Wed May 04 2022Alex Shepherd
It is always said that the job of a Data Scientist constitutes 20% modeling and 80% data cleaning. Every dataset that you deal with presents various challenges, the majority of which focus on the question of feasibility of the dataset itself. One of the sub-questions we ask as part of this is: Are there enough useable examples in order for our predictive models to generalize across wider populations?
biotx.ai’s COVID-19 treatment enters phase 2b clinical trials.
It has a clean and transparent safety record, it targets those patients that are severely ill, it works for new variants and it can be rolled out at scale. All development was done synthetically on our AI platform, in record time.
Tue Nov 30 2021Marco Schmidt
“The development of new drugs is complex, expensive and risky. Around 90 % of clinical trials fail because of the right selection of participating patients or because the drug target turns out not to be central to the disease mechanism, after sums in the billions have already been invested.”
Our CEO, Joern Klinger, talks about biotx.ai’s ability to fix these things, our new COVID-19 treatment and other things.
Link to the interview:
Fri Oct 29 2021Jörn Klinger
We're excited to host our 3rd biotx BEYOND webinar. This time it will be all about synthetic clinical trials and causal inference in clinical risk prediction models, and so bringing better treatments to patients faster.
Speakers will be Dr. Stefan Konigorski from the Hasso-Plattner-Institute and our own Dr. Marco Schmidt.
It will be on Dec 8, 2021 04:00 PM CET / 09:00 AM CST
Thu Oct 21 2021Marco Schmidt
Passive immunity shows a beneficial effect in the earliest stage of COVID-19 infection, prior to onset of symptoms, while immunosuppressants are beneficial for patients with critical respiratory failure much later in the course of infection. Therefore, a therapeutic gap exists and must be filled if the infection is not detected early and disease escalation is to be prevented.
In our latest webinar we discuss the future of clinical trials. John Zibert, CEO of Studies&Me talks about how his company conducts decentralized, virtual clinical trials. Our own Justin Cope then presents the technology behind biotx.ai, which is able to discover drug targets with a high likelihood of success in clinical trials.
Our treatment aims to prevent the dangerous overreaction of the immune system that results in patients becoming critically ill due to COVID-19. Using Biobank data, we identified CDK6 as a drug target. Inhibiting it will lower neutrophil cell count, which, when too high, is strongly linked with the severe and critical course of COVID-19. This potential treatment has been endorsed by Key Opionion Leaders from Harvard Medical School, Germany’s Robert-Koch-Institute and the University of Marburg. We are preparing a clinical phase 2b trial to show efficacy.
In the first post of this series, we introduced a type of data that is the opposite of big data: wide data. An extreme form of wide data is genomic data, where you have a limited sample size, usually in the hundreds or thousands, and for each sample/patient, you have millions of genetic variants that could cause a given disease.
biotx.ai's COVID-19 strategy is to find patterns linked to the disease in the genomes of patients as well as in the DNA of the virus itself. This process takes time, and the limiting factor is the rate at which the data becomes available.