A systematic review of state-of-the-art strategies for machine learning-based protein function prediction.

New drug discovery is inseparable from the discovery of drug targets, and the vast majority of the known targets are proteins. At the same time, proteins are essential structural and functional elements of living cells necessary for the maintenance of all forms of life. Therefore, protein functions have become the focus of many pharmacological and biological studies. Traditional experimental techniques are no longer adequate for rapidly growing annotation of protein sequences, and approaches to protein function prediction using computational methods have emerged and flourished. A significant trend has been to use machine learning to achieve this goal. In this review, approaches to protein function prediction based on the sequence, structure, protein-protein interaction (PPI) networks, and fusion of multi-information sources are discussed. The current status of research on protein function prediction using machine learning is considered, and existing challenges and prominent breakthroughs are discussed to provide ideas and methods for future studies.

A systematic review on the state-of-the-art strategies for protein representation.

The study of drug-target protein interaction is a key step in drug research. In recent years, machine learning techniques have become attractive for research, including drug research, due to their automated nature, predictive power, and expected efficiency. Protein representation is a key step in the study of drug-target protein interaction by machine learning, which plays a fundamental role in the ultimate accomplishment of accurate research. With the progress of machine learning, protein representation methods have gradually attracted attention and have consequently developed rapidly. Therefore, in this review, we systematically classify current protein representation methods, comprehensively review them, and discuss the latest advances of interest. According to the information extraction methods and information sources, these representation methods are generally divided into structure and sequence-based representation methods. Each primary class can be further divided into specific subcategories. As for the particular representation methods involve both traditional and the latest approaches. This review contains a comprehensive assessment of the various methods which researchers can use as a reference for their specific protein-related research requirements, including drug research.

EMNPD: a comprehensive endophytic microorganism natural products database for prompt the discovery of new bioactive substances.

The discovery and utilization of natural products derived from endophytic microorganisms have garnered significant attention in pharmaceutical research. While remarkable progress has been made in this field each year, the absence of dedicated open-access databases for endophytic microorganism natural products research is evident. To address the increasing demand for mining and sharing of data resources related to endophytic microorganism natural products, this study introduces EMNPD, a comprehensive endophytic microorganism natural products database comprising manually curated data. Currently, EMNPD offers 6632 natural products from 1017 endophytic microorganisms, targeting 1286 entities (including 94 proteins, 282 cell lines, and 910 species) with 91 diverse bioactivities. It encompasses the physico-chemical properties of natural products, ADMET information, quantitative activity data with their potency, natural products contents with diverse fermentation conditions, systematic taxonomy, and links to various well-established databases. EMNPD aims to function as an open-access knowledge repository for the study of endophytic microorganisms and their natural products, thereby facilitating drug discovery research and exploration of bioactive substances. The database can be accessed at http://emnpd.idrblab.cn/ without the need for registration, enabling researchers to freely download the data. EMNPD is expected to become a valuable resource in the field of endophytic microorganism natural products and contribute to future drug development endeavors.

[Knockdown of PLK1 mRNA by special siRNA].

To study knockdown effect of small interfering RNA (siRNA) to PLK1 (Polo-like kinase 1) mRNA in colorectal cancer cell line SW480 and its mitosis and growth was changed. Ten special siRNA molecules were designed targeting different sites of PLK1 mRNA sequence and chemically synthesized. The siRNA molecules were transfected into SW480 by Oligofectamine. The gene mRNA level was assayed by Real-Time PCR. The changes of PLK1 protein, SW480 cell cycle and survival percentage was checked by Western-blot, Flow cytometry and Cell counter assays respectively. All 10 siRNA molecules knocked PLK1 mRNA down in different level. Of them P1, P4 and P9 showed over 80% knockdown efficiency and the others had more than 20% knockdown efficiency to PLK1 mRNA. The best knockdown effect over 95% of all groups was at 25 nmol/L of a mixture with P1, P4 and P9 siRNA equally. In this situation the protein was very less and the cells were blocked at G2 phase of cell cycle. After 72 h cell survival percentages were consistent with PKL1 mRNA level change by siRNA gradient concentration. The results showed that siRNA targeting PLK1 mRNA had effectively knocked PLK1 mRNA down in SW480 cell line. And a blended siRNAs held the best knockdown effect. The cell was blocked on the mitosis and growth.

Evaluation of ST13 gene expression in colorectal cancer patients.

We identified a novel gene ST13 from a subtractive cDNA library of normal intestinal mucosa in 1993, more studies showed that ST13 was a co-chaperone of Hsp70s. Recently we detected the ST13 gene expression in tumor tissue and adjacent normal tissue of the same colorectal cancer patient and investigated if the ST13 gene expression might have any prognostic value. Analysis was performed at molecular level by reverse transcription-PCR using real-time detection method. We measured two genes simultaneously, ST13 as the target gene and glyceraldehydes-3-phosphate dehydrogenase as a reference gene, in primary colorectal tumor specimens and tumor-adjacent normal mucosa specimens from 50 colorectal cancer patients. The expression levels of the ST13 gene were significantly decreased in primary tumors compared with adjacent mucosa (P<0.05). But there were no significant differences in the expression of ST13 as compared with different Dukes' stage, tumor differentiation grade, invasion depth, lymph node metastasis and disease-specific survival.

[Study of an enhancer in promoter region of human colorectal cancer related ST13 gene].

OBJECTIVE: To study the base sequence of an enhancer in up-stream 5'-flank near regulation region (from -595 to +74) of human colorectal cancer related gene ST13. METHODS: Several deletion PCR primers were designed. Amplified DNA fragments of ST13 gene 5'-flank near region were cloned with pGEMT-EASY vector and sequenced; then subcloned into several pGL2 report vectors respectively. Equal quantitative recombined DNA was transfected into SW620 cell lines and the luciferase activity was checked. RESULTS: Several amplified base sequence fragments (669 bp,263 bp,163 bp) in pGL2-Basic all enhanced and promoted luciferase gene expression strongly. The 47 bp and 101 bp fragments didn't promote luciferase gene expression. 101 bp fragment recombined with pGL2-Promoter enhanced luciferase gene expression distinctly (P<0.01), but the effect was less strong than the positive pGL2-Control(P<0.05). CONCLUSION: The base sequence 101 bp (from -595 to -494) in up-stream 5'-flank near regulation region of colorectal cancer related gene ST13 is an enhancer regulating gene transcript.