Recombinant environmental libraries provide access to microbial diversity for drug discovery from natural products

Abstract

To further explore possible avenues for accessing microbial biodiversity for drug discovery from natural products, we constructed and screened a 5,000-clone "shotgun" environmental DNA library by using an Escherichia coli-Streptomyces lividans shuttle cosmid vector and DNA inserts from microbes derived directly (without cultivation) from soil. The library was analyzed by several means to assess diversity, genetic content, and expression of heterologous genes in both expression hosts. We found that the phylogenetic content of the DNA library was extremely diverse, representing mostly microorganisms that have not been described previously. The library was screened by PCR for sequences similar to parts of type I polyketide synthase genes and tested for the expression of new molecules by screening of live colonies and cell extracts. The results revealed new polyketide synthase genes in at least eight clones. In addition, at least five additional clones were confirmed by high-pressure liquid chromatography analysis and/or biological activity to produce heterologous molecules. These data reinforce the idea that exploiting previously unknown or uncultivated microorganisms for the discovery of novel natural products has potential value and, most importantly, suggest a strategy for developing this technology into a realistic and effective drug discovery tool.

FIG. 1.

ClustalX alignment of predicted amino acid sequences of soil PKS I genes and gene fragments. The PKS I consensus sequence pfam00109 is indicated. Soil genes and identities were as follows: a9B12-3, 54% identity to Nostoc sp. strain GSV224 NosB gene (227-amino-acid [aa] alignment; GenBank accession number AAF15892.2); a26G1-1.pep, 56% identity to Microcystis aeruginosa McyG gene (239-aa alignment; GenBank accession number AAF00957.1); a26G1-2.pep, 60% identity to S. aurantiaca MtaE gene (222-aa alignment; GenBank accession number AAF19813.1); a26G1-10.pep, 61% identity to Mycobacterium tuberculosis PpsA gene (247-aa alignment; GenBank accession number spQ10977); a35E4-16.pep, 59% identity to S. aurantiaca MtaD gene (234-aa alignment; GenBank accession number AAF19812.1); a49F1-32.pep, 55% identity to Nostoc sp. strain GSV224 NosB gene (228-aa alignment; GenBank accession number AAF15892.2); a17D2-3.pep, 46% identity to Mycobacterium leprae PKS gene (224-aa alignment; GenBank accession number embCAC29609.1); a53F11-13.pep, 59% identity to S. aurantiaca MtaB gene (249-aa alignment; GenBank accession number AAF19810.1); a53F11-14.pep, 58% identity to S. aurantiaca MtaE gene (244-aa alignment; GenBank accession number AAF19813.1); a36E8-1.pep^*, 60% identity to S. aurantiaca MtaB gene (225-aa alignment; GenBank accession number AAF19810.1); and a22A2-11.pep^*, 50% identity to Saccharopolyspora spinosa PKS gene (GenBank accession number AAG23263.1). An asterisk in the designations denotes sequences derived from primer set 2. All other sequences were derived from primer set 1. ^*, identity; :, strong similarity; ., weak similarity.

FIG. 2.

ORF map of cosmid a26G1 insert DNA. Domains were as follows: C, condensation; A, adenylation; MT, methylation; PCP, peptidyl carrier protein; KS, ketoacyl synthetase; AT, acyl transferase; DH, dehydratase; KR, keto reductase; ACP, acyl carrier protein; ER, enoyl redutase. aa, amino acids.

FIG. 3.

Similarity of predicted aminoglycoside acetyltransferase sequence to sequences of known proteins. Sequences were as follows: 8E12.AAT, putative aminoglycoside acetyltransferase in cosmid a8E12 (nucleotides 30829 to 31617; GenBank accession number AF486581); AAA25683.1, aminoglycoside 3′-N-acetyltransferase of Pseudomonas aeruginosa; AAA25682.1, AAC(3)-IIIB of P. aeruginosa; AAA88552.1, aminocyclitol 3-N-acetyltransferase, type VII, of S. rimosus. Unk, unknown.

FIG. 4.

RP HPLC elution profile of an extract of S. lividans TK24 containing library cosmid a22G9. Modified R5 agar plates (as described in reference 14, but omitting sucrose) were cut into pieces of approximately 0.5 cm³, transferred to 50-ml tubes, lyophilized for 48 h (Labconco Freezone 4.5), ground to a fine powder, extracted with methanol, filtered through Whatman Autovial PTFE filters (0.2-mm-pore size), placed in Waters SepPak Plus C₁₈ cartridges, concentrated to 1 ml (Savant Speedvac SC210A), and filtered again (Whatman 4-mm-diameter, 0.2-mm-pore-size PTFE syringe filters) prior to HPLC analysis. An Inertsil ODS-3 column (5 μm, 150 [length] by 4.6 [diameter] mm; GL Sciences) was used for analytical RP HPLC on a Waters 600 system with a Waters 996 photodiode-array detector (210 to 560 nm, 1.2-nm resolution; Millennium 4.0 software). The mobile phases were 0.08% TFA in water (A) and 0.08% TFA in acetonitrile (B). Elution was started with 100% A for 2 min, and a linear gradient was run from 0 to 100% B over 20 min with a 10-min hold at 100% B. The flow rate was 1 ml/min, and the injection volume was 10 ml. Identification of known compounds (undecylprodigiosin and actinorhodin) was based on their λ_max values. Traces for 254 and 490 nm are shown. Peaks a and b are new compounds that were not present in the control extract. Peaks c and d correspond to undecylprodigiosin and actinorhodin, respectively. AU, arbitrary units.

FIG. 5.

Structures of two fatty dienic alcohol isomers. For the isomers with a relative atomic mass of 294, x + y = 12.