UK Biobank & the data economy – part 2

A couple of weeks back I wrote a post about repositories for all the data that users generate these days and what to do with it.  (See our post on Data banks, deposits, … data economy – part 1).

This past week I read an article (see ScienceDaily Genetics of brain structure … article) which partially exemplifies what that post talked about. The research used publicly available genetic information to tease out brain structure hereditary characteristics.  The Science Daily article was a summary of research done at the University of Oxford using information provided from the UK Biobank.

Biobank as a data bank

The Biobank has recruited 500K participants from the UK,  aged 40-69,  between 2006-2010, to share their anonymized health data with researchers and scientist around the world. The Biobank is set up as a Scottish charity, funded by various health organizations in UK both gov’t and private. 

In addition to information collected during the baseline assessment: 

  • 100K participants have worn a 24 hour health monitoring device for a week and 20K have signed up to repeat this activity.
  • 500K participants are providing have been genotyped (DNA sequencing to determine hereditary genes)
  • 100K participants will be medically scanned (brain, heart, abdomen, bones, carotid artery) with images stored in the Biobank
  • 100K participants have signed up to receive questionnaires asking  about diet, exercise, work history, digestive health and other medical indicators..

There’s more. Biobank is linking to electronic health records (EHR) of participants to track their health over time. The Biobank is also starting to provide blood analysis and other detailed medical measures of subjects in the study.

UK Biobank (data bank) information uses

“UK Biobank is an open access resource. The Resource is open to bona fide scientists, undertaking health-related research that is in the public good. Approved scientists from the UK and overseas and from academia, government, charity and commercial companies can use the Resource. ….” (from UK Biobank scientists page).

Somewhat like open source code, the Biobank resource is made available to anyone (academia as well as industry), that can make valid use of its data BUT any research derived from its data must be published and made freely available to the Biobank and the world.

Biobank’s papers page documents some of the research that has already been published using their data. It lists the paper on genetics of brain study mentioned above and dozens more.

Differences from Data Banks

In the original data bank post:

  1. We thought data was only needed by  AI/deep learning. That seems naive now. The Biobank shows that AI/deep learning is not the only application/research that needs data.
  2. We thought data would be collected by only by hyper-scalars and other big web firms during normal user web activity. But their data is not the only data that matters.
  3. We thought data would be gathered for free. Good data can take many forms, and some may cost money.
  4. We thought profits from selling data would be split between the bank and users and could fund data bank operations. But in the Biobank, funding came from charitable contributions and data is available for free (to valid researchers).

Data banks can be an invaluable resource and may take many forms. Data that’s difficult to find can be gathered by charities and others that use funding to create, operate and gather the specific information needed for targeted research.

Comments?

Photo Credit(s): Bank on it by Alan Levine

Latest MRI – two screws in the kneecap by Becky Stern

Other graphics from the Genetics of brain structure… paper

 

 

Random access, DNA object storage system

Read a couple of articles this week Inching closer to a DNA-based file system in ArsTechnica and DNA storage gets random access in IEEE Spectrum. Both of these seem to be citing an article in Nature, Random access in large-scale DNA storage (paywall).

We’ve known for some time now that we can encode data into DNA strings (see my DNA as storage … and Genomic informatics takes off posts).

However, accessing DNA data has been sequential and reading and writing DNA data has been glacial. Researchers have started to attack the sequentiality of DNA data access. The prize, DNA can store 215PB of data in one gram and DNA data can conceivably last millions of years.

Researchers at Microsoft and the University of Washington have come up with a solution to the sequential access limitation. They have used polymerase chain reaction (PCR) primers as a unique identifier for files. They can construct a complementary PCR primer that can be used to extract just DNA segments that match this primer and amplify (replicate) all DNA sequences matching this primer tag that exist in the cell.

DNA data format

The researchers used a Reed-Solomon (R-S) erasure coding mechanism for data protection and encode the DNA data into many DNA strings, each with multiple (metadata) tags on them. One of tags is the PCR primer tag header, another tag indicates the position of the DNA data segment in the file and an end of data tag that is the same PCR primer tag.

The PCR primer tag was used as sort of a file address. They could configure a complementary PCR tag to match the primer tag of the file they wanted to access and then use the PCR process to replicate (amplify) only those DNA segments that matched the searched for primer tag.

Apparently the researchers chunk file data into a block of 150 base pairs. As there are 2 complementary base pairs, I assume one bit to one base pair mapping. As such, 150 base pairs or bits of data per segment means ~18 bytes of data per segment. Presumably this is to allow for more efficient/effective encoding of data into DNA strings.

DNA strings don’t work well with replicated sequences of base pairs, such as all zeros. So the researchers created a random sequence of 150 base pairs and XOR the file DNA data with this random sequence to determine the actual DNA sequence to use to encode the data. Reading the DNA data back they need to XOR the data segment with the random string again to reconstruct the actual file data segment.

Not clear how PCR replicated DNA segments are isolated and where they are originally decoded (with a read head). But presumably once you have thousands to millions of copies of a DNA segment,  it’s pretty straightforward to decode them.

Once decoded and XORed, they use the R-S erasure coding scheme to ensure that the all the DNA data segments represent the actual data that was encoded in them. They can then use the position of the DNA data segment tag to indicate how to put the file data back together again.

What’s missing?

I am assuming the cellular data storage system has multiple distinct cells of data, which are clustered together into some sort of organism.

Each cell in the cellular data storage system would hold unique file data and could be extracted and a file read out individually from the cell and then the cell could be placed back in the organism. Cells of data could be replicated within an organism or to other organisms.

To be a true storage system, I would think we need to add:

  • DNA data parity – inside each DNA data segment, every eighth base pair would be a parity for the eight preceding base pairs, used to indicate when a particular base pair in eight has mutated.
  • DNA data segment (block) and file checksums –  standard data checksums, used to verify and correct for double and triple base pair (bit) corruption in DNA data segments and in the whole file.
  • Cell directory – used to indicate the unique Cell ID of the cell, a file [name] to PCR primer tag mapping table, a version of DNA file metadata tags, a version of the DNA file XOR string, a DNA file data R-S version/level, the DNA file length or number of DNA data segments, the DNA data creation data time stamp, the DNA last access date-time stamp,and DNA data modification data-time stamp (these last two could be omited)
  • Organism directory – used to indicate unique organism ID, organism metadata version number, organism unique cell count,  unique cell ID to file list mapping, cell ID creation data-time stamp and cell ID replication count.

The problem with an organism cell-ID file list is that this could be quite long. It might be better to somehow indicate a range or list of ranges of PCR primer tags that are in the cell-ID. I can see other alternatives using a segmented organism directory or indirect organism cell to file lists b-tree, which could hold file name lists to cell-ID mapping.

It’s unclear whether DNA data storage should support a multi-level hierarchy, like file system  directories structures or a flat hierarchy like object storage data, which just has buckets of objects data. Considering the cellular structure of DNA data it appears to me more like buckets and the glacial access seems to be more useful to archive systems. So I would lean to a flat hierarchy and an object storage structure.

Is DNA data is WORM or modifiable? Given the effort required to encode and create DNA data segment storage, it would seem it’s more WORM like than modifiable storage.

How will the DNA data storage system persist or be kept alive, if that’s the right word for it. There must be some standard internal cell mechanisms to maintain its existence. Perhaps, the researchers have just inserted file data DNA into a standard cell as sort of junk DNA.

If this were the case, you’d almost want to create a separate, data  nucleus inside a cell, that would just hold file data and wouldn’t interfere with normal cellular operations.

But doesn’t the PCR primer tag approach lend itself better to a  key-value store data base?

Photo Credit(s): Cell structure National Cancer Institute

Prentice Hall textbook

Guide to Open VMS file applications

Unix Inodes CSE410 Washington.edu

Key Value Databases, Wikipedia By ClescopOwn work, CC BY-SA 4.0, Link

New techniques shed light on ancient codex & palimpsests

Read an article the other day from New York Times, A fragile biblical text gets a virtual read about an approach to use detailed CT scans combined with X-rays to read text on a codex (double sided, hand bound book) that’s been mashed together for ~1500 years.

How to read a codex

Dr. Seales created the technology and has used it successfully to read a small charred chunk of material that was a copy of the earliest known version of the Masoretic text, the authoritative Hebrew bible.

However, that only had text on one side. A codex is double sided and being able to distinguish between which side of a piece of papyrus or parchment was yet another level of granularity.

The approach uses X-ray scanning to triangulate where sides of the codex pages are with respect to the material and then uses detailed CT scans to read the ink of the letters of the text in space. Together, the two techniques can read letters and place them on sides of a codex.

Apparently the key to the technique was in creating software could model the surfaces of a codex or other contorted pieces of papyrus/parchment and combining that with the X-ray scans to determine where in space the sides of the papyrus/parchment resided. Then when the CT scans revealed letters in planar scans (space), they could be properly placed on sides of the codex and in sequence to be literally read.

M.910, an unreadable codex

In the article, Dr. Seales and team were testing the technique on a codex written sometime between 400 and 600AD that contained the Acts of the Apostles and one of the books of the New Testament and possibly another book.

The pages had been merged together by a cinder that burned through much of the book. Most famous codexes are named but this one was only known as M.910 for the 910th acquisition of the Morgan Library.

M.910 was so fragile that it couldn’t be moved from the library. So the team had to use a portable CT scanner and X-ray machine to scan the codex.

The scans for M.910 were completed this past December and the team should start producing (Coptic) readable pages later this month.

Reading Palimpsests

A palimpsests is a manuscript on which the original writing has been obscured or erased. Another article from UCLA Library News, Lost ancient texts recovered and published online,  that talks about the use of multi-wave length spectral imaging to reveal text and figures that have been erased or obscured from Sinai Palimpsests.  The texts can be read at Sinaipalimpsests.org and total 6800 pages in 10 languages.

In this case the text had been deliberately erased or obscured to reuse parchment or papyrus. The writings are from the 5th to 12th centuries.  The texts were located in St. Catherine’s Monastary and access to it’s collection of ancient and medieval manuscripts is considered 2nd only to that in the Vatican Library.

~~~~

There are many damaged codexes scurried away in libraries throughout the world today but up until now they were mere curiosities. If successful, this new technique will enable scholars to read their text, translate them and make them available for researchers and the rest of the world to read and understand.

Now if someone could just read my WordPerfect files from 1990’s and SCRIPT/VS files from 1980’s I’d be happy.

Comments:

Picture credit(s): From NY Times article by Nicole Craine 

Acts of apostles codex

From Sinai Palimpsests Project website

Scratch file use in HPC @ORNL, a statistical analysis

Attended SC17 (Supercomputing Conference) this past week and I received a copy of the accompanying research proceedings. There are a number of interesting papers in the research and I came across one, Scientific User Behavior and Data Sharing Trends in a Peta Scale File System by Seung-Hwan Lim, et al from Oak Ridge National Laboratory (ORNL) and the use of files at the Oak Ridge Leadership Computing Facility (OLCF) which was very interesting.

The paper statistically describes the use of a Scratch files in a multi PB file system (Lustre) at OLCF from January 2015 to August 2016. The OLCF supports over 32PB of storage, has a peak aggregate of over 1TB/s and Spider II (current Lustre file system) consists of 288 Lustre Object Storage Servers, all interconnected and connected to all the supercomputing cluster of  servers via an InfiniBand network. Spider II supports all scratch storage requirements for active/queued jobs for the Titan (#4 in Top 500 [super computer clusters worldwide] list) and other clusters at ORNL.

ORNL uses an HPSS (High Performance Storage System) archive for permanent storage but uses the Spider II file system for all scratch files generated and used during supercomputing applications.  ORNL is expecting Spider III (2018-2023) to host 10 billion files.

Scratch files are purged from Spider II after 90 days of no access.The paper is based on metadata analysis captured during scratch purging process for 500 days of access.

The paper displays a number of statistics and metrics on the use of Spider II:

  • Less than 3% of projects have a directory depth >15, the maximum directory depth was recorded at 432, with most projects having a shallow (<10) directory depth.
  • A project typically has 10X the files that a specific researcher has and a median file count/researcher is 2000 files with a median project having 20,000 files.
  • Storage system performance is actively managed by many projects. For instance, 20 out of 35 science domains manually managed their Lustre cluster configuration to improve throughput.
  • File count continues to grow and reached a peak of 1B files during the time being analyzed.
  • On average only 3% of files were accessed readonly, 10% of files updated (read-write) and 76% of files were untouched during a week period. However, median and maximum file age was 138 and 214 days respectively, which means that these scratch files can continue to be accessed over the course of 200+ days.

There was more information in the paper but one item missing is statistics on scratch file size distribution a concern.

Nonetheless, in paints an interesting picture of scratch file use in HPC application/supercluster environments today.

Comments?

(Storage QoM 16-001): Will we see NVM Express (NVMe) drives GA’d in enterprise storage over the next year

NVMeFirst, let me state that QoM stands for Question of the Month. Doing these forecast can be a lot of work, and rather than focusing my whole blog on weekly forecast questions and answers, I would like to do something else as well. So, from now on we are doing only one new forecast a month.

So for the first question of 2016, we will forecast whether NVMe SSDs will be GA’d in enterprise storage over the next year.

NVM Express (NVMe) means the new PCIe interface for SSD storage. Wikipedia has a nice description of NVMe. As discussed there, NVMe was designed for higher performance and enhanced parallelism which comes with the PCI Express (PCIe) bus. The current version of the NVMe spec is 1.2a (available here).

GA means generally available for purchase by any customer.

Enterprise storage systems refers to mid-range and enterprise class storage systems from major AND non-major storage vendors, which includes startups.

Over the next year means by 19 January 2017.

Special thanks to Kacey Lai (@mrdedupe), Primary Data for suggesting this months question.

Current and updates to previous forecasts

 

Update on QoW 15-001 (3DX) forecast:

News out today indicates that 3DX (3D XPoint non-volatile memory) samples may be available soon but it could take another 12 to 18 months to get it into production. 3DX manufacturing is more challenging than current planar NAND technology and uses about 100 new materials, many of which are currently single sourced. We already built into our 3DX forecast potential delays in reaching production in 6 months. The news above says this could be worse than  expected. As such, I feel even stronger that there is less of a possibility of 3DX shipping in storage systems by next December. So I would update my forecast for QoW 15-001 to NO with an 0.75 probability at this time.

So current forecasts for QoW 15-001 are:

A) YES with 0.85 probability; and

B) NO with 0.75 probability

Current QoW 15-002 (3D TLC) forecast

We have 3 active participants, current forecasts are:

A) Yes with 0.95 probability;

B) No with 0.53 probability; and

C) Yes with 1.0 probability

Current QoW 15-003 (SMR disk) forecast

We have 1 active participant, current forecast is:

A) Yes with 0.85 probability

 

Primary data’s path to better data storage presented at SFD8

IMG_5606rz A couple of weeks ago we met with Primary Data, Lance Smith, CEO, David Flynn, CTO and Kaycee Lai, SVP Product & Sales who were presenting at Storage Field Day 8 (SFD8, videos of their sessions available here). Primary Data has just emerged out of stealth late last year and has ~$60M in funding. Also they have Steve Wozniak (of Apple fame) as Chief Scientist, but he wasn’t at the SFD8 session 🙁

Primary Data seems out to change the world. At first I thought this was just another form of storage virtualization but they are laser focused on data virtualization or what they call data mobility. It differs from pure storage virtualization by being outside the data path.  (I have written about data virtualization before as well as the data hypervisor a long time ago). Nowadays they seem to be using the tag line of data in motion.

Why move data?

David has a theory behind the proliferation of startup storage companies. The spectrum behind capacity and performance has gotten immense, over time, which has provided an opening for a number of companies to address these widening needs.

David believes that caching at the storage system or in the servers is an attempt to address this issue by “loaning” the data from the storage silo to the cache. This is trying to supply a lower cost $/IOP for the data. Similar considerations are apparent at the other side where customer’s use archive or backup services to take advantage of much cheaper $/GB storage.

However, given the difficulty of moving data around in present day storage environments, customer data has become essentially immobile. Primary Data is trying to bring about a data mobility revolution and allow data to move over this spectrum of performance and capacity of storage with ease. Doing so easily, will provide significant benefits as customers can more fully take advantage of the various levels of performance and capacity in their data center storage environments.

Primary Data architecture

IMG_5607Primary Data is providing data mobility by using their meta-data service called the DataSphere appliance and their client software running on host servers called the Data Portal. Their offering can be best explained in three layers:

  • Data virtualization layer – provides continuity of identity and continuity of access across multiple physical storage systems. That is the same data (identity continuity) can be accessed wherever it resides (access continuity) by server applications. Such access and identity must transcend access protocols and interfaces. The Data Portal client software intercepts the server data activity and does control plane activity using the DataSphere appliance and performs IO directly using the physical storage.
  • Objective based data management – supplies a data affinity service. That is data can have a temporary location relationship with physical storage depending on the current performance (R:W, IOPS, bandwidth, latency) and protection (durability, availability, disaster recoverability, security, copy-ability, version-ability) characteristics of the data. These data objectives are matched to the capabilities or service catalog of the storage infrastructure and data objectives can change over time
  • Analytics in the loop – detects the performance and other characteristics of the storage and data in real-time. That is by monitoring the storage IO activity Primary Data can determine the actual performance attribute of the storage. Similarly, by monitoring the applications IO characteristics over time the system can determine the performance objectives of its data. The system also takes advantage of SMI-S to define some of the other characteristics of the storage systems.

How does Primary Data work?

Primary Data has taken advantage of parallel NFS extensions (pNFS) in NFSv4 to externalize and separate the storage control plane from the IO data plane. This works well for native Linux where the main developer of the Linux file system stack is on their payroll.IMG_5608rz

In Windows they put a filter driver in front of SMB to split off the control from data IO plane. Something similar is done for VMware ESX servers to supply the control-data plane split but in this case there is a software defined Data Portal that goes along with the DataSphere Service client that can do it all within the same ESX server. Another alternative exists and that is to use the Data Portal appliance as a storage virtualization service but then the IO data path goes through the portal.

According to their datasheet they currently support data virtualization services for NetApp cDOT and 7-mode, EMC Isilon OneFS7.2, and Nexenta 4.x&5.0 but plan on more.

They are not quite GA yet, but are close.

Comments?

 

 

 

The data is the hybrid cloud

CRKtHnqVEAABeviI have been at NetApp Insight2015 conference the past two days and have been struck with one common theme. They have been talking since the get-go about the Data Fabric and how Clustered Data ONTAP (cDOT) is the foundation to the NetApp Data Fabric which spans on premises, private cloud, off premises public cloud and everything in between.

But the truth of the matter is that it’s data that real needs to span all these domains. Hybrid cloud really needs to have data movement everywhere. NetApp cDOT is just the enabler that helps move the data around much easier.

NetApp cDOT data services

From a cDOT perspective, NetApp has available today:

  • Cloud ONTAP – a software defined ONTAP storage service executing in the cloud, operating on cloud server provider hardware using DAS storage and providing ONTAP data services for your private cloud resident data.
  • ONTAP Edge – similar to Cloud ONTAP, but operating on premises with customer commodity server & DAS hardware and providing ONTAP data services.
  • NetApp Private Storage (NPS) – NetApp storage systems operating in a “near cloud” environment that is directly connected to cloud service providers that provides NetApp storage services with low latency/high IOPs storage to cloud compute applications.
  • NetApp cDOT on premises storage hardware – NetApp storage hardware with All Flash FAS as well as normal disk-only and hybrid FAS storage hardware supplying ONTAP data services to on premises applications.

NetApp Data Fabric

NetApp’s Data Fabric is built on top of ONTAP data services and allows a customer to use any of the above storage instances to host their private data. Which is great in and of itself, but when you realize that a customer can also move their data from anyone of these ONTAP storage instances to any other storage instance that’s when you see the power of the Data Fabric.

The Data Fabric depends mostly on storage efficient ONTAP SnapMirror data replication and ONTAP data cloning capabilities. These services can be used to replicate ONTAP data (LUNs/volumes) from one cDOT storage instance to another and then use ONTAP data cloning services to create accessible copies of this data at the new location. This could be on premises to near cloud, to public cloud or back again, all within the confines of ONTAP data services.

Data Fabric in action

Now I like the concept but they also showed an impressive demo of using cDOT and AltaVault (NetApp’s solution acquired last year from Riverbed, their SteelStor backup appliance) to perform an application consistent backup of a SQL database. But once they had this it went a little crazy.

They SnapMirrored this data from the on premises storage to a near cloud, NPS storage instance, then cloned the data from the mirrors and after that fired up applications running in Azure to process the data. Then they shut down the Azure application and fired up a similar application in AWS using the exact same NPS hosted data. Of course they then SnapMirrored the same backup data (I think from the original on premises storage) to Cloud ONTAP, just to show it could be done there as well.

Ok I get it, you can replicate (mirror) data from any cDOT storage instance (whether on premises or remote site or near cloud NPS or in the cloud using Cloud ONTAP or …). Once there you can clone this data and use it with applications running in any environment running with access to this data instance (such as AWS, Azure and cloud service providers).

And I like the fact that all this can be accomplished in NetApp’s Snap Center software. And I especially like the fact that the clones don’t take up any extra space and the replicant mirroring is done in a quick, space efficient (read deduped) manner

But, having to setup a replication or mirror association between cDOT on premises and cDOT at NPS or Cloud ONTAP and then having to clone the volumes at the target side seems superflous. What I really want to do is just copy or move the data and have it be at the target site without the mirror association in the middle. It’s almost like what I want is CLONE that operates across cDOT storage instances wherever they reside.

Well I’m an analyst and don’t have to implement any of this (thank god). But what NetApp seems to have done is to use their current tools and ONTAP data service capabilities to allow customer data to move anywhere it needs to be, in  customer controlled, space efficient, private and secure manner. Once hosted at the new site, applications have access to this data and customers still have all the ONTAP data services they had on premises but in cloud and near cloud locations.

Seems pretty impressive to me for all of a customer’s ONTAP data. But when you combine the Data Fabric with Foreign LUN Import (importing non-NetApp data into ONTAP storage) and FlexArray (storage virtualization under ONTAP) you can see how all the Data Fabric can apply to non-NetApp storage instances as well and then it becomes really interesting.

~~~~

There was a company that once said that “The Network is the Computer” but today, I think a better tag line is “The Data is the Hybrid Cloud”.

Comments?

 

Nanterro emerges from stealth with CNT based NRAM

512px-Types_of_Carbon_NanotubesNanterro just came out of stealth this week and bagged $31.5M in a Series E funding round. Apparently, Nanterro has been developing a new form of non-volatile RAM (NRAM), based on Carbon Nanotubes (CNT), which seems to work like an old T-bar switch, only in the NM sphere and using CNT for the wiring.

They were founded in 2001, and are finally  ready to emerge from stealth. Nanterro already has 175+ issued patents, with another 200 patents pending. The NRAM is currently in production at 7 CMOS fabs already and they are sampling 4Mb NRAM chips  to a number of customers.

NRAM vs. NAND

Performance of the NRAM is on a par with DRAM (~100 times faster than NAND), can be configured in 3D and supports MLC (multi-bits per cell) configurations.  NRAM also supports orders of magnitude more (assume they mean writes) accesses and stores data much longer than NAND.

The only question is the capacity, with shipping NAND on the order of 200Gb, NRAM is  about 2**14X behind NAND. Nanterre claims that their CNT-NRAM CMOS process can be scaled down to <5nm. Which is one or two generations below the current NAND scale factor and assuming they can pack as many bits in the same area, should be able to compete well with NAND.They claim that their NRAM technology is capable of Terabit capacities (assumed to be at the 5nm node).

The other nice thing is that Nanterro says the new NRAM uses less power than DRAM, which means that in addition to attaining higher capacities, DRAM like access times, it will also reduce power consumption.

It seems a natural for mobile applications. The press release claims it was already tested in space and there are customers looking at the technology for automobiles. The company claims the total addressable market is ~$170B USD. Which probably includes DRAM and NAND together.

CNT in CMOS chips?

Key to Nanterro’s technology was incorporating the use of CNT in CMOS processes, so that chips can be manufactured on current fab lines. It’s probably just the start of the use of CNT in electronic chips but it’s one that could potentially pay for the technology development many times over. CNT has a number of characteristics which would be beneficial to other electronic circuitry beyond NRAM.

How quickly they can ramp the capacity up from 4Mb seems to be a significant factor. Which is no doubt, why they went out for Series E funding.

So we have another new non-volatile memory technology.On the other hand, these guys seem to be a long ways away from the lab, with something that works today and the potential to go all the way down to 5nm.

It should interesting as the other NV technologies start to emerge to see which one generates sufficient market traction to succeed in the long run. Especially as NAND doesn’t seem to be slowing down much.

Comments?

Picture Credits: Wikimedia.com