Supervised learning with word embeddings derived from PubMed captures latent knowledge about protein kinases and cancer.

Inhibiting protein kinases (PKs) that cause cancers has been an important topic in cancer therapy for years. So far, almost 8% of >530 PKs have been targeted by FDA-approved medications, and around 150 protein kinase inhibitors (PKIs) have been tested in clinical trials. We present an approach based on natural language processing and machine learning to investigate the relations between PKs and cancers, predicting PKs whose inhibition would be efficacious to treat a certain cancer. Our approach represents PKs and cancers as semantically meaningful 100-dimensional vectors based on word and concept neighborhoods in PubMed abstracts. We use information about phase I-IV trials in ClinicalTrials.gov to construct a training set for random forest classification. Our results with historical data show that associations between PKs and specific cancers can be predicted years in advance with good accuracy. Our tool can be used to predict the relevance of inhibiting PKs for specific cancers and to support the design of well-focused clinical trials to discover novel PKIs for cancer therapy.

An SF1 affinity model to identify branch point sequences in human introns.

Splicing factor 1 (SF1) binds to the branch point sequence (BPS) of mammalian introns and is believed to be important for the splicing of some, but not all, introns. To help identify BPSs, particularly those that depend on SF1, we generated a BPS profile model in which SF1 binding affinity data, validated by branch point mapping, were iteratively incorporated into computational models. We searched a data set of 117,499 human introns for best matches to the SF1 Affinity Model above a threshold, and counted the number of matches at each intronic position. After subtracting a background value, we found that 87.9% of remaining high-scoring matches identified were located in a region upstream of 3'-splice sites where BPSs are typically found. Since U2AF65 recognizes the polypyrimidine tract (PPT) and forms a cooperative RNA complex with SF1, we combined the SF1 model with a PPT model computed from high affinity binding sequences for U2AF65. The combined model, together with binding site location constraints, accurately identified introns bound by SF1 that are candidates for SF1-dependent splicing.

Snapshot of iron response in Shewanella oneidensis by gene network reconstruction.

BACKGROUND: Iron homeostasis of Shewanella oneidensis, a gamma-proteobacterium possessing high iron content, is regulated by a global transcription factor Fur. However, knowledge is incomplete about other biological pathways that respond to changes in iron concentration, as well as details of the responses. In this work, we integrate physiological, transcriptomics and genetic approaches to delineate the iron response of S. oneidensis. RESULTS: We show that the iron response in S. oneidensis is a rapid process. Temporal gene expression profiles were examined for iron depletion and repletion, and a gene co-expression network was reconstructed. Modules of iron acquisition systems, anaerobic energy metabolism and protein degradation were the most noteworthy in the gene network. Bioinformatics analyses suggested that genes in each of the modules might be regulated by DNA-binding proteins Fur, CRP and RpoH, respectively. Closer inspection of these modules revealed a transcriptional regulator (SO2426) involved in iron acquisition and ten transcriptional factors involved in anaerobic energy metabolism. Selected genes in the network were analyzed by genetic studies. Disruption of genes encoding a putative alcaligin biosynthesis protein (SO3032) and a gene previously implicated in protein degradation (SO2017) led to severe growth deficiency under iron depletion conditions. Disruption of a novel transcriptional factor (SO1415) caused deficiency in both anaerobic iron reduction and growth with thiosulfate or TMAO as an electronic acceptor, suggesting that SO1415 is required for specific branches of anaerobic energy metabolism pathways. CONCLUSION: Using a reconstructed gene network, we identified major biological pathways that were differentially expressed during iron depletion and repletion. Genetic studies not only demonstrated the importance of iron acquisition and protein degradation for iron depletion, but also characterized a novel transcriptional factor (SO1415) with a role in anaerobic energy metabolism.

Response of Desulfovibrio vulgaris to alkaline stress.

The response of exponentially growing Desulfovibrio vulgaris Hildenborough to pH 10 stress was studied using oligonucleotide microarrays and a study set of mutants with genes suggested by microarray data to be involved in the alkaline stress response deleted. The data showed that the response of D. vulgaris to increased pH is generally similar to that of Escherichia coli but is apparently controlled by unique regulatory circuits since the alternative sigma factors (sigma S and sigma E) contributing to this stress response in E. coli appear to be absent in D. vulgaris. Genes previously reported to be up-regulated in E. coli were up-regulated in D. vulgaris; these genes included three ATPase genes and a tryptophan synthase gene. Transcription of chaperone and protease genes (encoding ATP-dependent Clp and La proteases and DnaK) was also elevated in D. vulgaris. As in E. coli, genes involved in flagellum synthesis were down-regulated. The transcriptional data also identified regulators, distinct from sigma S and sigma E, that are likely part of a D. vulgaris Hildenborough-specific stress response system. Characterization of a study set of mutants with genes implicated in alkaline stress response deleted confirmed that there was protective involvement of the sodium/proton antiporter NhaC-2, tryptophanase A, and two putative regulators/histidine kinases (DVU0331 and DVU2580).