Discrimination of transcription factor binding sites (TFBS) from background sequences plays a key role in computational motif discovery. Current clustering based algorithms employ homogeneous model for problem solving, which assumes that motifs and background signals can be equivalently characterized. This assumption has some limitations because both sequence signals have distinct properties.
10 February 2018 in Biotechnology & Biotechnological Equipment
We propose an improved solution to the three-stage DNA motif prediction approach. The three-stage approach uses only a subset of input sequences for initial motif prediction, and the initial motifs obtained are employed for site detection in the remaining input subset of non-overlaps. The currently available solution is not robust because motifs obtained from the initial subset are represented as a position weight matrices, which results in high false positives. Our approach, called DeepFinder, employs deep learning neural networks with features associated with binding sites to construct a motif model. Furthermore, multiple prediction tools are used in the initial motif prediction process to obtain a higher number of positive hits. Our features are engineered from the context of binding sites, which are assumed to be enriched with specificity information of sites recognized by transcription factor proteins. DeepFinder is evaluated using several performance metrics on ten chromatin immunoprecipitation (ChIP) datasets. The results show marked improvement of our solution in comparison with the existing solution. This indicates the effectiveness and potential of our proposed DeepFinder for large-scale motif analysis.
1 February 2024 in Translational Lung Cancer Research
Despite significant advancements in screening, diagnosis, and treatment of non-small cell lung cancer (NSCLC), it remains the primary cause of cancer-related deaths globally. DNA damage is caused by the exposure to exogenous and endogenous factors and the correct functioning of DNA damage repair (DDR) is essential to maintain of normal cell circulation. The presence of genomic instability, which results from defective DDR, is a critical characteristic of cancer. The changes promote the accumulation of mutations, which are implicated in cancer cells, but these may be exploited for anti-cancer therapies. NSCLC has a distinct genomic profile compared to other tumors, making precision medicine essential for targeting actionable gene mutations. Although various treatment options for NSCLC exist including chemotherapy, targeted therapy, and immunotherapy, drug resistance inevitably arises. The identification of deleterious DDR mutations in 49.6% of NSCLC patients has led to the development of novel target therapies that have the potential to improve patient outcomes. Synthetic lethal treatment using poly (ADP-ribose) polymerase (PARP) inhibitors is a breakthrough in biomarker-driven therapy. Additionally, promising new compounds targeting DDR, such as ATR, CHK1, CHK2, DNA-PK, and WEE1, had demonstrated great potential for tumor selectivity. In this review, we provide an overview of DDR pathways and discuss the clinical translation of DDR inhibitors in NSCLC, including their application as single agents or in combination with chemotherapy, radiotherapy, and immunotherapy.
Convolutionary neural network (CNN) is a popular choice for supervised DNA motif prediction due to its excellent performances. To employ CNN, the input DNA sequences are required to be encoded as numerical values and represented as either vectors or multi-dimensional matrices. This paper evaluates a simple and more compact ordinal encoding method versus the popular one-hot encoding for DNA sequences. We compare the performances of both encoding methods using three sets of datasets enriched with DNA motifs. We found that the ordinal encoding performs comparable to the one-hot method but with significant reduction in training time. In addition, the one-hot encoding performances are rather consistent across various datasets but would require suitable CNN configuration to perform well. The ordinal encoding with matrix representation performs best in some of the evaluated datasets. This study implies that the performances of CNN for DNA motif discovery depends on the suitable design of the sequence encoding and representation. The good performances of the ordinal encoding method demonstrates that there are still rooms for improvement for the one-hot encoding method.
1 January 2009 in Lecture Notes in Computer Science