RNA is used by our bodies to translate instructions from DNA into proteins, enzymes, and hormones and is also used by retroviruses such as HIV. However, identifying RNA sequences that have certain properties is difficult and very time-consuming.
To predict 19-mer siRNA inhibition efficiency from sequences.
- Used publicly available data as a training set (N=4,000)
- Sequence embedding
- Bidirectional long short-term memory network
- BIOPREDsi, Novartis model (Huesken et al., 2005): R=0.66
- MysiRNA (Mysara et al., 2012): max R=0.70; AUC=0.83
- SMEpred (Dar et al., 2016): R=0.72
White-labeled solution (BLAST integration) built on top of NeoPulse.
Customer can integrate new data into model through automated retraining
We were able to successfully train an AI model to recognize complex industrial parts using Neopulse 3.0 on AWS. The AI solution was built very quickly and was able to recognize objects in unpredictable, real-world environments with high accuracy.
Everybody seems confident in AI, and they actually enjoy solving various AI problems.
The vendor’s services are integral to providing AI solutions for a wider audience. They had an effective project management style, accented by a quick working style.