A multi-omics, multi-algorithm approach will unleash a new wave of understanding around Alzheimers disease and diagnosis, that in time, will make precision diagnostics practical, speakers predicted at the Alzheimers Association International Conference 2020 virtual event, held July 27-31. At least a part of that understanding will be based on the biomarkers identified during this meeting.
For analytics, a multi-tool approach is moving the emphasis from determining which algorithm is better to how to put the tools together (to get the most accurate information possible), Christos Davatzilos, Ph.D., University of Pennsylvania School of Medicine, said during a live chat. That enables researchers to be less focused on the engineering aspects and thus to work as translational scientists as more is learned about the brain and neurological diseases.
There are different criteria for performance than for triaging individuals based on biomarkers, Duygu Tosun-Turgut, Ph.D., University of California San Francisco, said. We need to be very mindful of the algorithms and how they are meant to be used for clinical practice of translational trials.
Therefore, as Davatzilos said, Its difficult to say any one algorithm is the best, but you can say this is best under certain conditions or for certain problems. Ultimately, AI wont be very different from biostatistics now, in that there are many options and many criteria researchers need to consider when choosing their tools.
So far, vetting various algorithms and approaches has received a good deal of attention.
We need such a diversity of means of discovery. With a multi-omics approach, researchers have independent sources of validation they can use to verify (their results) using a separate approach, said Paul M. Thompson, Ph.D., University of Southern California.
Initially, Thompson recalled, We learned a lot from the psychiatric researchers. They advised against using physical self-maintenance (PSM) scores, as criteria during the first round of analysis because of the high percentage of false positives those scored could generate. Now that more computing power is available and machine learning can be applied to the research, that advice becomes less valid because researchers have the means of sorting through the data.
There will be a new wave of discovery when people accept machine learning, Dr. Thompson added.
Machine learning opens the door to increasingly predictive approaches. For example, Andrew Saykin, Psy.D., director of the Indiana Alzheimer Disease Center, pointed out, Were being so stringent that were filtering out things that may be important in our concern to eliminate noise.
As an example, Thompson mentioned an MRI study of 11,000 young to middle-aged people.
We didnt find apolipoprotein E (APOE), the strongest known genetic risk factor for developing Alzheimers disease. That study shows that subjects ages matter, because APOE becomes more prevalent in people after age 60. It also suggests that, as Thompson said, If you build in interactions or other conditions, such as druggable characteristics, there may be better filters than the statistical sledgehammer that is being used today.
One possibility is a better understanding of the effects of various risk factors on cognitive trajectories in early- and late-onset Alzheimers disease. A team from South Koreas Sungkyunkwan University, the Samsung Medical Center, Samsung Alzheimer Research Medical Center, and in the US, from Harvard Medical School and Indiana University found that conventional risk factors accelerated cognitive decline in late-onset Alzheimers but slowed the decline among early-onset patients.
In studying the effects of APOE4, they found that outcomes varied based upon whether the patients carried that protein. Specifically, early-onset patients who did not carry APEO4 had a more rapid cognitive decline, but not those with late-onset Alzheimers disease. Likewise, higher levels of education accelerated cognitive decline in both early- and late-onset patients, but the most pronounced effects were among those with early-onset Alzheimers disease.
This research team also found that hypertension and obesity slowed cognitive decline in early-onset Alzheimers patients, but not in late-onset patients. Not surprisingly, the team noted that additional research is needed to determine the genetic and environmental factors behind declines in early-onset patients who lack any known risk factors.
In other meeting highlights, a poster presented Tuesday by Xiaohui Yao, Ph.D., and Li Shen, PhD., both of the University of Pennsylvania, predicted tissue-specific gene targets for Alzheimers disease. The researchers combined genome-wide association studies and data from expression quantitative trait loci (eQTL) to identify several genes in various tissues that have multiple associations (pleiotrophy) between their expression levels and the diagnosis of Alzheimers disease.
Fourteen genes and 13 brain tissues showed 64 significant associations. The gene CTB-171A8.1 exhibited the highest level of associations, with log p values typically beyond 10m and, for specific tissues, often above 12.5. The highest levels were associated with the cortex, cerebellum, and caudate basal ganglia, although activity was exhibited in all 13 brain tissues. The next most active gene was CEACAM19, which was involved in 10 of the tissues. Yao and Shen plan to continue investigating these genes as targets for functional validation.
More:
- IOM not webcast today. Why Not? - November 8th, 2009 [November 8th, 2009]
- National Academies skeptical at Best. - November 8th, 2009 [November 8th, 2009]
- Some Confusion Exists - November 8th, 2009 [November 8th, 2009]
- Why DTC Genomics IS Medicine. - November 8th, 2009 [November 8th, 2009]
- First Mari, Now Linda. Who's next? - November 8th, 2009 [November 8th, 2009]
- Is it true? - November 8th, 2009 [November 8th, 2009]
- Re-Reviewing the National Academies - November 8th, 2009 [November 8th, 2009]
- The problem with nonclinicians....... - November 8th, 2009 [November 8th, 2009]
- Crazy Night of Emails to Government - November 8th, 2009 [November 8th, 2009]
- Adrienne Carlson's Personalized Medicine. - November 8th, 2009 [November 8th, 2009]
- Tell Me, How do you feel now? Sherpa's RX - November 8th, 2009 [November 8th, 2009]
- This Just In. 23andMe to go to GPs. I love my readers!! - November 8th, 2009 [November 8th, 2009]
- Sorry so long away - November 8th, 2009 [November 8th, 2009]
- 2D6 Rears its ugly head..... - November 8th, 2009 [November 8th, 2009]
- Ok, Fine, Back to Plavix - November 8th, 2009 [November 8th, 2009]
- Kaiser a protoype for Collins' Aim - November 8th, 2009 [November 8th, 2009]
- A few months late to the party.... - November 8th, 2009 [November 8th, 2009]
- Stated Another Way....... - November 8th, 2009 [November 8th, 2009]
- Excuse Me? Harvard and Navigenics? WTF? - November 8th, 2009 [November 8th, 2009]
- Follow up to Yesterday's WTF? Harvard, Navi? and Pfizer??? - November 8th, 2009 [November 8th, 2009]
- Did you get your kit? Thanks Dr. Rob from MedCo - November 8th, 2009 [November 8th, 2009]
- Gluco...Wha? Parkinson's Disease and Glucocerebrosidase mutations. - November 8th, 2009 [November 8th, 2009]
- Away and now back, What did I miss???? 23andme layoffs? Selling Genomes for cheap up next! - November 8th, 2009 [November 8th, 2009]
- Change IS Needed. I agree with William, sometimes. - November 8th, 2009 [November 8th, 2009]
- Good Enough Science? Apparently so at 23andme - November 8th, 2009 [November 8th, 2009]
- Long QT Syndrome, location matters - December 13th, 2009 [December 13th, 2009]
- Congratulations Generation Health. Nice pick up! - December 13th, 2009 [December 13th, 2009]
- An argument 23andSerge can't win...23andme but not medicine - December 13th, 2009 [December 13th, 2009]
- Stop. Breathe. Repeat. An analysis of the direction of DTC Genomics Field. - December 13th, 2009 [December 13th, 2009]
- Hey DTC genomics, Stay Private, Stay Alive, Go Public and Die - December 13th, 2009 [December 13th, 2009]
- You can't have it both way. Either scared your genome is sold off or not. - December 13th, 2009 [December 13th, 2009]
- 15 Days Away Gives Time for Perspective. - December 13th, 2009 [December 13th, 2009]
- What about the SACGHS registry? Another missed opportunity? - December 13th, 2009 [December 13th, 2009]
- AJHG is in and my Favorite Muin is in it! But He Is NOT the Father! - December 13th, 2009 [December 13th, 2009]
- Navigenics for 23andMe prices? - December 18th, 2009 [December 18th, 2009]
- Lp(a) Maybe there's something there that wasn't there before? - December 24th, 2009 [December 24th, 2009]
- Another Year, Another Bankruptcy - December 31st, 2009 [December 31st, 2009]
- 5 Technologies going bye bye in this decade? - January 6th, 2010 [January 6th, 2010]
- Hackers, HITECH and HIPAA in DTC Genomics, Oh My! - January 7th, 2010 [January 7th, 2010]
- Personal Genomics Flop.....big Belly Flop! - January 8th, 2010 [January 8th, 2010]
- Gotta Love It. Even the daycare....... - January 11th, 2010 [January 11th, 2010]
- Congratulations Navigenics. You ARE a clinical lab! Uh-Oh... - January 12th, 2010 [January 12th, 2010]
- CETP, Jewish Centenarians and Alzheimers - January 14th, 2010 [January 14th, 2010]
- Enter the "Not" DTC Genomics Rep - January 17th, 2010 [January 17th, 2010]
- Why Dr. Vanier's Navigenics appointment is good for PM - January 22nd, 2010 [January 22nd, 2010]
- Holy Crap! MedCo Follows in CVS footsteps - February 3rd, 2010 [February 3rd, 2010]
- FDA, Warfarin, still not as sexy to me. - February 5th, 2010 [February 5th, 2010]
- Hype, Hype, Hype from a single study. - February 11th, 2010 [February 11th, 2010]
- I love my readers, even Renata M! - February 17th, 2010 [February 17th, 2010]
- How can insurers use DTC genomics to profile? - February 17th, 2010 [February 17th, 2010]
- 9p21.....ahem. Paynter et.al. Smackdown. Again. - February 18th, 2010 [February 18th, 2010]
- Hey! It's Pete Hulick! Are you Going to GET? - February 19th, 2010 [February 19th, 2010]
- I was wrong......AHEM - February 28th, 2010 [February 28th, 2010]
- G2C2, finally a tool for genomic education! - March 2nd, 2010 [March 2nd, 2010]
- Just 4 million? What 23andMe is worth. - March 5th, 2010 [March 5th, 2010]
- What a difference a year makes - March 9th, 2010 [March 9th, 2010]
- ........DTC Genomic Medicine? - March 12th, 2010 [March 12th, 2010]
- The FDA, 2c19 and the ACC - March 13th, 2010 [March 13th, 2010]
- The problem with Comparative Whole Genomics...... - March 13th, 2010 [March 13th, 2010]
- BRCA testing by 23andME is the same as Myriad Genetics. - March 15th, 2010 [March 15th, 2010]
- The Argument Against DTC Genomics Marketing and such - March 16th, 2010 [March 16th, 2010]
- A moment of Clarity. Some DTCG is not bad. - March 18th, 2010 [March 18th, 2010]
- SNPs for breast cancer risk? It Depends. - March 18th, 2010 [March 18th, 2010]
- How can MDVIP use Navigenics Test for Medicine? - March 18th, 2010 [March 18th, 2010]
- Why did P&G invest in Navigenics? - March 23rd, 2010 [March 23rd, 2010]
- PGx in DTCG? Doesn't stand up to Useful testing. - March 25th, 2010 [March 25th, 2010]
- End of Gene Patents? - March 29th, 2010 [March 29th, 2010]
- Sherpa Accepting Chief Medical Officership - April 3rd, 2010 [April 3rd, 2010]
- The Rumors of My Death........ - April 20th, 2010 [April 20th, 2010]
- Happy DNA Day! - April 25th, 2010 [April 25th, 2010]
- 99 USD, DNA day and patient letters - April 25th, 2010 [April 25th, 2010]
- 2C19, Navigenics and Clinical Reality. - May 1st, 2010 [May 1st, 2010]
- Coriell Personalized Medicine Collaborative rising - May 7th, 2010 [May 7th, 2010]
- Personal Genomes in Clinical Care. Quake paper is a waste! - May 11th, 2010 [May 11th, 2010]
- Personal Genomes in Clinical Care. Quake paper Falls Short! - May 13th, 2010 [May 13th, 2010]
- Last post edited by Drew - May 13th, 2010 [May 13th, 2010]
- GateKeeper? FCUK U! - May 13th, 2010 [May 13th, 2010]
- GateKeeper? F! U! - May 15th, 2010 [May 15th, 2010]
- Potential of genomic medicine, LOST - May 19th, 2010 [May 19th, 2010]
- How Bad Can a House Investigation be for DTC Genomics? - May 20th, 2010 [May 20th, 2010]