO continues to orbit Mars over a full martian year and gather data with all six of the orbiter’s science instruments, a decade after what was initially planned as a two-year science mission to be followed by a two-year relay mission.
More than 1,200 scientific publications have been based on MRO observations, said NASA.
Two instruments, the High Resolution Imaging Science Experiment (HIRISE) camera and the Compact Reconnaissance Imaging Spectrometer for Mars (CRISM) mineral-mapper, were named most often in research papers.