Category Archives: Human Genetic Engineering

"During acute infection, HIV actively replicates," explained co-senior study investigator Kamel Khalili, Ph.D., professor and chair of the department of neuroscience at LKSOM. "With EcoHIV mice, we were able to investigate the ability of the CRISPR/Cas9 strategy to block viral replication and potentially prevent systemic infection." The excision efficiency of their strategy reached 96% in EcoHIV mice, providing the first evidence for HIV-1 eradication by prophylactic treatment with a CRISPR/Cas9 system.

In the third animal model, a latent HIV-1 infection was recapitulated in humanized mice engrafted with human immune cells, including T cells, followed by HIV-1 infection. "These animals carry latent HIV in the genomes of human T cells, where the virus can escape detection, Dr. Hu explained. Amazingly, after a single treatment with CRISPR/Cas9, viral fragments were successfully excised from latently infected human cells embedded in mouse tissues and organs.

In all three animal models, the researchers employed a recombinant adeno-associated viral (rAAV) vector delivery system based on a subtype known as AAV-DJ/8. "The AAV-DJ/8 subtype combines multiple serotypes, giving us a broader range of cell targets for the delivery of our CRISPR/Cas9 system," remarked Dr. Hu. Additionally, the researchers re-engineered their previous gene-editing apparatus to now carry a set of four guide RNAs, all designed to efficiently excise integrated HIV-1 DNA from the host cell genome and avoid potential HIV-1 mutational escape.

To determine the success of the strategy, the team measured levels of HIV-1 RNA and used a novel and cleverly designed live bioluminescence imaging system. "The imaging system, developed by Dr. Won-Bin Young while at the University of Pittsburgh, pinpoints the spatial and temporal location of HIV-1-infected cells in the body, allowing us to observe HIV-1 replication in real time and to essentially see HIV-1 reservoirs in latently infected cells and tissues," stated Dr. Khalili.

The researchers were excited by their findings and are optimistic about their next steps. The next stage would be to repeat the study in primates, a more suitable animal model where HIV infection induces disease, in order to further demonstrate the elimination of HIV-1 DNA in latently infected T cells and other sanctuary sites for HIV-1, including brain cells," Dr. Khalili concluded. "Our eventual goal is a clinical trial in human patients."

Continue reading here:
CRISPR Eliminates HIV in Live Animals - Genetic Engineering & Biotechnology News

First EPA-approved outdoor field trial for genetically engineered algae Science Daily "Just as agricultural experts for decades have used targeted genetic engineering to produce robust food crops that provide human food security, this study is the first step to demonstrate that we can do the same with genetically engineered algae," said ... and more »

Continue reading here:
First EPA-approved outdoor field trial for genetically engineered algae - Science Daily

French startup Vivet Therapeutics raised 37.5 million (about $41 million) in a Series A round of financing to support the development of gene therapies for rare inherited metabolic diseases. The firm was set up in 2016 to develop treatments based on adeno-associated virus (AAV) vector technology licensed exclusively from its close collaborator, the Fundacin para la Investigacin Mdica Aplicada (FIMA), at the Center for Applied Medical Research (CIMA) in Pamplona, Spain, and from Massachusetts Eye and Ear (MEE) in Boston.

Novartis Venture Fund and Columbus Venture Partners led the Series A investment round. Roche Venture Fund, HealthCap, Kurma Partners, and Ysios Capital also participated.Florent Gros, managing director at Novartis Venture Fund, commented, "We have searched extensively for next-generation AAV technologies and clinical applications. We are very excited by Vivet Therapeutics' clinical and commercial prospects; the company has outstanding management, assets, and capabilities."

Based in Paris, and with a wholly owned subsidiary in Spain, Vivetaims to develop gene therapies targeting disorders including Wilson disease, progressive familial intrahepatic cholestasis (PFIC), and citrullinemia.The firm is usinga novel, synthetic AAV, AAV-Anc80, to introduce genes into hepatocytes.Lead Wilson disease gene therapy program VTX801 comprises a truncated, functional version of the defective ATP7B gene, delivered directly into liver cells using the AAV vector technology. First-in-human trials with VTX801 are projected to start by the end of 2018.

Jean-Philippe Combal, Pharm.D., Ph.D., Vivet co-founder and CEO, noted, Early results from preclinical studies with VTX801 are very promising, and we are now well funded to advance this candidate into the clinic, while developing our portfolio and technologies."

Vivet's co-founders includeCombal (ex-Gensight Biologics, Sanofi),Jens Kurth, Ph.D. (ex-Anokion, Novartis), and Gloria Gonzlez-Aseguinolaza, Ph.D. (CIMA, University of Navarra).On announcement of Series A fundraising, Gloria Gonzlez-Aseguinolaza, Vivet CSO, said, By collaborating with leading institutions such as CIMA in Spain and MEE in the United States, Vivet has secured superior and novel gene therapy technologies and liver disease expertise. We believe these capabilities, combined with the international development expertise of the management team, create a company with very exciting prospects."

See original here:
Vivet Raises 37.5M to Develop Gene Therapies for Rare Liver Diseases - Genetic Engineering & Biotechnology News

The Trump administration wants to cut billions of dollars from funding biomedical research at the National Institutes of Health. Its unclear if it will be able to, considering how funding for cancer, diabetes, and other disease research tends to have bipartisan consensus, and many prominent Republicans in Congress are opposing the cuts.

The White House has suggested the size of the agencys budget roughly $32 billion in 2016 is the problem. Only in Washington do you literally judge the success of something by how much money you throw at the problem, not actually whether its solving the problem or coming up with anything, Sean Spicer, President Trumps press secretary, said in March, defending the proposed cuts of $6 billion to the 2018 budget. (Theres also talk of slashing $1.2 billion from NIH research grants this year.)

Bu we can judge the success of the NIH by measures other than the amount of money being spent at it. Because for decades scientists have been studying a version of this question: What does public spending on biomedical research actually buy us?

A lot, it turns out. So lets run through some of the evidence. (Many thanks to Matthew Hourihan, R&D budget analysis director at the American Association for the Advancement of Science, who helped compile this research.)

The NIH isnt just a research campus in Bethesda, Maryland. Its the major funder of biomedical research in universities across the country. Around 80 percent of the NIH budget goes to these grants.

Turns out giving money to some of the nations smartest people to answer tough problems in medicine and biology generates some good products and ideas, and stimulates the economy.

1) New patents for drugs, medical devices, and other technologies

In March, Science published a study looking at the impact of NIH grants over a 27-year period.

The main finding: 8.4 percent of all NIH grants go on to generate patents for new drugs, medical devices, or other medicine-related technologies.

The authors of the Science paper had previously figured out that a $10 million boost in NIH funding leads to a net increase of 2.3 patents. They estimate, roughly, that each patent is worth around $11.2 million in 2010 dollars. A back-of-the-envelope calculation indicate that a $10 million dollar increase in NIH funding would yield $34.7 million in firm market value, they reported in a recent NBER paper. Not a bad bet.

One single invention can make for a huge advancement in biotechnology. The NIHs most cited patent since 2000 was for a tiny and incredibly important invention: microscopic valves that allow scientists to create circuits of fluid that work kind of like computer chips. According to Battelle, a private research firm, the NIH spent about $500,000 developing these valves. Since then, biotech companies have seized on the invention, creating even smaller versions of chemistry labs that can diagnose diseases like HIV and Ebola (these are sometimes referred to as lab on a chip devices). Its an invention that has spurred a whole new biotech industry and also helps save lives.

2) Those patents then inspire new patents

The Science papers secondary finding is perhaps just as important: Grant money also has a carryover effect into the private sector. Around 30 percent of all scientific papers generated by NIH grants are cited by successful patent applications from private firms.

Which means even if a grant isnt directly generating a patent, it has a good chance of aiding the thinking behind the discovery of another.

And theres some research that suggests government funding is better at kickstarting this virtuous cycle than private sector funding: NIH-funded patents are cited by future patents at double the rate of those developed by the private sectors, a 2014 Nature Biotechnology paper found.

Furthermore, the Science analysis finds that both basic and applied research are just as likely to be cited by future patents. (Basic research seeks to understand the nuts and bolts of biological processes. It answers questions like: How does the retina work? Applied research seeks to generate ideas or products that can be put to use: Can this medical device improve retina functioning?)

That theres parity between basic and applied research means that generating knowledge for the sake of it is just as valuable as designing direct solutions to problems.

Between 2003 and 2013, every patent generated by an NIH grant was cited, on average, by five future patents, according to Battelle.

Again, this means research dollars spent by the NIH inspire other research institutions and industries to spend money on research and development, generating ideas to change and save lives.

Overall, Battelle calculated that every $100 million spent on NIH research leads to an additional $105.9 million in future research and development in both the public and private sectors.

3) Those patents form the basis of new biotech firms

NIH money lands in research institutions all across the country. In 2014, a report in the journal Research Policy asked: What happens to local economies that see that influx of NIH funds?

Quite simply, where NIH funds flow, new biotechnology firms follow. A $1 million increase in the average amount of federal R&D funding associates with an increase of 558 percent in the number of local biotechnology firm births a few years later, the authors reported.

In 2013, the Science Coalition, a science advocacy nonprofit, published a report on 100 companies that got their start because of federal research funds. Most of them are pretty small employing a few or a few dozen people. They produce things like custom strands of DNA for use in genetic engineering, or compounds to make pharmaceuticals more water-soluble.

NIH-funded research has also spurred gigantic new industries. Consider the human genome project, to which genetic testing companies like 23andMe, and the entire genomics industry, owe their existence. The human genome project cost around $3.8 billion. Its estimated to have generated $796 billion in economic impact.

4) All this research gives us drugs that save lives

In 2011, the New England Journal of Medicine published a report that found public sector funding is more effective at generating new, important drugs than spending in the private sector.

Looking at decades of Food and Drug Administration drug approvals, the researchers found virtually all the important, innovative vaccines that have been introduced during the past 25 years have been created by PSRIs [public sector research institutions].

Their definition of PSRI includes all universities, research hospitals, nonprofit research institutes, and federal laboratories in the United States, so its not just spending by the NIH.

The FDA prioritizes drugs in the approval pipeline based on potential impact. Drugs that began at public research institutions were more than two times more likely to be flagged as high-priority than those that began in the private sector. The analysis found that 46.2 percent of new-drug applications from PSRIs received priority reviews, as compared with 20.0 percent of applications that were based purely on private-sector research, an increase by a factor of 2.3.

And the public sector is particularly good at creating drugs to cure deadly diseases. Of the 153 approvals of drugs that began at public research institutions, 40 were for the treatment of cancer and 36 tackled infectious diseases, the report found.

Specifically, research also finds that spending at the NIH does spur new drug discoveries. A 2012 study found that a 10 percent increase in the funding for a particular disease yields about a 4.5 percent increase in novel drugs entering human clinical testing (phase I trials), after a lag of up to 12 years.

Heres a famous example: In the 1950s and 60s, NIH researcher Julius Axelrods work showed how neurotransmitters function in the brain, leading to a Nobel Prize. But more importantly, his ideas led to the drugs we now use to treat depression. All the major SSRIs [selective serotonin reuptake inhibitors] were discovered by pharmaceutical companies with the use of Axelrods basic discoveries, NEJM reports.

The White House believes spending at the NIH has gotten out of hand.

About 30 percent of the grant money that goes out is used for indirect expenses, which, as you know, means that that money goes for something other than the research thats being done, Health and Human Services Secretary Tom Price told reporters, justifying the proposed 18 percent cut to NIH funding for the 2018 budget.

Its true that the NIH also pays for overhead costs like electricity bills and lab equipment. And yes, there are legitimate concerns that these costs can spiral. Stat News has the best explanation of this argument here. In the piece, reporter Meghana Keshavan explains:

Critics suggest that the system gives universities an incentive to bump up their overhead costs, since the reimbursement rates are negotiated based on their previous years spending. So if a school builds a fancy new lab one year, it can claim the need for a higher reimbursement rate the next.

Should universities like Harvard, which have billion-dollar endowments, get federally funded money to keep the lights on?

The Government Accountability Office which analyzes government policies for inefficiencies flagged the potential for sprawling overhead costs at the NIH in a 2016 report, urging the institute to establish programs to better investigate potential fraud and abuse.

So theres some legitimate debate to be had about funding at the NIH. But its also clear that the severe, sudden cuts proposed by the Trump administration will have the immediate effect of stifling scientific progress.

For one, science need stable funding. Projects are funded on a multi-year basis. Yet Congress can change the NIH budget every year if it wants. The instability makes it harder to fund multi-year projects.

And already, competition for NIH grants is intense. Funding has basically plateaued over the past decade, while at the same time the cost of research keeps increasing and an ever-growing pool of PhDs is competing for a relatively smaller pile of grant money.

Consider this: In 2000, more than 30 percent of NIH grant applications got approved. Today, its closer to 17 percent. Its not crazy math: The less money there is to go around, the fewer projects get funded. If the Trump cuts go through, itll likely mean hundreds fewer research grants.

Congress will decide whether to include the immediate proposed cuts to this years budget by the end of April. But enthusiasm so far seems mixed.

When reporters asked Sen. Roy Blunt, a Republican who serves on the Senates Appropriations Committee, if the 2017 cuts could happen, he replied, No. No. Other Republicans are similarly skeptical, according to the New York Times. Rep. Kevin Yoder, a Republican from Kansas, has said, I will fight to ensure that these proposed cuts to medical research funding never make it into law.

But if Congress does vote to cut NIH funding which could very well happen who knows what ideas and breakthroughs well miss out on?

Go here to see the original:
Trump wants to cut billions from the NIH. This is what we'll miss out on if he does. - Vox

In the developed world, most people eat the root vegetable cassava only in tapioca pudding or bubble tea. But in sub-Saharan Africa, its the primary staple for half a billion people and is the continents most popular crop.It has gained prominence due to its tolerance to extreme weather conditions, making it a reliable food security crop.

But its future is in danger. It is threatened by twoviruses: brown streak (CBSD) and mosaic (CMD). Its estimated that $1.25 billion worth of cassava plants succumb to theviruses every year. It is the

African cassava mosaic virus

dream of farmers, scientists, and affected African governments to developa variety that is resistant to both of these killer diseases.

Previous efforts through conventional breeding have resulted in several tolerant varieties. These conventionally bred varieties, however, succumb to the virus after a short time and do not stay long enough in the ground to take subsistence farmers through dry spells. Farmers tend to prefer varieties with tubers that remain in the ground for long periods of time without rotting.

Geneticsolution?

In has stepped the Bill & Melinda Gates Foundation. The Foundation has releaseda $10.46 million grant through the Donald Danforth Plant Science Center for developing virus resistant cassava varieties. The project addressed varieties that would be grown inEast Africa (virus resistance) and West Africa (virus resistance & nutrients enhancement).

According to the Danforth Center, VIRCA Plusa collaborative project involving American and African institutions will use the grant to further joint efforts towards delivering disease-resistant cassava varieties.VIRCA Plus builds on the success of two predecessor projects: VIRCA project and BioCassava Plus project. The VIRCA project successfully developed varieties with strong and stable CBSD resistance in Kenya and Uganda. The two projects applied genetic engineering in developing these particular lines.

This is the second major project financed by the Gates Foundation to attack these deadly viruses. Another variety for Nigeria with elevated levels of iron and zinc, and resistant to viruses is also under research. But tests so far show the African BioCassava Plus project has developed cassava plants that accumulate greater than 10 times more iron and zinc than comparable varieties in Nigeria. In January, Gates himself outlinedthis project:

In the developed world, most people eat the root vegetable cassava only in tapioca pudding or bubble tea. But in Africa, its the primary staple for half a billion people and the continents most popular crop. Thats why Im super excited that scientists are using the most advanced hybridization techniques for the benefit of cassava farmers and those who depend on the crop. With the support of UK Department for International Development and our foundation, scientists are making great progress developing hybrids that are resistant to the major virus that cuts down on cassava yields (cassava mosaic virus). At the same time, these scientists are breeding strains that have more nutrients than the strains under cultivation today.

The joint efforts will not only involve partner institutions but will bring together conventional plant breeders and biotechnologists. One of the VIRCA Plus product development pathways is crossing the transgene resistant to brown streak virus with non transgenic varieties resistant to the mosaic virus in order to have a product resistant to both viruses. This decision meant VIRCA plus would need to employ the services of so-called human pollinators.

Human bees: Applying both conventional and genetic engineering breeding techniques

Some of the new breeding techniques that are being used on the transgenic crops are revolutionary. If breeding is the art and science of developing a new variety, thena special category of those involved in breeding, the pollinators or the human bees, fit in the art category.Unlike bees that visit flowers for nectar to feed the brood and carry along pollen that accidentally fertilize another flower, human pollinators are intentional. They must know the time of the day the female flower opens up to receive pollen. This time must not be missed as the gametes would eventually become nonviable. Pollinators ensure the male and the female flower about the same time to guarantee success. This, depending on the varieties under crossing, may require synchronized planting of the parental lines. Pollinators also keep records of where the pollen is coming from in order to maintain the integrity of the crosses.

Transgenic cassava is pollinated with a traditional variety.

Conventional breeding is more challenging for cassava pollinators because once they miss the chance of pollinating the flowers, either because the plants have flowered at different times or not flowered at all, they would have to wait for another flowering cycle or replant. Worse still, with one of the parents being transgenic, the research team might have to reapply again to government authorities for requisite permissions. This is costly in terms of time, deferred farmers expectations for solution, and additional financial burden on funding partners. A pollinator bears a big portion of these expectations and the pressure of making no mistakes.

14 years pollinating cassava

Solomon Agenoga is one of these human bees whose dream of a cassava variety resistant to cassava brown streak virus could be realized. He has been actively involved in the conventional breeding attempts that delivered different varieties to fight cassava brown streak disease at Ugandas national cassava program based in Namulonge.

Solomon grew up seeing a cassava crop grow up healthy without any major problems. He has eaten cassava for over 40 years. He recalls the emergence of CMD that threatened to wipe out cassava in his village. Scientists eventually developed CMD-resistant varieties but before longCBSD struck and up to today no resistant variety has beenreleased to farmers.

Solomon recalls, when I was young, It never crossed my mind that one day I would get directly involved in improving my main staple for yield, pests and diseases. For 14 years, Solomon has seen five different varieties released to farmers: NASE 14, NASE 16, NASE 19, NARO CAS1, NARO CAS2. To hisdisappointment, none of these varieties was resistant to bothviruses. All of themare tolerant but not resistant.His full satisfaction willonly come, he says, when a variety resistant to both mosaic virus and brown streak virus is developed. Following several conventional breeding attempts, only incorporating genetic engineering and conventional breeding approaches together could bring Solomons dream of a brown streak virus resistant variety into reality.

When the VIRCA project started in Solomons institution, there seemed to be irreconcilable differences between conventional breeding and genetic engineering. In fact, this technology that could do without flowers had a potential of rendering this experienced pollinator jobless. Solomon recalls, as a pollinator, in his mind, he could not imagine playing a role in this initiative that could help him save his childhood crop.

VIRCA Plus made a decision to incorporate conventional breeding techniques in its product development pathways. This decision elevated Solomon from being another pollinator to the key person who the project relied upon to deliver seeds of transgenic and non transgenic crosses. He rubbedshoulders with these modern scientists who transfer genes rather thanpollen. He left his home in Uganda for the first time to pollinate cassava across the border. It then occurred to him that he was playing an important role in ensuring that millions of African farmers get to have a variety that is resistant to the deadly CBSD.

Solomon has donehis best in leading a team of pollinators who, for the first time in their lives, make crosses involving a genetically modified parent working with a hybrid of conventional breeders and biotechnologists. According to Solomon, other than the additional regulatory procedures associated with transgenic crops, the steps involved were basically similar to the usual conventional breeding practices.

The Gates grant will not only unite scientists in rescuing millions of farm families from hunger due to crop failures, but could grant Solomon an opportunity to have a hand in saving his childhood crop from the viruses.

Isaac Ongu is an agriculturist, science writer and an advocate for science based interventions in solving agricultural challenges in Africa. Follow Isaac on twitter@onguisaac

For more background on the Genetic Literacy Project, read GLP on Wikipedia.

Read the rest here:
How 'human bees', biotechnologists and Gates Foundation are rescuing the African cassava staple - Genetic Literacy Project

The tech world has embraced Machine Learning (ML) for its powerful intuitive capabilitiesto increase click-through rates on ads, sell more books, and help you keep in touch with mom. Despite being increasingly common as a classification tool in applications ranging from transcriptomics, metabolomics, and neuronal synaptic activities, ML is still almost absent in the area of bioengineering. Why is that and what can we do to increase ML use in bioengineering?

Machine Learning algorithms that date back half a century are now commonly used for pattern-based analysis, including Decision Trees, Nearest Neighbors, Neural Nets, and more recently with significant success Deep Learninga version of Neural Net with more layers and more nodesreceived significant attention when it won against the best human in the ancient Chinese game of Go. Deep Learning has been enabled by access to new powerful computational hardware, in particular the graphical processing units (GPUs) originally developed for the gaming industry. These gaming GPUs allow for massively parallel computations, which is perfect for ML applications. Its comforting to know that Call of Duty brought something of value to this world. In recent years we have seen ML flourishing in a broad range of applications where there is sufficient amounts of data to digest and classify; from self-driving cars to Barcelona FC soccer strategy, to deciding if you get the bank loan.

But think instead about a common diabetes complication, diabetic retinopathy, which results in irreversible blindness if not caught early. There are today >400 million diabetic patients at risk, many in underserved areas with limited access to clinical diagnosis. In a recent JAMA publication, Google Research applied Deep Learning to diagnose diabetic retinopathy patients from photographs of their retina. An initial set of 128,000 retina images was analyzed and scored by trained ophthalmologists for signs of onset of diabetic retinopathy. The images and the scoring were then processed by Googles Deep Learning software to identify patterns in the images that correlated with the clinical scoring. The resulting algorithm was subsequently validated with a separate set of ~12,000 images that the software had not seen before.

Not only did the Deep Learning image analysis software recognize early signs of the disease just as well as the human experts, it did so much more consistently. Its easy to see a day in the not too distant future when anyone with a smartphone will be able to diagnose this disease accurately and save millions of people from going blind. It will be exciting to see how fast this and similar algorithms will transform medical image based diagnosis in the areas of radiology, pathology, and dermatology.

Small molecule drug discovery is another arena where ML is rapidly gaining traction. Companies ranging from GSK and Pfizer to Atomwise, Numerate, and InSilico Medicine are compiling large datasets of ligands, targets, and associated biological functions to identify and quantify the patterns of ligand-target interactions using Deep Learning. Atomwise has an undisclosed, previously approved drug candidate that blocks Ebola infection as well as another promising lead molecule to treat multiple sclerosis. Both were identified using Deep Learning to find patterns among thousands (in the case of Ebola) and millions (in the case of multiple sclerosis) of related molecules and their physicochemical properties.

So if we understand the powerful and intuitive nature of ML, what has limited its application in bioengineering?

Is it just too new an idea? Probably not, seeing as early as the 1990s, thought leaders like David Haussler at UCSC and Tim Hunkapiller at Caltech were publishing papers using hidden Markov models to capture patterns in DNA and protein datasets. These patterns have subsequently propagated into PFAM and other well-established databases to classify enzymes from protein sequences. So its not a new idea.

Is it because we lack sufficiently large datasets? Maybe. Most curated sequence datasets that include quantified biological function are tiny (in the hundreds) and nonsystematic in that variables are rarely tested in more than one context. On the other hand, Genbank and WGS today encompass ~2 x1012 bp of naturally existing biological sequences and are growing very rapidly. This enormous dataset is however inherently highly correlated because of its evolutionary origin, making it difficult to separate causality from correlation and thus limiting its use for identifying sequence-function relationships. Also, only a vanishingly small part of the data is associated with quantified biological function. Despite these limitations, the Genbank and WGS datasets are extremely informative for e.g. protein engineering as they can readily be used to tell us where not to go. Sequences, elements, or amino acid combinations that never or rarely occurred in biology below some statistical threshold can be assumed to not fold and to not generate new biological functions.

Is it because of differing philosophy of science? Thats part of it. Machine Learning is based on inductive reasoning, i.e. pattern recognition. The system learns from making many observations and finding patterns that can be generalized to a conclusion/hypothesis. Contrary to the inductive reasoning so abundantly and so successfully used by tech companies such as Google, biotechnology has historically been a discovery-based research field led by deductive reasoning. In deductive reasoning we start from a theory and make predictions about what the corresponding observations should be if the theory is correct. Then we look for those observations. However, biology is a gooey and redundant complex megadimensional mess of synergy and antagonism, and an abundance of variables that just came along for the 4 billion year ride of evolution. It quickly becomes humanly impossible to build complex hypotheses that explain biological observation in accordance with deductive reasoning. This instead is the type of data that inductive ML thrives on.

Is it because the cost of making specific observations? Yes and No. The medicinal chemist assessing structure-activity relationships has to independently make and characterize each molecule in the dataset at a large cost. There is thus a significant incentive for the chemist to design and test molecules as efficiently as possible using all available toolsincluding MLto ensure success. This is in stark contrast to the molecular biologist who can make large semi-random datasets through methods like error-prone PCR or DNA shuffling at basically no cost. These gene libraries at sizes of 107-109 can be screened for e.g. binding using phage display or similar high-throughput procedures. Accordingly, the cost of finding a binder is small, diminishing the perceived need for tools such as ML. However, finding a binder is still a long way from making a protein pharmaceutical.

Biotechnology is implicitly well set up for ML applications. Contrary to medicinal chemistry and image-based diagnosis, there are a defined number of available options at each residue and any sequence can be made and tested for function. If we can complement our historical dependence on deductive reasoning with the inductive inference from ML, and increasingly look at biology as something to be engineered instead of a discovery-based science, ML has a bright future in bioengineering.

After all, if we can see our way to a future where ML and a smart phone can diagnose anyone for diabetes-induced blindness, why not use the same methodology perfected over click-through ads and playing Go to make improved antibodies, better vaccines, and novel diagnostic sensors?

Original post:
Building Biology with Machine Learning - Genetic Engineering & Biotechnology News