Embodiments of the invention include systems and methods that enable the identification of candidate proteins that have desired features of a target protein. An example method comprises receiving first and second input proteins. The method further comprises applying a first machine learning model to the first and second input proteins to generate corresponding fragments. The method further comprises applying a second machine learning model to the fragments, wherein applying the second machine learning model comprises generating an encoded representation in a multidimensional space for each of the fragments. The method also comprises generating a similarity score between the fragments from the first input and the second input. The method then comprises generating a hierarchical scale of similarity between the first and second inputs according to the similarity score and selecting candidate proteins based on the hierarchical scale.

Embodiments of the invention include systems and methods that enable the identification of candidate proteins that have desired features of a target protein. An example method comprises receiving first and second input proteins. The method further comprises applying a first machine learning model to the first and second input proteins to generate corresponding fragments. The method further comprises applying a second machine learning model to the fragments, wherein applying the second machine learning model comprises generating an encoded representation in a multidimensional space for each of the fragments. The method also comprises generating a similarity score between the fragments from the first input and the second input. The method then comprises generating a hierarchical scale of similarity between the first and second inputs according to the similarity score and selecting candidate proteins based on the hierarchical scale.

A method and system for generating a protein sequence is implemented using a computer-implemented neural network. An empty or partially filed sequence of node elements, representing amino acid positions of the protein sequence, and an edge index, having edge elements defining physical interaction between amino acid positions, are received. The computer-implemented neural network operates to determine enhanced edge attribute values for edge elements of the edge index and enhanced amino acid values for node elements of the sequence. Amino acid values are generated for elements of the partially filed sequence having missing values.

A method and system for generating a protein sequence is implemented using a computer-implemented neural network. An empty or partially filed sequence of node elements, representing amino acid positions of the protein sequence, and an edge index, having edge elements defining physical interaction between amino acid positions, are received. The computer-implemented neural network operates to determine enhanced edge attribute values for edge elements of the edge index and enhanced amino acid values for node elements of the sequence. Amino acid values are generated for elements of the partially filed sequence having missing values.

In some aspects, described herein are cell culture media that are useful for in vitro culture of mammalian cells. The culture media contain a variety of small organic compounds that are found in normal adult human blood. Also described are methods of using the culture media for a variety of purposes. Also described are methods of treating cancer.

The present invention relates to compositions and methods for targeting cancer-specific DNA sequences, such as copy number amplifications and other types of cancer-specific sequence variations, such as cancer-specific polymorphisms, insertions, or deletions. The present invention provides hereto sequence-specific DNA targeting agents targeting a sequence within the amplified DNA region or a sequence otherwise specific for a cancer cell compared to a non-cancer cell. The invention further relates to methods for treating cancer, comprising administering such sequence-specific DNA targeting agents. The invention further relates to methods for preparing sequence-specific DNA targeting agent, as well as screening methods using the DNA targeting agents.

A preparation method of a novel natural bioactive peptide Tubulysin U includes: dissolving a compound 2 in trifluoroacetic acid, heating under reflux to prepare an intermediate, reacting with a compound 3 and N,N-diisopropylethylamine to obtain a product, reacting the product with 2, 6-dimethylpyridine and tert-butyldimethylsilyl trifluoromethanesulfonate, adding sodium hydroxide after the reaction to prepare an intermediate acid, reacting the intermediate acid with a compound 6, HATU and N,N-diisopropylethylamine to obtain a product, adding triphenylphosphine to prepare an intermediate amine, adding a compound 8 and HATU to react, adding ammonium fluoride to prepare a first intermediate, adding sodium hydroxide to the first intermediate to prepare a second intermediate, adding acetic anhydride to the second intermediate to prepare a third intermediate, adding trifluoroacetic acid to the third intermediate to prepare a fourth intermediate, and adding formaldehyde and sodium cyanoborohydride to the fourth intermediate to react, thereby obtaining a target product.

A computational method for constructing a synthetic peptide sequence is disclosed. The method of the present invention includes the steps of (i) identifying a candidate sequence building block set comprising candidate sequence building blocks from a base set comprising known functional peptide sequences and optionally known non-functional peptide sequences; (ii) selecting a qualified sequence building block set comprising qualified sequence building blocks from said candidate sequence building block set; said qualified sequence building blocks satisfying a threshold requirement and (iii) assembling said qualified sequence building blocks to generate a synthetic peptide sequence. A synthetic peptide sequence and a functional synthetic peptide are also described.

A computational method for constructing a synthetic peptide sequence is disclosed. The method of the present invention includes the steps of (i) identifying a candidate sequence building block set comprising candidate sequence building blocks from a base set comprising known functional peptide sequences and optionally known non-functional peptide sequences; (ii) selecting a qualified sequence building block set comprising qualified sequence building blocks from said candidate sequence building block set; said qualified sequence building blocks satisfying a threshold requirement and (iii) assembling said qualified sequence building blocks to generate a synthetic peptide sequence. A synthetic peptide sequence and a functional synthetic peptide are also described.

The purpose of the present invention is to provide an adhesion prevention material capable of exhibiting excellent adhesion preventive effect. This adhesion prevention material concurrently uses: (A) a peptide (A-1) having an amino acid sequence-(X-Pro-Y)n-[wherein X represents an arbitrary defined amino acid, Pro represents proline, Y represents hydroxyproline or proline, and n is an integer between 1 and 10] and/or a peptide (A-2) having an amino acid sequence-(Pro-Y)m-[wherein Pro represents proline, Y represents hydroxyproline or proline, and m is an integer between 1-10]; and (B) a gelatin gel. This adhesion prevention material exhibits a dramatically enhanced adhesion preventive effect as compared with the case where the abovementioned components are used individually, and in particular, has a markedly superior effect against adhesion of tendons.