One of the still unsolved mysteries in Science is the formation of prebiotic organic compounds on the prebiotic Earth. These organic compounds are prerequisite for the development of more complex molecular structures like lipids, proteins or nucleic acids, which were necessary components of the first living cell [1,2]. Several hypotheses are established on how organic compounds such as these have been formed and how they started to be integrated in processes leading to a living cell [3–8]. Alternatively and according to an earlier proposal, the first prebiotic chemistry and the formation of protocells could have occurred in the hydrothermal environment of tectonic fault zones in the upper continental crust, an environment where sensitive molecules are well protected against the destructive influence of UV radiation and could undergo complex reactions in a two-phase environment formed by hot water and supercritical carbon dioxide [9,10]. Tectonic fault zones offer a wide variety of reaction conditions regarding pressure, temperature, and catalytic surfaces. All reaction sites are interconnected by efficient material transport while isolated pockets allow for continuous reactions under constant conditions. Near a depth of 1 km (corresponding to T = 50°C and 100 bar of hydrostatic pressure), pressure variations caused by geysers or tidal phenomena cause a cyclic formation of vesicles [10]. At the same time, the whole system is under continuous supply of hydrothermal chemistry which is being formed at lower positions of the hydrothermal vents, maybe in a region between -2 and -4 km. Here, temperatures between 80° and 150°C as well as hydrostatic pressures between 200 and 400 bar provide the ideal reaction conditions for the formation of basic organic molecules.

Quartz crystals which have grown in this environment (an example of a hydrothermal quartz dyke is shown in Fig 1) should have entrapped small amounts of the fluid phase containing freshly formed organic compounds. Even though this fluid phase may have actually been formed at a point of time after the first living organisms already existed in other locations of the planet, it still would represent the original composition of the prebiotic stage provided that its origin is clearly abiotic.

In order to verify this hypothesis, a quartz dyke north of Jack Hills and >3 Ga old quartz pebbles from a conglomerate of the Jack Hills in Western Australia (a region where the oldest zircons, with an age of more than 4.3 Ga, were found [11–13]) were analyzed for organic constituents in their fluid inclusions (for details on the sites and on the sample collection see Text A in S1 File). Even though the ages of the quartz dyke and the fluid inclusions are poorly constrained and may well post-date the origin of life, this site represents an analogue for a setting that could plausibly have existed on the prebiotic Earth.

Initially, the crystals were carefully cleaned and analyzed for possible organic contaminants on their surface. In a second step, the material was further broken and ground to a fine powder. Finally, the organic components of the freshly released fluids were analyzed in detail by gas and liquid chromatography coupled with flame-ionization detector and mass spectrometry. An additional analysis using stable-isotope-ratio mass spectrometry was applied in order to prove the abiotic origin of the sample (see Text C in S1 File).

The content of organic substances in quartz crystals varied significantly from location to location. However, in contrast to minerals from the upper mantle (e.g. olivine from a mantle xenolith from a maar tuff ring, see Text H in S1 File), all quartz samples displayed at least minor concentrations of organic compounds in fluid inclusions. An example of the variety of molecular species found in quartz samples collected in and near Jack Hills is presented in Table 1.

Depending on the chemical composition, all compounds determined, except for those containing nitrogen, can be assigned to four classes: aliphatic hydrocarbons, halocarbons, alcohols, and aldehydes.

As a result of the given analytical method, the compounds listed under a = 1 and a = 2 reflect a fraction of substances which belongs to a given range of volatility. Therefore, the chlorinated molecules in Table 1 generally exhibit shorter chain lengths than the non-chlorinated compounds. Some of the aliphatic chains show methyl side groups, but most molecules exhibit unbranched backbones. The compounds listed under a = 3 could be determined only by their sum formula (see Text E in S1 File).

The collection of compounds contains some highly reactive species such as ethyne, alkenes, and aldehydes. Obviously, these compounds (or their precursors) must have been efficiently protected or stabilized in order to survive over billions of years. Given that the mineral environment inside the quartz inclusions offers a large choice of metal oxide surfaces (as from residues of transition metal cations which had originally been dissolved in the hydrothermal water), it is likely that the stabilization of some of these compounds occurred by formation of complexes with aldehydes or alkenes as single or multiple ligands [14, 15].

One may also speculate about the mechanisms of formation which have led to the given molecules. It is generally accepted that alkanes and alkenes may have been generated in analogy to the Fischer-Tropsch mechanism, catalyzed by various mineral surfaces present in the crustal cavities [16]. With chlorine or hydrogen chloride from volcanic sources, it is likely that the chlorinated compounds (which are actually known to occur in volcanic gases [17–20]) have formed as well. In fact, chlorine may have been the most efficient oxidizing agent under the given conditions. The monochlorinated alkanes and alkenes in turn are prone to hydrolysis in the presence of alkaline waters, hereby forming alcohols which are further oxidized to aldehydes, ketones, and carbonic acids [21]. Hence, the four classes of compounds listed in Table 1 could indicate a certain sequence of hydrothermal formation.

A very striking fact is the occurrence of the homologous series of aldehydes in the μg/kg concentration range (see Text G in S1 File). Within the given window of volatility, we were able to detect aldehydes with chain length between seven and seventeen carbon atoms (heptanal to heptadecanal) without any preference for even or uneven carbon numbers. The aldehydes were identified by spiking experiments with standard compounds (heptanal to hexadecanal). For heptadecanal, the retention time difference between the homologues and the mass spectra data bases were used for identification. These compounds have a strong potential to form amphiphilic units if the aldehydes are oxidized to fatty acids which (at higher pH values) form amphiphilic anions [22]. In addition, they may react with alcohols to form amphiphilic esters under hydrothermal conditions [22]. Therefore, they represent the chemical basis for larger associated structures like micelles, membranes, and vesicles which may have formed under the same conditions [4]. All the nitrogen-containing organic substances seem to be more polar and less volatile and could therefore be detected only by liquid chromatography (a = 3 in Table 1).

Even though the list of identified organic molecules does not contain known biomolecules, many substances observed can be considered their possible precursors: subsequent reaction with water and ammonia followed by an oxidation may turn most of the chlorinated compounds into amino acids [22]. As mentioned above, carboxylic acids which derive from the long-chained aldehydes may form various esters with the multivalent alcohols, leading to possible predecessors of lipid molecules [22]. The multivalent alcohols themselves may be seen as precursors of sugars [22].

Could other sources, such as contamination during the sample preparation or living organisms or thermal decomposition products thereof, have contributed to the observed organic substances? Our blanks clearly show that the sample preparation is not the source for the compounds listed in Table 1. Even though the composition of the identified organic compounds is atypical for petrochemistry, it is important to exclude that fossil organic material was the precursor for the organic compounds found in quartz samples. In order to support the hydrothermal origin of the enclosed contents, we measured the stable-isotope composition of CH₄ in the samples that contained a variety of complex organic substances (see Text C in S1 File). The results of the stable carbon and hydrogen isotope measurements of CH₄ are shown in Fig 2. The data regions generally assigned to biotic, thermogenic and abiotic methane sources according to Etiope and Sherwood Lollar [23] are indicated for comparison. The two-dimensional stable isotope results for CH₄ clearly indicate that the CH₄ found in the Australian quartz samples was formed from abiotic precursors such as carbon dioxide or elemental carbon and makes a biogenic (e.g. from microbes) or thermogenic origin (decomposition of organic matter) highly unlikely. Some data points are clearly found within and even beyond the region which has been assigned to abiotic methane on the basis of on present data. The data represent interesting counterparts to findings by Ueno et al. and Bell et al. who, by the same approach, could clearly prove that other fluid inclusions in hydrothermal precipitates from Pilbara Craton, Australia, and zirkons from Jack Hills, Australia, showed traces of methane and solid carbon deriving from biogenic origin [24, 25].

On this basis, it can be concluded that the organic compounds found in the inclusions have obviously been formed from abiotic sources by hydrothermal chemistry. Even though they may have been generated at a time where life was already established in other locations of the planet, they could be a possible example of the type of chemistry that may plausibly have occurred in similar settings on the prebiotic Earth. In fact, the chemical components listed in Table 1 have most likely been part of the fluid phase within the Earth’s crust from the very early beginning until the present day. On the primordial Earth, this or a similar mixture may have started the development and the fruitful evolution of prebiotic chemistry. In our opinion, these following steps may have occurred within the same environment, the system of hydrothermal vents, and may eventually have led to the formation of the first living cell.