New Machine Learning Method Predicts Damaging Missense Variants

The premise of genomic medicine is that a person’s genomic characterization can be used to improve medical diagnosis, prognosis, and treatment. Each person, however, has millions of genetic variants, the vast majority of which have negligible impact on their health. How to determine which variants are relevant to a particular condition is a central issue in genomic medicine.

The issue is most pressing in the case of missense variants, which alter a single amino acid in proteins. Only about 20–30 percent of these mutations have a functional impact. Thus the question of how likely a variant is to change protein function—contributing to a health condition—is extremely uncertain for missense variants. As a result, most missense variants in clinical genetic testing are classified as VUS (variant of uncertain significance).

Yufeng Shen, PhD, an associate professor in the Department of Systems Biology and the Department of Biomedical Informatics, and his group have developed a new method for predicting which missense variants are potentially damaging. The method, called gMVP (graphical model for predicting Missense Variant Pathogenicity), uses one of the latest machine learning techniques, a graph attention model, to capture information relevant to predicting which variants are potentially damaging. Their paper, “Predicting Functional Effect of Missense Variants Using Graph Attention Neural Networks,” was published in Nature Machine Intelligence on November 15th, 2022.

Andrea Califano will receive  $6,909,000 over seven years from the National Cancer Institute for “Predicting Cancer Cell Response to Endogenous and Exogenous Perturbations at the Single Cell Level”. The aims of the project are to create the first generation of genome-and proteome-wide network models that can effectively predict the probabilistic, dynamic response of mammalian cells to small molecule and genetic perturbations, as well as their ability to plastically reprogram  across the relatively small number of molecularly distinct states detected in a specific human malignancy. 

Andrea Califano will receive  $4,893,902 over five years from the National Cancer Institute for “Elucidating and Targeting tumor dependencies and drug resistance determinants at the single cell level”. The aims of the project are to elucidate Master Regulators representing non-oncogene dependencies of molecularly distinct malignant subpopulations coexisting in the same tumor to support novel combination and sequential therapy approaches.

The Department of Systems Biology at Columbia University Irving Medical Center welcomes new faculty member Sara Zaccara, PhD. Dr. Zaccara joins Columbia as an assistant professor, effective Sept. 1. Prior to coming to Columbia, she was a postdoctoral researcher at Weill Cornell Medicine.

Dr. Zaccara grew up in a small town in Italy. She received her PhD from the University of Trento, in Trento, Italy, where her thesis work was on p53-dependent translational regulation. She received her bachelor’s and master’s degrees in biotechnology from the University of Florence. “I studied biotechnology,” she says, “because I was fascinated by the idea of developing new methods that could improve our future in medicine.”

Dr. Zaccara’s research focuses on the intricate cellular mechanisms that control the chemical tag called m6A, which cells insert into almost 30 percent of their mRNA molecules. She has proposed a unified model of how m6A mRNAs are controlled in cells. She also helped show why the number of m6A sites in mRNAs has functional consequences for mRNA fate.

Currently, Dr. Zaccara’s group is working on characterizing the mechanisms that trigger m6A mRNA degradation in normal and disease states, in particular, acute myeloid leukemia. The group is also investigating the impact of the functional specialization of RNA binding proteins on mRNA fate. Their multidisciplinary approach includes the use of CRISPR-Cas9 base editor screens, massively parallel tethering screens, molecular tagging, imaging, and in vitro experiments. The integrated combination of these methodologies will enable investigation of critical components of the mRNA degradation pathway and their contribution to mRNA fate with unprecedented throughput and resolution.

Adolfo Ferrando, MD, PhD, and Raul Rabadan, PhD, Institute for Cancer Genetics: $2,500,000 over five years from the National Institute on Aging for “The role of PHF6 in the control of hematopoietic stem cell aging.” 

Peter Sims, PhD, and Donna Farber, PhD, Systems Biology: $2,275,349 over three years from the Aging Biology Foundation for a subaward of “Single cell analysis of aging in lymphoid compartments.” 

Chaolin Zhang, PhD, Systems Biology: $3,006,392 over five years from the National Institute of Neurological Disorders and Stroke for “RNA regulatory networks in neuronal cell type diversity and function.”

Precision medicine has been a buzzword across the medical field for over a decade. But what does it really mean for cancer care and how is it influencing new therapies for patients? Initially, precision cancer medicine focused on targeting specific mutated genes. We thought that understanding the genetic mutations of a tumor would help us develop targeted drugs that would solve the problem, one broken gene at a time.

What we found instead is that when you build an inventory of all the broken parts in cancer, the number of mutational patterns that could give rise to cancer is larger than the number of atoms in the universe.

Read full article on the Columbia News page.

Raul Rabadan, PhD, Systems Biology, will receive $6,804,000 over seven years from the National Cancer Institute for “Towards a quantitative understanding of tumor evolution” and $649,998 over two years from STAND UP TO CANCER for a subaward of “Multiomic Analysis of Immune System and Microbiota Influence on Temporal and Spatial Evolution of Tumor Microenvironments.”

Xuebing Wu, PhD, Medicine, will receive $600,000 over three years from the Pershing Square Sohn Cancer Research Alliance for “Targeting tumor with CRISPR/Cas13-based sequence-specific cell knockout.”