Thread by @Biotech2k1

What is #TechBio

Everyone has heard of Biotech. These are companies that develop technology around develop drugs. Its a very biology driven endeavor. Its about looking at the science, coming up with ideas and then testing them in the lab to find ones that work.

1/ Where Biotech is driven by Biology, #TechBio is driven by technology. Its about using tools like Computer Aided Design, Computer Modeling, Artificial Intelligence #AI, and Machine Learning #ML to design drugs. Its a technology first type of drug design.

2/ I have heard of it referred to as the Bionic Scientist. I love that concept as it truly represents what TechBio is all about. Its about using tools of technology to enable Scientists to better develop drugs. Lets look at the statistics of drug development.

3/ The cost of high drug prices comes from the high failure rates in drug discovery. Even before a drug reaches a clinical trial. It goes through many iterations in the lab. They design a drug and test it. They have to tweak it over and over again to get it work as they desire.

4/ This alone is labor and cost intensive. Then it gets into a clinical trial. The statistics show that 90% of all drugs that enter Phase 1 fail to make it to commercial. There is a massive cost of failure in drug development. It can cost upward of $1 billion to develop a drug.

5/ The concept of deploying Technology in Biotechnology is to reduce the rates of failure and improve the cost of drug development. Artificial Intelligence can collect the vast knowledge of human science.

6/ They can collect all the published science, all the genomics data, all the clinical data, and even all the patient data. It can search this data in ways we might not even think of. We can collect vast volumes of new data with #automation and #AI.

7/ We can build super data bases by knocking out every gene in a robotics lab and record all the reactions into a super computer. We can collect that data and make correlations between things that scientists never thought of before.

8/ We can take models of data and build large data sets. We can use them to train Machine Learning Algorithms to take those large data sets and use them as training data so it can take in new information and apply that learning.

9/ This machine learning can allow scientists to screen thousands of potential molecules for the ones that meet the best pharmacodynamics and pharmacokinetics for what they want to target. Here are some examples.

10/ $RLAY uses physics based modeling of proteins and enzymes using computer aided design. They use this to train machine learning algos to how these proteins fold and move.

11/ The machine learning can screen through thousands of potential drugs and pick the exact few that meets the requirements the scientist wants. The scientist here still come up with the basic biology to find a protein to target.

12/ The technology allows them to quickly screen thousands of candidates to find a few worth moving into the clinic for testing. This will speed up the time to development while reducing the cost. This prevents moving molecules to the lab that would have failed.

13/ $EXAI uses Artificial Intelligence to collect all the possible information from literature, scientific publications, genomics and clinical data. It feeds all this information into the computer and uses that to look for new targets for drug development.

14/ The #AI can often find or make linkages in the data that the human brain might miss. This empowers scientists with new ideas for developing drugs.

16/ $RXRX uses automation and robotics to do millions of experiment per week. They use #CRISPR to knock out genes in cells 1 gene at a time. They record all the phenotypic changes in the supercomputer.

17/ Then the #AI and #ML can look at all this collected data and make conclusions about new potential drugs.
These are just some of the many examples of how technology like Computer modeling, Artificial Intelligence and Machine Learning can have on drug development.

18/ The ultimate goal isn't to replace the scientist but to empower the scientists with technology to develop drugs faster, cheaper and with higher levels of success to reduce costs to both companies and patients.