Biomedical subjects

Giovanni Traverso

Publications and source records attributed to Giovanni Traverso.

7 recordsLinked to original sources

PubMed2026

The Use of Deep Learning in RNA Therapeutic Development.

Ribonucleic acid (RNA)-based therapeutics have emerged as promising methods of disease treatment due to their ability to target the human genome and influence protein production, their versatility, and their relative lack of toxicity compared to other gene therapies. However, the RNA therapeutic design space is extremely large, encompassing multiple variables, including codon identities, secondary structure, and design of specific regions. RNA therapeutic optimization is difficult due to the impracticality of exploring such a vast design space experimentally. To address this limitation, deep learning methods have been employed to optimize RNA therapeutic development. In this review, we examine the application of deep learning models across three key aspects of RNA therapeutic development (RNA structure prediction, CRISPR activity, and RNA delivery), highlighting major contributions in these fields and analyzing how deep learning model architectures could affect model performance. We then discuss challenges associated with using deep learning for RNA therapeutics, such as computational and data limitations. Finally, we offer perspectives on areas for future exploration, such as emerging model architectures and methods of integration with more advanced high-throughput screening techniques. Ultimately, this review provides an overview of how deep learning is used in RNA therapeutic development and how it can evolve in the future.

Deep Learning↗

PubMed2004

Three classes of genes mutated in colorectal cancers with chromosomal instability.

Although most colorectal cancers are chromosomally unstable, the basis for this instability has not been defined. To determine whether genes shown to cause chromosomal instability in model systems were mutated in colorectal cancers, we identified their human homologues and determined their sequence in a panel of colorectal cancers. We found 19 somatic mutations in five genes representing three distinct instability pathways. Seven mutations were found in MRE11, whose product is involved in double-strand break repair. Four mutations were found among hZw10, hZwilch/FLJ10036, and hRod/KNTC, whose products bind to one another in a complex that localizes to kinetochores and controls chromosome segregation. Eight mutations were found in Ding, a previously uncharacterized gene with sequence similarity to the Saccharomyces cerevisiae Pds1, whose product is essential for proper chromosome disjunction. This analysis buttresses the evidence that chromosomal instability has a genetic basis and provides clues to the mechanistic basis of instability in cancers.

Animals↗

PubMed2003

Hyper-recombination and genetic instability in BLM-deficient epithelial cells.

Genetic instability appears to be required for a normal colorectal epithelial cell to evolve into a cancerous one. Bloom syndrome patients have a strong predisposition to cancer that affects a variety of tissues. The mechanism of disease is attributed to genomic instability, but many questions about the nature of this instability have not yet been answered. To investigate these issues, we used gene-targeting techniques to disrupt the BLM gene in karyotypically stable colorectal cancer epithelial cells. BLM knockout cells showed an increased tendency of sister chromatids to exchange DNA strands and were substantially more likely to undergo homologous recombination at chromosomal loci than parental cells. Surprisingly, BLM-deficient colorectal cancer epithelial cells did not display gross chromosomal rearrangements nor a change in the rates of chromosome gains and losses. However, the enhanced homologous recombination was associated with losses of heterozygosity. These observations define a type of genetic instability that has significant implications for the evolution of cancer.

Adenosine Triphosphatases↗

PubMed2003

Multicolor in vitro translation.

In vitro translation is a widely used tool for both analytical and preparative purposes. For analytical purposes, small amounts of proteins are synthesized and visualized by detection of labeled amino acids incorporated during translation. The original strategy of incorporating radioactively labeled amino acids, such as [35S]methionine or [14C]leucine, has been superseded by the addition of antigenic tags or the incorporation of biotin-labeled or BODIPY-FL-labeled amino acids. Such nonradioactive tags are easier to visualize after translation and do not pose a radiation hazard. Among the nonradioactive tags, BODIPY-FL-lysine offers the advantage that proteins that have incorporated this amino acid can be directly visualized after gel electrophoresis. We show here that multiple fluorophores introduced into proteins can considerably extend their usefulness, particularly for the comparison of in vitro-translated proteins from related sources. This technology can be applied in various situations, including the simplified detection of rare truncating mutations in clinical samples from cancer patients.

Boron Compounds↗

PubMed2003

Transforming single DNA molecules into fluorescent magnetic particles for detection and enumeration of genetic variations.

Many areas of biomedical research depend on the analysis of uncommon variations in individual genes or transcripts. Here we describe a method that can quantify such variation at a scale and ease heretofore unattainable. Each DNA molecule in a collection of such molecules is converted into a single magnetic particle to which thousands of copies of DNA identical in sequence to the original are bound. This population of beads then corresponds to a one-to-one representation of the starting DNA molecules. Variation within the original population of DNA molecules can then be simply assessed by counting fluorescently labeled particles via flow cytometry. This approach is called BEAMing on the basis of four of its principal components (beads, emulsion, amplification, and magnetics). Millions of individual DNA molecules can be assessed in this fashion with standard laboratory equipment. Moreover, specific variants can be isolated by flow sorting and used for further experimentation. BEAMing can be used for the identification and quantification of rare mutations as well as to study variations in gene sequences or transcripts in specific populations or tissues.

Base Sequence↗

PubMed2002

Detection of proximal colorectal cancers through analysis of faecal DNA.

Detection of mutations in faecal DNA represents a promising, non-invasive approach for detecting colorectal cancers in average-risk populations. One of the first practical applications of this technology involves the examination of microsatellite markers in sporadic cancers with mismatch-repair deficiencies. Since such cancers nearly always occur in the proximal colon, this test might be useful as an adjunct to sigmoidoscopy, which detects only distal colorectal lesions. We report here the first in-depth analysis of faecal DNA from patients with proximal cancers to determine the feasibility, sensitivity, and specificity of this approach. Using a sensitive method for microsatellite mutation detection, we found that 18 of 46 cancers had microsatellite alterations and that identical mutations could be identified in the faecal DNA of 17 of these 18 cases.

Adenoma↗

PubMed2002

Detection of APC mutations in fecal DNA from patients with colorectal tumors.

BACKGROUND: Noninvasive methods for detecting colorectal tumors have the potential to reduce morbidity and mortality from this disease. The mutations in the adenomatous polyposis coli (APC) gene that initiate colorectal tumors theoretically provide an optimal marker for detecting colorectal tumors. The purpose of our study was to determine the feasibility of detecting APC mutations in fecal DNA with the use of newly developed methods. METHODS: We purified DNA from routinely collected stool samples and screened for APC mutations with the use of a novel approach called digital protein truncation. Many different mutations could potentially be identified in a sensitive and specific manner with this technique. RESULTS: Stool samples from 28 patients with nonmetastatic colorectal cancers, 18 patients with adenomas that were at least 1 cm in diameter, and 28 control patients without neoplastic disease were studied. APC mutations were identified in 26 of the 46 patients with neoplasia (57 percent; 95 percent confidence interval, 41 to 71 percent) and in none of the 28 control patients (0 percent; 95 percent confidence interval, 0 to 12 percent; P<0.001). In the patients with positive tests, mutant APC genes made up 0.4 to 14.1 percent of all APC genes in the stool. CONCLUSIONS: APC mutations can be detected in fecal DNA from patients with relatively early colorectal tumors. This feasibility study suggests a new approach for the early detection of colorectal neoplasms.

Adenoma↗