Tuberculosis (TB) is a leading cause of morbidity and mortality in the world, also affecting a wide range of animal species, particularly livestock, in both developed and developing countries. The disease is caused by tuberculous mycobacteria belonging to the Mycobacterium tuberculosis complex (MTC). This complex consists of several closely-related pathogenic species, namely M. tuberculosis, the main agent of human TB, and, amongst others, M. bovis and M. caprae that are primary agents of bovine and caprine TB, respectively [1]. These species are genetically very similar but may differ in host preference and epidemiological characteristics [2]. Mycobacterium bovis and M. caprae also represent a high potential for zoonotic transmission to humans [3–5], with evidence of possible person-to-person transmission [6]. However, the main routes of transmission are the contact with infected animals and ingestion of unpasteurized dairy products. These zoonotic MTC species may be responsible for up to 7.2% and 15% of human TB cases in industrialized and developing countries, respectively [7]. Rapid and reliable laboratory tests for the direct detection of tuberculous mycobacteria in biological samples are in high demand, in both human health and veterinary settings, and are crucial for an improved TB control.

In most developed countries, bovine tuberculosis has been tackled during the last decades by costly eradication programs, involving the culling of reactor animals and laboratory testing of suspect samples for the definitive confirmation of the presence of MTC. Presently, the detection of MTC bacteria in animal tissues is mainly based in lengthy and cumbersome conventional methods, involving the examination of Ziehl-Neelsen stained smears, histopathology and culture in selective media, followed by biochemical or molecular identification of typical mycobacteria colonies. The microscopic identification of acid-fast mycobacteria is non-specific and highly insensitive, particularly in the case of paucibacillary forms of TB. Culture remains the gold-standard method to confirm TB infection but requires several weeks to obtain positive results due to the extremely fastidious growth of tuberculous mycobacteria. In spite of the significant advances in the development of novel molecular diagnostic assays towards a faster and accurate detection of MTC in human samples, only a few assays have been described for detecting these agents in animal tissues, particularly in fresh tissues from livestock [8-12]. Most of these molecular approaches are PCR-based and target specific polymorphisms, insertion sequences, and the so-called regions of difference in the genome of MTC members [9,10,13-18]. Nevertheless, most of the amplification-based assays described for detecting MTC nucleic acids directly in fresh or formalin-fixed paraffin-embedded tissues only yield a moderate sensitivity, usually up to 75%, particularly when testing tissues without the characteristic lesions or detectable acid-fast bacilli [8-10,15,19]. This limitation is mostly related to the inefficiency of mycobacterial DNA extraction procedures from affected animal tissues, especially those exhibiting strong fibrosis, calcification, and with no histological evidence of acid-fast bacteria [8,19]. The use of immunomagnetic separation approaches to concentrate mycobacteria cells from animal tissues prior to DNA extraction may enhance PCR sensitivities [20,21]. Nevertheless, these approaches usually involve more experimental steps and expensive equipment and consumables not readily available in veterinary diagnostic settings.

In the present work we have developed a novel and simple Taqman-based semi-nested real-time PCR assay yielding extremely high sensitivity and specificity for the direct detection of tuberculous mycobacteria in fresh animal tissues, namely of bovine origin, capable of being introduced in routine diagnostic veterinary laboratories.

The availability of TB confirmatory tests allowing a fast and conclusive detection of tuberculous mycobacteria in suspect animal tissues would be a great advantage in improving the efficiency of TB eradication programs and in decreasing the associated economic burden. Improvements in specificity, sensitivity and detection limit of diagnostic assays are usually introduced by molecular approaches. Nevertheless, only a few diagnostic PCR-based assays have been described for detecting MTC members directly in animal specimens, usually yielding limited sensitivities when compared to the reference bacteriological culture [8-12,15,19]. These moderate sensitivities may well be linked to the increased complexity for disrupting and recovering genomic DNA from the tough mycobacterial cells and to the paucibacillary nature of many animal tissue lesions used for nucleic acids extraction [10]. The presence of amplification inhibitors in crude tissue extracts, namely of large amounts of co-extracted eukaryotic DNA, may represent an additional problem. An option that has been explored to enhance the sensitivity of PCR techniques involves the implementation of more effective DNA extraction and purification methods. Taylor and colleagues were able to increase the M. bovis PCR detection sensitivity in bovine tissue samples with visible lesions, from 70% to 91%, after the inclusion of an additional step of liquid nitrogen freeze-thaw cycles in the DNA extraction procedure [10]. The use of sequence capture or immunomagnetic separation approaches was also forecasted for recovering higher yields of mycobacterial DNA from samples [8,9,12,21]. Nevertheless, these DNA extraction approaches usually involve more experimental steps and expensive equipments and consumables.

In this work, an alternative approach was evaluated for enhancing MTC detection sensitivities directly from fresh animal tissues. An adapted and optimized user-friendly DNA extraction protocol, mainly based in the use of simple commercially obtainable extraction kits, was coupled with an IS6110-targeted semi-nested real-time PCR assay that allows the direct detection of MTC members in animal tissue specimens with very high sensitivity, specificity and positive and negative predictive values, namely in bovine specimens. These two last parameters are dependent on the prevalence of the tested condition in the population under study, as well as on the sensitivity and specificity of the testing assays. The prevalence of MTC (mostly M. bovis) infected samples among all TB-suspect samples submitted to the reference laboratory during the 2002-2010 period (n = 6364) was approximately 40% (reviewed by Cunha and colleagues [27]), which compares well with the prevalence values found in this work and used for the computation of PPV and NPV. Therefore, the PPV and NPV parameters computed may be considered good indicators of the performance of our IS6110-targeted assay for assessing the presence of MTC in specimens collected from animals clinically suspected of having tuberculosis and submitted for confirmatory culture analysis in a major reference laboratory.

Eight DNA-positive amplification results were obtained from tissue samples from which M. bovis could not be cultured (Table 2). However, lesions compatible with TB were observed in these tissues during histological analysis (sample types V and VI) (Table 2). The culture of tissue samples for the isolation of M. bovis and of other MTC members, followed by molecular or biochemical identification procedures, is usually the gold-standard method to validate alternative diagnostic assays. However, it is known that bacteriological culture is slow and laborious and can yield ambiguous or false-negative results, e.g. due to the presence of non-viable mycobacteria, raising concerns about its effectiveness as comparison reference method [19,31]. The results of culture assays may be affected by several factors, such as the harsh processing and decontamination procedures of samples, which can also have a harmful effect on M. bovis viability, as well as the growth media and incubation conditions used and the constrained distribution of mycobacteria in tissues [32]. Therefore, although TB-like lesions identified by histopathology can be induced by other bacteria or mycobacteria, the positive amplification results suggest that MTC members were most probably associated with the observed lesions and that the PCR test is more sensitive than bacteriological culture for detecting these pathogens in animal tissues. Non-MTC mycobacteria such as M. avium and M. scrofulaceum were cultured from five of those eight DNA-positive tissue samples (Table 2). These non-MTC mycobacteria may potentially overgrow any M. bovis isolate present in the sample and mask its presence [19]. Regardless of some discrepancies, the kappa measure of agreement between bacteriological culture and the semi-nested PCR was estimated in 0.859. Although the criteria for judging kappa statistic are not completely objective nor universally accepted, this value may allow us to infer an "almost perfect" agreement between the two MTC detection methods [33].

The enhancement of the MTC detection rates using the semi-nested amplification assay need to be balanced against the associated increased risk of cross contamination of samples. Therefore, we should emphasize the need of working in a veterinary diagnosis laboratory harboring good practice standard conditions for molecular analysis, which include working in separate clean rooms and the use of positive and negative controls.

In a preliminary survey the testing of TB positive and negative tissue samples employed a standard real-time PCR assay (corresponding to the second step of the semi-nested approach). The comparison of this assay with the reference of bacteriological culture showed a diagnostic sensitivity of only 40% (data not shown). The inclusion of the first step of conventional IS6110-targeted PCR amplification, in a semi-nested design, allowed to increase the sensitivity of the assay to near 100%. Previous studies found no significant improvements in the detection of MTC members in animal tissue samples using nested PCR assays, including with real-time PCR formats [10,14,15]. Nevertheless, the performance of PCR detection systems is highly dependent on the efficiency of the primers and probes, even when using the same genomic targets such as the IS6110 element [34]. The MTC-specific IS6110-targeted primers and probe used in this work were shown to be highly efficient for detecting tuberculous mycobacteria in animal tissue samples, although the isolates of the most relevant species, M. bovis, usually contain only one copy of this insertion sequence. It has recently been found that IS6110-like elements may be present in other non-MTC mycobacteria such as M. smegmatis [35]. However, the probe and respective flanking primers used show no relevant complementary regions with these IS6110-like nucleotide sequences (Figure 2).

The protocol for direct detection of MTC from fresh animal tissues, using an optimized DNA extraction and purification procedure coupled with a semi-nested real time PCR assay described in this work, was shown to be highly accurate and much faster than bacteriological culture, reducing the time for confirmatory TB diagnosis from several weeks to few hours, thus also potentially decreasing the arrest period of the suspect animal carcass and herd. The assay is amenable to future automation possibilities regarding both the DNA extraction and amplification steps. It may also allow the detection of MTC members when these pathogens become nonviable and non-cultivable or are overgrown by other less fastidious bacteria or mycobacteria also present in tissue samples. The use of a novel β-actin gene targeted probe, and respective flanking primers, with complementary targets in most mammal species, allowed to assess the presence of amplification inhibitors in the DNA extracts. Although the test is not able to distinguish between different members of the MTC, particularly M. bovis, the identification of any tuberculous mycobacteria infection in domestic or wildlife animals could have public health implications.