Abstract
Many protein engineering problems involve finding mutations that produce proteins with a particular function. Computational active learning is an attractive approach to discover desired biological activities. Traditional active learning techniques have been optimized to iteratively improve classifier accuracy, not to quickly discover biologically significant results. We report here a novel active learning technique, Most Informative Positive (MIP), which is tailored to biological problems because it seeks novel and informative positive results. MIP active learning differs from traditional active learning methods in two ways: (1) it preferentially seeks Positive (functionally active) examples; and (2) it may be effectively extended to select gene regions suitable for high throughput combinatorial mutagenesis. We applied MIP to discover mutations in the tumor suppressor protein p53 that reactivate mutated p53 found in human cancers. This is an important biomedical goal because p53 mutants have been implicated in half of all human cancers, and restoring active p53 in tumors leads to tumor regression. MIP found Positive (cancer rescue) p53 mutants in silico using 33% fewer experiments than traditional non-MIP active learning, with only a minor decrease in classifier accuracy. Applying MIP to in vivo experimentation yielded immediate Positive results. Ten different p53 mutations found in human cancers were paired in silico with all possible single amino acid rescue mutations, from which MIP was used to select a Positive Region predicted to be enriched for p53 cancer rescue mutants. In vivo assays showed that the predicted Positive Region: (1) had significantly more (p<0.01) new strong cancer rescue mutants than control regions (Negative, and non-MIP active learning); (2) had slightly more new strong cancer rescue mutants than an Expert region selected for purely biological considerations; and (3) rescued for the first time the previously unrescuable p53 cancer mutant P152L.
Highlights
Engineering existing proteins to change their properties [1,2] is an important task with many applications as diverse as environmental protection, synthetic biomaterials, and pharmacology [3,4,5,6,7,8]
Biology of p53 Cancer Rescue Mutants The p53 gene encodes a tumor suppressor protein that is a key cellular defense against cancer. p53 mutations occur in about 50% of human cancers
This paper presents Most Informative Positive (MIP) active learning, a novel integrated computational/ biological approach designed to help guide biological discovery of novel and informative positive mutants
Summary
Engineering existing proteins to change their properties [1,2] is an important task with many applications as diverse as environmental protection, synthetic biomaterials, and pharmacology [3,4,5,6,7,8]. We choose where to mutate cancerous p53 to restore tumor suppressor function, using structure-based features derived from in silico protein homology models. There have been many efforts to find small molecule drugs that mimic the cancer rescue effect of reactivating p53 and suppressing tumor growth [19,20,21,22,23,24]. A larger and more diverse collection of cancer rescue mutations that reactivate p53 cancer mutants is desired. Such a collection could lead to insight into general structural changes that can rescue p53 cancer mutants, and thereby facilitate rational drug design approaches by exploiting similar effects
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have