AI POLICY

Clinical Genomics


Uncover hidden patterns to benefit disease research and CRISPR genomic tools





With increasing complexity in genomic data, we help identify meaningful patterns for healthcare and research




OptimalAI supports the convergence of genomic and machine learning research. We can help improve the understanding of hidden patterns in large and complex genomics data sets from clinical research projects. Our analyses can benefit disease research and genomic tools like CRISPR.

Why the need for AI/ML in genomics?

The Human Genome Project, completed in 2003, covered about 92% of the total human genome sequence. The final, complete human genome sequence was described in a set of six papers in the April 1, 2022, issue of Science. Companion papers were also published in several other journals.

This milestone has led to the generation of an extraordinary amount of genomic data. Estimates predict that genomics research will generate between 2 and 40 exabytes of data within the next decade. DNA sequencing and other biological techniques will continue to increase the number and complexity of such data sets. This is why genomics researchers need AI/ML-based computational tools that can handle, extract and interpret the valuable information hidden within this large trove of data.


Identifying facial phenotypes of genetic disorders

Syndromic genetic conditions affect 8% of the population and many of these have recognizable facial features that are highly informative to clinical geneticists. Recent studies show that facial analysis technologies identify only a few disease phenotypes, limiting their role in clinical settings, where hundreds of diagnoses must be considered.  Facial image analysis using computer vision and deep-learning algorithms, can help quantify similarities to hundreds of syndromes.  This potentially adds value to phenotypic evaluations in clinical genetics, genetic testing, research and precision medicine.

Identifying primary types of cancer from a liquid biopsy

Cell-free DNA in the blood provides a non-invasive diagnostic for patients with cancer. However, characteristics of the origins and molecular features of cell-free DNA are poorly understood. Recent machine learning research has developed an approach to evaluate fragmentation patterns of cell-free DNA across the genome, and found that profiles of healthy individuals reflected nucleosomal patterns of white blood cells, whereas patients with cancer had altered fragmentation profiles. Combining approaches like these with mutation-based cell-free DNA analyses can detect 91% of patients with cancer.

Deep learning improves prediction of CRISPR

The rapid advancement of genetic engineering tools for functional genomics studies has facilitated a deeper understanding of biological processes. Recent deep learning algorithms have been able to predict the activity of AsCpf1 guide RNAs.