The #Ish25 left M¹ was found at Ishango 11 (IS-11) an archaeological site in the Semliki valley located in the DRC part of the Western Rift. This valley is best known for its Late Stone Age (LSA) artifacts and particularly for the early evidence for harpoons [28], but the recovery of stone tools in situ in the Semliki Formation (Late Lower to Middle Pleistocene) at Katanda 2, and possibly also in the Plio-Pleistocene Lusso Formation (first known as Kaiso beds [29]) at Kanyatsi 2 and Senga 5A, suggested that early hominins were present in the valley long before the Upper Pleistocene ([15], Text S1 in File S1).

Ishango 11 is located along the Semliki River where it flows out of Lake Rutanzige (or Lake Edward; see [12] p.3). The site was initially recognized and superficially explored in 1935 by Damas [30], but the first formal excavations were carried out by de Heinzelin in the 1950s during his geological and archaeological expeditions in the Upper Semliki region [30]–[33]. At Ishango, de Heinzelin excavated two perpendicular trenches as well as the area to the west of their junction (Text S2.1 and Figure S1 in File S1); the stratigraphy he established was later confirmed by the work of the Semliki Research Expedition [34]–[35]. Recent to Upper Pleistocene lithostratigraphic units compose a terrace complex TT (or Terrasse tuffacée) later redefined as the Ishango Gravels Formation [16] that truncated and overlies the Plio-Pleistocene Lusso Formation (Figure 2, Text S2.2 and Figure S2 in File S1). The latter have been dated using biochronology to between 2.6 Ma and 2.0 Ma ([13]–[14], [36]–[42], Text S2.2 in File S1). Towards the base of the Ishango Gravels Formation, overlying the ca. 1m thick basal gravels (G.INF), a 10–20 cm thick Niveau Fossilifère Principal (NFPr) yielded an early Late Stone Age (LSA) assemblage consisting of numerous lithic and bone artifacts as well as faunal remains ([31], [35], [43]–[49], Text S2.2 in File S1) in association with more than a hundred heavily mineralized hominin remains. Radiometric dating of the LSA layer (NFPr) yielded an age between 25–19 Ka ([34]–[35], [50], Text S2.2 in File S1), an age consistent with that suggested by characteristics of the faunal assemblage [48]. During the initial study of the 1950s LSA hominin remains, it was assumed that all were attributed to Homo sapiens. However, the exceptionally large size of a left M¹ (#Ish25) described by Twiesselmann [43], raised the possibility that evidence of a more primitive hominin may have been mixed in with a fossil assemblage that is otherwise similar to anatomically modern humans.

Although the precise location of the archeological samples and the description of their content were recorded by de Heinzelin in his notebook, there was no mention of an isolated tooth. Archival research, however, has revealed that #Ish25 was discovered the first day of de Heinzelin’s excavation, and that it came from the corner area, west of the junction of the trenches (Text S2.3 and Figures S3–S8 in File S1). This area preserved only the basal parts of the Upper Pleistocene Ishango Gravels Formation, namely levels G.INF and NFPr ([31], Text S2.3 in File S1). In the archives of the excavation, de Heinzelin indicated that intrusive fossils from the Lusso Formation had been reworked into the lower layers of the Ishango Gravels Formation (Figure S7 in File S1: “G.INF = Inferior gravels with few fossils, rare harpoons and reworked Kaiso fossils”). In 1955 and 1957, de Heinzelin described the G.INF layer as an unstratified mass of rolled gravels including numerous fragments of reworked fossils from the Lusso/Kaiso Formation (brown bullhead, crocodile, etc.) mixed together with fauna and artefacts accounting for the first stages of the Ishango civilization ([31]–[32], Text S2.3 and Figures S2 and S7 in File S1). The same observations were made by Greenwood [44] and Hopwood & Misonne [45] for the fish and mammal assemblage at the base of the Ishango Gravels Formation. The analysis of the fauna by Peters confirmed the heterogeneity of the basal layers from the Ishango Gravels Formation [48]. He identified reworked intrusive elements (shell fragments) in the G.INF and the NFPr deposits that originate from the older sediments. Since the presence of reworked fossils from the Lusso Formation is confirmed by archaeozoological studies in both basal layers of the Ishango Gravels Formation, this is a legitimate reason to argue that #Ish25 likely derives from the underlying Plio-Pleistocene Lusso Formation and should not be grouped with the LSA hominin fossils.

In order to test the hypothesis that #Ish25 may be a reworked element within the Ishango Gravels Formation, we used Raman spectroscopy, a non-destructive technique, to analyze and compare the diagenetic processes at work in this tooth with those seen in the three teeth from the LSA level that best represented the range of taphonomic alterations seen in fossils from this horizon (Text S3 and Figure S9 in File S1).

The Raman spectra acquired from the NFPr material show signatures consistent with dentine spectra ([51]–[52], Figure 3). The three teeth show a similar diagenetic signal, with a 963.5 cm⁻¹ peak (υ₁(PO₄)³⁻) with a mean signal-to-noise ratio (S/N) of 1250 (ranging from 967 to 1368); there is no evidence of (PO₄)³⁻ secondary features. The spectra from #Ish25 show an intense 963 cm⁻¹ peak (mean S/N of 2152) and a 1074 cm⁻¹ peak (υ₁ (CO₃)²⁻) with a mean S/N of 456; (PO₄)³⁻ secondary features at 430 cm⁻¹ and 590 cm⁻¹ (respectively υ₂(PO₄)³⁻ and υ₄(PO₄)³⁻) are also present (Text S3 in File S1). The results of the Raman spectroscopy suggest that #Ish25 has a distinctive Raman spectrum compared to the three teeth from the NFPr layer. In particular, #Ish25 has a doubled intensity for the (υ₁(PO₄)³⁻) phosphate peak and a clear carbonate signal, suggesting a difference in hydroxyapatite re-crystallization and carbonate integration. This supports the hypothesis that #Ish25 has a different diagenetic history than the remains from the NFPr layer, and is consistent with it being an intrusive element within the basal section of the Upper Pleistocene terrace.

The results from the Raman spectroscopy, plus the archival and geological evidence (Texts S1–S3 in File S1), are consistent with #Ish25 being a reworked element from the Lusso Formation.

The morphological characteristics of #Ish25 molar at the outer enamel surface (OES) and at the enamel-dentine junction (EDJ) confirm its primitive status ([18], Figure 4).

The stage of root formation (scale E; [53]), together with the absence of interproximal wear facets, suggests that it belongs to an immature individual and that the tooth was not fully erupted. The shape of the distobuccal corner of the crown, the relative equivalence of the mesiolingual-distobuccal and mesiobuccal-distolingual axes, the slightly larger dimension of the lingual face compared to the buccal one, and the triradiate fissure pattern in the central fossa of the occlusal surface indicate that this tooth is a first upper molar [54]–[55]. The identification of #Ish25 as a first molar is also supported by analysis of EDJ shape (see below and Text S4.4 and Tables S5–S7 in File S1).

The outer enamel surface of #Ish25 is marked by two crests - a C-shaped anterior transverse crest that joins the mesial marginal ridge (MMR) and a notched, but uninterrupted, crista obliqua between the protocone and the metacone. A third crest, a trigonal-hypocone crest that results in a shallow groove at this location on the OES, is only visible on the EDJ surface. The mesial marginal ridge bears three tubercles at the OES that correspond with dentine horn-like projections at the EDJ [56]. There is no metaconule (or cusp 5). A furrow-like Carabelli structure is visible on the lingual OES of #Ish25 with a corresponding depression at the EDJ.

The taxonomic implications of non-metric enamel and dentine characters have been debated [18], [20], [54]. The tubercles on the MMR have limited significance [56], and the expressions of the three crests on #Ish25 have been interpreted as primitive features [18]. The continuous crista obliqua is observed in a minority of recent modern humans at the OES (ca. 20%); it is most frequent in early Homo and it is also developed in hyper-megadont archaic hominins [18], [20]. The particular C-shaped anterior transverse crest on the EDJ is found in less than 2% of modern human individuals, and it is also rare among australopiths [18]. While the incidence of a furrow-like Carabelli structure in modern human populations varies ca. 12% to ca. 44% [57], its occurrence in early hominins is higher among early Homo (ca. 33%) than Australopithecus and Paranthropus (ca. 18.5%) [58].

The exceptional dimensions of the #Ish25 crown have been noted since its discovery [43], [59]. The mesiodistal and buccolingual diameters of #Ish25 align it with australopiths rather than with Pleistocene Homo and recent modern humans (Text S4.1, Table S1 and Figure S10 in File S1). The crown base area of the #Ish25 falls at the upper end of the early Homo variation and between the means of Australopithecus and Paranthropus (Text S4.2 and Table S2 in File S1). The cusp areas of #Ish25 have the following relative size relationships: protocone >paracone>metacone>hypocone. The ratio between the size of the paracone and the metacone separates Australopithecus and early Homo from later Pleistocene Homo [60]. In #Ish25 the paracone is 5.5% larger than the metacone, a relationship that aligns this individual with later Homo specimens (Figures S11–S12 in File S1). However, the complexity of the mesial marginal ridge morphology complicates this assessment, for it is not clear whether the diagnostic paracone/metacone relationship holds true for teeth with as many accessory cusps/cuspules as are observed in #Ish25.

Since the relative proportions of enamel and dentine have been used to assess hominid phylogeny, taxonomy and adaptation (e.g. [19], [61]–[64]), we further investigated the two- and three-dimensional dental tissue proportions of #Ish25 through micro-computed tomography. In Tables S3 and S4 (in File S1) we compare the results with the available data on hominin upper molars. With the exception of the Neanderthals ([61], Text S4.3 in File S1), dental tissue proportions similar to modern humans are documented back to the Middle Pleistocene [65]–[66], whereas australopiths are characterized by thicker enamel [67]–[68]. The proportions of enamel and dentine exhibited by #Ish25 are closer to the pattern seen in early hominins than to the values seen in both Middle-to-Upper Pleistocene Homo and recent humans. In relation to its crown size, the enamel thickness of #Ish25 is comparable to that of the M¹s from Sterkfontein (i.e. Sts 57) and Swartkrans (i.e. SK 832) (Figures S13–S14 in File S1).

We used geometric morphometrics to examine the shape of the #Ish25 EDJ based on landmarks and semilandmarks ([23], [69], Text S4.4 and Figure S15 in File S1). A principal component analysis of the Procrustes coordinates in both shape and form space (i.e. including also tooth size; see Text S4.4 in File S1) shows a clear separation on the first axis between the Pliocene-Lower Pleistocene hominins and the Middle Pleistocene-recent specimens (Figure 5), with #Ish25 clustering with the former group at the interface of the P. robustus and A. africanus convex hulls. A cross-validated canonical variates analysis of EDJ shape classifies #Ish25 as most similar in morphology to the early Homo comparative sample (Text S4.4 in File S1), while a nearest neighbor analysis links #Ish25 with the A. africanus specimen Sts 8 (not illustrated). A comparison of the EDJ shape of the #Ish25 with the mean shape of the post-Lower Pleistocene sample and the mean shape of the Plio-Pleistocene sample indicates that the relative size and position of the dentine horns of the four main cusps (the ridge curve) and the shape of the cervix of #Ish25 match more closely the mean of the Plio-Pleistocene sample. This pattern is even more pronounced in form space, which includes tooth size in the comparison (Figure S16 in File S1). While it is clear that the EDJ shape of the Ishango molar is consistent with it belonging to an early hominin taxon, the lack of a more comprehensive early Homo EDJ sample prevents definitive assignment to a specific taxon.

A reassessment of the Ishango archaeological collections has highlighted the uniqueness of #Ish25, a particularly large hominin first upper molar. The combination of archival evidence about its geological context and the results of Raman spectroscopic analysis suggest that #Ish25 does not belong to the Upper Pleistocene LSA modern human assemblage. With the exception of the derived relative cusp proportions, the external and internal dental morphology of #Ish25 resembles that of australopiths or early Homo and the absolute and relative dimensions of the crown and its relatively thick enamel align it with East and southern African early hominins. Finally, in a detailed analysis of the EDJ, which discriminates between australopiths/early Homo and post-Lower Pleistocene Homo, #Ish25 clusters with the former.

The attribution of #Ish25 to an early hominin has several implications. Locally, this occurrence is consistent with archaeological evidence suggesting that early hominins were in the Semliki valley close to, if not prior to, two million years before the present. More globally, our understanding of early hominin evolution, adaptation and dispersion during the Plio-Pleistocene period is mainly based on fossil evidence from just two regions within the vast African continent, the Eastern Rift Valley from Ethiopia to Tanzania, and southern Africa. The #Ish25 first upper molar is meager, but compelling, evidence that by ca. 2 Ma early hominins had expanded their geographical range into the Western Rift valley of Central Africa, and had occupied a region whose environment has been reconstructed as a woodland to grassland ecotone adjacent to dense lowland forests [14], [70].

Overall, the evidence from Ishango provides a new perspective on hominin morphological and ecological diversity during the Plio-Pleistocene and contributes to our understanding of the patterns of dispersal and evolution of early hominins.